From a8220ab2d293bb7f4b014b79d16b2fb05090fa93 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Feb 2021 12:45:55 +0100 Subject: Adding upstream version 1.29.0. Signed-off-by: Daniel Baumann --- exporting/Makefile.am | 29 + exporting/README.md | 312 ++++ exporting/TIMESCALE.md | 69 + exporting/WALKTHROUGH.md | 259 +++ exporting/aws_kinesis/Makefile.am | 8 + exporting/aws_kinesis/README.md | 58 + exporting/aws_kinesis/aws_kinesis.c | 217 +++ exporting/aws_kinesis/aws_kinesis.h | 16 + exporting/aws_kinesis/aws_kinesis_put_record.cc | 151 ++ exporting/aws_kinesis/aws_kinesis_put_record.h | 35 + exporting/check_filters.c | 78 + exporting/clean_connectors.c | 81 + exporting/exporting.conf | 89 + exporting/exporting_engine.c | 143 ++ exporting/exporting_engine.h | 304 +++ exporting/graphite/Makefile.am | 4 + exporting/graphite/README.md | 30 + exporting/graphite/graphite.c | 228 +++ exporting/graphite/graphite.h | 18 + exporting/init_connectors.c | 145 ++ exporting/json/Makefile.am | 4 + exporting/json/README.md | 30 + exporting/json/json.c | 362 ++++ exporting/json/json.h | 21 + exporting/mongodb/Makefile.am | 8 + exporting/mongodb/README.md | 38 + exporting/mongodb/mongodb.c | 387 ++++ exporting/mongodb/mongodb.h | 35 + exporting/nc-exporting.sh | 158 ++ exporting/opentsdb/Makefile.am | 8 + exporting/opentsdb/README.md | 30 + exporting/opentsdb/opentsdb.c | 422 +++++ exporting/opentsdb/opentsdb.h | 26 + exporting/process_data.c | 426 +++++ exporting/prometheus/Makefile.am | 12 + exporting/prometheus/README.md | 461 +++++ exporting/prometheus/prometheus.c | 916 +++++++++ exporting/prometheus/prometheus.h | 41 + exporting/prometheus/remote_write/Makefile.am | 14 + exporting/prometheus/remote_write/README.md | 51 + exporting/prometheus/remote_write/remote_write.c | 345 ++++ exporting/prometheus/remote_write/remote_write.h | 25 + .../prometheus/remote_write/remote_write.proto | 29 + .../remote_write/remote_write_request.cc | 186 ++ .../prometheus/remote_write/remote_write_request.h | 33 + exporting/pubsub/Makefile.am | 8 + exporting/pubsub/README.md | 45 + exporting/pubsub/pubsub.c | 194 ++ exporting/pubsub/pubsub.h | 14 + exporting/pubsub/pubsub_publish.cc | 258 +++ exporting/pubsub/pubsub_publish.h | 37 + exporting/read_config.c | 503 +++++ exporting/send_data.c | 440 +++++ exporting/send_internal_metrics.c | 172 ++ exporting/tests/Makefile.am | 4 + exporting/tests/exporting_doubles.c | 395 ++++ exporting/tests/exporting_fixtures.c | 163 ++ exporting/tests/netdata_doubles.c | 247 +++ exporting/tests/system_doubles.c | 61 + exporting/tests/test_exporting_engine.c | 1939 ++++++++++++++++++++ exporting/tests/test_exporting_engine.h | 203 ++ 61 files changed, 11025 insertions(+) create mode 100644 exporting/Makefile.am create mode 100644 exporting/README.md create mode 100644 exporting/TIMESCALE.md create mode 100644 exporting/WALKTHROUGH.md create mode 100644 exporting/aws_kinesis/Makefile.am create mode 100644 exporting/aws_kinesis/README.md create mode 100644 exporting/aws_kinesis/aws_kinesis.c create mode 100644 exporting/aws_kinesis/aws_kinesis.h create mode 100644 exporting/aws_kinesis/aws_kinesis_put_record.cc create mode 100644 exporting/aws_kinesis/aws_kinesis_put_record.h create mode 100644 exporting/check_filters.c create mode 100644 exporting/clean_connectors.c create mode 100644 exporting/exporting.conf create mode 100644 exporting/exporting_engine.c create mode 100644 exporting/exporting_engine.h create mode 100644 exporting/graphite/Makefile.am create mode 100644 exporting/graphite/README.md create mode 100644 exporting/graphite/graphite.c create mode 100644 exporting/graphite/graphite.h create mode 100644 exporting/init_connectors.c create mode 100644 exporting/json/Makefile.am create mode 100644 exporting/json/README.md create mode 100644 exporting/json/json.c create mode 100644 exporting/json/json.h create mode 100644 exporting/mongodb/Makefile.am create mode 100644 exporting/mongodb/README.md create mode 100644 exporting/mongodb/mongodb.c create mode 100644 exporting/mongodb/mongodb.h create mode 100755 exporting/nc-exporting.sh create mode 100644 exporting/opentsdb/Makefile.am create mode 100644 exporting/opentsdb/README.md create mode 100644 exporting/opentsdb/opentsdb.c create mode 100644 exporting/opentsdb/opentsdb.h create mode 100644 exporting/process_data.c create mode 100644 exporting/prometheus/Makefile.am create mode 100644 exporting/prometheus/README.md create mode 100644 exporting/prometheus/prometheus.c create mode 100644 exporting/prometheus/prometheus.h create mode 100644 exporting/prometheus/remote_write/Makefile.am create mode 100644 exporting/prometheus/remote_write/README.md create mode 100644 exporting/prometheus/remote_write/remote_write.c create mode 100644 exporting/prometheus/remote_write/remote_write.h create mode 100644 exporting/prometheus/remote_write/remote_write.proto create mode 100644 exporting/prometheus/remote_write/remote_write_request.cc create mode 100644 exporting/prometheus/remote_write/remote_write_request.h create mode 100644 exporting/pubsub/Makefile.am create mode 100644 exporting/pubsub/README.md create mode 100644 exporting/pubsub/pubsub.c create mode 100644 exporting/pubsub/pubsub.h create mode 100644 exporting/pubsub/pubsub_publish.cc create mode 100644 exporting/pubsub/pubsub_publish.h create mode 100644 exporting/read_config.c create mode 100644 exporting/send_data.c create mode 100644 exporting/send_internal_metrics.c create mode 100644 exporting/tests/Makefile.am create mode 100644 exporting/tests/exporting_doubles.c create mode 100644 exporting/tests/exporting_fixtures.c create mode 100644 exporting/tests/netdata_doubles.c create mode 100644 exporting/tests/system_doubles.c create mode 100644 exporting/tests/test_exporting_engine.c create mode 100644 exporting/tests/test_exporting_engine.h (limited to 'exporting') diff --git a/exporting/Makefile.am b/exporting/Makefile.am new file mode 100644 index 000000000..41fcac0bd --- /dev/null +++ b/exporting/Makefile.am @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +SUBDIRS = \ + tests \ + graphite \ + json \ + opentsdb \ + prometheus \ + aws_kinesis \ + pubsub \ + mongodb \ + $(NULL) + +dist_libconfig_DATA = \ + exporting.conf \ + $(NULL) + +dist_noinst_DATA = \ + README.md \ + TIMESCALE.md \ + WALKTHROUGH.md \ + $(NULL) + +dist_noinst_SCRIPTS = \ + nc-exporting.sh \ + $(NULL) diff --git a/exporting/README.md b/exporting/README.md new file mode 100644 index 000000000..933de0e07 --- /dev/null +++ b/exporting/README.md @@ -0,0 +1,312 @@ + + +# Exporting engine reference + +Welcome to the exporting engine reference guide. This guide contains comprehensive information about enabling, +configuring, and monitoring Netdata's exporting engine, which allows you to send metrics to external time-series +databases. + +For a quick introduction to the exporting engine's features, read our doc on [exporting metrics to time-series +databases](/docs/export/external-databases.md), or jump in to [enabling a connector](/docs/export/enable-connector.md). + +The exporting engine has a modular structure and supports metric exporting via multiple exporting connector instances at +the same time. You can have different update intervals and filters configured for every exporting connector instance. + +When you enable the exporting engine and a connector, the Netdata Agent exports metrics _beginning from the time you +restart its process_, not the entire [database of long-term metrics](/docs/store/change-metrics-storage.md). + +The exporting engine has its own configuration file `exporting.conf`. The configuration is almost similar to the +deprecated [backends](/backends/README.md#configuration) system. The most important difference is that type of a +connector should be specified in a section name before a colon and an instance name after the colon. Also, you can't use +`host tags` anymore. Set your labels using the [`[host labels]`](/docs/guides/using-host-labels.md) section in +`netdata.conf`. + +Since Netdata collects thousands of metrics per server per second, which would easily congest any database server when +several Netdata servers are sending data to it, Netdata allows sending metrics at a lower frequency, by resampling them. + +So, although Netdata collects metrics every second, it can send to the external database servers averages or sums every +X seconds (though, it can send them per second if you need it to). + +## Features + +1. The exporting engine uses a number of connectors to send Netdata metrics to external time-series databases. See our + [list of supported databases](/docs/export/external-databases.md#supported-databases) for information on which + connector to enable and configure for your database of choice. + + - [**AWS Kinesis Data Streams**](/exporting/aws_kinesis/README.md): Metrics are sent to the service in `JSON` + format. + - [**Google Cloud Pub/Sub Service**](/exporting/pubsub/README.md): Metrics are sent to the service in `JSON` + format. + - [**Graphite**](/exporting/graphite/README.md): A plaintext interface. Metrics are sent to the database server as + `prefix.hostname.chart.dimension`. `prefix` is configured below, `hostname` is the hostname of the machine (can + also be configured). Learn more in our guide to [export and visualize Netdata metrics in + Graphite](/docs/guides/export/export-netdata-metrics-graphite.md). + - [**JSON** document databases](/exporting/json/README.md) + - [**OpenTSDB**](/exporting/opentsdb/README.md): Use a plaintext or HTTP interfaces. Metrics are sent to + OpenTSDB as `prefix.chart.dimension` with tag `host=hostname`. + - [**MongoDB**](/exporting/mongodb/README.md): Metrics are sent to the database in `JSON` format. + - [**Prometheus**](/exporting/prometheus/README.md): Use an existing Prometheus installation to scrape metrics + from node using the Netdata API. + - [**Prometheus remote write**](/exporting/prometheus/remote_write/README.md). A binary snappy-compressed protocol + buffer encoding over HTTP. Supports many [storage + providers](https://prometheus.io/docs/operating/integrations/#remote-endpoints-and-storage). + - [**TimescaleDB**](/exporting/TIMESCALE.md): Use a community-built connector that takes JSON streams from a + Netdata client and writes them to a TimescaleDB table. + +2. Netdata can filter metrics (at the chart level), to send only a subset of the collected metrics. + +3. Netdata supports three modes of operation for all exporting connectors: + + - `as-collected` sends to external databases the metrics as they are collected, in the units they are collected. + So, counters are sent as counters and gauges are sent as gauges, much like all data collectors do. For example, + to calculate CPU utilization in this format, you need to know how to convert kernel ticks to percentage. + + - `average` sends to external databases normalized metrics from the Netdata database. In this mode, all metrics + are sent as gauges, in the units Netdata uses. This abstracts data collection and simplifies visualization, but + you will not be able to copy and paste queries from other sources to convert units. For example, CPU utilization + percentage is calculated by Netdata, so Netdata will convert ticks to percentage and send the average percentage + to the external database. + + - `sum` or `volume`: the sum of the interpolated values shown on the Netdata graphs is sent to the external + database. So, if Netdata is configured to send data to the database every 10 seconds, the sum of the 10 values + shown on the Netdata charts will be used. + + Time-series databases suggest to collect the raw values (`as-collected`). If you plan to invest on building your + monitoring around a time-series database and you already know (or you will invest in learning) how to convert units + and normalize the metrics in Grafana or other visualization tools, we suggest to use `as-collected`. + + If, on the other hand, you just need long term archiving of Netdata metrics and you plan to mainly work with + Netdata, we suggest to use `average`. It decouples visualization from data collection, so it will generally be a lot + simpler. Furthermore, if you use `average`, the charts shown in the external service will match exactly what you + see in Netdata, which is not necessarily true for the other modes of operation. + +4. This code is smart enough, not to slow down Netdata, independently of the speed of the external database server. You + should keep in mind though that many exporting connector instances can consume a lot of CPU resources if they run + their batches at the same time. You can set different update intervals for every exporting connector instance, but + even in that case they can occasionally synchronize their batches for a moment. + +## Configuration + +Here are the configuration blocks for every supported connector. Your current `exporting.conf` file may look a little +different. + +You can configure each connector individually using the available [options](#options). The +`[graphite:my_graphite_instance]` block contains examples of some of these additional options in action. + +```conf +[exporting:global] + enabled = yes + send configured labels = no + send automatic labels = no + update every = 10 + +[prometheus:exporter] + send names instead of ids = yes + send configured labels = yes + end automatic labels = no + send charts matching = * + send hosts matching = localhost * + prefix = netdata + +[graphite:my_graphite_instance] + enabled = yes + destination = localhost:2003 + data source = average + prefix = Netdata + hostname = my-name + update every = 10 + buffer on failures = 10 + timeout ms = 20000 + send charts matching = * + send hosts matching = localhost * + send names instead of ids = yes + send configured labels = yes + send automatic labels = yes + +[prometheus_remote_write:my_prometheus_remote_write_instance] + enabled = yes + destination = localhost + remote write URL path = /receive + +[kinesis:my_kinesis_instance] + enabled = yes + destination = us-east-1 + stream name = netdata + aws_access_key_id = my_access_key_id + aws_secret_access_key = my_aws_secret_access_key + +[pubsub:my_pubsub_instance] + enabled = yes + destination = pubsub.googleapis.com + credentials file = /etc/netdata/pubsub_credentials.json + project id = my_project + topic id = my_topic + +[mongodb:my_mongodb_instance] + enabled = yes + destination = localhost + database = my_database + collection = my_collection + +[json:my_json_instance] + enabled = yes + destination = localhost:5448 + +[opentsdb:my_opentsdb_plaintext_instance] + enabled = yes + destination = localhost:4242 + +[opentsdb:http:my_opentsdb_http_instance] + enabled = yes + destination = localhost:4242 + +[opentsdb:https:my_opentsdb_https_instance] + enabled = yes + destination = localhost:8082 +``` + +### Sections + +- `[exporting:global]` is a section where you can set your defaults for all exporting connectors +- `[prometheus:exporter]` defines settings for Prometheus exporter API queries (e.g.: + `http://NODE:19999/api/v1/allmetrics?format=prometheus&help=yes&source=as-collected`). +- `[:]` keeps settings for a particular exporting connector instance, where: + - `type` selects the exporting connector type: graphite | opentsdb:telnet | opentsdb:http | + prometheus_remote_write | json | kinesis | pubsub | mongodb. For graphite, opentsdb, + json, and prometheus_remote_write connectors you can also use `:http` or `:https` modifiers + (e.g.: `opentsdb:https`). + - `name` can be arbitrary instance name you chose. + +### Options + +Configure individual connectors and override any global settings with the following options. + +- `enabled = yes | no`, enables or disables an exporting connector instance + +- `destination = host1 host2 host3 ...`, accepts **a space separated list** of hostnames, IPs (IPv4 and IPv6) and + ports to connect to. Netdata will use the **first available** to send the metrics. + + The format of each item in this list, is: `[PROTOCOL:]IP[:PORT]`. + + `PROTOCOL` can be `udp` or `tcp`. `tcp` is the default and only supported by the current exporting engine. + + `IP` can be `XX.XX.XX.XX` (IPv4), or `[XX:XX...XX:XX]` (IPv6). For IPv6 you can to enclose the IP in `[]` to + separate it from the port. + + `PORT` can be a number of a service name. If omitted, the default port for the exporting connector will be used + (graphite = 2003, opentsdb = 4242). + + Example IPv4: + +```conf + destination = 10.11.14.2:4242 10.11.14.3:4242 10.11.14.4:4242 +``` + + Example IPv6 and IPv4 together: + +```conf + destination = [ffff:...:0001]:2003 10.11.12.1:2003 +``` + + When multiple servers are defined, Netdata will try the next one when the previous one fails. + + Netdata also ships `nc-exporting.sh`, a script that can be used as a fallback exporting connector to save the + metrics to disk and push them to the time-series database when it becomes available again. It can also be used to + monitor / trace / debug the metrics Netdata generates. + + For the Kinesis exporting connector `destination` should be set to an AWS region (for example, `us-east-1`). + + For the MongoDB exporting connector `destination` should be set to a + [MongoDB URI](https://docs.mongodb.com/manual/reference/connection-string/). + + For the Pub/Sub exporting connector `destination` can be set to a specific service endpoint. + +- `data source = as collected`, or `data source = average`, or `data source = sum`, selects the kind of data that will + be sent to the external database. + +- `hostname = my-name`, is the hostname to be used for sending data to the external database server. By default this + is `[global].hostname`. + +- `prefix = Netdata`, is the prefix to add to all metrics. + +- `update every = 10`, is the number of seconds between sending data to the external database. Netdata will add some + randomness to this number, to prevent stressing the external server when many Netdata servers send data to the same + database. This randomness does not affect the quality of the data, only the time they are sent. + +- `buffer on failures = 10`, is the number of iterations (each iteration is `update every` seconds) to buffer data, + when the external database server is not available. If the server fails to receive the data after that many + failures, data loss on the connector instance is expected (Netdata will also log it). + +- `timeout ms = 20000`, is the timeout in milliseconds to wait for the external database server to process the data. + By default this is `2 * update_every * 1000`. + +- `send hosts matching = localhost *` includes one or more space separated patterns, using `*` as wildcard (any number + of times within each pattern). The patterns are checked against the hostname (the localhost is always checked as + `localhost`), allowing us to filter which hosts will be sent to the external database when this Netdata is a central + Netdata aggregating multiple hosts. A pattern starting with `!` gives a negative match. So to match all hosts named + `*db*` except hosts containing `*child*`, use `!*child* *db*` (so, the order is important: the first + pattern matching the hostname will be used - positive or negative). + +- `send charts matching = *` includes one or more space separated patterns, using `*` as wildcard (any number of times + within each pattern). The patterns are checked against both chart id and chart name. A pattern starting with `!` + gives a negative match. So to match all charts named `apps.*` except charts ending in `*reads`, use `!*reads + apps.*` (so, the order is important: the first pattern matching the chart id or the chart name will be used - + positive or negative). + +- `send names instead of ids = yes | no` controls the metric names Netdata should send to the external database. + Netdata supports names and IDs for charts and dimensions. Usually IDs are unique identifiers as read by the system + and names are human friendly labels (also unique). Most charts and metrics have the same ID and name, but in several + cases they are different: disks with device-mapper, interrupts, QoS classes, statsd synthetic charts, etc. + +- `send configured labels = yes | no` controls if labels defined in the `[host labels]` section in `netdata.conf` + should be sent to the external database + +- `send automatic labels = yes | no` controls if automatically created labels, like `_os_name` or `_architecture` + should be sent to the external database + +> Starting from Netdata v1.20 the host tags (defined in the `[backend]` section of `netdata.conf`) are parsed in +> accordance with a configured backend type and stored as host labels so that they can be reused in API responses and +> exporting connectors. The parsing is supported for graphite, json, opentsdb, and prometheus (default) backend types. +> You can check how the host tags were parsed using the /api/v1/info API call. But, keep in mind that backends subsystem +> is deprecated and will be deleted soon. Please move your existing tags to the `[host labels]` section. + +## HTTPS + +Netdata can send metrics to external databases using the TLS/SSL protocol. Unfortunately, some of +them does not support encrypted connections, so you will have to configure a reverse proxy to enable +HTTPS communication between Netdata and an external database. You can set up a reverse proxy with +[Nginx](/docs/Running-behind-nginx.md). + +## Exporting engine monitoring + +Netdata creates five charts in the dashboard, under the **Netdata Monitoring** section, to help you monitor the health +and performance of the exporting engine itself: + +1. **Buffered metrics**, the number of metrics Netdata added to the buffer for dispatching them to the + external database server. + +2. **Exporting data size**, the amount of data (in KB) Netdata added the buffer. + +3. **Exporting operations**, the number of operations performed by Netdata. + +4. **Exporting thread CPU usage**, the CPU resources consumed by the Netdata thread, that is responsible for sending + the metrics to the external database server. + +![image](https://cloud.githubusercontent.com/assets/2662304/20463536/eb196084-af3d-11e6-8ee5-ddbd3b4d8449.png) + +## Exporting engine alarms + +Netdata adds 3 alarms: + +1. `exporting_last_buffering`, number of seconds since the last successful buffering of exported data +2. `exporting_metrics_sent`, percentage of metrics sent to the external database server +3. `exporting_metrics_lost`, number of metrics lost due to repeating failures to contact the external database server + +![image](https://cloud.githubusercontent.com/assets/2662304/20463779/a46ed1c2-af43-11e6-91a5-07ca4533cac3.png) + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/TIMESCALE.md b/exporting/TIMESCALE.md new file mode 100644 index 000000000..c98003ed4 --- /dev/null +++ b/exporting/TIMESCALE.md @@ -0,0 +1,69 @@ + + +# Writing metrics to TimescaleDB + +Thanks to Netdata's community of developers and system administrators, and Mahlon Smith +([GitHub](https://github.com/mahlonsmith)/[Website](http://www.martini.nu/)) in particular, Netdata now supports +archiving metrics directly to TimescaleDB. + +What's TimescaleDB? Here's how their team defines the project on their [GitHub page](https://github.com/timescale/timescaledb): + +> TimescaleDB is an open-source database designed to make SQL scalable for time-series data. It is engineered up from +> PostgreSQL, providing automatic partitioning across time and space (partitioning key), as well as full SQL support. + +## Quickstart + +To get started archiving metrics to TimescaleDB right away, check out Mahlon's [`netdata-timescale-relay` +repository](https://github.com/mahlonsmith/netdata-timescale-relay) on GitHub. Please be aware that backends subsystem +is deprecated and Netdata configuration should be moved to the new `exporting conf` configuration file. Use +```conf +[json:my_instance] +``` +in `exporting.conf` instead of +```conf +[backend] + type = json +``` +in `netdata.conf`. + +This small program takes JSON streams from a Netdata client and writes them to a PostgreSQL (aka TimescaleDB) table. +You'll run this program in parallel with Netdata, and after a short [configuration +process](https://github.com/mahlonsmith/netdata-timescale-relay#configuration), your metrics should start populating +TimescaleDB. + +Finally, another member of Netdata's community has built a project that quickly launches Netdata, TimescaleDB, and +Grafana in easy-to-manage Docker containers. Rune Juhl Jacobsen's +[project](https://github.com/runejuhl/grafana-timescaledb) uses a `Makefile` to create everything, which makes it +perfect for testing and experimentation. + +## Netdata↔TimescaleDB in action + +Aside from creating incredible contributions to Netdata, Mahlon works at [LAIKA](https://www.laika.com/), an +Oregon-based animation studio that's helped create acclaimed films like _Coraline_ and _Kubo and the Two Strings_. + +As part of his work to maintain the company's infrastructure of render farms, workstations, and virtual machines, he's +using Netdata, `netdata-timescale-relay`, and TimescaleDB to store Netdata metrics alongside other data from other +sources. + +> LAIKA is a long-time PostgreSQL user and added TimescaleDB to their infrastructure in 2018 to help manage and store +> their IT metrics and time-series data. So far, the tool has been in production at LAIKA for over a year and helps them +> with their use case of time-based logging, where they record over 8 million metrics an hour for netdata content alone. + +By archiving Netdata metrics to a database like TimescaleDB, LAIKA can consolidate metrics data from distributed +machines efficiently. Mahlon can then correlate Netdata metrics with other sources directly in TimescaleDB. + +And, because LAIKA will soon be storing years worth of Netdata metrics data in TimescaleDB, they can analyze long-term +metrics as their films move from concept to final cut. + +Read the full blog post from LAIKA at the [TimescaleDB +blog](https://blog.timescale.com/blog/writing-it-metrics-from-netdata-to-timescaledb/amp/). + +Thank you to Mahlon, Rune, TimescaleDB, and the members of the Netdata community that requested and then built this +exporting connection between Netdata and TimescaleDB! + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2FTIMESCALE&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/WALKTHROUGH.md b/exporting/WALKTHROUGH.md new file mode 100644 index 000000000..ac1712916 --- /dev/null +++ b/exporting/WALKTHROUGH.md @@ -0,0 +1,259 @@ + + +# Netdata, Prometheus, Grafana stack + +## Intro + +In this article I will walk you through the basics of getting Netdata, Prometheus and Grafana all working together and +monitoring your application servers. This article will be using docker on your local workstation. We will be working +with docker in an ad-hoc way, launching containers that run `/bin/bash` and attaching a TTY to them. I use docker here +in a purely academic fashion and do not condone running Netdata in a container. I pick this method so individuals +without cloud accounts or access to VMs can try this out and for it's speed of deployment. + +## Why Netdata, Prometheus, and Grafana + +Some time ago I was introduced to Netdata by a coworker. We were attempting to troubleshoot python code which seemed to +be bottlenecked. I was instantly impressed by the amount of metrics Netdata exposes to you. I quickly added Netdata to +my set of go-to tools when troubleshooting systems performance. + +Some time ago, even later, I was introduced to Prometheus. Prometheus is a monitoring application which flips the normal +architecture around and polls rest endpoints for its metrics. This architectural change greatly simplifies and decreases +the time necessary to begin monitoring your applications. Compared to current monitoring solutions the time spent on +designing the infrastructure is greatly reduced. Running a single Prometheus server per application becomes feasible +with the help of Grafana. + +Grafana has been the go to graphing tool for… some time now. It's awesome, anyone that has used it knows it's awesome. +We can point Grafana at Prometheus and use Prometheus as a data source. This allows a pretty simple overall monitoring +architecture: Install Netdata on your application servers, point Prometheus at Netdata, and then point Grafana at +Prometheus. + +I'm omitting an important ingredient in this stack in order to keep this tutorial simple and that is service discovery. +My personal preference is to use Consul. Prometheus can plug into consul and automatically begin to scrape new hosts +that register a Netdata client with Consul. + +At the end of this tutorial you will understand how each technology fits together to create a modern monitoring stack. +This stack will offer you visibility into your application and systems performance. + +## Getting Started - Netdata + +To begin let's create our container which we will install Netdata on. We need to run a container, forward the necessary +port that Netdata listens on, and attach a tty so we can interact with the bash shell on the container. But before we do +this we want name resolution between the two containers to work. In order to accomplish this we will create a +user-defined network and attach both containers to this network. The first command we should run is: + +```sh +docker network create --driver bridge netdata-tutorial +``` + +With this user-defined network created we can now launch our container we will install Netdata on and point it to this +network. + +```sh +docker run -it --name netdata --hostname netdata --network=netdata-tutorial -p 19999:19999 centos:latest '/bin/bash' +``` + +This command creates an interactive tty session (`-it`), gives the container both a name in relation to the docker +daemon and a hostname (this is so you know what container is which when working in the shells and docker maps hostname +resolution to this container), forwards the local port 19999 to the container's port 19999 (`-p 19999:19999`), sets the +command to run (`/bin/bash`) and then chooses the base container images (`centos:latest`). After running this you should +be sitting inside the shell of the container. + +After we have entered the shell we can install Netdata. This process could not be easier. If you take a look at [this +link](/packaging/installer/README.md), the Netdata devs give us several one-liners to install Netdata. I have not had +any issues with these one liners and their bootstrapping scripts so far (If you guys run into anything do share). Run +the following command in your container. + +```sh +bash <(curl -Ss https://my-netdata.io/kickstart.sh) --dont-wait +``` + +After the install completes you should be able to hit the Netdata dashboard at (replace +localhost if you're doing this on a VM or have the docker container hosted on a machine not on your local system). If +this is your first time using Netdata I suggest you take a look around. The amount of time I've spent digging through +`/proc` and calculating my own metrics has been greatly reduced by this tool. Take it all in. + +Next I want to draw your attention to a particular endpoint. Navigate to + In your browser. This is the endpoint which +publishes all the metrics in a format which Prometheus understands. Let's take a look at one of these metrics. +`netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="system"} 0.0831255 1501271696000` This +metric is representing several things which I will go in more details in the section on Prometheus. For now understand +that this metric: `netdata_system_cpu_percentage_average` has several labels: (`chart`, `family`, `dimension`). This +corresponds with the first cpu chart you see on the Netdata dashboard. + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%204.00.45%20PM.png) + +This CHART is called `system.cpu`, The FAMILY is `cpu`, and the DIMENSION we are observing is `system`. You can begin to +draw links between the charts in Netdata to the Prometheus metrics format in this manner. + +## Prometheus + +We will be installing Prometheus in a container for purpose of demonstration. While Prometheus does have an official +container I would like to walk through the install process and setup on a fresh container. This will allow anyone +reading to migrate this tutorial to a VM or Server of any sort. + +Let's start another container in the same fashion as we did the Netdata container. + +```sh +docker run -it --name prometheus --hostname prometheus +--network=netdata-tutorial -p 9090:9090 centos:latest '/bin/bash' +``` + +This should drop you into a shell once again. Once there quickly install your favorite editor as we will be editing +files later in this tutorial. + +```sh +yum install vim -y +``` + +Prometheus provides a tarball of their latest stable versions [here](https://prometheus.io/download/). + +Let's download the latest version and install into your container. + +```sh +cd /tmp && curl -s https://api.github.com/repos/prometheus/prometheus/releases/latest \ +| grep "browser_download_url.*linux-amd64.tar.gz" \ +| cut -d '"' -f 4 \ +| wget -qi - + +mkdir /opt/prometheus + +sudo tar -xvf /tmp/prometheus-*linux-amd64.tar.gz -C /opt/prometheus --strip=1 +``` + +This should get Prometheus installed into the container. Let's test that we can run Prometheus and connect to it's web +interface. + +```sh +/opt/prometheus/prometheus +``` + +Now attempt to go to . You should be presented with the Prometheus homepage. This is a good +point to talk about Prometheus's data model which can be viewed here: +As explained we have two key elements in Prometheus metrics. We have the _metric_ and its _labels_. Labels allow for +granularity between metrics. Let's use our previous example to further explain. + +```conf +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="system"} 0.0831255 1501271696000 +``` + +Here our metric is `netdata_system_cpu_percentage_average` and our labels are `chart`, `family`, and `dimension`. The +last two values constitute the actual metric value for the metric type (gauge, counter, etc…). We can begin graphing +system metrics with this information, but first we need to hook up Prometheus to poll Netdata stats. + +Let's move our attention to Prometheus's configuration. Prometheus gets it config from the file located (in our example) +at `/opt/prometheus/prometheus.yml`. I won't spend an extensive amount of time going over the configuration values +documented here: . We will be adding a new job under the +`scrape_configs`. Let's make the `scrape_configs` section look like this (we can use the DNS name Netdata due to the +custom user-defined network we created in docker beforehand). + +```yaml +scrape_configs: + # The job name is added as a label `job=` to any timeseries scraped from this config. + - job_name: 'prometheus' + + # metrics_path defaults to '/metrics' + # scheme defaults to 'http'. + + static_configs: + - targets: ['localhost:9090'] + + - job_name: 'netdata' + + metrics_path: /api/v1/allmetrics + params: + format: [ prometheus ] + + static_configs: + - targets: ['netdata:19999'] +``` + +Let's start Prometheus once again by running `/opt/prometheus/prometheus`. If we now navigate to Prometheus at + we should see our target being successfully scraped. If we now go back to the +Prometheus's homepage and begin to type `netdata\_` Prometheus should auto complete metrics it is now scraping. + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%205.13.43%20PM.png) + +Let's now start exploring how we can graph some metrics. Back in our NetData container lets get the CPU spinning with a +pointless busy loop. On the shell do the following: + +```sh +[root@netdata /]# while true; do echo "HOT HOT HOT CPU"; done +``` + +Our NetData cpu graph should be showing some activity. Let's represent this in Prometheus. In order to do this let's +keep our metrics page open for reference: . We are +setting out to graph the data in the CPU chart so let's search for `system.cpu` in the metrics page above. We come +across a section of metrics with the first comments `# COMMENT homogeneous chart "system.cpu", context "system.cpu", +family "cpu", units "percentage"` followed by the metrics. This is a good start now let us drill down to the specific +metric we would like to graph. + +```conf +# COMMENT +netdata_system_cpu_percentage_average: dimension "system", value is percentage, gauge, dt 1501275951 to 1501275951 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="system"} 0.0000000 1501275951000 +``` + +Here we learn that the metric name we care about is `netdata_system_cpu_percentage_average` so throw this into +Prometheus and see what we get. We should see something similar to this (I shut off my busy loop) + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%205.47.53%20PM.png) + +This is a good step toward what we want. Also make note that Prometheus will tag on an `instance` label for us which +corresponds to our statically defined job in the configuration file. This allows us to tailor our queries to specific +instances. Now we need to isolate the dimension we want in our query. To do this let us refine the query slightly. Let's +query the dimension also. Place this into our query text box. +`netdata_system_cpu_percentage_average{dimension="system"}` We now wind up with the following graph. + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%205.54.40%20PM.png) + +Awesome, this is exactly what we wanted. If you haven't caught on yet we can emulate entire charts from NetData by using +the `chart` dimension. If you'd like you can combine the `chart` and `instance` dimension to create per-instance charts. +Let's give this a try: `netdata_system_cpu_percentage_average{chart="system.cpu", instance="netdata:19999"}` + +This is the basics of using Prometheus to query NetData. I'd advise everyone at this point to read [this +page](/exporting/prometheus/#using-netdata-with-prometheus). The key point here is that NetData can export metrics from +its internal DB or can send metrics _as-collected_ by specifying the `source=as-collected` URL parameter like so. + If you choose to use +this method you will need to use Prometheus's set of functions here: to +obtain useful metrics as you are now dealing with raw counters from the system. For example you will have to use the +`irate()` function over a counter to get that metric's rate per second. If your graphing needs are met by using the +metrics returned by NetData's internal database (not specifying any source= URL parameter) then use that. If you find +limitations then consider re-writing your queries using the raw data and using Prometheus functions to get the desired +chart. + +## Grafana + +Finally we make it to grafana. This is the easiest part in my opinion. This time we will actually run the official +grafana docker container as all configuration we need to do is done via the GUI. Let's run the following command: + +```sh +docker run -i -p 3000:3000 --network=netdata-tutorial grafana/grafana +``` + +This will get grafana running at . Let's go there and +login using the credentials Admin:Admin. + +The first thing we want to do is click "Add data source". Let's make it look like the following screenshot + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%206.36.55%20PM.png) + +With this completed let's graph! Create a new Dashboard by clicking on the top left Grafana Icon and create a new graph +in that dashboard. Fill in the query like we did above and save. + +![](https://github.com/ldelossa/NetdataTutorial/raw/master/Screen%20Shot%202017-07-28%20at%206.39.38%20PM.png) + +## Conclusion + +There you have it, a complete systems monitoring stack which is very easy to deploy. From here I would begin to +understand how Prometheus and a service discovery mechanism such as Consul can play together nicely. My current prod +deployments automatically register Netdata services into Consul and Prometheus automatically begins to scrape them. Once +achieved you do not have to think about the monitoring system until Prometheus cannot keep up with your scale. Once this +happens there are options presented in the Prometheus documentation for solving this. Hope this was helpful, happy +monitoring. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2FWALKTHROUGH&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/aws_kinesis/Makefile.am b/exporting/aws_kinesis/Makefile.am new file mode 100644 index 000000000..161784b8f --- /dev/null +++ b/exporting/aws_kinesis/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/exporting/aws_kinesis/README.md b/exporting/aws_kinesis/README.md new file mode 100644 index 000000000..299fec581 --- /dev/null +++ b/exporting/aws_kinesis/README.md @@ -0,0 +1,58 @@ + + +# Export metrics to AWS Kinesis Data Streams + +## Prerequisites + +To use AWS Kinesis for metric collecting and processing, you should first +[install](https://docs.aws.amazon.com/en_us/sdk-for-cpp/v1/developer-guide/setup.html) AWS SDK for C++. +`libcrypto`, `libssl`, and `libcurl` are also required to compile Netdata with Kinesis support enabled. Next, Netdata +should be re-installed from the source. The installer will detect that the required libraries are now available. + +If the AWS SDK for C++ is being installed from source, it is useful to set `-DBUILD_ONLY=kinesis`. Otherwise, the +build process could take a very long time. Note, that the default installation path for the libraries is +`/usr/local/lib64`. Many Linux distributions don't include this path as the default one for a library search, so it is +advisable to use the following options to `cmake` while building the AWS SDK: + +```sh +sudo cmake -DCMAKE_INSTALL_PREFIX=/usr -DBUILD_ONLY=kinesis +``` + +The `-DCMAKE_INSTALL_PREFIX=/usr` option also ensures that +[third party dependencies](https://github.com/aws/aws-sdk-cpp#third-party-dependencies) are installed in your system +during the SDK build process. + +## Configuration + +To enable data sending to the Kinesis service, run `./edit-config exporting.conf` in the Netdata configuration directory +and set the following options: + +```conf +[kinesis:my_instance] + enabled = yes + destination = us-east-1 +``` + +Set the `destination` option to an AWS region. + +Set AWS credentials and stream name: + +```conf + # AWS credentials + aws_access_key_id = your_access_key_id + aws_secret_access_key = your_secret_access_key + # destination stream + stream name = your_stream_name +``` + +Alternatively, you can set AWS credentials for the `netdata` user using AWS SDK for C++ [standard methods](https://docs.aws.amazon.com/sdk-for-cpp/v1/developer-guide/credentials.html). + +Netdata automatically computes a partition key for every record with the purpose to distribute records across +available shards evenly. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Faws_kinesis%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/aws_kinesis/aws_kinesis.c b/exporting/aws_kinesis/aws_kinesis.c new file mode 100644 index 000000000..036afb49f --- /dev/null +++ b/exporting/aws_kinesis/aws_kinesis.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "aws_kinesis.h" + +/** + * Clean AWS Kinesis * + */ +void aws_kinesis_cleanup(struct instance *instance) +{ + info("EXPORTING: cleaning up instance %s ...", instance->config.name); + kinesis_shutdown(instance->connector_specific_data); + + freez(instance->connector_specific_data); + + struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config; + if (connector_specific_config) { + freez(connector_specific_config->auth_key_id); + freez(connector_specific_config->secure_key); + freez(connector_specific_config->stream_name); + + freez(connector_specific_config); + } + + info("EXPORTING: instance %s exited", instance->config.name); + instance->exited = 1; +} + +/** + * Initialize AWS Kinesis connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_aws_kinesis_instance(struct instance *instance) +{ + instance->worker = aws_kinesis_connector_worker; + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_json_plaintext; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_json_plaintext; + else + instance->metric_formatting = format_dimension_stored_json_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = NULL; + + instance->prepare_header = NULL; + instance->check_response = NULL; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for AWS Kinesis exporting connector instance %s", instance->config.name); + return 1; + } + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + if (!instance->engine->aws_sdk_initialized) { + aws_sdk_init(); + instance->engine->aws_sdk_initialized = 1; + } + + struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config; + struct aws_kinesis_specific_data *connector_specific_data = callocz(1, sizeof(struct aws_kinesis_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + if (!strcmp(connector_specific_config->stream_name, "")) { + error("stream name is a mandatory Kinesis parameter but it is not configured"); + return 1; + } + + kinesis_init( + (void *)connector_specific_data, + instance->config.destination, + connector_specific_config->auth_key_id, + connector_specific_config->secure_key, + instance->config.timeoutms); + + return 0; +} + +/** + * AWS Kinesis connector worker + * + * Runs in a separate thread for every instance. + * + * @param instance_p an instance data structure. + */ +void aws_kinesis_connector_worker(void *instance_p) +{ + struct instance *instance = (struct instance *)instance_p; + struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config; + struct aws_kinesis_specific_data *connector_specific_data = instance->connector_specific_data; + + while (!instance->engine->exit) { + unsigned long long partition_key_seq = 0; + struct stats *stats = &instance->stats; + + uv_mutex_lock(&instance->mutex); + while (!instance->data_is_ready) + uv_cond_wait(&instance->cond_var, &instance->mutex); + instance->data_is_ready = 0; + + if (unlikely(instance->engine->exit)) { + uv_mutex_unlock(&instance->mutex); + break; + } + + // reset the monitoring chart counters + stats->received_bytes = + stats->sent_bytes = + stats->sent_metrics = + stats->lost_metrics = + stats->receptions = + stats->transmission_successes = + stats->transmission_failures = + stats->data_lost_events = + stats->lost_bytes = + stats->reconnects = 0; + + BUFFER *buffer = (BUFFER *)instance->buffer; + size_t buffer_len = buffer_strlen(buffer); + + stats->buffered_bytes = buffer_len; + + size_t sent = 0; + + while (sent < buffer_len) { + char partition_key[KINESIS_PARTITION_KEY_MAX + 1]; + snprintf(partition_key, KINESIS_PARTITION_KEY_MAX, "netdata_%llu", partition_key_seq++); + size_t partition_key_len = strnlen(partition_key, KINESIS_PARTITION_KEY_MAX); + + const char *first_char = buffer_tostring(buffer) + sent; + + size_t record_len = 0; + + // split buffer into chunks of maximum allowed size + if (buffer_len - sent < KINESIS_RECORD_MAX - partition_key_len) { + record_len = buffer_len - sent; + } else { + record_len = KINESIS_RECORD_MAX - partition_key_len; + while (record_len && *(first_char + record_len - 1) != '\n') + record_len--; + } + char error_message[ERROR_LINE_MAX + 1] = ""; + + debug( + D_BACKEND, + "EXPORTING: kinesis_put_record(): dest = %s, id = %s, key = %s, stream = %s, partition_key = %s, \ + buffer = %zu, record = %zu", + instance->config.destination, + connector_specific_config->auth_key_id, + connector_specific_config->secure_key, + connector_specific_config->stream_name, + partition_key, + buffer_len, + record_len); + + kinesis_put_record( + connector_specific_data, connector_specific_config->stream_name, partition_key, first_char, record_len); + + sent += record_len; + stats->transmission_successes++; + + size_t sent_bytes = 0, lost_bytes = 0; + + if (unlikely(kinesis_get_result( + connector_specific_data->request_outcomes, error_message, &sent_bytes, &lost_bytes))) { + // oops! we couldn't send (all or some of the) data + error("EXPORTING: %s", error_message); + error( + "EXPORTING: failed to write data to database backend '%s'. Willing to write %zu bytes, wrote %zu bytes.", + instance->config.destination, sent_bytes, sent_bytes - lost_bytes); + + stats->transmission_failures++; + stats->data_lost_events++; + stats->lost_bytes += lost_bytes; + + // estimate the number of lost metrics + stats->lost_metrics += (collected_number)( + stats->buffered_metrics * + (buffer_len && (lost_bytes > buffer_len) ? (double)lost_bytes / buffer_len : 1)); + + break; + } else { + stats->receptions++; + } + + if (unlikely(instance->engine->exit)) + break; + } + + stats->sent_bytes += sent; + if (likely(sent == buffer_len)) + stats->sent_metrics = stats->buffered_metrics; + + buffer_flush(buffer); + + send_internal_metrics(instance); + + stats->buffered_metrics = 0; + + uv_mutex_unlock(&instance->mutex); + +#ifdef UNIT_TESTING + return; +#endif + } + + aws_kinesis_cleanup(instance); +} diff --git a/exporting/aws_kinesis/aws_kinesis.h b/exporting/aws_kinesis/aws_kinesis.h new file mode 100644 index 000000000..d88a45861 --- /dev/null +++ b/exporting/aws_kinesis/aws_kinesis.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_KINESIS_H +#define NETDATA_EXPORTING_KINESIS_H + +#include "exporting/exporting_engine.h" +#include "exporting/json/json.h" +#include "aws_kinesis_put_record.h" + +#define KINESIS_PARTITION_KEY_MAX 256 +#define KINESIS_RECORD_MAX 1024 * 1024 + +int init_aws_kinesis_instance(struct instance *instance); +void aws_kinesis_connector_worker(void *instance_p); + +#endif //NETDATA_EXPORTING_KINESIS_H diff --git a/exporting/aws_kinesis/aws_kinesis_put_record.cc b/exporting/aws_kinesis/aws_kinesis_put_record.cc new file mode 100644 index 000000000..b20ec1373 --- /dev/null +++ b/exporting/aws_kinesis/aws_kinesis_put_record.cc @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include +#include +#include +#include +#include +#include +#include "aws_kinesis_put_record.h" + +using namespace Aws; + +static SDKOptions options; + +struct request_outcome { + Kinesis::Model::PutRecordOutcomeCallable future_outcome; + size_t data_len; +}; + +/** + * Initialize AWS SDK API + */ +void aws_sdk_init() +{ + InitAPI(options); +} + +/** + * Shutdown AWS SDK API + */ +void aws_sdk_shutdown() +{ + ShutdownAPI(options); +} + +/** + * Initialize a client and a data structure for request outcomes + * + * @param kinesis_specific_data_p a pointer to a structure with client and request outcome information. + * @param region AWS region. + * @param access_key_id AWS account access key ID. + * @param secret_key AWS account secret access key. + * @param timeout communication timeout. + */ +void kinesis_init( + void *kinesis_specific_data_p, const char *region, const char *access_key_id, const char *secret_key, + const long timeout) +{ + struct aws_kinesis_specific_data *kinesis_specific_data = + (struct aws_kinesis_specific_data *)kinesis_specific_data_p; + + Client::ClientConfiguration config; + + config.region = region; + config.requestTimeoutMs = timeout; + config.connectTimeoutMs = timeout; + + Kinesis::KinesisClient *client; + + if (access_key_id && *access_key_id && secret_key && *secret_key) { + client = New("client", Auth::AWSCredentials(access_key_id, secret_key), config); + } else { + client = New("client", config); + } + kinesis_specific_data->client = (void *)client; + + Vector *request_outcomes; + + request_outcomes = new Vector; + kinesis_specific_data->request_outcomes = (void *)request_outcomes; +} + +/** + * Deallocate Kinesis specific data + * + * @param kinesis_specific_data_p a pointer to a structure with client and request outcome information. + */ +void kinesis_shutdown(void *kinesis_specific_data_p) +{ + struct aws_kinesis_specific_data *kinesis_specific_data = + (struct aws_kinesis_specific_data *)kinesis_specific_data_p; + + Delete((Kinesis::KinesisClient *)kinesis_specific_data->client); + delete (Vector *)kinesis_specific_data->request_outcomes; +} + +/** + * Send data to the Kinesis service + * + * @param kinesis_specific_data_p a pointer to a structure with client and request outcome information. + * @param stream_name the name of a stream to send to. + * @param partition_key a partition key which automatically maps data to a specific stream. + * @param data a data buffer to send to the stream. + * @param data_len the length of the data buffer. + */ +void kinesis_put_record( + void *kinesis_specific_data_p, const char *stream_name, const char *partition_key, const char *data, + size_t data_len) +{ + struct aws_kinesis_specific_data *kinesis_specific_data = + (struct aws_kinesis_specific_data *)kinesis_specific_data_p; + Kinesis::Model::PutRecordRequest request; + + request.SetStreamName(stream_name); + request.SetPartitionKey(partition_key); + request.SetData(Utils::ByteBuffer((unsigned char *)data, data_len)); + + ((Vector *)(kinesis_specific_data->request_outcomes))->push_back( + { ((Kinesis::KinesisClient *)(kinesis_specific_data->client))->PutRecordCallable(request), data_len }); +} + +/** + * Get results from service responces + * + * @param request_outcomes_p request outcome information. + * @param error_message report error message to a caller. + * @param sent_bytes report to a caller how many bytes was successfuly sent. + * @param lost_bytes report to a caller how many bytes was lost during transmission. + * @return Returns 0 if all data was sent successfully, 1 when data was lost on transmission + */ +int kinesis_get_result(void *request_outcomes_p, char *error_message, size_t *sent_bytes, size_t *lost_bytes) +{ + Vector *request_outcomes = (Vector *)request_outcomes_p; + Kinesis::Model::PutRecordOutcome outcome; + *sent_bytes = 0; + *lost_bytes = 0; + + for (auto request_outcome = request_outcomes->begin(); request_outcome != request_outcomes->end();) { + std::future_status status = request_outcome->future_outcome.wait_for(std::chrono::microseconds(100)); + + if (status == std::future_status::ready || status == std::future_status::deferred) { + outcome = request_outcome->future_outcome.get(); + *sent_bytes += request_outcome->data_len; + + if (!outcome.IsSuccess()) { + *lost_bytes += request_outcome->data_len; + outcome.GetError().GetMessage().copy(error_message, ERROR_LINE_MAX); + } + + request_outcomes->erase(request_outcome); + } else { + ++request_outcome; + } + } + + if (*lost_bytes) { + return 1; + } + + return 0; +} diff --git a/exporting/aws_kinesis/aws_kinesis_put_record.h b/exporting/aws_kinesis/aws_kinesis_put_record.h new file mode 100644 index 000000000..321baf669 --- /dev/null +++ b/exporting/aws_kinesis/aws_kinesis_put_record.h @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_KINESIS_PUT_RECORD_H +#define NETDATA_EXPORTING_KINESIS_PUT_RECORD_H + +#define ERROR_LINE_MAX 1023 + +#ifdef __cplusplus +extern "C" { +#endif + +struct aws_kinesis_specific_data { + void *client; + void *request_outcomes; +}; + +void aws_sdk_init(); +void aws_sdk_shutdown(); + +void kinesis_init( + void *kinesis_specific_data_p, const char *region, const char *access_key_id, const char *secret_key, + const long timeout); +void kinesis_shutdown(void *client); + +void kinesis_put_record( + void *kinesis_specific_data_p, const char *stream_name, const char *partition_key, const char *data, + size_t data_len); + +int kinesis_get_result(void *request_outcomes_p, char *error_message, size_t *sent_bytes, size_t *lost_bytes); + +#ifdef __cplusplus +} +#endif + +#endif //NETDATA_EXPORTING_KINESIS_PUT_RECORD_H diff --git a/exporting/check_filters.c b/exporting/check_filters.c new file mode 100644 index 000000000..cfe0b4ce4 --- /dev/null +++ b/exporting/check_filters.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +/** + * Check if the connector instance should export the host metrics + * + * @param instance an exporting connector instance. + * @param host a data collecting host. + * @return Returns 1 if the connector instance should export the host metrics + */ +int rrdhost_is_exportable(struct instance *instance, RRDHOST *host) +{ + if (host->exporting_flags == NULL) + host->exporting_flags = callocz(instance->engine->instance_num, sizeof(size_t)); + + RRDHOST_FLAGS *flags = &host->exporting_flags[instance->index]; + + if (unlikely((*flags & (RRDHOST_FLAG_BACKEND_SEND | RRDHOST_FLAG_BACKEND_DONT_SEND)) == 0)) { + char *host_name = (host == localhost) ? "localhost" : host->hostname; + + if (!instance->config.hosts_pattern || simple_pattern_matches(instance->config.hosts_pattern, host_name)) { + *flags |= RRDHOST_FLAG_BACKEND_SEND; + info("enabled exporting of host '%s' for instance '%s'", host_name, instance->config.name); + } else { + *flags |= RRDHOST_FLAG_BACKEND_DONT_SEND; + info("disabled exporting of host '%s' for instance '%s'", host_name, instance->config.name); + } + } + + if (likely(*flags & RRDHOST_FLAG_BACKEND_SEND)) + return 1; + else + return 0; +} + +/** + * Check if the connector instance should export the chart + * + * @param instance an exporting connector instance. + * @param st a chart. + * @return Returns 1 if the connector instance should export the chart + */ +int rrdset_is_exportable(struct instance *instance, RRDSET *st) +{ + RRDHOST *host = st->rrdhost; + + if (st->exporting_flags == NULL) + st->exporting_flags = callocz(instance->engine->instance_num, sizeof(size_t)); + + RRDSET_FLAGS *flags = &st->exporting_flags[instance->index]; + + if(unlikely(*flags & RRDSET_FLAG_BACKEND_IGNORE)) + return 0; + + if(unlikely(!(*flags & RRDSET_FLAG_BACKEND_SEND))) { + // we have not checked this chart + if(simple_pattern_matches(instance->config.charts_pattern, st->id) || simple_pattern_matches(instance->config.charts_pattern, st->name)) + *flags |= RRDSET_FLAG_BACKEND_SEND; + else { + *flags |= RRDSET_FLAG_BACKEND_IGNORE; + debug(D_BACKEND, "BACKEND: not sending chart '%s' of host '%s', because it is disabled for backends.", st->id, host->hostname); + return 0; + } + } + + if(unlikely(!rrdset_is_available_for_backends(st))) { + debug(D_BACKEND, "BACKEND: not sending chart '%s' of host '%s', because it is not available for backends.", st->id, host->hostname); + return 0; + } + + if(unlikely(st->rrd_memory_mode == RRD_MEMORY_MODE_NONE && !(EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED))) { + debug(D_BACKEND, "BACKEND: not sending chart '%s' of host '%s' because its memory mode is '%s' and the backend requires database access.", st->id, host->hostname, rrd_memory_mode_name(host->rrd_memory_mode)); + return 0; + } + + return 1; +} diff --git a/exporting/clean_connectors.c b/exporting/clean_connectors.c new file mode 100644 index 000000000..890e8daac --- /dev/null +++ b/exporting/clean_connectors.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +/** + * Clean the instance config. + * + * @param config an instance config structure. + */ +static void clean_instance_config(struct instance_config *config) +{ + if(!config) + return; + + freez((void *)config->type_name); + freez((void *)config->name); + freez((void *)config->destination); + freez((void *)config->prefix); + freez((void *)config->hostname); + + simple_pattern_free(config->charts_pattern); + + simple_pattern_free(config->hosts_pattern); +} + +/** + * Clean the allocated variables + * + * @param instance an instance data structure. + */ +void clean_instance(struct instance *instance) +{ + clean_instance_config(&instance->config); + buffer_free(instance->labels); + + uv_cond_destroy(&instance->cond_var); + // uv_mutex_destroy(&instance->mutex); +} + +/** + * Clean up a simple connector instance on Netdata exit + * + * @param instance an instance data structure. + */ +void simple_connector_cleanup(struct instance *instance) +{ + info("EXPORTING: cleaning up instance %s ...", instance->config.name); + + struct simple_connector_data *simple_connector_data = + (struct simple_connector_data *)instance->connector_specific_data; + + buffer_free(instance->buffer); + buffer_free(simple_connector_data->buffer); + buffer_free(simple_connector_data->header); + + struct simple_connector_buffer *next_buffer = simple_connector_data->first_buffer; + for (int i = 0; i < instance->config.buffer_on_failures; i++) { + struct simple_connector_buffer *current_buffer = next_buffer; + next_buffer = next_buffer->next; + + buffer_free(current_buffer->header); + buffer_free(current_buffer->buffer); + freez(current_buffer); + } + +#ifdef ENABLE_HTTPS + if (simple_connector_data->conn) + SSL_free(simple_connector_data->conn); +#endif + + freez(simple_connector_data); + + struct simple_connector_config *simple_connector_config = + (struct simple_connector_config *)instance->config.connector_specific_config; + freez(simple_connector_config); + + info("EXPORTING: instance %s exited", instance->config.name); + instance->exited = 1; + + return; +} diff --git a/exporting/exporting.conf b/exporting/exporting.conf new file mode 100644 index 000000000..c2e902c05 --- /dev/null +++ b/exporting/exporting.conf @@ -0,0 +1,89 @@ +[exporting:global] + enabled = no + # send configured labels = yes + # send automatic labels = no + # update every = 10 + +[prometheus:exporter] + # data source = average + # send names instead of ids = yes + # send configured labels = yes + # send automatic labels = no + # send charts matching = * + # send hosts matching = localhost * + # prefix = netdata + +# An example configuration for graphite, json, opentsdb exporting connectors +# [graphite:my_graphite_instance] + # enabled = no + # destination = localhost + # data source = average + # prefix = netdata + # hostname = my_hostname + # update every = 10 + # buffer on failures = 10 + # timeout ms = 20000 + # send names instead of ids = yes + # send charts matching = * + # send hosts matching = localhost * + +# [prometheus_remote_write:my_prometheus_remote_write_instance] + # enabled = no + # destination = localhost + # remote write URL path = /receive + # data source = average + # prefix = netdata + # hostname = my_hostname + # update every = 10 + # buffer on failures = 10 + # timeout ms = 20000 + # send names instead of ids = yes + # send charts matching = * + # send hosts matching = localhost * + +# [kinesis:my_kinesis_instance] + # enabled = no + # destination = us-east-1 + # stream name = netdata + # aws_access_key_id = my_access_key_id + # aws_secret_access_key = my_aws_secret_access_key + # data source = average + # prefix = netdata + # hostname = my_hostname + # update every = 10 + # buffer on failures = 10 + # timeout ms = 20000 + # send names instead of ids = yes + # send charts matching = * + # send hosts matching = localhost * + +# [pubsub:my_pubsub_instance] + # enabled = no + # destination = pubsub.googleapis.com + # credentials file = /etc/netdata/pubsub_credentials.json + # project id = my_project + # topic id = my_topic + # data source = average + # prefix = netdata + # hostname = my_hostname + # update every = 10 + # buffer on failures = 10 + # timeout ms = 20000 + # send names instead of ids = yes + # send charts matching = * + # send hosts matching = localhost * + +# [mongodb:my_mongodb_instance] + # enabled = no + # destination = localhost + # database = my_database + # collection = my_collection + # data source = average + # prefix = netdata + # hostname = my_hostname + # update every = 10 + # buffer on failures = 10 + # timeout ms = 20000 + # send names instead of ids = yes + # send charts matching = * + # send hosts matching = localhost * diff --git a/exporting/exporting_engine.c b/exporting/exporting_engine.c new file mode 100644 index 000000000..6a1320cd1 --- /dev/null +++ b/exporting/exporting_engine.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +static struct engine *engine = NULL; + +/** + * Exporting Clean Engine + * + * Clean all variables allocated inside engine structure + * + * @param en a pointer to the strcuture that will be cleaned. + */ +static void exporting_clean_engine() +{ + if (!engine) + return; + +#if HAVE_KINESIS + if (engine->aws_sdk_initialized) + aws_sdk_shutdown(); +#endif + +#if ENABLE_PROMETHEUS_REMOTE_WRITE + if (engine->protocol_buffers_initialized) + protocol_buffers_shutdown(); +#endif + + //Cleanup web api + prometheus_clean_server_root(); + + for (struct instance *instance = engine->instance_root; instance;) { + struct instance *current_instance = instance; + instance = instance->next; + + clean_instance(current_instance); + } + + freez((void *)engine->config.hostname); + freez(engine); +} + +/** + * Clean up the main exporting thread and all connector workers on Netdata exit + * + * @param ptr thread data. + */ +static void exporting_main_cleanup(void *ptr) +{ + struct netdata_static_thread *static_thread = (struct netdata_static_thread *)ptr; + static_thread->enabled = NETDATA_MAIN_THREAD_EXITING; + + info("cleaning up..."); + + if (!engine) { + static_thread->enabled = NETDATA_MAIN_THREAD_EXITED; + return; + } + + engine->exit = 1; + + int found = 0; + usec_t max = 2 * USEC_PER_SEC, step = 50000; + + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (!instance->exited) { + found++; + info("stopping worker for instance %s", instance->config.name); + uv_mutex_unlock(&instance->mutex); + instance->data_is_ready = 1; + uv_cond_signal(&instance->cond_var); + } else + info("found stopped worker for instance %s", instance->config.name); + } + + while (found && max > 0) { + max -= step; + info("Waiting %d exporting connectors to finish...", found); + sleep_usec(step); + found = 0; + + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (!instance->exited) + found++; + } + } + + exporting_clean_engine(); + static_thread->enabled = NETDATA_MAIN_THREAD_EXITED; +} + +/** + * Exporting engine main + * + * The main thread used to control the exporting engine. + * + * @param ptr a pointer to netdata_static_structure. + * + * @return It always returns NULL. + */ +void *exporting_main(void *ptr) +{ + netdata_thread_cleanup_push(exporting_main_cleanup, ptr); + + engine = read_exporting_config(); + if (!engine) { + info("EXPORTING: no exporting connectors configured"); + goto cleanup; + } + + if (init_connectors(engine) != 0) { + error("EXPORTING: cannot initialize exporting connectors"); + send_statistics("EXPORTING_START", "FAIL", "-"); + goto cleanup; + } + + RRDSET *st_main_rusage = NULL; + RRDDIM *rd_main_user = NULL; + RRDDIM *rd_main_system = NULL; + create_main_rusage_chart(&st_main_rusage, &rd_main_user, &rd_main_system); + + usec_t step_ut = localhost->rrd_update_every * USEC_PER_SEC; + heartbeat_t hb; + heartbeat_init(&hb); + + while (!netdata_exit) { + heartbeat_next(&hb, step_ut); + engine->now = now_realtime_sec(); + + if (mark_scheduled_instances(engine)) + prepare_buffers(engine); + + send_main_rusage(st_main_rusage, rd_main_user, rd_main_system); + +#ifdef UNIT_TESTING + return NULL; +#endif + } + +cleanup: + netdata_thread_cleanup_pop(1); + return NULL; +} diff --git a/exporting/exporting_engine.h b/exporting/exporting_engine.h new file mode 100644 index 000000000..1d9feb7dd --- /dev/null +++ b/exporting/exporting_engine.h @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_ENGINE_H +#define NETDATA_EXPORTING_ENGINE_H 1 + +#include "daemon/common.h" + +#include + +#define exporter_get(section, name, value) expconfig_get(&exporting_config, section, name, value) +#define exporter_get_number(section, name, value) expconfig_get_number(&exporting_config, section, name, value) +#define exporter_get_boolean(section, name, value) expconfig_get_boolean(&exporting_config, section, name, value) + +extern struct config exporting_config; + +#define EXPORTING_UPDATE_EVERY_OPTION_NAME "update every" +#define EXPORTING_UPDATE_EVERY_DEFAULT 10 + +typedef enum exporting_options { + EXPORTING_OPTION_NON = 0, + + EXPORTING_SOURCE_DATA_AS_COLLECTED = (1 << 0), + EXPORTING_SOURCE_DATA_AVERAGE = (1 << 1), + EXPORTING_SOURCE_DATA_SUM = (1 << 2), + + EXPORTING_OPTION_SEND_CONFIGURED_LABELS = (1 << 3), + EXPORTING_OPTION_SEND_AUTOMATIC_LABELS = (1 << 4), + EXPORTING_OPTION_USE_TLS = (1 << 5), + + EXPORTING_OPTION_SEND_NAMES = (1 << 16) +} EXPORTING_OPTIONS; + +#define EXPORTING_OPTIONS_SOURCE_BITS \ + (EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_SOURCE_DATA_SUM) +#define EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) (exporting_options & EXPORTING_OPTIONS_SOURCE_BITS) + +#define sending_labels_configured(instance) \ + (instance->config.options & (EXPORTING_OPTION_SEND_CONFIGURED_LABELS | EXPORTING_OPTION_SEND_AUTOMATIC_LABELS)) + +#define should_send_label(instance, label) \ + ((instance->config.options & EXPORTING_OPTION_SEND_CONFIGURED_LABELS && \ + label->label_source == LABEL_SOURCE_NETDATA_CONF) || \ + (instance->config.options & EXPORTING_OPTION_SEND_AUTOMATIC_LABELS && \ + label->label_source != LABEL_SOURCE_NETDATA_CONF)) + +typedef enum exporting_connector_types { + EXPORTING_CONNECTOR_TYPE_UNKNOWN, // Invalid type + EXPORTING_CONNECTOR_TYPE_GRAPHITE, // Send plain text to Graphite + EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP, // Send data to Graphite using HTTP API + EXPORTING_CONNECTOR_TYPE_JSON, // Send data in JSON format + EXPORTING_CONNECTOR_TYPE_JSON_HTTP, // Send data in JSON format using HTTP API + EXPORTING_CONNECTOR_TYPE_OPENTSDB, // Send data to OpenTSDB using telnet API + EXPORTING_CONNECTOR_TYPE_OPENTSDB_HTTP, // Send data to OpenTSDB using HTTP API + EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE, // User selected to use Prometheus backend + EXPORTING_CONNECTOR_TYPE_KINESIS, // Send message to AWS Kinesis + EXPORTING_CONNECTOR_TYPE_PUBSUB, // Send message to Google Cloud Pub/Sub + EXPORTING_CONNECTOR_TYPE_MONGODB, // Send data to MongoDB collection + EXPORTING_CONNECTOR_TYPE_NUM // Number of backend types +} EXPORTING_CONNECTOR_TYPE; + +struct engine; + +struct instance_config { + EXPORTING_CONNECTOR_TYPE type; + const char *type_name; + + const char *name; + const char *destination; + const char *prefix; + const char *hostname; + + int update_every; + int buffer_on_failures; + long timeoutms; + + EXPORTING_OPTIONS options; + SIMPLE_PATTERN *charts_pattern; + SIMPLE_PATTERN *hosts_pattern; + + void *connector_specific_config; +}; + +struct simple_connector_config { + int default_port; +}; + +struct simple_connector_buffer { + BUFFER *header; + BUFFER *buffer; + + size_t buffered_metrics; + size_t buffered_bytes; + + int used; + + struct simple_connector_buffer *next; +}; + +struct simple_connector_data { + void *connector_specific_data; + + size_t total_buffered_metrics; + + BUFFER *header; + BUFFER *buffer; + size_t buffered_metrics; + size_t buffered_bytes; + + struct simple_connector_buffer *previous_buffer; + struct simple_connector_buffer *first_buffer; + struct simple_connector_buffer *last_buffer; + +#ifdef ENABLE_HTTPS + SSL *conn; //SSL connection + int flags; //The flags for SSL connection +#endif +}; + +struct prometheus_remote_write_specific_config { + char *remote_write_path; +}; + +struct aws_kinesis_specific_config { + char *stream_name; + char *auth_key_id; + char *secure_key; +}; + +struct pubsub_specific_config { + char *credentials_file; + char *project_id; + char *topic_id; +}; + +struct mongodb_specific_config { + char *database; + char *collection; +}; + +struct engine_config { + const char *hostname; + int update_every; +}; + +struct stats { + collected_number buffered_metrics; + collected_number lost_metrics; + collected_number sent_metrics; + collected_number buffered_bytes; + collected_number lost_bytes; + collected_number sent_bytes; + collected_number received_bytes; + collected_number transmission_successes; + collected_number data_lost_events; + collected_number reconnects; + collected_number transmission_failures; + collected_number receptions; + + int initialized; + + RRDSET *st_metrics; + RRDDIM *rd_buffered_metrics; + RRDDIM *rd_lost_metrics; + RRDDIM *rd_sent_metrics; + + RRDSET *st_bytes; + RRDDIM *rd_buffered_bytes; + RRDDIM *rd_lost_bytes; + RRDDIM *rd_sent_bytes; + RRDDIM *rd_received_bytes; + + RRDSET *st_ops; + RRDDIM *rd_transmission_successes; + RRDDIM *rd_data_lost_events; + RRDDIM *rd_reconnects; + RRDDIM *rd_transmission_failures; + RRDDIM *rd_receptions; + + RRDSET *st_rusage; + RRDDIM *rd_user; + RRDDIM *rd_system; +}; + +struct instance { + struct instance_config config; + void *buffer; + void (*worker)(void *instance_p); + struct stats stats; + + int scheduled; + int disabled; + int skip_host; + int skip_chart; + + BUFFER *labels; + + time_t after; + time_t before; + + uv_thread_t thread; + uv_mutex_t mutex; + uv_cond_t cond_var; + int data_is_ready; + + int (*start_batch_formatting)(struct instance *instance); + int (*start_host_formatting)(struct instance *instance, RRDHOST *host); + int (*start_chart_formatting)(struct instance *instance, RRDSET *st); + int (*metric_formatting)(struct instance *instance, RRDDIM *rd); + int (*end_chart_formatting)(struct instance *instance, RRDSET *st); + int (*end_host_formatting)(struct instance *instance, RRDHOST *host); + int (*end_batch_formatting)(struct instance *instance); + + void (*prepare_header)(struct instance *instance); + int (*check_response)(BUFFER *buffer, struct instance *instance); + + void *connector_specific_data; + + size_t index; + struct instance *next; + struct engine *engine; + + volatile sig_atomic_t exited; +}; + +struct engine { + struct engine_config config; + + size_t instance_num; + time_t now; + + int aws_sdk_initialized; + int protocol_buffers_initialized; + int mongoc_initialized; + + struct instance *instance_root; + + volatile sig_atomic_t exit; +}; + +extern struct instance *prometheus_exporter_instance; + +void *exporting_main(void *ptr); + +struct engine *read_exporting_config(); +EXPORTING_CONNECTOR_TYPE exporting_select_type(const char *type); + +int init_connectors(struct engine *engine); +void simple_connector_init(struct instance *instance); + +int mark_scheduled_instances(struct engine *engine); +void prepare_buffers(struct engine *engine); + +size_t exporting_name_copy(char *dst, const char *src, size_t max_len); + +int rrdhost_is_exportable(struct instance *instance, RRDHOST *host); +int rrdset_is_exportable(struct instance *instance, RRDSET *st); + +calculated_number exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp); + +void start_batch_formatting(struct engine *engine); +void start_host_formatting(struct engine *engine, RRDHOST *host); +void start_chart_formatting(struct engine *engine, RRDSET *st); +void metric_formatting(struct engine *engine, RRDDIM *rd); +void end_chart_formatting(struct engine *engine, RRDSET *st); +void end_host_formatting(struct engine *engine, RRDHOST *host); +void end_batch_formatting(struct engine *engine); +int flush_host_labels(struct instance *instance, RRDHOST *host); +int simple_connector_end_batch(struct instance *instance); + +int exporting_discard_response(BUFFER *buffer, struct instance *instance); +void simple_connector_receive_response(int *sock, struct instance *instance); +void simple_connector_send_buffer( + int *sock, int *failures, struct instance *instance, BUFFER *header, BUFFER *buffer, size_t buffered_metrics); +void simple_connector_worker(void *instance_p); + +void create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_system); +void send_main_rusage(RRDSET *st_rusage, RRDDIM *rd_user, RRDDIM *rd_system); +void send_internal_metrics(struct instance *instance); + +extern void clean_instance(struct instance *ptr); +void simple_connector_cleanup(struct instance *instance); + +static inline void disable_instance(struct instance *instance) +{ + instance->disabled = 1; + instance->scheduled = 0; + uv_mutex_unlock(&instance->mutex); + error("EXPORTING: Instance %s disabled", instance->config.name); +} + +#include "exporting/prometheus/prometheus.h" +#include "exporting/opentsdb/opentsdb.h" +#if ENABLE_PROMETHEUS_REMOTE_WRITE +#include "exporting/prometheus/remote_write/remote_write.h" +#endif + +#if HAVE_KINESIS +#include "exporting/aws_kinesis/aws_kinesis.h" +#endif + +#endif /* NETDATA_EXPORTING_ENGINE_H */ diff --git a/exporting/graphite/Makefile.am b/exporting/graphite/Makefile.am new file mode 100644 index 000000000..babdcf0df --- /dev/null +++ b/exporting/graphite/Makefile.am @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in diff --git a/exporting/graphite/README.md b/exporting/graphite/README.md new file mode 100644 index 000000000..a6a25ef7a --- /dev/null +++ b/exporting/graphite/README.md @@ -0,0 +1,30 @@ + + +# Export metrics to Graphite providers + +You can use the Graphite connector for the [exporting engine](/exporting/README.md) to archive your agent's metrics to +Graphite providers for long-term storage, further analysis, or correlation with data from other sources. + +## Configuration + +To enable data exporting to a Graphite database, run `./edit-config exporting.conf` in the Netdata configuration +directory and set the following options: + +```conf +[graphite:my_graphite_instance] + enabled = yes + destination = localhost:2003 +``` + +Add `:http` or `:https` modifiers to the connector type if you need to use other than a plaintext protocol. For example: `graphite:http:my_graphite_instance`, +`graphite:https:my_graphite_instance`. + +The Graphite connector is further configurable using additional settings. See the [exporting reference +doc](/exporting/README.md#options) for details. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fjson%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/graphite/graphite.c b/exporting/graphite/graphite.c new file mode 100644 index 000000000..9c09631f1 --- /dev/null +++ b/exporting/graphite/graphite.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "graphite.h" + +/** + * Initialize Graphite connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_graphite_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + struct simple_connector_config *connector_specific_config = callocz(1, sizeof(struct simple_connector_config)); + instance->config.connector_specific_config = (void *)connector_specific_config; + connector_specific_config->default_port = 2003; + + struct simple_connector_data *connector_specific_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = connector_specific_data; + +#ifdef ENABLE_HTTPS + connector_specific_data->flags = NETDATA_SSL_START; + connector_specific_data->conn = NULL; + if (instance->config.options & EXPORTING_OPTION_USE_TLS) { + security_start_ssl(NETDATA_SSL_CONTEXT_EXPORTING); + } +#endif + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_graphite_plaintext; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_graphite_plaintext; + else + instance->metric_formatting = format_dimension_stored_graphite_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = simple_connector_end_batch; + + if (instance->config.type == EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP) + instance->prepare_header = graphite_http_prepare_header; + else + instance->prepare_header = NULL; + + instance->check_response = exporting_discard_response; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for graphite exporting connector instance %s", instance->config.name); + return 1; + } + + simple_connector_init(instance); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + return 0; +} + +/** + * Copy a label value and substitute underscores in place of charachters which can't be used in Graphite output + * + * @param dst a destination string. + * @param src a source string. + * @param len the maximum number of characters copied. + */ + +void sanitize_graphite_label_value(char *dst, char *src, size_t len) +{ + while (*src != '\0' && len) { + if (isspace(*src) || *src == ';' || *src == '~') + *dst++ = '_'; + else + *dst++ = *src; + src++; + len--; + } + *dst = '\0'; +} + +/** + * Format host labels for JSON connector + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int format_host_labels_graphite_plaintext(struct instance *instance, RRDHOST *host) +{ + if (!instance->labels) + instance->labels = buffer_create(1024); + + if (unlikely(!sending_labels_configured(instance))) + return 0; + + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char value[CONFIG_MAX_VALUE + 1]; + sanitize_graphite_label_value(value, label->value, CONFIG_MAX_VALUE); + + if (*value) { + buffer_strcat(instance->labels, ";"); + buffer_sprintf(instance->labels, "%s=%s", label->key, value); + } + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); + + return 0; +} + +/** + * Format dimension using collected data for Graphite connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_collected_graphite_plaintext(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + buffer_sprintf( + instance->buffer, + "%s.%s.%s.%s%s%s%s " COLLECTED_NUMBER_FORMAT " %llu\n", + instance->config.prefix, + (host == localhost) ? instance->config.hostname : host->hostname, + chart_name, + dimension_name, + (host->tags) ? ";" : "", + (host->tags) ? host->tags : "", + (instance->labels) ? buffer_tostring(instance->labels) : "", + rd->last_collected_value, + (unsigned long long)rd->last_collected_time.tv_sec); + + return 0; +} + +/** + * Format dimension using a calculated value from stored data for Graphite connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_stored_graphite_plaintext(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + time_t last_t; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_t); + + if(isnan(value)) + return 0; + + buffer_sprintf( + instance->buffer, + "%s.%s.%s.%s%s%s%s " CALCULATED_NUMBER_FORMAT " %llu\n", + instance->config.prefix, + (host == localhost) ? instance->config.hostname : host->hostname, + chart_name, + dimension_name, + (host->tags) ? ";" : "", + (host->tags) ? host->tags : "", + (instance->labels) ? buffer_tostring(instance->labels) : "", + value, + (unsigned long long)last_t); + + return 0; +} + +/** + * Ppepare HTTP header + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +void graphite_http_prepare_header(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = instance->connector_specific_data; + + buffer_sprintf( + simple_connector_data->last_buffer->header, + "POST /api/put HTTP/1.1\r\n" + "Host: %s\r\n" + "Content-Type: application/graphite\r\n" + "Content-Length: %lu\r\n" + "\r\n", + instance->config.destination, + buffer_strlen(simple_connector_data->last_buffer->buffer)); + + return; +} diff --git a/exporting/graphite/graphite.h b/exporting/graphite/graphite.h new file mode 100644 index 000000000..993c12e57 --- /dev/null +++ b/exporting/graphite/graphite.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_GRAPHITE_H +#define NETDATA_EXPORTING_GRAPHITE_H + +#include "exporting/exporting_engine.h" + +int init_graphite_instance(struct instance *instance); + +void sanitize_graphite_label_value(char *dst, char *src, size_t len); +int format_host_labels_graphite_plaintext(struct instance *instance, RRDHOST *host); + +int format_dimension_collected_graphite_plaintext(struct instance *instance, RRDDIM *rd); +int format_dimension_stored_graphite_plaintext(struct instance *instance, RRDDIM *rd); + +void graphite_http_prepare_header(struct instance *instance); + +#endif //NETDATA_EXPORTING_GRAPHITE_H diff --git a/exporting/init_connectors.c b/exporting/init_connectors.c new file mode 100644 index 000000000..6aff26354 --- /dev/null +++ b/exporting/init_connectors.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" +#include "graphite/graphite.h" +#include "json/json.h" +#include "opentsdb/opentsdb.h" + +#if ENABLE_PROMETHEUS_REMOTE_WRITE +#include "prometheus/remote_write/remote_write.h" +#endif + +#if HAVE_KINESIS +#include "aws_kinesis/aws_kinesis.h" +#endif + +#if ENABLE_EXPORTING_PUBSUB +#include "pubsub/pubsub.h" +#endif + +#if HAVE_MONGOC +#include "mongodb/mongodb.h" +#endif + +/** + * Initialize connectors + * + * @param engine an engine data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_connectors(struct engine *engine) +{ + engine->now = now_realtime_sec(); + + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + instance->index = engine->instance_num++; + instance->after = engine->now; + + switch (instance->config.type) { + case EXPORTING_CONNECTOR_TYPE_GRAPHITE: + if (init_graphite_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP: + if (init_graphite_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_JSON: + if (init_json_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_JSON_HTTP: + if (init_json_http_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_OPENTSDB: + if (init_opentsdb_telnet_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_OPENTSDB_HTTP: + if (init_opentsdb_http_instance(instance) != 0) + return 1; + break; + case EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE: +#if ENABLE_PROMETHEUS_REMOTE_WRITE + if (init_prometheus_remote_write_instance(instance) != 0) + return 1; +#endif + break; + case EXPORTING_CONNECTOR_TYPE_KINESIS: +#if HAVE_KINESIS + if (init_aws_kinesis_instance(instance) != 0) + return 1; +#endif + break; + case EXPORTING_CONNECTOR_TYPE_PUBSUB: +#if ENABLE_EXPORTING_PUBSUB + if (init_pubsub_instance(instance) != 0) + return 1; +#endif + break; + case EXPORTING_CONNECTOR_TYPE_MONGODB: +#if HAVE_MONGOC + if (init_mongodb_instance(instance) != 0) + return 1; +#endif + break; + default: + error("EXPORTING: unknown exporting connector type"); + return 1; + } + + // dispatch the instance worker thread + int error = uv_thread_create(&instance->thread, instance->worker, instance); + if (error) { + error("EXPORTING: cannot create tread worker. uv_thread_create(): %s", uv_strerror(error)); + return 1; + } + char threadname[NETDATA_THREAD_NAME_MAX + 1]; + snprintfz(threadname, NETDATA_THREAD_NAME_MAX, "EXPORTING-%zu", instance->index); + uv_thread_set_name_np(instance->thread, threadname); + + send_statistics("EXPORTING_START", "OK", instance->config.type_name); + } + + return 0; +} + +/** + * Initialize a ring buffer for a simple connector + * + * @param instance an instance data structure. + */ +void simple_connector_init(struct instance *instance) +{ + struct simple_connector_data *connector_specific_data = + (struct simple_connector_data *)instance->connector_specific_data; + + if (connector_specific_data->first_buffer) + return; + + connector_specific_data->header = buffer_create(0); + connector_specific_data->buffer = buffer_create(0); + + // create a ring buffer + struct simple_connector_buffer *first_buffer = NULL; + + if (instance->config.buffer_on_failures < 1) + instance->config.buffer_on_failures = 1; + + for (int i = 0; i < instance->config.buffer_on_failures; i++) { + struct simple_connector_buffer *current_buffer = callocz(1, sizeof(struct simple_connector_buffer)); + + if (!connector_specific_data->first_buffer) + first_buffer = current_buffer; + else + current_buffer->next = connector_specific_data->first_buffer; + + connector_specific_data->first_buffer = current_buffer; + } + + first_buffer->next = connector_specific_data->first_buffer; + connector_specific_data->last_buffer = connector_specific_data->first_buffer; + + return; +} diff --git a/exporting/json/Makefile.am b/exporting/json/Makefile.am new file mode 100644 index 000000000..babdcf0df --- /dev/null +++ b/exporting/json/Makefile.am @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in diff --git a/exporting/json/README.md b/exporting/json/README.md new file mode 100644 index 000000000..a0f8472a0 --- /dev/null +++ b/exporting/json/README.md @@ -0,0 +1,30 @@ + + +# Export metrics to JSON document databases + +You can use the JSON connector for the [exporting engine](/exporting/README.md) to archive your agent's metrics to JSON +document databases for long-term storage, further analysis, or correlation with data from other sources. + +## Configuration + +To enable data exporting to a JSON document database, run `./edit-config exporting.conf` in the Netdata configuration +directory and set the following options: + +```conf +[json:my_json_instance] + enabled = yes + destination = localhost:5448 +``` + +Add `:http` or `:https` modifiers to the connector type if you need to use other than a plaintext protocol. For example: `json:http:my_json_instance`, +`json:https:my_json_instance`. + +The JSON connector is further configurable using additional settings. See the [exporting reference +doc](/exporting/README.md#options) for details. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fjson%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/json/json.c b/exporting/json/json.c new file mode 100644 index 000000000..f2396bafa --- /dev/null +++ b/exporting/json/json.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "json.h" + +/** + * Initialize JSON connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_json_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + struct simple_connector_config *connector_specific_config = callocz(1, sizeof(struct simple_connector_config)); + instance->config.connector_specific_config = (void *)connector_specific_config; + connector_specific_config->default_port = 5448; + + struct simple_connector_data *connector_specific_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = connector_specific_data; + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_json_plaintext; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_json_plaintext; + else + instance->metric_formatting = format_dimension_stored_json_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = simple_connector_end_batch; + + instance->prepare_header = NULL; + + instance->check_response = exporting_discard_response; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for json exporting connector instance %s", instance->config.name); + return 1; + } + + simple_connector_init(instance); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + return 0; +} + +/** + * Initialize JSON connector instance for HTTP protocol + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_json_http_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + struct simple_connector_config *connector_specific_config = callocz(1, sizeof(struct simple_connector_config)); + instance->config.connector_specific_config = (void *)connector_specific_config; + connector_specific_config->default_port = 5448; + + struct simple_connector_data *connector_specific_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = connector_specific_data; + +#ifdef ENABLE_HTTPS + connector_specific_data->flags = NETDATA_SSL_START; + connector_specific_data->conn = NULL; + if (instance->config.options & EXPORTING_OPTION_USE_TLS) { + security_start_ssl(NETDATA_SSL_CONTEXT_EXPORTING); + } +#endif + + instance->start_batch_formatting = open_batch_json_http; + instance->start_host_formatting = format_host_labels_json_plaintext; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_json_plaintext; + else + instance->metric_formatting = format_dimension_stored_json_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = close_batch_json_http; + + instance->prepare_header = json_http_prepare_header; + + instance->check_response = exporting_discard_response; + + instance->buffer = (void *)buffer_create(0); + + simple_connector_init(instance); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + return 0; +} + +/** + * Format host labels for JSON connector + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int format_host_labels_json_plaintext(struct instance *instance, RRDHOST *host) +{ + if (!instance->labels) + instance->labels = buffer_create(1024); + + if (unlikely(!sending_labels_configured(instance))) + return 0; + + buffer_strcat(instance->labels, "\"labels\":{"); + + int count = 0; + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char value[CONFIG_MAX_VALUE * 2 + 1]; + sanitize_json_string(value, label->value, CONFIG_MAX_VALUE); + if (count > 0) + buffer_strcat(instance->labels, ","); + buffer_sprintf(instance->labels, "\"%s\":\"%s\"", label->key, value); + + count++; + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); + + buffer_strcat(instance->labels, "},"); + + return 0; +} + +/** + * Format dimension using collected data for JSON connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_collected_json_plaintext(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + const char *tags_pre = "", *tags_post = "", *tags = host->tags; + if (!tags) + tags = ""; + + if (*tags) { + if (*tags == '{' || *tags == '[' || *tags == '"') { + tags_pre = "\"host_tags\":"; + tags_post = ","; + } else { + tags_pre = "\"host_tags\":\""; + tags_post = "\","; + } + } + + if (instance->config.type == EXPORTING_CONNECTOR_TYPE_JSON_HTTP) { + if (buffer_strlen((BUFFER *)instance->buffer) > 2) + buffer_strcat(instance->buffer, ",\n"); + } + + buffer_sprintf( + instance->buffer, + + "{" + "\"prefix\":\"%s\"," + "\"hostname\":\"%s\"," + "%s%s%s" + "%s" + + "\"chart_id\":\"%s\"," + "\"chart_name\":\"%s\"," + "\"chart_family\":\"%s\"," + "\"chart_context\":\"%s\"," + "\"chart_type\":\"%s\"," + "\"units\":\"%s\"," + + "\"id\":\"%s\"," + "\"name\":\"%s\"," + "\"value\":" COLLECTED_NUMBER_FORMAT "," + + "\"timestamp\":%llu}", + + instance->config.prefix, + (host == localhost) ? instance->config.hostname : host->hostname, + tags_pre, + tags, + tags_post, + instance->labels ? buffer_tostring(instance->labels) : "", + + st->id, + st->name, + st->family, + st->context, + st->type, + st->units, + + rd->id, + rd->name, + rd->last_collected_value, + + (unsigned long long)rd->last_collected_time.tv_sec); + + if (instance->config.type != EXPORTING_CONNECTOR_TYPE_JSON_HTTP) { + buffer_strcat(instance->buffer, "\n"); + } + + return 0; +} + +/** + * Format dimension using a calculated value from stored data for JSON connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_stored_json_plaintext(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + time_t last_t; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_t); + + if(isnan(value)) + return 0; + + const char *tags_pre = "", *tags_post = "", *tags = host->tags; + if (!tags) + tags = ""; + + if (*tags) { + if (*tags == '{' || *tags == '[' || *tags == '"') { + tags_pre = "\"host_tags\":"; + tags_post = ","; + } else { + tags_pre = "\"host_tags\":\""; + tags_post = "\","; + } + } + + if (instance->config.type == EXPORTING_CONNECTOR_TYPE_JSON_HTTP) { + if (buffer_strlen((BUFFER *)instance->buffer) > 2) + buffer_strcat(instance->buffer, ",\n"); + } + + buffer_sprintf( + instance->buffer, + "{" + "\"prefix\":\"%s\"," + "\"hostname\":\"%s\"," + "%s%s%s" + "%s" + + "\"chart_id\":\"%s\"," + "\"chart_name\":\"%s\"," + "\"chart_family\":\"%s\"," + "\"chart_context\": \"%s\"," + "\"chart_type\":\"%s\"," + "\"units\": \"%s\"," + + "\"id\":\"%s\"," + "\"name\":\"%s\"," + "\"value\":" CALCULATED_NUMBER_FORMAT "," + + "\"timestamp\": %llu}", + + instance->config.prefix, + (host == localhost) ? instance->config.hostname : host->hostname, + tags_pre, + tags, + tags_post, + instance->labels ? buffer_tostring(instance->labels) : "", + + st->id, + st->name, + st->family, + st->context, + st->type, + st->units, + + rd->id, + rd->name, + value, + + (unsigned long long)last_t); + + if (instance->config.type != EXPORTING_CONNECTOR_TYPE_JSON_HTTP) { + buffer_strcat(instance->buffer, "\n"); + } + + return 0; +} + +/** + * Open a JSON list for a bach + * + * @param instance an instance data structure. + * @return Always returns 0. + */ +int open_batch_json_http(struct instance *instance) +{ + buffer_strcat(instance->buffer, "[\n"); + + return 0; +} + +/** + * Close a JSON list for a bach and update buffered bytes counter + * + * @param instance an instance data structure. + * @return Always returns 0. + */ +int close_batch_json_http(struct instance *instance) +{ + buffer_strcat(instance->buffer, "\n]\n"); + + simple_connector_end_batch(instance); + + return 0; +} + +/** + * Prepare HTTP header + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +void json_http_prepare_header(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = instance->connector_specific_data; + + buffer_sprintf( + simple_connector_data->last_buffer->header, + "POST /api/put HTTP/1.1\r\n" + "Host: %s\r\n" + "Content-Type: application/json\r\n" + "Content-Length: %lu\r\n" + "\r\n", + instance->config.destination, + buffer_strlen(simple_connector_data->last_buffer->buffer)); + + return; +} diff --git a/exporting/json/json.h b/exporting/json/json.h new file mode 100644 index 000000000..d916263a9 --- /dev/null +++ b/exporting/json/json.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_JSON_H +#define NETDATA_EXPORTING_JSON_H + +#include "exporting/exporting_engine.h" + +int init_json_instance(struct instance *instance); +int init_json_http_instance(struct instance *instance); + +int format_host_labels_json_plaintext(struct instance *instance, RRDHOST *host); + +int format_dimension_collected_json_plaintext(struct instance *instance, RRDDIM *rd); +int format_dimension_stored_json_plaintext(struct instance *instance, RRDDIM *rd); + +int open_batch_json_http(struct instance *instance); +int close_batch_json_http(struct instance *instance); + +void json_http_prepare_header(struct instance *instance); + +#endif //NETDATA_EXPORTING_JSON_H diff --git a/exporting/mongodb/Makefile.am b/exporting/mongodb/Makefile.am new file mode 100644 index 000000000..161784b8f --- /dev/null +++ b/exporting/mongodb/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/exporting/mongodb/README.md b/exporting/mongodb/README.md new file mode 100644 index 000000000..2934f38c5 --- /dev/null +++ b/exporting/mongodb/README.md @@ -0,0 +1,38 @@ + + +# Export metrics to MongoDB + +You can use the MongoDB connector for the [exporting engine](/exporting/README.md) to archive your agent's metrics to a +MongoDB database for long-term storage, further analysis, or correlation with data from other sources. + +## Prerequisites + +To use MongoDB as an external storage for long-term archiving, you should first +[install](http://mongoc.org/libmongoc/current/installing.html) `libmongoc` 1.7.0 or higher. Next, re-install Netdata +from the source, which detects that the required library is now available. + +## Configuration + +To enable data exporting to a MongoDB database, run `./edit-config exporting.conf` in the Netdata configuration +directory and set the following options: + +```conf +[mongodb:my_instance] + enabled = yes + destination = mongodb:// + database = your_database_name + collection = your_collection_name +``` + +You can find more information about the `destination` string URI format in the MongoDB +[documentation](https://docs.mongodb.com/manual/reference/connection-string/) + +The default socket timeout depends on the exporting connector update interval. The timeout is 500 ms shorter than the +interval (but not less than 1000 ms). You can alter the timeout using the `sockettimeoutms` MongoDB URI option. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fmongodb%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/mongodb/mongodb.c b/exporting/mongodb/mongodb.c new file mode 100644 index 000000000..44922a242 --- /dev/null +++ b/exporting/mongodb/mongodb.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#define EXPORTING_INTERNALS +#include "mongodb.h" + +#define CONFIG_FILE_LINE_MAX ((CONFIG_MAX_NAME + CONFIG_MAX_VALUE + 1024) * 2) + +/** + * Initialize MongoDB connector specific data, including a ring buffer + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int mongodb_init(struct instance *instance) +{ + struct mongodb_specific_config *connector_specific_config = instance->config.connector_specific_config; + mongoc_uri_t *uri; + bson_error_t bson_error; + + if (unlikely(!connector_specific_config->collection || !*connector_specific_config->collection)) { + error("EXPORTING: collection name is a mandatory MongoDB parameter, but it is not configured"); + return 1; + } + + uri = mongoc_uri_new_with_error(instance->config.destination, &bson_error); + if (unlikely(!uri)) { + error( + "EXPORTING: failed to parse URI: %s. Error message: %s", instance->config.destination, bson_error.message); + return 1; + } + + int32_t socket_timeout = + mongoc_uri_get_option_as_int32(uri, MONGOC_URI_SOCKETTIMEOUTMS, instance->config.timeoutms); + if (!mongoc_uri_set_option_as_int32(uri, MONGOC_URI_SOCKETTIMEOUTMS, socket_timeout)) { + error("EXPORTING: failed to set %s to the value %d", MONGOC_URI_SOCKETTIMEOUTMS, socket_timeout); + return 1; + }; + + struct mongodb_specific_data *connector_specific_data = + (struct mongodb_specific_data *)instance->connector_specific_data; + + connector_specific_data->client = mongoc_client_new_from_uri(uri); + if (unlikely(!connector_specific_data->client)) { + error("EXPORTING: failed to create a new client"); + return 1; + } + + if (!mongoc_client_set_appname(connector_specific_data->client, "netdata")) { + error("EXPORTING: failed to set client appname"); + }; + + connector_specific_data->collection = mongoc_client_get_collection( + connector_specific_data->client, connector_specific_config->database, connector_specific_config->collection); + + mongoc_uri_destroy(uri); + + // create a ring buffer + struct bson_buffer *first_buffer = NULL; + + if (instance->config.buffer_on_failures < 2) + instance->config.buffer_on_failures = 1; + else + instance->config.buffer_on_failures -= 1; + + for (int i = 0; i < instance->config.buffer_on_failures; i++) { + struct bson_buffer *current_buffer = callocz(1, sizeof(struct bson_buffer)); + + if (!connector_specific_data->first_buffer) + first_buffer = current_buffer; + else + current_buffer->next = connector_specific_data->first_buffer; + + connector_specific_data->first_buffer = current_buffer; + } + + first_buffer->next = connector_specific_data->first_buffer; + connector_specific_data->last_buffer = connector_specific_data->first_buffer; + + return 0; +} + +/** + * Initialize a MongoDB connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_mongodb_instance(struct instance *instance) +{ + instance->worker = mongodb_connector_worker; + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_json_plaintext; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_json_plaintext; + else + instance->metric_formatting = format_dimension_stored_json_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = format_batch_mongodb; + + instance->prepare_header = NULL; + instance->check_response = NULL; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for MongoDB exporting connector instance %s", instance->config.name); + return 1; + } + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + struct mongodb_specific_data *connector_specific_data = callocz(1, sizeof(struct mongodb_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + instance->config.timeoutms = + (instance->config.update_every >= 2) ? (instance->engine->config.update_every * MSEC_PER_SEC - 500) : 1000; + + if (!instance->engine->mongoc_initialized) { + mongoc_init(); + instance->engine->mongoc_initialized = 1; + } + + if (unlikely(mongodb_init(instance))) { + error("EXPORTING: cannot initialize MongoDB exporting connector"); + return 1; + } + + return 0; +} + +/** + * Free an array of BSON structures + * + * @param insert an array of documents. + * @param documents_inserted the number of documents inserted. + */ +void free_bson(bson_t **insert, size_t documents_inserted) +{ + size_t i; + + for (i = 0; i < documents_inserted; i++) + bson_destroy(insert[i]); + + freez(insert); +} + +/** + * Format a batch for the MongoDB connector + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int format_batch_mongodb(struct instance *instance) +{ + struct mongodb_specific_data *connector_specific_data = + (struct mongodb_specific_data *)instance->connector_specific_data; + struct stats *stats = &instance->stats; + + bson_t **insert = connector_specific_data->last_buffer->insert; + if (insert) { + // ring buffer is full, reuse the oldest element + connector_specific_data->first_buffer = connector_specific_data->first_buffer->next; + free_bson(insert, connector_specific_data->last_buffer->documents_inserted); + connector_specific_data->total_documents_inserted -= connector_specific_data->last_buffer->documents_inserted; + stats->buffered_bytes -= connector_specific_data->last_buffer->buffered_bytes; + } + insert = callocz((size_t)stats->buffered_metrics, sizeof(bson_t *)); + connector_specific_data->last_buffer->insert = insert; + + BUFFER *buffer = (BUFFER *)instance->buffer; + char *start = (char *)buffer_tostring(buffer); + char *end = start; + + size_t documents_inserted = 0; + + while (*end && documents_inserted <= (size_t)stats->buffered_metrics) { + while (*end && *end != '\n') + end++; + + if (likely(*end)) { + *end = '\0'; + end++; + } else { + break; + } + + bson_error_t bson_error; + insert[documents_inserted] = bson_new_from_json((const uint8_t *)start, -1, &bson_error); + + if (unlikely(!insert[documents_inserted])) { + error( + "EXPORTING: Failed creating a BSON document from a JSON string \"%s\" : %s", start, bson_error.message); + free_bson(insert, documents_inserted); + return 1; + } + + start = end; + + documents_inserted++; + } + + stats->buffered_bytes += connector_specific_data->last_buffer->buffered_bytes = buffer_strlen(buffer); + + buffer_flush(buffer); + + // The stats->buffered_metrics is used in the MongoDB batch formatting as a variable for the number + // of metrics, added in the current iteration, so we are clearing it here. We will use the + // connector_specific_data->total_documents_inserted in the worker to show the statistics. + stats->buffered_metrics = 0; + connector_specific_data->total_documents_inserted += documents_inserted; + + connector_specific_data->last_buffer->documents_inserted = documents_inserted; + connector_specific_data->last_buffer = connector_specific_data->last_buffer->next; + + return 0; +} + +/** + * Clean a MongoDB connector instance up + * + * @param instance an instance data structure. + */ +void mongodb_cleanup(struct instance *instance) +{ + info("EXPORTING: cleaning up instance %s ...", instance->config.name); + + struct mongodb_specific_data *connector_specific_data = + (struct mongodb_specific_data *)instance->connector_specific_data; + + mongoc_collection_destroy(connector_specific_data->collection); + mongoc_client_destroy(connector_specific_data->client); + if (instance->engine->mongoc_initialized) { + mongoc_cleanup(); + instance->engine->mongoc_initialized = 0; + } + + buffer_free(instance->buffer); + + struct bson_buffer *next_buffer = connector_specific_data->first_buffer; + for (int i = 0; i < instance->config.buffer_on_failures; i++) { + struct bson_buffer *current_buffer = next_buffer; + next_buffer = next_buffer->next; + + if (current_buffer->insert) + free_bson(current_buffer->insert, current_buffer->documents_inserted); + freez(current_buffer); + } + + freez(connector_specific_data); + + struct mongodb_specific_config *connector_specific_config = + (struct mongodb_specific_config *)instance->config.connector_specific_config; + freez(connector_specific_config->database); + freez(connector_specific_config->collection); + freez(connector_specific_config); + + info("EXPORTING: instance %s exited", instance->config.name); + instance->exited = 1; + + return; +} + +/** + * MongoDB connector worker + * + * Runs in a separate thread for every instance. + * + * @param instance_p an instance data structure. + */ +void mongodb_connector_worker(void *instance_p) +{ + struct instance *instance = (struct instance *)instance_p; + struct mongodb_specific_config *connector_specific_config = instance->config.connector_specific_config; + struct mongodb_specific_data *connector_specific_data = + (struct mongodb_specific_data *)instance->connector_specific_data; + + while (!instance->engine->exit) { + struct stats *stats = &instance->stats; + + uv_mutex_lock(&instance->mutex); + if (!connector_specific_data->first_buffer->insert || + !connector_specific_data->first_buffer->documents_inserted) { + while (!instance->data_is_ready) + uv_cond_wait(&instance->cond_var, &instance->mutex); + instance->data_is_ready = 0; + } + + if (unlikely(instance->engine->exit)) { + uv_mutex_unlock(&instance->mutex); + break; + } + + // reset the monitoring chart counters + stats->received_bytes = + stats->sent_bytes = + stats->sent_metrics = + stats->lost_metrics = + stats->receptions = + stats->transmission_successes = + stats->transmission_failures = + stats->data_lost_events = + stats->lost_bytes = + stats->reconnects = 0; + + bson_t **insert = connector_specific_data->first_buffer->insert; + size_t documents_inserted = connector_specific_data->first_buffer->documents_inserted; + size_t buffered_bytes = connector_specific_data->first_buffer->buffered_bytes; + + connector_specific_data->first_buffer->insert = NULL; + connector_specific_data->first_buffer->documents_inserted = 0; + connector_specific_data->first_buffer->buffered_bytes = 0; + connector_specific_data->first_buffer = connector_specific_data->first_buffer->next; + + uv_mutex_unlock(&instance->mutex); + + size_t data_size = 0; + for (size_t i = 0; i < documents_inserted; i++) { + data_size += insert[i]->len; + } + + debug( + D_BACKEND, + "EXPORTING: mongodb_insert(): destination = %s, database = %s, collection = %s, data size = %zu", + instance->config.destination, + connector_specific_config->database, + connector_specific_config->collection, + data_size); + + if (likely(documents_inserted != 0)) { + bson_error_t bson_error; + if (likely(mongoc_collection_insert_many( + connector_specific_data->collection, + (const bson_t **)insert, + documents_inserted, + NULL, + NULL, + &bson_error))) { + stats->sent_metrics = documents_inserted; + stats->sent_bytes += data_size; + stats->transmission_successes++; + stats->receptions++; + } else { + // oops! we couldn't send (all or some of the) data + error("EXPORTING: %s", bson_error.message); + error( + "EXPORTING: failed to write data to the database '%s'. " + "Willing to write %zu bytes, wrote %zu bytes.", + instance->config.destination, data_size, 0UL); + + stats->transmission_failures++; + stats->data_lost_events++; + stats->lost_bytes += buffered_bytes; + stats->lost_metrics += documents_inserted; + } + } + + free_bson(insert, documents_inserted); + + if (unlikely(instance->engine->exit)) + break; + + uv_mutex_lock(&instance->mutex); + + stats->buffered_metrics = connector_specific_data->total_documents_inserted; + + send_internal_metrics(instance); + + connector_specific_data->total_documents_inserted -= documents_inserted; + + stats->buffered_metrics = 0; + stats->buffered_bytes -= buffered_bytes; + + uv_mutex_unlock(&instance->mutex); + +#ifdef UNIT_TESTING + return; +#endif + } + + mongodb_cleanup(instance); +} diff --git a/exporting/mongodb/mongodb.h b/exporting/mongodb/mongodb.h new file mode 100644 index 000000000..f1867b288 --- /dev/null +++ b/exporting/mongodb/mongodb.h @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_MONGODB_H +#define NETDATA_EXPORTING_MONGODB_H + +#include "exporting/exporting_engine.h" +#include "exporting/json/json.h" +#include + +struct bson_buffer { + bson_t **insert; + size_t documents_inserted; + size_t buffered_bytes; + + struct bson_buffer *next; +}; + +struct mongodb_specific_data { + mongoc_client_t *client; + mongoc_collection_t *collection; + + size_t total_documents_inserted; + + struct bson_buffer *first_buffer; + struct bson_buffer *last_buffer; +}; + +int mongodb_init(struct instance *instance); +void mongodb_cleanup(struct instance *instance); + +int init_mongodb_instance(struct instance *instance); +int format_batch_mongodb(struct instance *instance); +void mongodb_connector_worker(void *instance_p); + +#endif //NETDATA_EXPORTING_MONGODB_H diff --git a/exporting/nc-exporting.sh b/exporting/nc-exporting.sh new file mode 100755 index 000000000..9c8b08e60 --- /dev/null +++ b/exporting/nc-exporting.sh @@ -0,0 +1,158 @@ +#!/usr/bin/env bash + +# SPDX-License-Identifier: GPL-3.0-or-later + +# This is a simple backend database proxy, written in BASH, using the nc command. +# Run the script without any parameters for help. + +MODE="${1}" +MY_PORT="${2}" +BACKEND_HOST="${3}" +BACKEND_PORT="${4}" +FILE="${NETDATA_NC_BACKEND_DIR-/tmp}/netdata-nc-backend-${MY_PORT}" + +log() { + logger --stderr --id=$$ --tag "netdata-nc-backend" "${*}" +} + +mync() { + local ret + + log "Running: nc ${*}" + nc "${@}" + ret=$? + + log "nc stopped with return code ${ret}." + + return ${ret} +} + +listen_save_replay_forever() { + local file="${1}" port="${2}" real_backend_host="${3}" real_backend_port="${4}" ret delay=1 started ended + + while true + do + log "Starting nc to listen on port ${port} and save metrics to ${file}" + + started=$(date +%s) + mync -l -p "${port}" | tee -a -p --output-error=exit "${file}" + ended=$(date +%s) + + if [ -s "${file}" ] + then + if [ -n "${real_backend_host}" ] && [ -n "${real_backend_port}" ] + then + log "Attempting to send the metrics to the real backend at ${real_backend_host}:${real_backend_port}" + + mync "${real_backend_host}" "${real_backend_port}" <"${file}" + ret=$? + + if [ ${ret} -eq 0 ] + then + log "Successfuly sent the metrics to ${real_backend_host}:${real_backend_port}" + mv "${file}" "${file}.old" + touch "${file}" + else + log "Failed to send the metrics to ${real_backend_host}:${real_backend_port} (nc returned ${ret}) - appending more data to ${file}" + fi + else + log "No backend configured - appending more data to ${file}" + fi + fi + + # prevent a CPU hungry infinite loop + # if nc cannot listen to port + if [ $((ended - started)) -lt 5 ] + then + log "nc has been stopped too fast." + delay=30 + else + delay=1 + fi + + log "Waiting ${delay} seconds before listening again for data." + sleep ${delay} + done +} + +if [ "${MODE}" = "start" ] + then + + # start the listener, in exclusive mode + # only one can use the same file/port at a time + { + flock -n 9 + # shellcheck disable=SC2181 + if [ $? -ne 0 ] + then + log "Cannot get exclusive lock on file ${FILE}.lock - Am I running multiple times?" + exit 2 + fi + + # save our PID to the lock file + echo "$$" >"${FILE}.lock" + + listen_save_replay_forever "${FILE}" "${MY_PORT}" "${BACKEND_HOST}" "${BACKEND_PORT}" + ret=$? + + log "listener exited." + exit ${ret} + + } 9>>"${FILE}.lock" + + # we can only get here if ${FILE}.lock cannot be created + log "Cannot create file ${FILE}." + exit 3 + +elif [ "${MODE}" = "stop" ] + then + + { + flock -n 9 + # shellcheck disable=SC2181 + if [ $? -ne 0 ] + then + pid=$(<"${FILE}".lock) + log "Killing process ${pid}..." + kill -TERM "-${pid}" + exit 0 + fi + + log "File ${FILE}.lock has been locked by me but it shouldn't. Is a collector running?" + exit 4 + + } 9<"${FILE}.lock" + + log "File ${FILE}.lock does not exist. Is a collector running?" + exit 5 + +else + + cat < + +# Export metrics to OpenTSDB + +You can use the OpenTSDB connector for the [exporting engine](/exporting/README.md) to archive your agent's metrics to OpenTSDB +databases for long-term storage, further analysis, or correlation with data from other sources. + +## Configuration + +To enable data exporting to an OpenTSDB database, run `./edit-config exporting.conf` in the Netdata configuration +directory and set the following options: + +```conf +[opentsdb:my_opentsdb_instance] + enabled = yes + destination = localhost:4242 +``` + +Add `:http` or `:https` modifiers to the connector type if you need to use other than a plaintext protocol. For example: `opentsdb:http:my_opentsdb_instance`, +`opentsdb:https:my_opentsdb_instance`. + +The OpenTSDB connector is further configurable using additional settings. See the [exporting reference +doc](/exporting/README.md#options) for details. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fopentsdb%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/opentsdb/opentsdb.c b/exporting/opentsdb/opentsdb.c new file mode 100644 index 000000000..d7b843dff --- /dev/null +++ b/exporting/opentsdb/opentsdb.c @@ -0,0 +1,422 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "opentsdb.h" +#include "../json/json.h" + +/** + * Initialize OpenTSDB telnet connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_opentsdb_telnet_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + struct simple_connector_config *connector_specific_config = callocz(1, sizeof(struct simple_connector_config)); + instance->config.connector_specific_config = (void *)connector_specific_config; + connector_specific_config->default_port = 4242; + + struct simple_connector_data *connector_specific_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = connector_specific_data; + +#ifdef ENABLE_HTTPS + connector_specific_data->flags = NETDATA_SSL_START; + connector_specific_data->conn = NULL; + if (instance->config.options & EXPORTING_OPTION_USE_TLS) { + security_start_ssl(NETDATA_SSL_CONTEXT_EXPORTING); + } +#endif + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_opentsdb_telnet; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_opentsdb_telnet; + else + instance->metric_formatting = format_dimension_stored_opentsdb_telnet; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = simple_connector_end_batch; + + instance->prepare_header = NULL; + instance->check_response = exporting_discard_response; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for opentsdb telnet exporting connector instance %s", instance->config.name); + return 1; + } + + simple_connector_init(instance); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + return 0; +} + +/** + * Initialize OpenTSDB HTTP connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_opentsdb_http_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + struct simple_connector_config *connector_specific_config = callocz(1, sizeof(struct simple_connector_config)); + instance->config.connector_specific_config = (void *)connector_specific_config; + connector_specific_config->default_port = 4242; + + struct simple_connector_data *connector_specific_data = callocz(1, sizeof(struct simple_connector_data)); +#ifdef ENABLE_HTTPS + connector_specific_data->flags = NETDATA_SSL_START; + connector_specific_data->conn = NULL; + if (instance->config.options & EXPORTING_OPTION_USE_TLS) { + security_start_ssl(NETDATA_SSL_CONTEXT_EXPORTING); + } +#endif + instance->connector_specific_data = connector_specific_data; + + instance->start_batch_formatting = open_batch_json_http; + instance->start_host_formatting = format_host_labels_opentsdb_http; + instance->start_chart_formatting = NULL; + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_opentsdb_http; + else + instance->metric_formatting = format_dimension_stored_opentsdb_http; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = close_batch_json_http; + + instance->prepare_header = opentsdb_http_prepare_header; + instance->check_response = exporting_discard_response; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for opentsdb HTTP exporting connector instance %s", instance->config.name); + return 1; + } + + simple_connector_init(instance); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + return 0; +} + +/** + * Copy a label value and substitute underscores in place of charachters which can't be used in OpenTSDB output + * + * @param dst a destination string. + * @param src a source string. + * @param len the maximum number of characters copied. + */ + +void sanitize_opentsdb_label_value(char *dst, char *src, size_t len) +{ + while (*src != '\0' && len) { + if (isalpha(*src) || isdigit(*src) || *src == '-' || *src == '_' || *src == '.' || *src == '/' || IS_UTF8_BYTE(*src)) + *dst++ = *src; + else + *dst++ = '_'; + src++; + len--; + } + *dst = '\0'; +} + +/** + * Format host labels for JSON connector + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int format_host_labels_opentsdb_telnet(struct instance *instance, RRDHOST *host) +{ + if (!instance->labels) + instance->labels = buffer_create(1024); + + if (unlikely(!sending_labels_configured(instance))) + return 0; + + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char value[CONFIG_MAX_VALUE + 1]; + sanitize_opentsdb_label_value(value, label->value, CONFIG_MAX_VALUE); + + if (*value) + buffer_sprintf(instance->labels, " %s=%s", label->key, value); + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); + + return 0; +} + +/** + * Format dimension using collected data for OpenTSDB telnet connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_collected_opentsdb_telnet(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + buffer_sprintf( + instance->buffer, + "put %s.%s.%s %llu " COLLECTED_NUMBER_FORMAT " host=%s%s%s%s\n", + instance->config.prefix, + chart_name, + dimension_name, + (unsigned long long)rd->last_collected_time.tv_sec, + rd->last_collected_value, + (host == localhost) ? instance->config.hostname : host->hostname, + (host->tags) ? " " : "", + (host->tags) ? host->tags : "", + (instance->labels) ? buffer_tostring(instance->labels) : ""); + + return 0; +} + +/** + * Format dimension using a calculated value from stored data for OpenTSDB telnet connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_stored_opentsdb_telnet(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + time_t last_t; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_t); + + if(isnan(value)) + return 0; + + buffer_sprintf( + instance->buffer, + "put %s.%s.%s %llu " CALCULATED_NUMBER_FORMAT " host=%s%s%s%s\n", + instance->config.prefix, + chart_name, + dimension_name, + (unsigned long long)last_t, + value, + (host == localhost) ? instance->config.hostname : host->hostname, + (host->tags) ? " " : "", + (host->tags) ? host->tags : "", + (instance->labels) ? buffer_tostring(instance->labels) : ""); + + return 0; +} + +/** + * Ppepare HTTP header + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +void opentsdb_http_prepare_header(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = instance->connector_specific_data; + + buffer_sprintf( + simple_connector_data->last_buffer->header, + "POST /api/put HTTP/1.1\r\n" + "Host: %s\r\n" + "Content-Type: application/json\r\n" + "Content-Length: %lu\r\n" + "\r\n", + instance->config.destination, + buffer_strlen(simple_connector_data->last_buffer->buffer)); + + return; +} + +/** + * Format host labels for OpenTSDB HTTP connector + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int format_host_labels_opentsdb_http(struct instance *instance, RRDHOST *host) +{ + if (!instance->labels) + instance->labels = buffer_create(1024); + + if (unlikely(!sending_labels_configured(instance))) + return 0; + + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char escaped_value[CONFIG_MAX_VALUE * 2 + 1]; + sanitize_json_string(escaped_value, label->value, CONFIG_MAX_VALUE); + + char value[CONFIG_MAX_VALUE + 1]; + sanitize_opentsdb_label_value(value, escaped_value, CONFIG_MAX_VALUE); + + if (*value) { + buffer_strcat(instance->labels, ","); + buffer_sprintf(instance->labels, "\"%s\":\"%s\"", label->key, value); + } + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); + + return 0; +} + +/** + * Format dimension using collected data for OpenTSDB HTTP connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_collected_opentsdb_http(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + if (buffer_strlen((BUFFER *)instance->buffer) > 2) + buffer_strcat(instance->buffer, ",\n"); + + buffer_sprintf( + instance->buffer, + "{" + "\"metric\":\"%s.%s.%s\"," + "\"timestamp\":%llu," + "\"value\":"COLLECTED_NUMBER_FORMAT"," + "\"tags\":{" + "\"host\":\"%s%s%s\"%s" + "}" + "}", + instance->config.prefix, + chart_name, + dimension_name, + (unsigned long long)rd->last_collected_time.tv_sec, + rd->last_collected_value, + (host == localhost) ? instance->config.hostname : host->hostname, + (host->tags) ? " " : "", + (host->tags) ? host->tags : "", + instance->labels ? buffer_tostring(instance->labels) : ""); + + return 0; +} + +/** + * Format dimension using a calculated value from stored data for OpenTSDB HTTP connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_stored_opentsdb_http(struct instance *instance, RRDDIM *rd) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + + char chart_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + chart_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + RRD_ID_LENGTH_MAX); + + char dimension_name[RRD_ID_LENGTH_MAX + 1]; + exporting_name_copy( + dimension_name, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + RRD_ID_LENGTH_MAX); + + time_t last_t; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_t); + + if(isnan(value)) + return 0; + + if (buffer_strlen((BUFFER *)instance->buffer) > 2) + buffer_strcat(instance->buffer, ",\n"); + + buffer_sprintf( + instance->buffer, + "{" + "\"metric\":\"%s.%s.%s\"," + "\"timestamp\":%llu," + "\"value\":"CALCULATED_NUMBER_FORMAT"," + "\"tags\":{" + "\"host\":\"%s%s%s\"%s" + "}" + "}", + instance->config.prefix, + chart_name, + dimension_name, + (unsigned long long)last_t, + value, + (host == localhost) ? instance->config.hostname : host->hostname, + (host->tags) ? " " : "", + (host->tags) ? host->tags : "", + instance->labels ? buffer_tostring(instance->labels) : ""); + + return 0; +} diff --git a/exporting/opentsdb/opentsdb.h b/exporting/opentsdb/opentsdb.h new file mode 100644 index 000000000..d53a5054f --- /dev/null +++ b/exporting/opentsdb/opentsdb.h @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_OPENTSDB_H +#define NETDATA_EXPORTING_OPENTSDB_H + +#include "exporting/exporting_engine.h" + +int init_opentsdb_telnet_instance(struct instance *instance); +int init_opentsdb_http_instance(struct instance *instance); + +void sanitize_opentsdb_label_value(char *dst, char *src, size_t len); +int format_host_labels_opentsdb_telnet(struct instance *instance, RRDHOST *host); +int format_host_labels_opentsdb_http(struct instance *instance, RRDHOST *host); + +int format_dimension_collected_opentsdb_telnet(struct instance *instance, RRDDIM *rd); +int format_dimension_stored_opentsdb_telnet(struct instance *instance, RRDDIM *rd); + +int format_dimension_collected_opentsdb_http(struct instance *instance, RRDDIM *rd); +int format_dimension_stored_opentsdb_http(struct instance *instance, RRDDIM *rd); + +int open_batch_opentsdb_http(struct instance *instance); +int close_batch_opentsdb_http(struct instance *instance); + +void opentsdb_http_prepare_header(struct instance *instance); + +#endif //NETDATA_EXPORTING_OPENTSDB_H diff --git a/exporting/process_data.c b/exporting/process_data.c new file mode 100644 index 000000000..5e11b3948 --- /dev/null +++ b/exporting/process_data.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +/** + * Normalize chart and dimension names + * + * Substitute '_' for any special character except '.'. + * + * @param dst where to copy name to. + * @param src where to copy name from. + * @param max_len the maximum size of copied name. + * @return Returns the size of the copied name. + */ +size_t exporting_name_copy(char *dst, const char *src, size_t max_len) +{ + size_t n; + + for (n = 0; *src && n < max_len; dst++, src++, n++) { + char c = *src; + + if (c != '.' && !isalnum(c)) + *dst = '_'; + else + *dst = c; + } + *dst = '\0'; + + return n; +} + +/** + * Mark scheduled instances + * + * Any instance can have its own update interval. On every exporting engine update only those instances are picked, + * which are scheduled for the update. + * + * @param engine an engine data structure. + * @return Returns 1 if there are instances to process + */ +int mark_scheduled_instances(struct engine *engine) +{ + int instances_were_scheduled = 0; + + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (!instance->disabled && (engine->now % instance->config.update_every >= + instance->config.update_every - localhost->rrd_update_every)) { + instance->scheduled = 1; + instances_were_scheduled = 1; + instance->before = engine->now; + } + } + + return instances_were_scheduled; +} + +/** + * Calculate the SUM or AVERAGE of a dimension, for any timeframe + * + * May return NAN if the database does not have any value in the give timeframe. + * + * @param instance an instance data structure. + * @param rd a dimension(metric) in the Netdata database. + * @param last_timestamp the timestamp that should be reported to the exporting connector instance. + * @return Returns the value, calculated over the given period. + */ +calculated_number exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp) +{ + RRDSET *st = rd->rrdset; + RRDHOST *host = st->rrdhost; + time_t after = instance->after; + time_t before = instance->before; + + // find the edges of the rrd database for this chart + time_t first_t = rd->state->query_ops.oldest_time(rd); + time_t last_t = rd->state->query_ops.latest_time(rd); + time_t update_every = st->update_every; + struct rrddim_query_handle handle; + storage_number n; + + // step back a little, to make sure we have complete data collection + // for all metrics + after -= update_every * 2; + before -= update_every * 2; + + // align the time-frame + after = after - (after % update_every); + before = before - (before % update_every); + + // for before, loose another iteration + // the latest point will be reported the next time + before -= update_every; + + if (unlikely(after > before)) + // this can happen when update_every > before - after + after = before; + + if (unlikely(after < first_t)) + after = first_t; + + if (unlikely(before > last_t)) + before = last_t; + + if (unlikely(before < first_t || after > last_t)) { + // the chart has not been updated in the wanted timeframe + debug( + D_BACKEND, + "EXPORTING: %s.%s.%s: aligned timeframe %lu to %lu is outside the chart's database range %lu to %lu", + host->hostname, + st->id, + rd->id, + (unsigned long)after, + (unsigned long)before, + (unsigned long)first_t, + (unsigned long)last_t); + return NAN; + } + + *last_timestamp = before; + + size_t counter = 0; + calculated_number sum = 0; + + for (rd->state->query_ops.init(rd, &handle, after, before); !rd->state->query_ops.is_finished(&handle);) { + time_t curr_t; + n = rd->state->query_ops.next_metric(&handle, &curr_t); + + if (unlikely(!does_storage_number_exist(n))) { + // not collected + continue; + } + + calculated_number value = unpack_storage_number(n); + sum += value; + + counter++; + } + rd->state->query_ops.finalize(&handle); + if (unlikely(!counter)) { + debug( + D_BACKEND, + "EXPORTING: %s.%s.%s: no values stored in database for range %lu to %lu", + host->hostname, + st->id, + rd->id, + (unsigned long)after, + (unsigned long)before); + return NAN; + } + + if (unlikely(EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_SUM)) + return sum; + + return sum / (calculated_number)counter; +} + +/** + * Start batch formatting for every connector instance's buffer + * + * @param engine an engine data structure. + */ +void start_batch_formatting(struct engine *engine) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled) { + uv_mutex_lock(&instance->mutex); + if (instance->start_batch_formatting && instance->start_batch_formatting(instance) != 0) { + error("EXPORTING: cannot start batch formatting for %s", instance->config.name); + disable_instance(instance); + } + } + } +} + +/** + * Start host formatting for every connector instance's buffer + * + * @param engine an engine data structure. + * @param host a data collecting host. + */ +void start_host_formatting(struct engine *engine, RRDHOST *host) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled) { + if (rrdhost_is_exportable(instance, host)) { + if (instance->start_host_formatting && instance->start_host_formatting(instance, host) != 0) { + error("EXPORTING: cannot start host formatting for %s", instance->config.name); + disable_instance(instance); + } + } else { + instance->skip_host = 1; + } + } + } +} + +/** + * Start chart formatting for every connector instance's buffer + * + * @param engine an engine data structure. + * @param st a chart. + */ +void start_chart_formatting(struct engine *engine, RRDSET *st) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled && !instance->skip_host) { + if (rrdset_is_exportable(instance, st)) { + if (instance->start_chart_formatting && instance->start_chart_formatting(instance, st) != 0) { + error("EXPORTING: cannot start chart formatting for %s", instance->config.name); + disable_instance(instance); + } + } else { + instance->skip_chart = 1; + } + } + } +} + +/** + * Format metric for every connector instance's buffer + * + * @param engine an engine data structure. + * @param rd a dimension(metric) in the Netdata database. + */ +void metric_formatting(struct engine *engine, RRDDIM *rd) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled && !instance->skip_host && !instance->skip_chart) { + if (instance->metric_formatting && instance->metric_formatting(instance, rd) != 0) { + error("EXPORTING: cannot format metric for %s", instance->config.name); + disable_instance(instance); + continue; + } + instance->stats.buffered_metrics++; + } + } +} + +/** + * End chart formatting for every connector instance's buffer + * + * @param engine an engine data structure. + * @param a chart. + */ +void end_chart_formatting(struct engine *engine, RRDSET *st) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled && !instance->skip_host && !instance->skip_chart) { + if (instance->end_chart_formatting && instance->end_chart_formatting(instance, st) != 0) { + error("EXPORTING: cannot end chart formatting for %s", instance->config.name); + disable_instance(instance); + continue; + } + } + instance->skip_chart = 0; + } +} + +/** + * End host formatting for every connector instance's buffer + * + * @param engine an engine data structure. + * @param host a data collecting host. + */ +void end_host_formatting(struct engine *engine, RRDHOST *host) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled && !instance->skip_host) { + if (instance->end_host_formatting && instance->end_host_formatting(instance, host) != 0) { + error("EXPORTING: cannot end host formatting for %s", instance->config.name); + disable_instance(instance); + continue; + } + } + instance->skip_host = 0; + } +} + +/** + * End batch formatting for every connector instance's buffer + * + * @param engine an engine data structure. + */ +void end_batch_formatting(struct engine *engine) +{ + for (struct instance *instance = engine->instance_root; instance; instance = instance->next) { + if (instance->scheduled) { + if (instance->end_batch_formatting && instance->end_batch_formatting(instance) != 0) { + error("EXPORTING: cannot end batch formatting for %s", instance->config.name); + disable_instance(instance); + continue; + } + uv_mutex_unlock(&instance->mutex); + instance->data_is_ready = 1; + uv_cond_signal(&instance->cond_var); + + instance->scheduled = 0; + instance->after = instance->before; + } + } +} + +/** + * Prepare buffers + * + * Walk through the Netdata database and fill buffers for every scheduled exporting connector instance according to + * configured rules. + * + * @param engine an engine data structure. + */ +void prepare_buffers(struct engine *engine) +{ + netdata_thread_disable_cancelability(); + start_batch_formatting(engine); + + rrd_rdlock(); + RRDHOST *host; + rrdhost_foreach_read(host) + { + rrdhost_rdlock(host); + start_host_formatting(engine, host); + RRDSET *st; + rrdset_foreach_read(st, host) + { + rrdset_rdlock(st); + start_chart_formatting(engine, st); + + RRDDIM *rd; + rrddim_foreach_read(rd, st) + metric_formatting(engine, rd); + + end_chart_formatting(engine, st); + rrdset_unlock(st); + } + + end_host_formatting(engine, host); + rrdhost_unlock(host); + } + rrd_unlock(); + netdata_thread_enable_cancelability(); + + end_batch_formatting(engine); +} + +/** + * Flush a buffer with host labels + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int flush_host_labels(struct instance *instance, RRDHOST *host) +{ + (void)host; + + if (instance->labels) + buffer_flush(instance->labels); + + return 0; +} + +/** + * End a batch for a simple connector + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int simple_connector_end_batch(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = + (struct simple_connector_data *)instance->connector_specific_data; + struct stats *stats = &instance->stats; + + BUFFER *instance_buffer = (BUFFER *)instance->buffer; + struct simple_connector_buffer *last_buffer = simple_connector_data->last_buffer; + + if (!last_buffer->buffer) { + last_buffer->buffer = buffer_create(0); + } + + if (last_buffer->used) { + // ring buffer is full, reuse the oldest element + simple_connector_data->first_buffer = simple_connector_data->first_buffer->next; + + stats->data_lost_events++; + stats->lost_metrics += last_buffer->buffered_metrics; + stats->lost_bytes += last_buffer->buffered_bytes; + } + + // swap buffers + BUFFER *tmp_buffer = last_buffer->buffer; + last_buffer->buffer = instance_buffer; + instance->buffer = instance_buffer = tmp_buffer; + + buffer_flush(instance_buffer); + + if (last_buffer->header) + buffer_flush(last_buffer->header); + else + last_buffer->header = buffer_create(0); + + if (instance->prepare_header) + instance->prepare_header(instance); + + // The stats->buffered_metrics is used in the simple connector batch formatting as a variable for the number + // of metrics, added in the current iteration, so we are clearing it here. We will use the + // simple_connector_data->total_buffered_metrics in the worker to show the statistics. + size_t buffered_metrics = (size_t)stats->buffered_metrics; + stats->buffered_metrics = 0; + + size_t buffered_bytes = buffer_strlen(last_buffer->buffer); + + last_buffer->buffered_metrics = buffered_metrics; + last_buffer->buffered_bytes = buffered_bytes; + last_buffer->used++; + + simple_connector_data->total_buffered_metrics += buffered_metrics; + stats->buffered_bytes += buffered_bytes; + + simple_connector_data->last_buffer = simple_connector_data->last_buffer->next; + + return 0; +} diff --git a/exporting/prometheus/Makefile.am b/exporting/prometheus/Makefile.am new file mode 100644 index 000000000..334fca81c --- /dev/null +++ b/exporting/prometheus/Makefile.am @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +SUBDIRS = \ + remote_write \ + $(NULL) + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/exporting/prometheus/README.md b/exporting/prometheus/README.md new file mode 100644 index 000000000..d718a366e --- /dev/null +++ b/exporting/prometheus/README.md @@ -0,0 +1,461 @@ + + +# Using Netdata with Prometheus + +> IMPORTANT: the format Netdata sends metrics to Prometheus has changed since Netdata v1.7. The new Prometheus exporting +> connector for Netdata supports a lot more features and is aligned to the development of the rest of the Netdata +> exporting connectors. + +Prometheus is a distributed monitoring system which offers a very simple setup along with a robust data model. Recently +Netdata added support for Prometheus. I'm going to quickly show you how to install both Netdata and Prometheus on the +same server. We can then use Grafana pointed at Prometheus to obtain long term metrics Netdata offers. I'm assuming we +are starting at a fresh ubuntu shell (whether you'd like to follow along in a VM or a cloud instance is up to you). + +## Installing Netdata and Prometheus + +### Installing Netdata + +There are number of ways to install Netdata according to [Installation](/packaging/installer/README.md). The suggested way +of installing the latest Netdata and keep it upgrade automatically. Using one line installation: + +```sh +bash <(curl -Ss https://my-netdata.io/kickstart.sh) +``` + +At this point we should have Netdata listening on port 19999. Attempt to take your browser here: + +```sh +http://your.netdata.ip:19999 +``` + +_(replace `your.netdata.ip` with the IP or hostname of the server running Netdata)_ + +### Installing Prometheus + +In order to install Prometheus we are going to introduce our own systemd startup script along with an example of +prometheus.yaml configuration. Prometheus needs to be pointed to your server at a specific target url for it to scrape +Netdata's api. Prometheus is always a pull model meaning Netdata is the passive client within this architecture. +Prometheus always initiates the connection with Netdata. + +#### Download Prometheus + +```sh +cd /tmp && curl -s https://api.github.com/repos/prometheus/prometheus/releases/latest \ +| grep "browser_download_url.*linux-amd64.tar.gz" \ +| cut -d '"' -f 4 \ +| wget -qi - +``` + +#### Create prometheus system user + +```sh +sudo useradd -r prometheus +``` + +#### Create prometheus directory + +```sh +sudo mkdir /opt/prometheus +sudo chown prometheus:prometheus /opt/prometheus +``` + +#### Untar prometheus directory + +```sh +sudo tar -xvf /tmp/prometheus-*linux-amd64.tar.gz -C /opt/prometheus --strip=1 +``` + +#### Install prometheus.yml + +We will use the following `prometheus.yml` file. Save it at `/opt/prometheus/prometheus.yml`. + +Make sure to replace `your.netdata.ip` with the IP or hostname of the host running Netdata. + +```yaml +# my global config +global: + scrape_interval: 5s # Set the scrape interval to every 5 seconds. Default is every 1 minute. + evaluation_interval: 5s # Evaluate rules every 5 seconds. The default is every 1 minute. + # scrape_timeout is set to the global default (10s). + + # Attach these labels to any time series or alerts when communicating with + # external systems (federation, remote storage, Alertmanager). + external_labels: + monitor: 'codelab-monitor' + +# Load rules once and periodically evaluate them according to the global 'evaluation_interval'. +rule_files: + # - "first.rules" + # - "second.rules" + +# A scrape configuration containing exactly one endpoint to scrape: +# Here it's Prometheus itself. +scrape_configs: + # The job name is added as a label `job=` to any timeseries scraped from this config. + - job_name: 'prometheus' + + # metrics_path defaults to '/metrics' + # scheme defaults to 'http'. + + static_configs: + - targets: ['0.0.0.0:9090'] + + - job_name: 'netdata-scrape' + + metrics_path: '/api/v1/allmetrics' + params: + # format: prometheus | prometheus_all_hosts + # You can use `prometheus_all_hosts` if you want Prometheus to set the `instance` to your hostname instead of IP + format: [prometheus] + # + # sources: as-collected | raw | average | sum | volume + # default is: average + #source: [as-collected] + # + # server name for this prometheus - the default is the client IP + # for Netdata to uniquely identify it + #server: ['prometheus1'] + honor_labels: true + + static_configs: + - targets: ['{your.netdata.ip}:19999'] +``` + +#### Install nodes.yml + +The following is completely optional, it will enable Prometheus to generate alerts from some NetData sources. Tweak the +values to your own needs. We will use the following `nodes.yml` file below. Save it at `/opt/prometheus/nodes.yml`, and +add a _- "nodes.yml"_ entry under the _rule_files:_ section in the example prometheus.yml file above. + +```yaml +groups: +- name: nodes + + rules: + - alert: node_high_cpu_usage_70 + expr: avg(rate(netdata_cpu_cpu_percentage_average{dimension="idle"}[1m])) by (job) > 70 + for: 1m + annotations: + description: '{{ $labels.job }} on ''{{ $labels.job }}'' CPU usage is at {{ humanize $value }}%.' + summary: CPU alert for container node '{{ $labels.job }}' + + - alert: node_high_memory_usage_70 + expr: 100 / sum(netdata_system_ram_MB_average) by (job) + * sum(netdata_system_ram_MB_average{dimension=~"free|cached"}) by (job) < 30 + for: 1m + annotations: + description: '{{ $labels.job }} memory usage is {{ humanize $value}}%.' + summary: Memory alert for container node '{{ $labels.job }}' + + - alert: node_low_root_filesystem_space_20 + expr: 100 / sum(netdata_disk_space_GB_average{family="/"}) by (job) + * sum(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}) by (job) < 20 + for: 1m + annotations: + description: '{{ $labels.job }} root filesystem space is {{ humanize $value}}%.' + summary: Root filesystem alert for container node '{{ $labels.job }}' + + - alert: node_root_filesystem_fill_rate_6h + expr: predict_linear(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}[1h], 6 * 3600) < 0 + for: 1h + labels: + severity: critical + annotations: + description: Container node {{ $labels.job }} root filesystem is going to fill up in 6h. + summary: Disk fill alert for Swarm node '{{ $labels.job }}' +``` + +#### Install prometheus.service + +Save this service file as `/etc/systemd/system/prometheus.service`: + +```sh +[Unit] +Description=Prometheus Server +AssertPathExists=/opt/prometheus + +[Service] +Type=simple +WorkingDirectory=/opt/prometheus +User=prometheus +Group=prometheus +ExecStart=/opt/prometheus/prometheus --config.file=/opt/prometheus/prometheus.yml --log.level=info +ExecReload=/bin/kill -SIGHUP $MAINPID +ExecStop=/bin/kill -SIGINT $MAINPID + +[Install] +WantedBy=multi-user.target +``` + +##### Start Prometheus + +```sh +sudo systemctl start prometheus +sudo systemctl enable prometheus +``` + +Prometheus should now start and listen on port 9090. Attempt to head there with your browser. + +If everything is working correctly when you fetch `http://your.prometheus.ip:9090` you will see a 'Status' tab. Click +this and click on 'targets' We should see the Netdata host as a scraped target. + +--- + +## Netdata support for Prometheus + +> IMPORTANT: the format Netdata sends metrics to Prometheus has changed since Netdata v1.6. The new format allows easier +> queries for metrics and supports both `as collected` and normalized metrics. + +Before explaining the changes, we have to understand the key differences between Netdata and Prometheus. + +### understanding Netdata metrics + +#### charts + +Each chart in Netdata has several properties (common to all its metrics): + +- `chart_id` - uniquely identifies a chart. + +- `chart_name` - a more human friendly name for `chart_id`, also unique. + +- `context` - this is the template of the chart. All disk I/O charts have the same context, all mysql requests charts + have the same context, etc. This is used for alarm templates to match all the charts they should be attached to. + +- `family` groups a set of charts together. It is used as the submenu of the dashboard. + +- `units` is the units for all the metrics attached to the chart. + +#### dimensions + +Then each Netdata chart contains metrics called `dimensions`. All the dimensions of a chart have the same units of +measurement, and are contextually in the same category (ie. the metrics for disk bandwidth are `read` and `write` and +they are both in the same chart). + +### Netdata data source + +Netdata can send metrics to Prometheus from 3 data sources: + +- `as collected` or `raw` - this data source sends the metrics to Prometheus as they are collected. No conversion is + done by Netdata. The latest value for each metric is just given to Prometheus. This is the most preferred method by + Prometheus, but it is also the harder to work with. To work with this data source, you will need to understand how + to get meaningful values out of them. + + The format of the metrics is: `CONTEXT{chart="CHART",family="FAMILY",dimension="DIMENSION"}`. + + If the metric is a counter (`incremental` in Netdata lingo), `_total` is appended the context. + + Unlike Prometheus, Netdata allows each dimension of a chart to have a different algorithm and conversion constants + (`multiplier` and `divisor`). In this case, that the dimensions of a charts are heterogeneous, Netdata will use this + format: `CONTEXT_DIMENSION{chart="CHART",family="FAMILY"}` + +- `average` - this data source uses the Netdata database to send the metrics to Prometheus as they are presented on + the Netdata dashboard. So, all the metrics are sent as gauges, at the units they are presented in the Netdata + dashboard charts. This is the easiest to work with. + + The format of the metrics is: `CONTEXT_UNITS_average{chart="CHART",family="FAMILY",dimension="DIMENSION"}`. + + When this source is used, Netdata keeps track of the last access time for each Prometheus server fetching the + metrics. This last access time is used at the subsequent queries of the same Prometheus server to identify the + time-frame the `average` will be calculated. + + So, no matter how frequently Prometheus scrapes Netdata, it will get all the database data. + To identify each Prometheus server, Netdata uses by default the IP of the client fetching the metrics. + + If there are multiple Prometheus servers fetching data from the same Netdata, using the same IP, each Prometheus + server can append `server=NAME` to the URL. Netdata will use this `NAME` to uniquely identify the Prometheus server. + +- `sum` or `volume`, is like `average` but instead of averaging the values, it sums them. + + The format of the metrics is: `CONTEXT_UNITS_sum{chart="CHART",family="FAMILY",dimension="DIMENSION"}`. All the + other operations are the same with `average`. + + To change the data source to `sum` or `as-collected` you need to provide the `source` parameter in the request URL. + e.g.: `http://your.netdata.ip:19999/api/v1/allmetrics?format=prometheus&help=yes&source=as-collected` + + Keep in mind that early versions of Netdata were sending the metrics as: `CHART_DIMENSION{}`. + +### Querying Metrics + +Fetch with your web browser this URL: + +`http://your.netdata.ip:19999/api/v1/allmetrics?format=prometheus&help=yes` + +_(replace `your.netdata.ip` with the ip or hostname of your Netdata server)_ + +Netdata will respond with all the metrics it sends to Prometheus. + +If you search that page for `"system.cpu"` you will find all the metrics Netdata is exporting to Prometheus for this +chart. `system.cpu` is the chart name on the Netdata dashboard (on the Netdata dashboard all charts have a text heading +such as : `Total CPU utilization (system.cpu)`. What we are interested here in the chart name: `system.cpu`). + +Searching for `"system.cpu"` reveals: + +```sh +# COMMENT homogeneous chart "system.cpu", context "system.cpu", family "cpu", units "percentage" +# COMMENT netdata_system_cpu_percentage_average: dimension "guest_nice", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="guest_nice"} 0.0000000 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "guest", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="guest"} 1.7837326 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "steal", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="steal"} 0.0000000 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "softirq", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="softirq"} 0.5275442 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "irq", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="irq"} 0.2260836 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "user", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="user"} 2.3362762 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "system", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="system"} 1.7961062 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "nice", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="nice"} 0.0000000 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "iowait", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="iowait"} 0.9671802 1500066662000 +# COMMENT netdata_system_cpu_percentage_average: dimension "idle", value is percentage, gauge, dt 1500066653 to 1500066662 inclusive +netdata_system_cpu_percentage_average{chart="system.cpu",family="cpu",dimension="idle"} 92.3630770 1500066662000 +``` + +_(Netdata response for `system.cpu` with source=`average`)_ + +In `average` or `sum` data sources, all values are normalized and are reported to Prometheus as gauges. Now, use the +'expression' text form in Prometheus. Begin to type the metrics we are looking for: `netdata_system_cpu`. You should see +that the text form begins to auto-fill as Prometheus knows about this metric. + +If the data source was `as collected`, the response would be: + +```sh +# COMMENT homogeneous chart "system.cpu", context "system.cpu", family "cpu", units "percentage" +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "guest_nice", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="guest_nice"} 0 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "guest", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="guest"} 63945 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "steal", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="steal"} 0 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "softirq", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="softirq"} 8295 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "irq", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="irq"} 4079 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "user", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="user"} 116488 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "system", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="system"} 35084 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "nice", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="nice"} 505 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "iowait", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="iowait"} 23314 1500066716438 +# COMMENT netdata_system_cpu_total: chart "system.cpu", context "system.cpu", family "cpu", dimension "idle", value * 1 / 1 delta gives percentage (counter) +netdata_system_cpu_total{chart="system.cpu",family="cpu",dimension="idle"} 918470 1500066716438 +``` + +_(Netdata response for `system.cpu` with source=`as-collected`)_ + +For more information check Prometheus documentation. + +### Streaming data from upstream hosts + +The `format=prometheus` parameter only exports the host's Netdata metrics. If you are using the parent-child +functionality of Netdata this ignores any upstream hosts - so you should consider using the below in your +**prometheus.yml**: + +```yaml + metrics_path: '/api/v1/allmetrics' + params: + format: [prometheus_all_hosts] + honor_labels: true +``` + +This will report all upstream host data, and `honor_labels` will make Prometheus take note of the instance names +provided. + +### Timestamps + +To pass the metrics through Prometheus pushgateway, Netdata supports the option `×tamps=no` to send the metrics +without timestamps. + +## Netdata host variables + +Netdata collects various system configuration metrics, like the max number of TCP sockets supported, the max number of +files allowed system-wide, various IPC sizes, etc. These metrics are not exposed to Prometheus by default. + +To expose them, append `variables=yes` to the Netdata URL. + +### TYPE and HELP + +To save bandwidth, and because Prometheus does not use them anyway, `# TYPE` and `# HELP` lines are suppressed. If +wanted they can be re-enabled via `types=yes` and `help=yes`, e.g. +`/api/v1/allmetrics?format=prometheus&types=yes&help=yes` + +Note that if enabled, the `# TYPE` and `# HELP` lines are repeated for every occurrence of a metric, which goes against the Prometheus documentation's [specification for these lines](https://github.com/prometheus/docs/blob/master/content/docs/instrumenting/exposition_formats.md#comments-help-text-and-type-information). + +### Names and IDs + +Netdata supports names and IDs for charts and dimensions. Usually IDs are unique identifiers as read by the system and +names are human friendly labels (also unique). + +Most charts and metrics have the same ID and name, but in several cases they are different: disks with device-mapper, +interrupts, QoS classes, statsd synthetic charts, etc. + +The default is controlled in `exporting.conf`: + +```conf +[prometheus:exporter] + send names instead of ids = yes | no +``` + +You can overwrite it from Prometheus, by appending to the URL: + +- `&names=no` to get IDs (the old behaviour) +- `&names=yes` to get names + +### Filtering metrics sent to Prometheus + +Netdata can filter the metrics it sends to Prometheus with this setting: + +```conf +[prometheus:exporter] + send charts matching = * +``` + +This settings accepts a space separated list of [simple patterns](/libnetdata/simple_pattern/README.md) to match the +**charts** to be sent to Prometheus. Each pattern can use `*` as wildcard, any number of times (e.g `*a*b*c*` is valid). +Patterns starting with `!` give a negative match (e.g `!*.bad users.* groups.*` will send all the users and groups +except `bad` user and `bad` group). The order is important: the first match (positive or negative) left to right, is +used. + +### Changing the prefix of Netdata metrics + +Netdata sends all metrics prefixed with `netdata_`. You can change this in `netdata.conf`, like this: + +```conf +[prometheus:exporter] + prefix = netdata +``` + +It can also be changed from the URL, by appending `&prefix=netdata`. + +### Metric Units + +The default source `average` adds the unit of measurement to the name of each metric (e.g. `_KiB_persec`). To hide the +units and get the same metric names as with the other sources, append to the URL `&hideunits=yes`. + +The units were standardized in v1.12, with the effect of changing the metric names. To get the metric names as they were +before v1.12, append to the URL `&oldunits=yes` + +### Accuracy of `average` and `sum` data sources + +When the data source is set to `average` or `sum`, Netdata remembers the last access of each client accessing Prometheus +metrics and uses this last access time to respond with the `average` or `sum` of all the entries in the database since +that. This means that Prometheus servers are not losing data when they access Netdata with data source = `average` or +`sum`. + +To uniquely identify each Prometheus server, Netdata uses the IP of the client accessing the metrics. If however the IP +is not good enough for identifying a single Prometheus server (e.g. when Prometheus servers are accessing Netdata +through a web proxy, or when multiple Prometheus servers are NATed to a single IP), each Prometheus may append +`&server=NAME` to the URL. This `NAME` is used by Netdata to uniquely identify each Prometheus server and keep track of +its last access time. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fprometheus%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/prometheus/prometheus.c b/exporting/prometheus/prometheus.c new file mode 100644 index 000000000..371f5a520 --- /dev/null +++ b/exporting/prometheus/prometheus.c @@ -0,0 +1,916 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#define EXPORTINGS_INTERNALS +#include "prometheus.h" + +// ---------------------------------------------------------------------------- +// PROMETHEUS +// /api/v1/allmetrics?format=prometheus and /api/v1/allmetrics?format=prometheus_all_hosts + +/** + * Check if a chart can be sent to Prometheus + * + * @param instance an instance data structure. + * @param st a chart. + * @return Returns 1 if the chart can be sent, 0 otherwise. + */ +inline int can_send_rrdset(struct instance *instance, RRDSET *st) +{ + RRDHOST *host = st->rrdhost; + + if (unlikely(rrdset_flag_check(st, RRDSET_FLAG_BACKEND_IGNORE))) + return 0; + + if (unlikely(!rrdset_flag_check(st, RRDSET_FLAG_BACKEND_SEND))) { + // we have not checked this chart + if (simple_pattern_matches(instance->config.charts_pattern, st->id) || + simple_pattern_matches(instance->config.charts_pattern, st->name)) + rrdset_flag_set(st, RRDSET_FLAG_BACKEND_SEND); + else { + rrdset_flag_set(st, RRDSET_FLAG_BACKEND_IGNORE); + debug( + D_BACKEND, + "EXPORTING: not sending chart '%s' of host '%s', because it is disabled for exporting.", + st->id, + host->hostname); + return 0; + } + } + + if (unlikely(!rrdset_is_available_for_backends(st))) { + debug( + D_BACKEND, + "EXPORTING: not sending chart '%s' of host '%s', because it is not available for exporting.", + st->id, + host->hostname); + return 0; + } + + if (unlikely( + st->rrd_memory_mode == RRD_MEMORY_MODE_NONE && + !(EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED))) { + debug( + D_BACKEND, + "EXPORTING: not sending chart '%s' of host '%s' because its memory mode is '%s' and the exporting connector requires database access.", + st->id, + host->hostname, + rrd_memory_mode_name(host->rrd_memory_mode)); + return 0; + } + + return 1; +} + +static struct prometheus_server { + const char *server; + uint32_t hash; + RRDHOST *host; + time_t last_access; + struct prometheus_server *next; +} *prometheus_server_root = NULL; + +static netdata_mutex_t prometheus_server_root_mutex = NETDATA_MUTEX_INITIALIZER; + +/** + * Clean server root local structure + */ +void prometheus_clean_server_root() +{ + if (prometheus_server_root) { + netdata_mutex_lock(&prometheus_server_root_mutex); + + struct prometheus_server *ps; + for (ps = prometheus_server_root; ps; ) { + struct prometheus_server *current = ps; + ps = ps->next; + if(current->server) + freez((void *)current->server); + + freez(current); + } + prometheus_server_root = NULL; + netdata_mutex_unlock(&prometheus_server_root_mutex); + } +} + +/** + * Get the last time when a Prometheus server scraped the Netdata Prometheus exporter. + * + * @param server the name of the Prometheus server. + * @param host a data collecting host. + * @param now actual time. + * @return Returns the last time when the server accessed Netdata, or 0 if it is the first occurrence. + */ +static inline time_t prometheus_server_last_access(const char *server, RRDHOST *host, time_t now) +{ +#ifdef UNIT_TESTING + return 0; +#endif + uint32_t hash = simple_hash(server); + + netdata_mutex_lock(&prometheus_server_root_mutex); + + struct prometheus_server *ps; + for (ps = prometheus_server_root; ps; ps = ps->next) { + if (host == ps->host && hash == ps->hash && !strcmp(server, ps->server)) { + time_t last = ps->last_access; + ps->last_access = now; + netdata_mutex_unlock(&prometheus_server_root_mutex); + return last; + } + } + + ps = callocz(1, sizeof(struct prometheus_server)); + ps->server = strdupz(server); + ps->hash = hash; + ps->host = host; + ps->last_access = now; + ps->next = prometheus_server_root; + prometheus_server_root = ps; + + netdata_mutex_unlock(&prometheus_server_root_mutex); + return 0; +} + +/** + * Copy and sanitize name. + * + * @param d a destination string. + * @param s a source sting. + * @param usable the number of characters to copy. + * @return Returns the length of the copied string. + */ +inline size_t prometheus_name_copy(char *d, const char *s, size_t usable) +{ + size_t n; + + for (n = 0; *s && n < usable; d++, s++, n++) { + register char c = *s; + + if (!isalnum(c)) + *d = '_'; + else + *d = c; + } + *d = '\0'; + + return n; +} + +/** + * Copy and sanitize label. + * + * @param d a destination string. + * @param s a source sting. + * @param usable the number of characters to copy. + * @return Returns the length of the copied string. + */ +inline size_t prometheus_label_copy(char *d, const char *s, size_t usable) +{ + size_t n; + + // make sure we can escape one character without overflowing the buffer + usable--; + + for (n = 0; *s && n < usable; d++, s++, n++) { + register char c = *s; + + if (unlikely(c == '"' || c == '\\' || c == '\n')) { + *d++ = '\\'; + n++; + } + *d = c; + } + *d = '\0'; + + return n; +} + +/** + * Copy and sanitize units. + * + * @param d a destination string. + * @param s a source sting. + * @param usable the number of characters to copy. + * @param showoldunits set this flag to 1 to show old (before v1.12) units. + * @return Returns the destination string. + */ +inline char *prometheus_units_copy(char *d, const char *s, size_t usable, int showoldunits) +{ + const char *sorig = s; + char *ret = d; + size_t n; + + // Fix for issue 5227 + if (unlikely(showoldunits)) { + static struct { + const char *newunit; + uint32_t hash; + const char *oldunit; + } units[] = { { "KiB/s", 0, "kilobytes/s" }, + { "MiB/s", 0, "MB/s" }, + { "GiB/s", 0, "GB/s" }, + { "KiB", 0, "KB" }, + { "MiB", 0, "MB" }, + { "GiB", 0, "GB" }, + { "inodes", 0, "Inodes" }, + { "percentage", 0, "percent" }, + { "faults/s", 0, "page faults/s" }, + { "KiB/operation", 0, "kilobytes per operation" }, + { "milliseconds/operation", 0, "ms per operation" }, + { NULL, 0, NULL } }; + static int initialized = 0; + int i; + + if (unlikely(!initialized)) { + for (i = 0; units[i].newunit; i++) + units[i].hash = simple_hash(units[i].newunit); + initialized = 1; + } + + uint32_t hash = simple_hash(s); + for (i = 0; units[i].newunit; i++) { + if (unlikely(hash == units[i].hash && !strcmp(s, units[i].newunit))) { + // info("matched extension for filename '%s': '%s'", filename, last_dot); + s = units[i].oldunit; + sorig = s; + break; + } + } + } + *d++ = '_'; + for (n = 1; *s && n < usable; d++, s++, n++) { + register char c = *s; + + if (!isalnum(c)) + *d = '_'; + else + *d = c; + } + + if (n == 2 && sorig[0] == '%') { + n = 0; + d = ret; + s = "_percent"; + for (; *s && n < usable; n++) + *d++ = *s++; + } else if (n > 3 && sorig[n - 3] == '/' && sorig[n - 2] == 's') { + n = n - 2; + d -= 2; + s = "_persec"; + for (; *s && n < usable; n++) + *d++ = *s++; + } + + *d = '\0'; + + return ret; +} + +/** + * Format host labels for the Prometheus exporter + * + * @param instance an instance data structure. + * @param host a data collecting host. + */ +void format_host_labels_prometheus(struct instance *instance, RRDHOST *host) +{ + if (unlikely(!sending_labels_configured(instance))) + return; + + if (!instance->labels) + instance->labels = buffer_create(1024); + + int count = 0; + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char key[PROMETHEUS_ELEMENT_MAX + 1]; + char value[PROMETHEUS_ELEMENT_MAX + 1]; + + prometheus_name_copy(key, label->key, PROMETHEUS_ELEMENT_MAX); + prometheus_label_copy(value, label->value, PROMETHEUS_ELEMENT_MAX); + + if (*key && *value) { + if (count > 0) + buffer_strcat(instance->labels, ","); + buffer_sprintf(instance->labels, "%s=\"%s\"", key, value); + count++; + } + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); +} + +struct host_variables_callback_options { + RRDHOST *host; + BUFFER *wb; + EXPORTING_OPTIONS exporting_options; + PROMETHEUS_OUTPUT_OPTIONS output_options; + const char *prefix; + const char *labels; + time_t now; + int host_header_printed; + char name[PROMETHEUS_VARIABLE_MAX + 1]; +}; + +/** + * Print host variables. + * + * @param rv a variable. + * @param data callback options. + * @return Returns 1 if the chart can be sent, 0 otherwise. + */ +static int print_host_variables(RRDVAR *rv, void *data) +{ + struct host_variables_callback_options *opts = data; + + if (rv->options & (RRDVAR_OPTION_CUSTOM_HOST_VAR | RRDVAR_OPTION_CUSTOM_CHART_VAR)) { + if (!opts->host_header_printed) { + opts->host_header_printed = 1; + + if (opts->output_options & PROMETHEUS_OUTPUT_HELP) { + buffer_sprintf(opts->wb, "\n# COMMENT global host and chart variables\n"); + } + } + + calculated_number value = rrdvar2number(rv); + if (isnan(value) || isinf(value)) { + if (opts->output_options & PROMETHEUS_OUTPUT_HELP) + buffer_sprintf( + opts->wb, "# COMMENT variable \"%s\" is %s. Skipped.\n", rv->name, (isnan(value)) ? "NAN" : "INF"); + + return 0; + } + + char *label_pre = ""; + char *label_post = ""; + if (opts->labels && *opts->labels) { + label_pre = "{"; + label_post = "}"; + } + + prometheus_name_copy(opts->name, rv->name, sizeof(opts->name)); + + if (opts->output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) + buffer_sprintf( + opts->wb, + "%s_%s%s%s%s " CALCULATED_NUMBER_FORMAT " %llu\n", + opts->prefix, + opts->name, + label_pre, + opts->labels, + label_post, + value, + opts->now * 1000ULL); + else + buffer_sprintf( + opts->wb, + "%s_%s%s%s%s " CALCULATED_NUMBER_FORMAT "\n", + opts->prefix, + opts->name, + label_pre, + opts->labels, + label_post, + value); + + return 1; + } + + return 0; +} + +struct gen_parameters { + const char *prefix; + char *context; + char *suffix; + + char *chart; + char *dimension; + char *family; + char *labels; + + PROMETHEUS_OUTPUT_OPTIONS output_options; + RRDSET *st; + RRDDIM *rd; + + const char *relation; + const char *type; +}; + +/** + * Write an as-collected help comment to a buffer. + * + * @param wb the buffer to write the comment to. + * @param p parameters for generating the comment string. + * @param homogeneous a flag for homogeneous charts. + * @param prometheus_collector a flag for metrics from prometheus collector. + */ +static void generate_as_collected_prom_help(BUFFER *wb, struct gen_parameters *p, int homogeneous, int prometheus_collector) +{ + buffer_sprintf(wb, "# COMMENT %s_%s", p->prefix, p->context); + + if (!homogeneous) + buffer_sprintf(wb, "_%s", p->dimension); + + buffer_sprintf( + wb, + "%s: chart \"%s\", context \"%s\", family \"%s\", dimension \"%s\", value * ", + p->suffix, + (p->output_options & PROMETHEUS_OUTPUT_NAMES && p->st->name) ? p->st->name : p->st->id, + p->st->context, + p->st->family, + (p->output_options & PROMETHEUS_OUTPUT_NAMES && p->rd->name) ? p->rd->name : p->rd->id); + + if (prometheus_collector) + buffer_sprintf(wb, "1 / 1"); + else + buffer_sprintf(wb, COLLECTED_NUMBER_FORMAT " / " COLLECTED_NUMBER_FORMAT, p->rd->multiplier, p->rd->divisor); + + buffer_sprintf(wb, " %s %s (%s)\n", p->relation, p->st->units, p->type); +} + +/** + * Write an as-collected metric to a buffer. + * + * @param wb the buffer to write the metric to. + * @param p parameters for generating the metric string. + * @param homogeneous a flag for homogeneous charts. + * @param prometheus_collector a flag for metrics from prometheus collector. + */ +static void generate_as_collected_prom_metric(BUFFER *wb, struct gen_parameters *p, int homogeneous, int prometheus_collector) +{ + buffer_sprintf(wb, "%s_%s", p->prefix, p->context); + + if (!homogeneous) + buffer_sprintf(wb, "_%s", p->dimension); + + buffer_sprintf(wb, "%s{chart=\"%s\",family=\"%s\"", p->suffix, p->chart, p->family); + + if (homogeneous) + buffer_sprintf(wb, ",dimension=\"%s\"", p->dimension); + + buffer_sprintf(wb, "%s} ", p->labels); + + if (prometheus_collector) + buffer_sprintf( + wb, + CALCULATED_NUMBER_FORMAT, + (calculated_number)p->rd->last_collected_value * (calculated_number)p->rd->multiplier / + (calculated_number)p->rd->divisor); + else + buffer_sprintf(wb, COLLECTED_NUMBER_FORMAT, p->rd->last_collected_value); + + if (p->output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) + buffer_sprintf(wb, " %llu\n", timeval_msec(&p->rd->last_collected_time)); + else + buffer_sprintf(wb, "\n"); +} + +/** + * Write metrics in Prometheus format to a buffer. + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @param wb the buffer to fill with metrics. + * @param prefix a prefix for every metric. + * @param exporting_options options to configure what data is exported. + * @param allhosts set to 1 if host instance should be in the output for tags. + * @param output_options options to configure the format of the output. + */ +static void rrd_stats_api_v1_charts_allmetrics_prometheus( + struct instance *instance, + RRDHOST *host, + BUFFER *wb, + const char *prefix, + EXPORTING_OPTIONS exporting_options, + int allhosts, + PROMETHEUS_OUTPUT_OPTIONS output_options) +{ + rrdhost_rdlock(host); + + char hostname[PROMETHEUS_ELEMENT_MAX + 1]; + prometheus_label_copy(hostname, host->hostname, PROMETHEUS_ELEMENT_MAX); + + format_host_labels_prometheus(instance, host); + + if (output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) + buffer_sprintf( + wb, + "netdata_info{instance=\"%s\",application=\"%s\",version=\"%s\"} 1 %llu\n", + hostname, + host->program_name, + host->program_version, + now_realtime_usec() / USEC_PER_MS); + else + buffer_sprintf( + wb, + "netdata_info{instance=\"%s\",application=\"%s\",version=\"%s\"} 1\n", + hostname, + host->program_name, + host->program_version); + + char labels[PROMETHEUS_LABELS_MAX + 1] = ""; + if (allhosts) { + if (instance->labels && buffer_tostring(instance->labels)) { + if (output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) { + buffer_sprintf( + wb, + "netdata_host_tags_info{instance=\"%s\",%s} 1 %llu\n", + hostname, + buffer_tostring(instance->labels), + now_realtime_usec() / USEC_PER_MS); + + // deprecated, exists only for compatibility with older queries + buffer_sprintf( + wb, + "netdata_host_tags{instance=\"%s\",%s} 1 %llu\n", + hostname, + buffer_tostring(instance->labels), + now_realtime_usec() / USEC_PER_MS); + } else { + buffer_sprintf( + wb, "netdata_host_tags_info{instance=\"%s\",%s} 1\n", hostname, buffer_tostring(instance->labels)); + + // deprecated, exists only for compatibility with older queries + buffer_sprintf( + wb, "netdata_host_tags{instance=\"%s\",%s} 1\n", hostname, buffer_tostring(instance->labels)); + } + } + + snprintfz(labels, PROMETHEUS_LABELS_MAX, ",instance=\"%s\"", hostname); + } else { + if (instance->labels && buffer_tostring(instance->labels)) { + if (output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) { + buffer_sprintf( + wb, + "netdata_host_tags_info{%s} 1 %llu\n", + buffer_tostring(instance->labels), + now_realtime_usec() / USEC_PER_MS); + + // deprecated, exists only for compatibility with older queries + buffer_sprintf( + wb, + "netdata_host_tags{%s} 1 %llu\n", + buffer_tostring(instance->labels), + now_realtime_usec() / USEC_PER_MS); + } else { + buffer_sprintf(wb, "netdata_host_tags_info{%s} 1\n", buffer_tostring(instance->labels)); + + // deprecated, exists only for compatibility with older queries + buffer_sprintf(wb, "netdata_host_tags{%s} 1\n", buffer_tostring(instance->labels)); + } + } + } + + if (instance->labels) + buffer_flush(instance->labels); + + // send custom variables set for the host + if (output_options & PROMETHEUS_OUTPUT_VARIABLES) { + struct host_variables_callback_options opts = { .host = host, + .wb = wb, + .labels = (labels[0] == ',') ? &labels[1] : labels, + .exporting_options = exporting_options, + .output_options = output_options, + .prefix = prefix, + .now = now_realtime_sec(), + .host_header_printed = 0 }; + foreach_host_variable_callback(host, print_host_variables, &opts); + } + + // for each chart + RRDSET *st; + rrdset_foreach_read(st, host) + { + + if (likely(can_send_rrdset(instance, st))) { + rrdset_rdlock(st); + + char chart[PROMETHEUS_ELEMENT_MAX + 1]; + char context[PROMETHEUS_ELEMENT_MAX + 1]; + char family[PROMETHEUS_ELEMENT_MAX + 1]; + char units[PROMETHEUS_ELEMENT_MAX + 1] = ""; + + prometheus_label_copy( + chart, (output_options & PROMETHEUS_OUTPUT_NAMES && st->name) ? st->name : st->id, PROMETHEUS_ELEMENT_MAX); + prometheus_label_copy(family, st->family, PROMETHEUS_ELEMENT_MAX); + prometheus_name_copy(context, st->context, PROMETHEUS_ELEMENT_MAX); + + int as_collected = (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_AS_COLLECTED); + int homogeneous = 1; + int prometheus_collector = 0; + if (as_collected) { + if (rrdset_flag_check(st, RRDSET_FLAG_HOMOGENEOUS_CHECK)) + rrdset_update_heterogeneous_flag(st); + + if (rrdset_flag_check(st, RRDSET_FLAG_HETEROGENEOUS)) + homogeneous = 0; + + if (st->module_name && !strcmp(st->module_name, "prometheus")) + prometheus_collector = 1; + } else { + if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_AVERAGE && + !(output_options & PROMETHEUS_OUTPUT_HIDEUNITS)) + prometheus_units_copy( + units, st->units, PROMETHEUS_ELEMENT_MAX, output_options & PROMETHEUS_OUTPUT_OLDUNITS); + } + + if (unlikely(output_options & PROMETHEUS_OUTPUT_HELP)) + buffer_sprintf( + wb, + "\n# COMMENT %s chart \"%s\", context \"%s\", family \"%s\", units \"%s\"\n", + (homogeneous) ? "homogeneous" : "heterogeneous", + (output_options & PROMETHEUS_OUTPUT_NAMES && st->name) ? st->name : st->id, + st->context, + st->family, + st->units); + + // for each dimension + RRDDIM *rd; + rrddim_foreach_read(rd, st) + { + if (rd->collections_counter && !rrddim_flag_check(rd, RRDDIM_FLAG_OBSOLETE)) { + char dimension[PROMETHEUS_ELEMENT_MAX + 1]; + char *suffix = ""; + + if (as_collected) { + // we need as-collected / raw data + + struct gen_parameters p; + p.prefix = prefix; + p.context = context; + p.suffix = suffix; + p.chart = chart; + p.dimension = dimension; + p.family = family; + p.labels = labels; + p.output_options = output_options; + p.st = st; + p.rd = rd; + + if (unlikely(rd->last_collected_time.tv_sec < instance->after)) + continue; + + p.type = "gauge"; + p.relation = "gives"; + if (rd->algorithm == RRD_ALGORITHM_INCREMENTAL || + rd->algorithm == RRD_ALGORITHM_PCENT_OVER_DIFF_TOTAL) { + p.type = "counter"; + p.relation = "delta gives"; + p.suffix = "_total"; + } + + if (homogeneous) { + // all the dimensions of the chart, has the same algorithm, multiplier and divisor + // we add all dimensions as labels + + prometheus_label_copy( + dimension, + (output_options & PROMETHEUS_OUTPUT_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_HELP)) + generate_as_collected_prom_help(wb, &p, homogeneous, prometheus_collector); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_TYPES)) + buffer_sprintf(wb, "# TYPE %s_%s%s %s\n", prefix, context, suffix, p.type); + + generate_as_collected_prom_metric(wb, &p, homogeneous, prometheus_collector); + } else { + // the dimensions of the chart, do not have the same algorithm, multiplier or divisor + // we create a metric per dimension + + prometheus_name_copy( + dimension, + (output_options & PROMETHEUS_OUTPUT_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_HELP)) + generate_as_collected_prom_help(wb, &p, homogeneous, prometheus_collector); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_TYPES)) + buffer_sprintf( + wb, "# TYPE %s_%s_%s%s %s\n", prefix, context, dimension, suffix, p.type); + + generate_as_collected_prom_metric(wb, &p, homogeneous, prometheus_collector); + } + } else { + // we need average or sum of the data + + time_t first_time = instance->after; + time_t last_time = instance->before; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_time); + + if (!isnan(value) && !isinf(value)) { + if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_AVERAGE) + suffix = "_average"; + else if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_SUM) + suffix = "_sum"; + + prometheus_label_copy( + dimension, + (output_options & PROMETHEUS_OUTPUT_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_HELP)) + buffer_sprintf( + wb, + "# COMMENT %s_%s%s%s: dimension \"%s\", value is %s, gauge, dt %llu to %llu inclusive\n", + prefix, + context, + units, + suffix, + (output_options & PROMETHEUS_OUTPUT_NAMES && rd->name) ? rd->name : rd->id, + st->units, + (unsigned long long)first_time, + (unsigned long long)last_time); + + if (unlikely(output_options & PROMETHEUS_OUTPUT_TYPES)) + buffer_sprintf(wb, "# TYPE %s_%s%s%s gauge\n", prefix, context, units, suffix); + + if (output_options & PROMETHEUS_OUTPUT_TIMESTAMPS) + buffer_sprintf( + wb, + "%s_%s%s%s{chart=\"%s\",family=\"%s\",dimension=\"%s\"%s} " CALCULATED_NUMBER_FORMAT + " %llu\n", + prefix, + context, + units, + suffix, + chart, + family, + dimension, + labels, + value, + last_time * MSEC_PER_SEC); + else + buffer_sprintf( + wb, + "%s_%s%s%s{chart=\"%s\",family=\"%s\",dimension=\"%s\"%s} " CALCULATED_NUMBER_FORMAT + "\n", + prefix, + context, + units, + suffix, + chart, + family, + dimension, + labels, + value); + } + } + } + } + + rrdset_unlock(st); + } + } + + rrdhost_unlock(host); +} + +/** + * Get the last time time when a server accessed Netdata. Write information about an API request to a buffer. + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @param wb the buffer to write to. + * @param exporting_options options to configure what data is exported. + * @param server the name of a Prometheus server.. + * @param now actual time. + * @param output_options options to configure the format of the output. + * @return Returns the last time when the server accessed Netdata. + */ +static inline time_t prometheus_preparation( + struct instance *instance, + RRDHOST *host, + BUFFER *wb, + EXPORTING_OPTIONS exporting_options, + const char *server, + time_t now, + PROMETHEUS_OUTPUT_OPTIONS output_options) +{ + if (!server || !*server) + server = "default"; + + time_t after = prometheus_server_last_access(server, host, now); + + int first_seen = 0; + if (!after) { + after = now - instance->config.update_every; + first_seen = 1; + } + + if (after > now) { + // oops! this should never happen + after = now - instance->config.update_every; + } + + if (output_options & PROMETHEUS_OUTPUT_HELP) { + char *mode; + if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + mode = "as collected"; + else if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_AVERAGE) + mode = "average"; + else if (EXPORTING_OPTIONS_DATA_SOURCE(exporting_options) == EXPORTING_SOURCE_DATA_SUM) + mode = "sum"; + else + mode = "unknown"; + + buffer_sprintf( + wb, + "# COMMENT netdata \"%s\" to %sprometheus \"%s\", source \"%s\", last seen %lu %s, time range %lu to %lu\n\n", + host->hostname, + (first_seen) ? "FIRST SEEN " : "", + server, + mode, + (unsigned long)((first_seen) ? 0 : (now - after)), + (first_seen) ? "never" : "seconds ago", + (unsigned long)after, + (unsigned long)now); + } + + return after; +} + +/** + * Write metrics and auxiliary information for one host to a buffer. + * + * @param host a data collecting host. + * @param wb the buffer to write to. + * @param server the name of a Prometheus server. + * @param prefix a prefix for every metric. + * @param exporting_options options to configure what data is exported. + * @param output_options options to configure the format of the output. + */ +void rrd_stats_api_v1_charts_allmetrics_prometheus_single_host( + RRDHOST *host, + BUFFER *wb, + const char *server, + const char *prefix, + EXPORTING_OPTIONS exporting_options, + PROMETHEUS_OUTPUT_OPTIONS output_options) +{ + if (unlikely(!prometheus_exporter_instance)) + return; + + prometheus_exporter_instance->before = now_realtime_sec(); + + // we start at the point we had stopped before + prometheus_exporter_instance->after = prometheus_preparation( + prometheus_exporter_instance, + host, + wb, + exporting_options, + server, + prometheus_exporter_instance->before, + output_options); + + rrd_stats_api_v1_charts_allmetrics_prometheus( + prometheus_exporter_instance, host, wb, prefix, exporting_options, 0, output_options); +} + +/** + * Write metrics and auxiliary information for all hosts to a buffer. + * + * @param host a data collecting host. + * @param wb the buffer to write to. + * @param server the name of a Prometheus server. + * @param prefix a prefix for every metric. + * @param exporting_options options to configure what data is exported. + * @param output_options options to configure the format of the output. + */ +void rrd_stats_api_v1_charts_allmetrics_prometheus_all_hosts( + RRDHOST *host, + BUFFER *wb, + const char *server, + const char *prefix, + EXPORTING_OPTIONS exporting_options, + PROMETHEUS_OUTPUT_OPTIONS output_options) +{ + if (unlikely(!prometheus_exporter_instance)) + return; + + prometheus_exporter_instance->before = now_realtime_sec(); + + // we start at the point we had stopped before + prometheus_exporter_instance->after = prometheus_preparation( + prometheus_exporter_instance, + host, + wb, + exporting_options, + server, + prometheus_exporter_instance->before, + output_options); + + rrd_rdlock(); + rrdhost_foreach_read(host) + { + rrd_stats_api_v1_charts_allmetrics_prometheus( + prometheus_exporter_instance, host, wb, prefix, exporting_options, 1, output_options); + } + rrd_unlock(); +} diff --git a/exporting/prometheus/prometheus.h b/exporting/prometheus/prometheus.h new file mode 100644 index 000000000..2f0845ce9 --- /dev/null +++ b/exporting/prometheus/prometheus.h @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_PROMETHEUS_H +#define NETDATA_EXPORTING_PROMETHEUS_H 1 + +#include "exporting/exporting_engine.h" + +#define PROMETHEUS_ELEMENT_MAX 256 +#define PROMETHEUS_LABELS_MAX 1024 +#define PROMETHEUS_VARIABLE_MAX 256 + +#define PROMETHEUS_LABELS_MAX_NUMBER 128 + +typedef enum prometheus_output_flags { + PROMETHEUS_OUTPUT_NONE = 0, + PROMETHEUS_OUTPUT_HELP = (1 << 0), + PROMETHEUS_OUTPUT_TYPES = (1 << 1), + PROMETHEUS_OUTPUT_NAMES = (1 << 2), + PROMETHEUS_OUTPUT_TIMESTAMPS = (1 << 3), + PROMETHEUS_OUTPUT_VARIABLES = (1 << 4), + PROMETHEUS_OUTPUT_OLDUNITS = (1 << 5), + PROMETHEUS_OUTPUT_HIDEUNITS = (1 << 6) +} PROMETHEUS_OUTPUT_OPTIONS; + +extern void rrd_stats_api_v1_charts_allmetrics_prometheus_single_host( + RRDHOST *host, BUFFER *wb, const char *server, const char *prefix, + EXPORTING_OPTIONS exporting_options, PROMETHEUS_OUTPUT_OPTIONS output_options); +extern void rrd_stats_api_v1_charts_allmetrics_prometheus_all_hosts( + RRDHOST *host, BUFFER *wb, const char *server, const char *prefix, + EXPORTING_OPTIONS exporting_options, PROMETHEUS_OUTPUT_OPTIONS output_options); + +int can_send_rrdset(struct instance *instance, RRDSET *st); +size_t prometheus_name_copy(char *d, const char *s, size_t usable); +size_t prometheus_label_copy(char *d, const char *s, size_t usable); +char *prometheus_units_copy(char *d, const char *s, size_t usable, int showoldunits); + +void format_host_labels_prometheus(struct instance *instance, RRDHOST *host); + +extern void prometheus_clean_server_root(); + +#endif //NETDATA_EXPORTING_PROMETHEUS_H diff --git a/exporting/prometheus/remote_write/Makefile.am b/exporting/prometheus/remote_write/Makefile.am new file mode 100644 index 000000000..d049ef48c --- /dev/null +++ b/exporting/prometheus/remote_write/Makefile.am @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +CLEANFILES = \ + remote_write.pb.cc \ + remote_write.pb.h \ + $(NULL) + +dist_noinst_DATA = \ + remote_write.proto \ + README.md \ + $(NULL) diff --git a/exporting/prometheus/remote_write/README.md b/exporting/prometheus/remote_write/README.md new file mode 100644 index 000000000..fe901024b --- /dev/null +++ b/exporting/prometheus/remote_write/README.md @@ -0,0 +1,51 @@ + + +# Prometheus remote write exporting connector + +The Prometheus remote write exporting connector uses the exporting engine to send Netdata metrics to your choice of more +than 20 external storage providers for long-term archiving and further analysis. + +## Prerequisites + +To use the Prometheus remote write API with [storage +providers](https://prometheus.io/docs/operating/integrations/#remote-endpoints-and-storage), install +[protobuf](https://developers.google.com/protocol-buffers/) and [snappy](https://github.com/google/snappy) libraries. +Next, [reinstall Netdata](/packaging/installer/REINSTALL.md), which detects that the required libraries and utilities +are now available. + +## Configuration + +To enable data exporting to a storage provider using the Prometheus remote write API, run `./edit-config exporting.conf` +in the Netdata configuration directory and set the following options: + +```conf +[prometheus_remote_write:my_instance] + enabled = yes + destination = example.domain:example_port + remote write URL path = /receive +``` + +You can also add `:https` modifier to the connector type if you need to use the TLS/SSL protocol. For example: +`remote_write:https:my_instance`. + +`remote write URL path` is used to set an endpoint path for the remote write protocol. The default value is `/receive`. +For example, if your endpoint is `http://example.domain:example_port/storage/read`: + +```conf + destination = example.domain:example_port + remote write URL path = /storage/read +``` + +`buffered` and `lost` dimensions in the Netdata Exporting Connector Data Size operation monitoring chart estimate uncompressed +buffer size on failures. + +## Notes + +The remote write exporting connector does not support `buffer on failures` + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fprometheus%2Fremote_write%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/prometheus/remote_write/remote_write.c b/exporting/prometheus/remote_write/remote_write.c new file mode 100644 index 000000000..30bd05ad7 --- /dev/null +++ b/exporting/prometheus/remote_write/remote_write.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "remote_write.h" + +static int as_collected; +static int homogeneous; +char context[PROMETHEUS_ELEMENT_MAX + 1]; +char chart[PROMETHEUS_ELEMENT_MAX + 1]; +char family[PROMETHEUS_ELEMENT_MAX + 1]; +char units[PROMETHEUS_ELEMENT_MAX + 1] = ""; + +/** + * Prepare HTTP header + * + * @param instance an instance data structure. + */ +void prometheus_remote_write_prepare_header(struct instance *instance) +{ + struct prometheus_remote_write_specific_config *connector_specific_config = + instance->config.connector_specific_config; + struct simple_connector_data *simple_connector_data = instance->connector_specific_data; + + buffer_sprintf( + simple_connector_data->last_buffer->header, + "POST %s HTTP/1.1\r\n" + "Host: %s\r\n" + "Accept: */*\r\n" + "Content-Encoding: snappy\r\n" + "Content-Type: application/x-protobuf\r\n" + "X-Prometheus-Remote-Write-Version: 0.1.0\r\n" + "Content-Length: %zu\r\n" + "\r\n", + connector_specific_config->remote_write_path, + instance->config.destination, + buffer_strlen(simple_connector_data->last_buffer->buffer)); +} + +/** + * Process a responce received after Prometheus remote write connector had sent data + * + * @param buffer a response from a remote service. + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int process_prometheus_remote_write_response(BUFFER *buffer, struct instance *instance) +{ + if (unlikely(!buffer)) + return 1; + + const char *s = buffer_tostring(buffer); + int len = buffer_strlen(buffer); + + // do nothing with HTTP responses 200 or 204 + + while (!isspace(*s) && len) { + s++; + len--; + } + s++; + len--; + + if (likely(len > 4 && (!strncmp(s, "200 ", 4) || !strncmp(s, "204 ", 4)))) + return 0; + else + return exporting_discard_response(buffer, instance); +} + +/** + * Release specific data allocated. + * + * @param instance an instance data structure. + */ +void clean_prometheus_remote_write(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = instance->connector_specific_data; + freez(simple_connector_data->connector_specific_data); + + struct prometheus_remote_write_specific_config *connector_specific_config = + instance->config.connector_specific_config; + freez(connector_specific_config->remote_write_path); +} + +/** + * Initialize Prometheus Remote Write connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_prometheus_remote_write_instance(struct instance *instance) +{ + instance->worker = simple_connector_worker; + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_prometheus_remote_write; + instance->start_chart_formatting = format_chart_prometheus_remote_write; + instance->metric_formatting = format_dimension_prometheus_remote_write; + instance->end_chart_formatting = NULL; + instance->end_host_formatting = NULL; + instance->end_batch_formatting = format_batch_prometheus_remote_write; + + instance->prepare_header = prometheus_remote_write_prepare_header; + instance->check_response = process_prometheus_remote_write_response; + + instance->buffer = (void *)buffer_create(0); + + if (uv_mutex_init(&instance->mutex)) + return 1; + if (uv_cond_init(&instance->cond_var)) + return 1; + + struct simple_connector_data *simple_connector_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = simple_connector_data; + +#ifdef ENABLE_HTTPS + simple_connector_data->flags = NETDATA_SSL_START; + simple_connector_data->conn = NULL; + if (instance->config.options & EXPORTING_OPTION_USE_TLS) { + security_start_ssl(NETDATA_SSL_CONTEXT_EXPORTING); + } +#endif + + struct prometheus_remote_write_specific_data *connector_specific_data = + callocz(1, sizeof(struct prometheus_remote_write_specific_data)); + simple_connector_data->connector_specific_data = (void *)connector_specific_data; + + simple_connector_init(instance); + + connector_specific_data->write_request = init_write_request(); + + instance->engine->protocol_buffers_initialized = 1; + + return 0; +} + +/** + * Format host data for Prometheus Remote Write connector + * + * @param instance an instance data structure. + * @param host a data collecting host. + * @return Always returns 0. + */ +int format_host_prometheus_remote_write(struct instance *instance, RRDHOST *host) +{ + struct simple_connector_data *simple_connector_data = + (struct simple_connector_data *)instance->connector_specific_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + (struct prometheus_remote_write_specific_data *)simple_connector_data->connector_specific_data; + + char hostname[PROMETHEUS_ELEMENT_MAX + 1]; + prometheus_label_copy( + hostname, + (host == localhost) ? instance->config.hostname : host->hostname, + PROMETHEUS_ELEMENT_MAX); + + add_host_info( + connector_specific_data->write_request, + "netdata_info", hostname, host->program_name, host->program_version, now_realtime_usec() / USEC_PER_MS); + + if (unlikely(sending_labels_configured(instance))) { + rrdhost_check_rdlock(host); + netdata_rwlock_rdlock(&host->labels.labels_rwlock); + for (struct label *label = host->labels.head; label; label = label->next) { + if (!should_send_label(instance, label)) + continue; + + char key[PROMETHEUS_ELEMENT_MAX + 1]; + prometheus_name_copy(key, label->key, PROMETHEUS_ELEMENT_MAX); + + char value[PROMETHEUS_ELEMENT_MAX + 1]; + prometheus_label_copy(value, label->value, PROMETHEUS_ELEMENT_MAX); + + add_label(connector_specific_data->write_request, key, value); + } + netdata_rwlock_unlock(&host->labels.labels_rwlock); + } + + return 0; +} + +/** + * Format chart data for Prometheus Remote Write connector + * + * @param instance an instance data structure. + * @param st a chart. + * @return Always returns 0. + */ +int format_chart_prometheus_remote_write(struct instance *instance, RRDSET *st) +{ + prometheus_label_copy( + chart, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && st->name) ? st->name : st->id, + PROMETHEUS_ELEMENT_MAX); + prometheus_label_copy(family, st->family, PROMETHEUS_ELEMENT_MAX); + prometheus_name_copy(context, st->context, PROMETHEUS_ELEMENT_MAX); + + as_collected = (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED); + homogeneous = 1; + if (as_collected) { + if (rrdset_flag_check(st, RRDSET_FLAG_HOMOGENEOUS_CHECK)) + rrdset_update_heterogeneous_flag(st); + + if (rrdset_flag_check(st, RRDSET_FLAG_HETEROGENEOUS)) + homogeneous = 0; + } else { + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AVERAGE) + prometheus_units_copy(units, st->units, PROMETHEUS_ELEMENT_MAX, 0); + } + + return 0; +} + +/** + * Format dimension data for Prometheus Remote Write connector + * + * @param instance an instance data structure. + * @param rd a dimension. + * @return Always returns 0. + */ +int format_dimension_prometheus_remote_write(struct instance *instance, RRDDIM *rd) +{ + struct simple_connector_data *simple_connector_data = + (struct simple_connector_data *)instance->connector_specific_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + (struct prometheus_remote_write_specific_data *)simple_connector_data->connector_specific_data; + + if (rd->collections_counter && !rrddim_flag_check(rd, RRDDIM_FLAG_OBSOLETE)) { + char name[PROMETHEUS_LABELS_MAX + 1]; + char dimension[PROMETHEUS_ELEMENT_MAX + 1]; + char *suffix = ""; + RRDHOST *host = rd->rrdset->rrdhost; + + if (as_collected) { + // we need as-collected / raw data + + if (unlikely(rd->last_collected_time.tv_sec < instance->after)) { + debug( + D_BACKEND, + "EXPORTING: not sending dimension '%s' of chart '%s' from host '%s', " + "its last data collection (%lu) is not within our timeframe (%lu to %lu)", + rd->id, rd->rrdset->id, + (host == localhost) ? instance->config.hostname : host->hostname, + (unsigned long)rd->last_collected_time.tv_sec, + (unsigned long)instance->after, + (unsigned long)instance->before); + return 0; + } + + if (homogeneous) { + // all the dimensions of the chart, has the same algorithm, multiplier and divisor + // we add all dimensions as labels + + prometheus_label_copy( + dimension, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + snprintf(name, PROMETHEUS_LABELS_MAX, "%s_%s%s", instance->config.prefix, context, suffix); + + add_metric( + connector_specific_data->write_request, + name, chart, family, dimension, + (host == localhost) ? instance->config.hostname : host->hostname, + rd->last_collected_value, timeval_msec(&rd->last_collected_time)); + } else { + // the dimensions of the chart, do not have the same algorithm, multiplier or divisor + // we create a metric per dimension + + prometheus_name_copy( + dimension, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + snprintf( + name, PROMETHEUS_LABELS_MAX, "%s_%s_%s%s", instance->config.prefix, context, dimension, + suffix); + + add_metric( + connector_specific_data->write_request, + name, chart, family, NULL, + (host == localhost) ? instance->config.hostname : host->hostname, + rd->last_collected_value, timeval_msec(&rd->last_collected_time)); + } + } else { + // we need average or sum of the data + + time_t last_t = instance->before; + calculated_number value = exporting_calculate_value_from_stored_data(instance, rd, &last_t); + + if (!isnan(value) && !isinf(value)) { + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AVERAGE) + suffix = "_average"; + else if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_SUM) + suffix = "_sum"; + + prometheus_label_copy( + dimension, + (instance->config.options & EXPORTING_OPTION_SEND_NAMES && rd->name) ? rd->name : rd->id, + PROMETHEUS_ELEMENT_MAX); + snprintf( + name, PROMETHEUS_LABELS_MAX, "%s_%s%s%s", instance->config.prefix, context, units, suffix); + + add_metric( + connector_specific_data->write_request, + name, chart, family, dimension, + (host == localhost) ? instance->config.hostname : host->hostname, + value, last_t * MSEC_PER_SEC); + } + } + } + + return 0; +} + +/** + * Format a batch for Prometheus Remote Write connector + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int format_batch_prometheus_remote_write(struct instance *instance) +{ + struct simple_connector_data *simple_connector_data = + (struct simple_connector_data *)instance->connector_specific_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + (struct prometheus_remote_write_specific_data *)simple_connector_data->connector_specific_data; + + size_t data_size = get_write_request_size(connector_specific_data->write_request); + + if (unlikely(!data_size)) { + error("EXPORTING: write request size is out of range"); + return 1; + } + + BUFFER *buffer = instance->buffer; + + buffer_need_bytes(buffer, data_size); + if (unlikely(pack_and_clear_write_request(connector_specific_data->write_request, buffer->buffer, &data_size))) { + error("EXPORTING: cannot pack write request"); + return 1; + } + buffer->len = data_size; + instance->stats.buffered_bytes = (collected_number)buffer_strlen(buffer); + + simple_connector_end_batch(instance); + + return 0; +} diff --git a/exporting/prometheus/remote_write/remote_write.h b/exporting/prometheus/remote_write/remote_write.h new file mode 100644 index 000000000..d738f5126 --- /dev/null +++ b/exporting/prometheus/remote_write/remote_write.h @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_H +#define NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_H + +#include "exporting/exporting_engine.h" +#include "exporting/prometheus/prometheus.h" +#include "remote_write_request.h" + +struct prometheus_remote_write_specific_data { + void *write_request; +}; + +int init_prometheus_remote_write_instance(struct instance *instance); +extern void clean_prometheus_remote_write(struct instance *instance); + +int format_host_prometheus_remote_write(struct instance *instance, RRDHOST *host); +int format_chart_prometheus_remote_write(struct instance *instance, RRDSET *st); +int format_dimension_prometheus_remote_write(struct instance *instance, RRDDIM *rd); +int format_batch_prometheus_remote_write(struct instance *instance); + +void prometheus_remote_write_prepare_header(struct instance *instance); +int process_prometheus_remote_write_response(BUFFER *buffer, struct instance *instance); + +#endif //NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_H diff --git a/exporting/prometheus/remote_write/remote_write.proto b/exporting/prometheus/remote_write/remote_write.proto new file mode 100644 index 000000000..dfde254e1 --- /dev/null +++ b/exporting/prometheus/remote_write/remote_write.proto @@ -0,0 +1,29 @@ +syntax = "proto3"; +package prometheus; + +option cc_enable_arenas = true; + +import "google/protobuf/descriptor.proto"; + +message WriteRequest { + repeated TimeSeries timeseries = 1 [(nullable) = false]; +} + +message TimeSeries { + repeated Label labels = 1 [(nullable) = false]; + repeated Sample samples = 2 [(nullable) = false]; +} + +message Label { + string name = 1; + string value = 2; +} + +message Sample { + double value = 1; + int64 timestamp = 2; +} + +extend google.protobuf.FieldOptions { + bool nullable = 65001; +} diff --git a/exporting/prometheus/remote_write/remote_write_request.cc b/exporting/prometheus/remote_write/remote_write_request.cc new file mode 100644 index 000000000..48d19efd6 --- /dev/null +++ b/exporting/prometheus/remote_write/remote_write_request.cc @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include +#include "remote_write.pb.h" +#include "remote_write_request.h" + +using namespace prometheus; + +google::protobuf::Arena arena; + +/** + * Initialize a write request + * + * @return Returns a new write request + */ +void *init_write_request() +{ + GOOGLE_PROTOBUF_VERIFY_VERSION; + WriteRequest *write_request = google::protobuf::Arena::CreateMessage(&arena); + return (void *)write_request; +} + +/** + * Adds information about a host to a write request + * + * @param write_request_p the write request + * @param name the name of a metric which is used for providing the host information + * @param instance the name of the host itself + * @param application the name of a program which sends the information + * @param version the version of the program + * @param timestamp the timestamp for the metric in milliseconds + */ +void add_host_info( + void *write_request_p, + const char *name, const char *instance, const char *application, const char *version, const int64_t timestamp) +{ + WriteRequest *write_request = (WriteRequest *)write_request_p; + TimeSeries *timeseries; + Sample *sample; + Label *label; + + timeseries = write_request->add_timeseries(); + + label = timeseries->add_labels(); + label->set_name("__name__"); + label->set_value(name); + + label = timeseries->add_labels(); + label->set_name("instance"); + label->set_value(instance); + + if (application) { + label = timeseries->add_labels(); + label->set_name("application"); + label->set_value(application); + } + + if (version) { + label = timeseries->add_labels(); + label->set_name("version"); + label->set_value(version); + } + + sample = timeseries->add_samples(); + sample->set_value(1); + sample->set_timestamp(timestamp); +} + +/** + * Adds a label to the last created timeseries + * + * @param write_request_p the write request with the timeseries + * @param key the key of the label + * @param value the value of the label + */ +void add_label(void *write_request_p, char *key, char *value) +{ + WriteRequest *write_request = (WriteRequest *)write_request_p; + TimeSeries *timeseries; + Label *label; + + timeseries = write_request->mutable_timeseries(write_request->timeseries_size() - 1); + + label = timeseries->add_labels(); + label->set_name(key); + label->set_value(value); +} + +/** + * Adds a metric to a write request + * + * @param write_request_p the write request + * @param name the name of the metric + * @param chart the chart, the metric belongs to + * @param family the family, the metric belongs to + * @param dimension the dimension, the metric belongs to + * @param instance the name of the host, the metric belongs to + * @param value the value of the metric + * @param timestamp the timestamp for the metric in milliseconds + */ +void add_metric( + void *write_request_p, + const char *name, const char *chart, const char *family, const char *dimension, const char *instance, + const double value, const int64_t timestamp) +{ + WriteRequest *write_request = (WriteRequest *)write_request_p; + TimeSeries *timeseries; + Sample *sample; + Label *label; + + timeseries = write_request->add_timeseries(); + + label = timeseries->add_labels(); + label->set_name("__name__"); + label->set_value(name); + + label = timeseries->add_labels(); + label->set_name("chart"); + label->set_value(chart); + + label = timeseries->add_labels(); + label->set_name("family"); + label->set_value(family); + + if (dimension) { + label = timeseries->add_labels(); + label->set_name("dimension"); + label->set_value(dimension); + } + + label = timeseries->add_labels(); + label->set_name("instance"); + label->set_value(instance); + + sample = timeseries->add_samples(); + sample->set_value(value); + sample->set_timestamp(timestamp); +} + +/** + * Gets the size of a write request + * + * @param write_request_p the write request + * @return Returns the size of the write request + */ +size_t get_write_request_size(void *write_request_p) +{ + WriteRequest *write_request = (WriteRequest *)write_request_p; + +#if GOOGLE_PROTOBUF_VERSION < 3001000 + size_t size = (size_t)snappy::MaxCompressedLength(write_request->ByteSize()); +#else + size_t size = (size_t)snappy::MaxCompressedLength(write_request->ByteSizeLong()); +#endif + + return (size < INT_MAX) ? size : 0; +} + +/** + * Packs a write request into a buffer and clears the request + * + * @param write_request_p the write request + * @param buffer a buffer, where compressed data is written + * @param size gets the size of the write request, returns the size of the compressed data + * @return Returns 0 on success, 1 on failure + */ +int pack_and_clear_write_request(void *write_request_p, char *buffer, size_t *size) +{ + WriteRequest *write_request = (WriteRequest *)write_request_p; + std::string uncompressed_write_request; + + if (write_request->SerializeToString(&uncompressed_write_request) == false) + return 1; + write_request->clear_timeseries(); + snappy::RawCompress(uncompressed_write_request.data(), uncompressed_write_request.size(), buffer, size); + + return 0; +} + +/** + * Shuts down the Protobuf library + */ +void protocol_buffers_shutdown() +{ + google::protobuf::ShutdownProtobufLibrary(); +} diff --git a/exporting/prometheus/remote_write/remote_write_request.h b/exporting/prometheus/remote_write/remote_write_request.h new file mode 100644 index 000000000..e1dfacaf8 --- /dev/null +++ b/exporting/prometheus/remote_write/remote_write_request.h @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_REQUEST_H +#define NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_REQUEST_H + +#ifdef __cplusplus +extern "C" { +#endif + +void *init_write_request(); + +void add_host_info( + void *write_request_p, + const char *name, const char *instance, const char *application, const char *version, const int64_t timestamp); + +void add_label(void *write_request_p, char *key, char *value); + +void add_metric( + void *write_request_p, + const char *name, const char *chart, const char *family, const char *dimension, + const char *instance, const double value, const int64_t timestamp); + +size_t get_write_request_size(void *write_request_p); + +int pack_and_clear_write_request(void *write_request_p, char *buffer, size_t *size); + +void protocol_buffers_shutdown(); + +#ifdef __cplusplus +} +#endif + +#endif //NETDATA_EXPORTING_PROMETHEUS_REMOTE_WRITE_REQUEST_H diff --git a/exporting/pubsub/Makefile.am b/exporting/pubsub/Makefile.am new file mode 100644 index 000000000..161784b8f --- /dev/null +++ b/exporting/pubsub/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/exporting/pubsub/README.md b/exporting/pubsub/README.md new file mode 100644 index 000000000..6da14c44f --- /dev/null +++ b/exporting/pubsub/README.md @@ -0,0 +1,45 @@ + + +# Export metrics to Google Cloud Pub/Sub Service + +## Prerequisites + +To use the Pub/Sub service for metric collecting and processing, you should first +[install](https://github.com/googleapis/cpp-cmakefiles) Google Cloud Platform C++ Proto Libraries. +Pub/Sub support is also dependent on the dependencies of those libraries, like `protobuf`, `protoc`, and `grpc`. Next, +Netdata should be re-installed from the source. The installer will detect that the required libraries are now available. + +> You [cannot compile Netdata](https://github.com/netdata/netdata/issues/10193) with Pub/Sub support enabled using +> `grpc` 1.32 or higher. +> +> Some distributions don't have `.cmake` files in packages. To build the C++ Proto Libraries on such distributions we +> advise you to delete `protobuf`, `protoc`, and `grpc` related packages and +> [install](https://github.com/grpc/grpc/blob/master/BUILDING.md) `grpc` with its dependencies from source. + +## Configuration + +To enable data sending to the Pub/Sub service, run `./edit-config exporting.conf` in the Netdata configuration directory +and set the following options: + +```conf +[pubsub:my_instance] + enabled = yes + destination = pubsub.googleapis.com + credentials file = /etc/netdata/google_cloud_credentials.json + project id = my_project + topic id = my_topic +``` + +Set the `destination` option to a Pub/Sub service endpoint. `pubsub.googleapis.com` is the default one. + +Next, create the credentials JSON file by following Google Cloud's [authentication guide](https://cloud.google.com/docs/authentication/getting-started#creating_a_service_account). The user running the Agent +(typically `netdata`) needs read access to `google_cloud_credentials.json`, which you can set with +`chmod 400 google_cloud_credentials.json; chown netdata google_cloud_credentials.json`. Set the `credentials file` +option to the full path of the file. + +[![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fexporting%2Fpubsub%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/exporting/pubsub/pubsub.c b/exporting/pubsub/pubsub.c new file mode 100644 index 000000000..336a096ab --- /dev/null +++ b/exporting/pubsub/pubsub.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "pubsub.h" + +/** + * Initialize Pub/Sub connector instance + * + * @param instance an instance data structure. + * @return Returns 0 on success, 1 on failure. + */ +int init_pubsub_instance(struct instance *instance) +{ + instance->worker = pubsub_connector_worker; + + instance->start_batch_formatting = NULL; + instance->start_host_formatting = format_host_labels_json_plaintext; + instance->start_chart_formatting = NULL; + + + if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED) + instance->metric_formatting = format_dimension_collected_json_plaintext; + else + instance->metric_formatting = format_dimension_stored_json_plaintext; + + instance->end_chart_formatting = NULL; + instance->end_host_formatting = flush_host_labels; + instance->end_batch_formatting = NULL; + + instance->prepare_header = NULL; + instance->check_response = NULL; + + instance->buffer = (void *)buffer_create(0); + if (!instance->buffer) { + error("EXPORTING: cannot create buffer for Pub/Sub exporting connector instance %s", instance->config.name); + return 1; + } + uv_mutex_init(&instance->mutex); + uv_cond_init(&instance->cond_var); + + struct pubsub_specific_data *connector_specific_data = callocz(1, sizeof(struct pubsub_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + struct pubsub_specific_config *connector_specific_config = + (struct pubsub_specific_config *)instance->config.connector_specific_config; + char error_message[ERROR_LINE_MAX + 1] = ""; + if (pubsub_init( + (void *)connector_specific_data, error_message, instance->config.destination, + connector_specific_config->credentials_file, connector_specific_config->project_id, + connector_specific_config->topic_id)) { + error( + "EXPORTING: Cannot initialize a Pub/Sub publisher for instance %s: %s", + instance->config.name, error_message); + return 1; + } + + return 0; +} + +/** + * Clean a PubSub connector instance + * + * @param instance an instance data structure. + */ +void clean_pubsub_instance(struct instance *instance) +{ + info("EXPORTING: cleaning up instance %s ...", instance->config.name); + + struct pubsub_specific_data *connector_specific_data = + (struct pubsub_specific_data *)instance->connector_specific_data; + pubsub_cleanup(connector_specific_data); + freez(connector_specific_data); + + buffer_free(instance->buffer); + + struct pubsub_specific_config *connector_specific_config = + (struct pubsub_specific_config *)instance->config.connector_specific_config; + freez(connector_specific_config->credentials_file); + freez(connector_specific_config->project_id); + freez(connector_specific_config->topic_id); + freez(connector_specific_config); + + info("EXPORTING: instance %s exited", instance->config.name); + instance->exited = 1; + + return; +} + +/** + * Pub/Sub connector worker + * + * Runs in a separate thread for every instance. + * + * @param instance_p an instance data structure. + */ +void pubsub_connector_worker(void *instance_p) +{ + struct instance *instance = (struct instance *)instance_p; + struct pubsub_specific_config *connector_specific_config = instance->config.connector_specific_config; + struct pubsub_specific_data *connector_specific_data = instance->connector_specific_data; + + while (!instance->engine->exit) { + struct stats *stats = &instance->stats; + char error_message[ERROR_LINE_MAX + 1] = ""; + + uv_mutex_lock(&instance->mutex); + while (!instance->data_is_ready) + uv_cond_wait(&instance->cond_var, &instance->mutex); + instance->data_is_ready = 0; + + + if (unlikely(instance->engine->exit)) { + uv_mutex_unlock(&instance->mutex); + break; + } + + // reset the monitoring chart counters + stats->received_bytes = + stats->sent_bytes = + stats->sent_metrics = + stats->lost_metrics = + stats->receptions = + stats->transmission_successes = + stats->transmission_failures = + stats->data_lost_events = + stats->lost_bytes = + stats->reconnects = 0; + + BUFFER *buffer = (BUFFER *)instance->buffer; + size_t buffer_len = buffer_strlen(buffer); + + stats->buffered_bytes = buffer_len; + + if (pubsub_add_message(instance->connector_specific_data, (char *)buffer_tostring(buffer))) { + error("EXPORTING: Instance %s: Cannot add data to a message", instance->config.name); + + stats->data_lost_events++; + stats->lost_metrics += stats->buffered_metrics; + stats->lost_bytes += buffer_len; + + goto cleanup; + } + + debug( + D_BACKEND, "EXPORTING: pubsub_publish(): project = %s, topic = %s, buffer = %zu", + connector_specific_config->project_id, connector_specific_config->topic_id, buffer_len); + + if (pubsub_publish((void *)connector_specific_data, error_message, stats->buffered_metrics, buffer_len)) { + error("EXPORTING: Instance: %s: Cannot publish a message: %s", instance->config.name, error_message); + + stats->transmission_failures++; + stats->data_lost_events++; + stats->lost_metrics += stats->buffered_metrics; + stats->lost_bytes += buffer_len; + + goto cleanup; + } + + stats->sent_bytes = buffer_len; + stats->transmission_successes++; + + size_t sent_metrics = 0, lost_metrics = 0, sent_bytes = 0, lost_bytes = 0; + + if (unlikely(pubsub_get_result( + connector_specific_data, error_message, &sent_metrics, &sent_bytes, &lost_metrics, &lost_bytes))) { + // oops! we couldn't send (all or some of the) data + error("EXPORTING: %s", error_message); + error( + "EXPORTING: failed to write data to service '%s'. Willing to write %zu bytes, wrote %zu bytes.", + instance->config.destination, lost_bytes, sent_bytes); + + stats->transmission_failures++; + stats->data_lost_events++; + stats->lost_metrics += lost_metrics; + stats->lost_bytes += lost_bytes; + } else { + stats->receptions++; + stats->sent_metrics = sent_metrics; + } + + cleanup: + send_internal_metrics(instance); + + buffer_flush(buffer); + stats->buffered_metrics = 0; + + uv_mutex_unlock(&instance->mutex); + +#ifdef UNIT_TESTING + return; +#endif + } + + clean_pubsub_instance(instance); +} diff --git a/exporting/pubsub/pubsub.h b/exporting/pubsub/pubsub.h new file mode 100644 index 000000000..0bcb76f9b --- /dev/null +++ b/exporting/pubsub/pubsub.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_PUBSUB_H +#define NETDATA_EXPORTING_PUBSUB_H + +#include "exporting/exporting_engine.h" +#include "exporting/json/json.h" +#include "pubsub_publish.h" + +int init_pubsub_instance(struct instance *instance); +void clean_pubsub_instance(struct instance *instance); +void pubsub_connector_worker(void *instance_p); + +#endif //NETDATA_EXPORTING_PUBSUB_H diff --git a/exporting/pubsub/pubsub_publish.cc b/exporting/pubsub/pubsub_publish.cc new file mode 100644 index 000000000..dc237cf22 --- /dev/null +++ b/exporting/pubsub/pubsub_publish.cc @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include +#include +#include +#include "pubsub_publish.h" + +#define EVENT_CHECK_TIMEOUT 50 + +struct response { + grpc::ClientContext *context; + google::pubsub::v1::PublishResponse *publish_response; + size_t tag; + grpc::Status *status; + + size_t published_metrics; + size_t published_bytes; +}; + +static inline void copy_error_message(char *error_message_dst, const char *error_message_src) +{ + std::strncpy(error_message_dst, error_message_src, ERROR_LINE_MAX); + error_message_dst[ERROR_LINE_MAX] = '\0'; +} + +/** + * Initialize a Pub/Sub client and a data structure for responses. + * + * @param pubsub_specific_data_p a pointer to a structure with instance-wide data. + * @param error_message report error message to a caller. + * @param destination a Pub/Sub service endpoint. + * @param credentials_file a full path for a file with google application credentials. + * @param project_id a project ID. + * @param topic_id a topic ID. + * @return Returns 0 on success, 1 on failure. + */ +int pubsub_init( + void *pubsub_specific_data_p, char *error_message, const char *destination, const char *credentials_file, + const char *project_id, const char *topic_id) +{ + struct pubsub_specific_data *connector_specific_data = (struct pubsub_specific_data *)pubsub_specific_data_p; + + try { + setenv("GOOGLE_APPLICATION_CREDENTIALS", credentials_file, 0); + + std::shared_ptr credentials = grpc::GoogleDefaultCredentials(); + if (credentials == nullptr) { + copy_error_message(error_message, "Can't load credentials"); + return 1; + } + + std::shared_ptr channel = grpc::CreateChannel(destination, credentials); + + google::pubsub::v1::Publisher::Stub *stub = new google::pubsub::v1::Publisher::Stub(channel); + if (!stub) { + copy_error_message(error_message, "Can't create a publisher stub"); + return 1; + } + + connector_specific_data->stub = stub; + + google::pubsub::v1::PublishRequest *request = new google::pubsub::v1::PublishRequest; + connector_specific_data->request = request; + ((google::pubsub::v1::PublishRequest *)(connector_specific_data->request)) + ->set_topic(std::string("projects/") + project_id + "/topics/" + topic_id); + + grpc::CompletionQueue *cq = new grpc::CompletionQueue; + connector_specific_data->completion_queue = cq; + + connector_specific_data->responses = new std::list; + + return 0; + } catch (std::exception const &ex) { + std::string em(std::string("Standard exception raised: ") + ex.what()); + copy_error_message(error_message, em.c_str()); + return 1; + } + + return 0; +} + +/** + * Clean the PubSub connector instance specific data + */ +void pubsub_cleanup(void *pubsub_specific_data_p) +{ + struct pubsub_specific_data *connector_specific_data = (struct pubsub_specific_data *)pubsub_specific_data_p; + + std::list *responses = (std::list *)connector_specific_data->responses; + std::list::iterator response; + for (response = responses->begin(); response != responses->end(); ++response) { + // TODO: If we do this, there are a huge amount of possibly lost records. We need to find a right way of + // cleaning up contexts + // delete response->context; + delete response->publish_response; + delete response->status; + } + delete responses; + + ((grpc::CompletionQueue *)connector_specific_data->completion_queue)->Shutdown(); + delete (grpc::CompletionQueue *)connector_specific_data->completion_queue; + delete (google::pubsub::v1::PublishRequest *)connector_specific_data->request; + delete (google::pubsub::v1::Publisher::Stub *)connector_specific_data->stub; + + // TODO: Find how to shutdown grpc gracefully. grpc_shutdown() doesn't seem to work. + // grpc_shutdown(); + + return; +} + +/** + * Add data to a Pub/Sub request message. + * + * @param pubsub_specific_data_p a pointer to a structure with instance-wide data. + * @param data a text buffer with metrics. + * @return Returns 0 on success, 1 on failure. + */ +int pubsub_add_message(void *pubsub_specific_data_p, char *data) +{ + struct pubsub_specific_data *connector_specific_data = (struct pubsub_specific_data *)pubsub_specific_data_p; + + try { + google::pubsub::v1::PubsubMessage *message = + ((google::pubsub::v1::PublishRequest *)(connector_specific_data->request))->add_messages(); + if (!message) + return 1; + + message->set_data(data); + } catch (std::exception const &ex) { + return 1; + } + + return 0; +} + +/** + * Send data to the Pub/Sub service + * + * @param pubsub_specific_data_p a pointer to a structure with client and request outcome information. + * @param error_message report error message to a caller. + * @param buffered_metrics the number of metrics we are going to send. + * @param buffered_bytes the number of bytes we are going to send. + * @return Returns 0 on success, 1 on failure. + */ +int pubsub_publish(void *pubsub_specific_data_p, char *error_message, size_t buffered_metrics, size_t buffered_bytes) +{ + struct pubsub_specific_data *connector_specific_data = (struct pubsub_specific_data *)pubsub_specific_data_p; + + try { + grpc::ClientContext *context = new grpc::ClientContext; + + std::unique_ptr > rpc( + ((google::pubsub::v1::Publisher::Stub *)(connector_specific_data->stub)) + ->AsyncPublish( + context, (*(google::pubsub::v1::PublishRequest *)(connector_specific_data->request)), + ((grpc::CompletionQueue *)(connector_specific_data->completion_queue)))); + + struct response response; + response.context = context; + response.publish_response = new google::pubsub::v1::PublishResponse; + response.tag = connector_specific_data->last_tag++; + response.status = new grpc::Status; + response.published_metrics = buffered_metrics; + response.published_bytes = buffered_bytes; + + rpc->Finish(response.publish_response, response.status, (void *)response.tag); + + ((google::pubsub::v1::PublishRequest *)(connector_specific_data->request))->clear_messages(); + + ((std::list *)(connector_specific_data->responses))->push_back(response); + } catch (std::exception const &ex) { + std::string em(std::string("Standard exception raised: ") + ex.what()); + copy_error_message(error_message, em.c_str()); + return 1; + } + + return 0; +} + +/** + * Get results from service responces + * + * @param pubsub_specific_data_p a pointer to a structure with instance-wide data. + * @param error_message report error message to a caller. + * @param sent_metrics report to a caller how many metrics was successfuly sent. + * @param sent_bytes report to a caller how many bytes was successfuly sent. + * @param lost_metrics report to a caller how many metrics was lost during transmission. + * @param lost_bytes report to a caller how many bytes was lost during transmission. + * @return Returns 0 if all data was sent successfully, 1 when data was lost on transmission. + */ +int pubsub_get_result( + void *pubsub_specific_data_p, char *error_message, + size_t *sent_metrics, size_t *sent_bytes, size_t *lost_metrics, size_t *lost_bytes) +{ + struct pubsub_specific_data *connector_specific_data = (struct pubsub_specific_data *)pubsub_specific_data_p; + std::list *responses = (std::list *)connector_specific_data->responses; + grpc_impl::CompletionQueue::NextStatus next_status; + + *sent_metrics = 0; + *sent_bytes = 0; + *lost_metrics = 0; + *lost_bytes = 0; + + try { + do { + std::list::iterator response; + void *got_tag; + bool ok = false; + + auto deadline = std::chrono::system_clock::now() + std::chrono::milliseconds(50); + next_status = (*(grpc::CompletionQueue *)(connector_specific_data->completion_queue)) + .AsyncNext(&got_tag, &ok, deadline); + + if (next_status == grpc::CompletionQueue::GOT_EVENT) { + for (response = responses->begin(); response != responses->end(); ++response) { + if ((void *)response->tag == got_tag) + break; + } + + if (response == responses->end()) { + copy_error_message(error_message, "Cannot get Pub/Sub response"); + return 1; + } + + if (ok && response->publish_response->message_ids_size()) { + *sent_metrics += response->published_metrics; + *sent_bytes += response->published_bytes; + } else { + *lost_metrics += response->published_metrics; + *lost_bytes += response->published_bytes; + response->status->error_message().copy(error_message, ERROR_LINE_MAX); + error_message[ERROR_LINE_MAX] = '\0'; + } + + delete response->context; + delete response->publish_response; + delete response->status; + responses->erase(response); + } + + if (next_status == grpc::CompletionQueue::SHUTDOWN) { + copy_error_message(error_message, "Completion queue shutdown"); + return 1; + } + + } while (next_status == grpc::CompletionQueue::GOT_EVENT); + } catch (std::exception const &ex) { + std::string em(std::string("Standard exception raised: ") + ex.what()); + copy_error_message(error_message, em.c_str()); + return 1; + } + + if (*lost_metrics) { + return 1; + } + + return 0; +} diff --git a/exporting/pubsub/pubsub_publish.h b/exporting/pubsub/pubsub_publish.h new file mode 100644 index 000000000..567a262f0 --- /dev/null +++ b/exporting/pubsub/pubsub_publish.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EXPORTING_PUBSUB_PUBLISH_H +#define NETDATA_EXPORTING_PUBSUB_PUBLISH_H + +#define ERROR_LINE_MAX 1023 + +#ifdef __cplusplus +extern "C" { +#endif + +struct pubsub_specific_data { + void *stub; + void *request; + void *completion_queue; + + void *responses; + size_t last_tag; +}; + +int pubsub_init( + void *pubsub_specific_data_p, char *error_message, const char *destination, const char *credentials_file, + const char *project_id, const char *topic_id); +void pubsub_cleanup(void *pubsub_specific_data_p); + +int pubsub_add_message(void *pubsub_specific_data_p, char *data); + +int pubsub_publish(void *pubsub_specific_data_p, char *error_message, size_t buffered_metrics, size_t buffered_bytes); +int pubsub_get_result( + void *pubsub_specific_data_p, char *error_message, + size_t *sent_metrics, size_t *sent_bytes, size_t *lost_metrics, size_t *lost_bytes); + +#ifdef __cplusplus +} +#endif + +#endif //NETDATA_EXPORTING_PUBSUB_PUBLISH_H diff --git a/exporting/read_config.c b/exporting/read_config.c new file mode 100644 index 000000000..995ba578f --- /dev/null +++ b/exporting/read_config.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +struct config exporting_config = { .first_section = NULL, + .last_section = NULL, + .mutex = NETDATA_MUTEX_INITIALIZER, + .index = { .avl_tree = { .root = NULL, .compar = appconfig_section_compare }, + .rwlock = AVL_LOCK_INITIALIZER } }; + +struct instance *prometheus_exporter_instance = NULL; + +static _CONNECTOR_INSTANCE *find_instance(const char *section) +{ + _CONNECTOR_INSTANCE *local_ci; + + local_ci = add_connector_instance(NULL, NULL); // Get root section + if (unlikely(!local_ci)) + return local_ci; + + if (!section) + return local_ci; + + while (local_ci) { + if (!strcmp(local_ci->instance_name, section)) + break; + local_ci = local_ci->next; + } + return local_ci; +} + +char *expconfig_get(struct config *root, const char *section, const char *name, const char *default_value) +{ + _CONNECTOR_INSTANCE *local_ci; + + if (!strcmp(section, CONFIG_SECTION_EXPORTING)) + return appconfig_get(root, CONFIG_SECTION_EXPORTING, name, default_value); + + local_ci = find_instance(section); + + if (!local_ci) + return NULL; // TODO: Check if it is meaningful to return default_value + + return appconfig_get( + root, local_ci->instance_name, name, + appconfig_get( + root, local_ci->connector_name, name, appconfig_get(root, CONFIG_SECTION_EXPORTING, name, default_value))); +} + +int expconfig_get_boolean(struct config *root, const char *section, const char *name, int default_value) +{ + _CONNECTOR_INSTANCE *local_ci; + + if (!strcmp(section, CONFIG_SECTION_EXPORTING)) + return appconfig_get_boolean(root, CONFIG_SECTION_EXPORTING, name, default_value); + + local_ci = find_instance(section); + + if (!local_ci) + return 0; // TODO: Check if it is meaningful to return default_value + + return appconfig_get_boolean( + root, local_ci->instance_name, name, + appconfig_get_boolean( + root, local_ci->connector_name, name, + appconfig_get_boolean(root, CONFIG_SECTION_EXPORTING, name, default_value))); +} + +long long expconfig_get_number(struct config *root, const char *section, const char *name, long long default_value) +{ + _CONNECTOR_INSTANCE *local_ci; + + if (!strcmp(section, CONFIG_SECTION_EXPORTING)) + return appconfig_get_number(root, CONFIG_SECTION_EXPORTING, name, default_value); + + local_ci = find_instance(section); + + if (!local_ci) + return 0; // TODO: Check if it is meaningful to return default_value + + return appconfig_get_number( + root, local_ci->instance_name, name, + appconfig_get_number( + root, local_ci->connector_name, name, + appconfig_get_number(root, CONFIG_SECTION_EXPORTING, name, default_value))); +} + +/* + * Get the next connector instance that we need to activate + * + * @param @target_ci will be filled with instance name and connector name + * + * @return - 1 if more connectors to be fetched, 0 done + * + */ + +int get_connector_instance(struct connector_instance *target_ci) +{ + static _CONNECTOR_INSTANCE *local_ci = NULL; + _CONNECTOR_INSTANCE *global_connector_instance; + + global_connector_instance = find_instance(NULL); // Fetch head of instances + + if (unlikely(!global_connector_instance)) + return 0; + + if (target_ci == NULL) { + local_ci = NULL; + return 1; + } + if (local_ci == NULL) + local_ci = global_connector_instance; + else { + local_ci = local_ci->next; + if (local_ci == NULL) + return 0; + } + + strcpy(target_ci->instance_name, local_ci->instance_name); + strcpy(target_ci->connector_name, local_ci->connector_name); + + return 1; +} + +/** + * Select Type + * + * Select the connector type based on the user input + * + * @param type is the string that defines the connector type + * + * @return It returns the connector id. + */ +EXPORTING_CONNECTOR_TYPE exporting_select_type(const char *type) +{ + if (!strcmp(type, "graphite") || !strcmp(type, "graphite:plaintext")) { + return EXPORTING_CONNECTOR_TYPE_GRAPHITE; + } else if (!strcmp(type, "graphite:http") || !strcmp(type, "graphite:https")) { + return EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP; + } else if (!strcmp(type, "json") || !strcmp(type, "json:plaintext")) { + return EXPORTING_CONNECTOR_TYPE_JSON; + } else if (!strcmp(type, "json:http") || !strcmp(type, "json:https")) { + return EXPORTING_CONNECTOR_TYPE_JSON_HTTP; + } else if (!strcmp(type, "opentsdb") || !strcmp(type, "opentsdb:telnet")) { + return EXPORTING_CONNECTOR_TYPE_OPENTSDB; + } else if (!strcmp(type, "opentsdb:http") || !strcmp(type, "opentsdb:https")) { + return EXPORTING_CONNECTOR_TYPE_OPENTSDB_HTTP; + } else if ( + !strcmp(type, "prometheus_remote_write") || + !strcmp(type, "prometheus_remote_write:http") || + !strcmp(type, "prometheus_remote_write:https")) { + return EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE; + } else if (!strcmp(type, "kinesis") || !strcmp(type, "kinesis:plaintext")) { + return EXPORTING_CONNECTOR_TYPE_KINESIS; + } else if (!strcmp(type, "pubsub") || !strcmp(type, "pubsub:plaintext")) { + return EXPORTING_CONNECTOR_TYPE_PUBSUB; + } else if (!strcmp(type, "mongodb") || !strcmp(type, "mongodb:plaintext")) + return EXPORTING_CONNECTOR_TYPE_MONGODB; + + return EXPORTING_CONNECTOR_TYPE_UNKNOWN; +} + +EXPORTING_OPTIONS exporting_parse_data_source(const char *data_source, EXPORTING_OPTIONS exporting_options) +{ + if (!strcmp(data_source, "raw") || !strcmp(data_source, "as collected") || !strcmp(data_source, "as-collected") || + !strcmp(data_source, "as_collected") || !strcmp(data_source, "ascollected")) { + exporting_options |= EXPORTING_SOURCE_DATA_AS_COLLECTED; + exporting_options &= ~(EXPORTING_OPTIONS_SOURCE_BITS ^ EXPORTING_SOURCE_DATA_AS_COLLECTED); + } else if (!strcmp(data_source, "average")) { + exporting_options |= EXPORTING_SOURCE_DATA_AVERAGE; + exporting_options &= ~(EXPORTING_OPTIONS_SOURCE_BITS ^ EXPORTING_SOURCE_DATA_AVERAGE); + } else if (!strcmp(data_source, "sum") || !strcmp(data_source, "volume")) { + exporting_options |= EXPORTING_SOURCE_DATA_SUM; + exporting_options &= ~(EXPORTING_OPTIONS_SOURCE_BITS ^ EXPORTING_SOURCE_DATA_SUM); + } else { + error("EXPORTING: invalid data data_source method '%s'.", data_source); + } + + return exporting_options; +} + +/** + * Read configuration + * + * Based on read configuration an engine data structure is filled with exporting connector instances. + * + * @return Returns a filled engine data structure or NULL if there are no connector instances configured. + */ +struct engine *read_exporting_config() +{ + int instances_to_activate = 0; + int exporting_config_exists = 0; + + static struct engine *engine = NULL; + struct connector_instance_list { + struct connector_instance local_ci; + EXPORTING_CONNECTOR_TYPE backend_type; + + struct connector_instance_list *next; + }; + struct connector_instance local_ci; + struct connector_instance_list *tmp_ci_list = NULL, *tmp_ci_list1 = NULL, *tmp_ci_list_prev = NULL; + + if (unlikely(engine)) + return engine; + + char *filename = strdupz_path_subpath(netdata_configured_user_config_dir, EXPORTING_CONF); + + exporting_config_exists = appconfig_load(&exporting_config, filename, 0, NULL); + if (!exporting_config_exists) { + info("CONFIG: cannot load user exporting config '%s'. Will try the stock version.", filename); + freez(filename); + + filename = strdupz_path_subpath(netdata_configured_stock_config_dir, EXPORTING_CONF); + exporting_config_exists = appconfig_load(&exporting_config, filename, 0, NULL); + if (!exporting_config_exists) + info("CONFIG: cannot load stock exporting config '%s'. Running with internal defaults.", filename); + } + + freez(filename); + +#define prometheus_config_get(name, value) \ + appconfig_get( \ + &exporting_config, CONFIG_SECTION_PROMETHEUS, name, \ + appconfig_get(&exporting_config, CONFIG_SECTION_EXPORTING, name, value)) +#define prometheus_config_get_number(name, value) \ + appconfig_get_number( \ + &exporting_config, CONFIG_SECTION_PROMETHEUS, name, \ + appconfig_get_number(&exporting_config, CONFIG_SECTION_EXPORTING, name, value)) +#define prometheus_config_get_boolean(name, value) \ + appconfig_get_boolean( \ + &exporting_config, CONFIG_SECTION_PROMETHEUS, name, \ + appconfig_get_boolean(&exporting_config, CONFIG_SECTION_EXPORTING, name, value)) + + if (!prometheus_exporter_instance) { + prometheus_exporter_instance = callocz(1, sizeof(struct instance)); + + prometheus_exporter_instance->config.update_every = + prometheus_config_get_number(EXPORTING_UPDATE_EVERY_OPTION_NAME, EXPORTING_UPDATE_EVERY_DEFAULT); + + // wait for backend subsystem to be initialized + for (int retries = 0; !global_backend_source && retries < 1000; retries++) + sleep_usec(10000); + + if (!global_backend_source) + global_backend_source = "average"; + + prometheus_exporter_instance->config.options |= global_backend_options & EXPORTING_OPTIONS_SOURCE_BITS; + + char *data_source = prometheus_config_get("data source", global_backend_source); + prometheus_exporter_instance->config.options = + exporting_parse_data_source(data_source, prometheus_exporter_instance->config.options); + + if (prometheus_config_get_boolean( + "send names instead of ids", global_backend_options & EXPORTING_OPTION_SEND_NAMES)) + prometheus_exporter_instance->config.options |= EXPORTING_OPTION_SEND_NAMES; + else + prometheus_exporter_instance->config.options &= ~EXPORTING_OPTION_SEND_NAMES; + + if (prometheus_config_get_boolean("send configured labels", CONFIG_BOOLEAN_YES)) + prometheus_exporter_instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + else + prometheus_exporter_instance->config.options &= ~EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + + if (prometheus_config_get_boolean("send automatic labels", CONFIG_BOOLEAN_NO)) + prometheus_exporter_instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + else + prometheus_exporter_instance->config.options &= ~EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + prometheus_exporter_instance->config.charts_pattern = + simple_pattern_create(prometheus_config_get("send charts matching", "*"), NULL, SIMPLE_PATTERN_EXACT); + prometheus_exporter_instance->config.hosts_pattern = simple_pattern_create( + prometheus_config_get("send hosts matching", "localhost *"), NULL, SIMPLE_PATTERN_EXACT); + + prometheus_exporter_instance->config.prefix = prometheus_config_get("prefix", global_backend_prefix); + } + + // TODO: change BACKEND to EXPORTING + while (get_connector_instance(&local_ci)) { + info("Processing connector instance (%s)", local_ci.instance_name); + + if (exporter_get_boolean(local_ci.instance_name, "enabled", 0)) { + info( + "Instance (%s) on connector (%s) is enabled and scheduled for activation", + local_ci.instance_name, local_ci.connector_name); + + tmp_ci_list = (struct connector_instance_list *)callocz(1, sizeof(struct connector_instance_list)); + memcpy(&tmp_ci_list->local_ci, &local_ci, sizeof(local_ci)); + tmp_ci_list->backend_type = exporting_select_type(local_ci.connector_name); + tmp_ci_list->next = tmp_ci_list_prev; + tmp_ci_list_prev = tmp_ci_list; + instances_to_activate++; + } else + info("Instance (%s) on connector (%s) is not enabled", local_ci.instance_name, local_ci.connector_name); + } + + if (unlikely(!instances_to_activate)) { + info("No connector instances to activate"); + return NULL; + } + + engine = (struct engine *)callocz(1, sizeof(struct engine)); + // TODO: Check and fill engine fields if actually needed + + if (exporting_config_exists) { + engine->config.hostname = + strdupz(exporter_get(CONFIG_SECTION_EXPORTING, "hostname", netdata_configured_hostname)); + engine->config.update_every = exporter_get_number( + CONFIG_SECTION_EXPORTING, EXPORTING_UPDATE_EVERY_OPTION_NAME, EXPORTING_UPDATE_EVERY_DEFAULT); + } + + while (tmp_ci_list) { + struct instance *tmp_instance; + char *instance_name; + char *default_destination = "localhost"; + + info("Instance %s on %s", tmp_ci_list->local_ci.instance_name, tmp_ci_list->local_ci.connector_name); + + if (tmp_ci_list->backend_type == EXPORTING_CONNECTOR_TYPE_UNKNOWN) { + error("Unknown exporting connector type"); + goto next_connector_instance; + } + +#ifndef ENABLE_PROMETHEUS_REMOTE_WRITE + if (tmp_ci_list->backend_type == EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE) { + error("Prometheus Remote Write support isn't compiled"); + goto next_connector_instance; + } +#endif + +#ifndef HAVE_KINESIS + if (tmp_ci_list->backend_type == EXPORTING_CONNECTOR_TYPE_KINESIS) { + error("AWS Kinesis support isn't compiled"); + goto next_connector_instance; + } +#endif + +#ifndef ENABLE_EXPORTING_PUBSUB + if (tmp_ci_list->backend_type == EXPORTING_CONNECTOR_TYPE_PUBSUB) { + error("Google Cloud Pub/Sub support isn't compiled"); + goto next_connector_instance; + } +#endif + +#ifndef HAVE_MONGOC + if (tmp_ci_list->backend_type == EXPORTING_CONNECTOR_TYPE_MONGODB) { + error("MongoDB support isn't compiled"); + goto next_connector_instance; + } +#endif + + tmp_instance = (struct instance *)callocz(1, sizeof(struct instance)); + tmp_instance->next = engine->instance_root; + engine->instance_root = tmp_instance; + + tmp_instance->engine = engine; + tmp_instance->config.type = tmp_ci_list->backend_type; + + instance_name = tmp_ci_list->local_ci.instance_name; + + tmp_instance->config.type_name = strdupz(tmp_ci_list->local_ci.connector_name); + tmp_instance->config.name = strdupz(tmp_ci_list->local_ci.instance_name); + + + tmp_instance->config.update_every = + exporter_get_number(instance_name, EXPORTING_UPDATE_EVERY_OPTION_NAME, EXPORTING_UPDATE_EVERY_DEFAULT); + + tmp_instance->config.buffer_on_failures = exporter_get_number(instance_name, "buffer on failures", 10); + + tmp_instance->config.timeoutms = exporter_get_number(instance_name, "timeout ms", 10000); + + tmp_instance->config.charts_pattern = + simple_pattern_create(exporter_get(instance_name, "send charts matching", "*"), NULL, SIMPLE_PATTERN_EXACT); + + tmp_instance->config.hosts_pattern = simple_pattern_create( + exporter_get(instance_name, "send hosts matching", "localhost *"), NULL, SIMPLE_PATTERN_EXACT); + + char *data_source = exporter_get(instance_name, "data source", "average"); + + tmp_instance->config.options = exporting_parse_data_source(data_source, tmp_instance->config.options); + if (EXPORTING_OPTIONS_DATA_SOURCE(tmp_instance->config.options) != EXPORTING_SOURCE_DATA_AS_COLLECTED && + tmp_instance->config.update_every % localhost->rrd_update_every) + info( + "The update interval %d for instance %s is not a multiple of the database update interval %d. " + "Metric values will deviate at different points in time.", + tmp_instance->config.update_every, tmp_instance->config.name, localhost->rrd_update_every); + + if (exporter_get_boolean(instance_name, "send configured labels", CONFIG_BOOLEAN_YES)) + tmp_instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + else + tmp_instance->config.options &= ~EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + + if (exporter_get_boolean(instance_name, "send automatic labels", CONFIG_BOOLEAN_NO)) + tmp_instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + else + tmp_instance->config.options &= ~EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + if (exporter_get_boolean(instance_name, "send names instead of ids", CONFIG_BOOLEAN_YES)) + tmp_instance->config.options |= EXPORTING_OPTION_SEND_NAMES; + else + tmp_instance->config.options &= ~EXPORTING_OPTION_SEND_NAMES; + + if (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE) { + struct prometheus_remote_write_specific_config *connector_specific_config = + callocz(1, sizeof(struct prometheus_remote_write_specific_config)); + + tmp_instance->config.connector_specific_config = connector_specific_config; + + connector_specific_config->remote_write_path = + strdupz(exporter_get(instance_name, "remote write URL path", "/receive")); + } + + if (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_KINESIS) { + struct aws_kinesis_specific_config *connector_specific_config = + callocz(1, sizeof(struct aws_kinesis_specific_config)); + + default_destination = "us-east-1"; + + tmp_instance->config.connector_specific_config = connector_specific_config; + + connector_specific_config->stream_name = strdupz(exporter_get(instance_name, "stream name", "")); + + connector_specific_config->auth_key_id = strdupz(exporter_get(instance_name, "aws_access_key_id", "")); + connector_specific_config->secure_key = strdupz(exporter_get(instance_name, "aws_secret_access_key", "")); + } + + if (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_PUBSUB) { + struct pubsub_specific_config *connector_specific_config = + callocz(1, sizeof(struct pubsub_specific_config)); + + default_destination = "pubsub.googleapis.com"; + + tmp_instance->config.connector_specific_config = connector_specific_config; + + connector_specific_config->credentials_file = strdupz(exporter_get(instance_name, "credentials file", "")); + connector_specific_config->project_id = strdupz(exporter_get(instance_name, "project id", "")); + connector_specific_config->topic_id = strdupz(exporter_get(instance_name, "topic id", "")); + } + + if (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_MONGODB) { + struct mongodb_specific_config *connector_specific_config = + callocz(1, sizeof(struct mongodb_specific_config)); + + tmp_instance->config.connector_specific_config = connector_specific_config; + + connector_specific_config->database = strdupz(exporter_get( + instance_name, "database", "")); + + connector_specific_config->collection = strdupz(exporter_get( + instance_name, "collection", "")); + } + + tmp_instance->config.destination = strdupz(exporter_get(instance_name, "destination", default_destination)); + + tmp_instance->config.prefix = strdupz(exporter_get(instance_name, "prefix", "netdata")); + + tmp_instance->config.hostname = strdupz(exporter_get(instance_name, "hostname", engine->config.hostname)); + +#ifdef ENABLE_HTTPS + +#define STR_GRAPHITE_HTTPS "graphite:https" +#define STR_JSON_HTTPS "json:https" +#define STR_OPENTSDB_HTTPS "opentsdb:https" +#define STR_PROMETHEUS_REMOTE_WRITE_HTTPS "prometheus_remote_write:https" + + if ((tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP && + !strncmp(tmp_ci_list->local_ci.connector_name, STR_GRAPHITE_HTTPS, strlen(STR_GRAPHITE_HTTPS))) || + (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_JSON_HTTP && + !strncmp(tmp_ci_list->local_ci.connector_name, STR_JSON_HTTPS, strlen(STR_JSON_HTTPS))) || + (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_OPENTSDB_HTTP && + !strncmp(tmp_ci_list->local_ci.connector_name, STR_OPENTSDB_HTTPS, strlen(STR_OPENTSDB_HTTPS))) || + (tmp_instance->config.type == EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE && + !strncmp( + tmp_ci_list->local_ci.connector_name, STR_PROMETHEUS_REMOTE_WRITE_HTTPS, + strlen(STR_PROMETHEUS_REMOTE_WRITE_HTTPS)))) { + tmp_instance->config.options |= EXPORTING_OPTION_USE_TLS; + } +#endif + +#ifdef NETDATA_INTERNAL_CHECKS + info( + " Dest=[%s], upd=[%d], buffer=[%d] timeout=[%ld] options=[%u]", + tmp_instance->config.destination, + tmp_instance->config.update_every, + tmp_instance->config.buffer_on_failures, + tmp_instance->config.timeoutms, + tmp_instance->config.options); +#endif + + if (unlikely(!exporting_config_exists) && !engine->config.hostname) { + engine->config.hostname = strdupz(config_get(instance_name, "hostname", netdata_configured_hostname)); + engine->config.update_every = + config_get_number(instance_name, EXPORTING_UPDATE_EVERY_OPTION_NAME, EXPORTING_UPDATE_EVERY_DEFAULT); + } + + next_connector_instance: + tmp_ci_list1 = tmp_ci_list->next; + freez(tmp_ci_list); + tmp_ci_list = tmp_ci_list1; + } + + return engine; +} diff --git a/exporting/send_data.c b/exporting/send_data.c new file mode 100644 index 000000000..1e932e98f --- /dev/null +++ b/exporting/send_data.c @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +/** + * Check if TLS is enabled in the configuration + * + * @param type buffer with response data. + * @param options an instance data structure. + * @return Returns 1 if TLS should be enabled, 0 otherwise. + */ +static int exporting_tls_is_enabled(EXPORTING_CONNECTOR_TYPE type, EXPORTING_OPTIONS options) +{ + return (type == EXPORTING_CONNECTOR_TYPE_GRAPHITE_HTTP || + type == EXPORTING_CONNECTOR_TYPE_JSON_HTTP || + type == EXPORTING_CONNECTOR_TYPE_OPENTSDB_HTTP || + type == EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE) && + options & EXPORTING_OPTION_USE_TLS; +} + +/** + * Discard response + * + * Discards a response received by an exporting connector instance after logging a sample of it to error.log + * + * @param buffer buffer with response data. + * @param instance an instance data structure. + * @return Always returns 0. + */ +int exporting_discard_response(BUFFER *buffer, struct instance *instance) { +#if NETDATA_INTERNAL_CHECKS + char sample[1024]; + const char *s = buffer_tostring(buffer); + char *d = sample, *e = &sample[sizeof(sample) - 1]; + + for(; *s && d < e ;s++) { + char c = *s; + if(unlikely(!isprint(c))) c = ' '; + *d++ = c; + } + *d = '\0'; + + debug( + D_BACKEND, + "EXPORTING: received %zu bytes from %s connector instance. Ignoring them. Sample: '%s'", + buffer_strlen(buffer), + instance->config.name, + sample); +#else + UNUSED(instance); +#endif /* NETDATA_INTERNAL_CHECKS */ + + buffer_flush(buffer); + return 0; +} + +/** + * Receive response + * + * @param sock communication socket. + * @param instance an instance data structure. + */ +void simple_connector_receive_response(int *sock, struct instance *instance) +{ + static BUFFER *response = NULL; + if (!response) + response = buffer_create(4096); + + struct stats *stats = &instance->stats; +#ifdef ENABLE_HTTPS + uint32_t options = (uint32_t)instance->config.options; + struct simple_connector_data *connector_specific_data = instance->connector_specific_data; + + if (options & EXPORTING_OPTION_USE_TLS) + ERR_clear_error(); +#endif + + errno = 0; + + // loop through to collect all data + while (*sock != -1 && errno != EWOULDBLOCK) { + ssize_t r; +#ifdef ENABLE_HTTPS + if (exporting_tls_is_enabled(instance->config.type, options) && + connector_specific_data->conn && + connector_specific_data->flags == NETDATA_SSL_HANDSHAKE_COMPLETE) { + r = (ssize_t)SSL_read(connector_specific_data->conn, + &response->buffer[response->len], + (int) (response->size - response->len)); + + if (likely(r > 0)) { + // we received some data + response->len += r; + stats->received_bytes += r; + stats->receptions++; + continue; + } else { + int sslerrno = SSL_get_error(connector_specific_data->conn, (int) r); + u_long sslerr = ERR_get_error(); + char buf[256]; + switch (sslerrno) { + case SSL_ERROR_WANT_READ: + case SSL_ERROR_WANT_WRITE: + goto endloop; + default: + ERR_error_string_n(sslerr, buf, sizeof(buf)); + error("SSL error (%s)", + ERR_error_string((long)SSL_get_error(connector_specific_data->conn, (int)r), NULL)); + goto endloop; + } + } + } else { + r = recv(*sock, &response->buffer[response->len], response->size - response->len, MSG_DONTWAIT); + } +#else + r = recv(*sock, &response->buffer[response->len], response->size - response->len, MSG_DONTWAIT); +#endif + if (likely(r > 0)) { + // we received some data + response->len += r; + stats->received_bytes += r; + stats->receptions++; + } else if (r == 0) { + error("EXPORTING: '%s' closed the socket", instance->config.destination); + close(*sock); + *sock = -1; + } else { + // failed to receive data + if (errno != EAGAIN && errno != EWOULDBLOCK) { + error("EXPORTING: cannot receive data from '%s'.", instance->config.destination); + } + } + +#ifdef UNIT_TESTING + break; +#endif + } +#ifdef ENABLE_HTTPS +endloop: +#endif + + // if we received data, process them + if (buffer_strlen(response)) + instance->check_response(response, instance); +} + +/** + * Send buffer to a server + * + * @param sock communication socket. + * @param failures the number of communication failures. + * @param instance an instance data structure. + */ +void simple_connector_send_buffer( + int *sock, int *failures, struct instance *instance, BUFFER *header, BUFFER *buffer, size_t buffered_metrics) +{ + int flags = 0; +#ifdef MSG_NOSIGNAL + flags += MSG_NOSIGNAL; +#endif + +#ifdef ENABLE_HTTPS + uint32_t options = (uint32_t)instance->config.options; + struct simple_connector_data *connector_specific_data = instance->connector_specific_data; + + if (options & EXPORTING_OPTION_USE_TLS) + ERR_clear_error(); +#endif + + struct stats *stats = &instance->stats; + ssize_t header_sent_bytes = 0; + ssize_t buffer_sent_bytes = 0; + size_t header_len = buffer_strlen(header); + size_t buffer_len = buffer_strlen(buffer); + +#ifdef ENABLE_HTTPS + if (exporting_tls_is_enabled(instance->config.type, options) && + connector_specific_data->conn && + connector_specific_data->flags == NETDATA_SSL_HANDSHAKE_COMPLETE) { + if (header_len) + header_sent_bytes = (ssize_t)SSL_write(connector_specific_data->conn, buffer_tostring(header), header_len); + if ((size_t)header_sent_bytes == header_len) + buffer_sent_bytes = (ssize_t)SSL_write(connector_specific_data->conn, buffer_tostring(buffer), buffer_len); + } else { + if (header_len) + header_sent_bytes = send(*sock, buffer_tostring(header), header_len, flags); + if ((size_t)header_sent_bytes == header_len) + buffer_sent_bytes = send(*sock, buffer_tostring(buffer), buffer_len, flags); + } +#else + if (header_len) + header_sent_bytes = send(*sock, buffer_tostring(header), header_len, flags); + if ((size_t)header_sent_bytes == header_len) + buffer_sent_bytes = send(*sock, buffer_tostring(buffer), buffer_len, flags); +#endif + + if ((size_t)buffer_sent_bytes == buffer_len) { + // we sent the data successfully + stats->transmission_successes++; + stats->sent_metrics += buffered_metrics; + stats->sent_bytes += buffer_sent_bytes; + + // reset the failures count + *failures = 0; + + // empty the buffer + buffer_flush(buffer); + } else { + // oops! we couldn't send (all or some of the) data + error( + "EXPORTING: failed to write data to '%s'. Willing to write %zu bytes, wrote %zd bytes. Will re-connect.", + instance->config.destination, + buffer_len, + buffer_sent_bytes); + stats->transmission_failures++; + + if(buffer_sent_bytes != -1) + stats->sent_bytes += buffer_sent_bytes; + + // increment the counter we check for data loss + (*failures)++; + + // close the socket - we will re-open it next time + close(*sock); + *sock = -1; + } +} + +/** + * Simple connector worker + * + * Runs in a separate thread for every instance. + * + * @param instance_p an instance data structure. + */ +void simple_connector_worker(void *instance_p) +{ + struct instance *instance = (struct instance*)instance_p; + struct simple_connector_data *connector_specific_data = instance->connector_specific_data; + +#ifdef ENABLE_HTTPS + uint32_t options = (uint32_t)instance->config.options; + + if (options & EXPORTING_OPTION_USE_TLS) + ERR_clear_error(); +#endif + struct simple_connector_config *connector_specific_config = instance->config.connector_specific_config; + + int sock = -1; + struct timeval timeout = { .tv_sec = (instance->config.timeoutms * 1000) / 1000000, + .tv_usec = (instance->config.timeoutms * 1000) % 1000000 }; + int failures = 0; + + while (!instance->engine->exit) { + struct stats *stats = &instance->stats; + int send_stats = 0; + + if (instance->data_is_ready) + send_stats = 1; + + uv_mutex_lock(&instance->mutex); + if (!connector_specific_data->first_buffer->used || failures) { + while (!instance->data_is_ready) + uv_cond_wait(&instance->cond_var, &instance->mutex); + instance->data_is_ready = 0; + send_stats = 1; + } + + if (unlikely(instance->engine->exit)) { + uv_mutex_unlock(&instance->mutex); + break; + } + + // ------------------------------------------------------------------------ + // detach buffer + + size_t buffered_metrics; + + if (!connector_specific_data->previous_buffer || + (connector_specific_data->previous_buffer == connector_specific_data->first_buffer && + connector_specific_data->first_buffer->used == 1)) { + BUFFER *header, *buffer; + + header = connector_specific_data->first_buffer->header; + buffer = connector_specific_data->first_buffer->buffer; + connector_specific_data->buffered_metrics = connector_specific_data->first_buffer->buffered_metrics; + connector_specific_data->buffered_bytes = connector_specific_data->first_buffer->buffered_bytes; + + buffered_metrics = connector_specific_data->buffered_metrics; + + buffer_flush(connector_specific_data->header); + connector_specific_data->first_buffer->header = connector_specific_data->header; + connector_specific_data->header = header; + + buffer_flush(connector_specific_data->buffer); + connector_specific_data->first_buffer->buffer = connector_specific_data->buffer; + connector_specific_data->buffer = buffer; + } else { + buffered_metrics = connector_specific_data->buffered_metrics; + } + + uv_mutex_unlock(&instance->mutex); + + // ------------------------------------------------------------------------ + // if we are connected, receive a response, without blocking + + if (likely(sock != -1)) + simple_connector_receive_response(&sock, instance); + + // ------------------------------------------------------------------------ + // if we are not connected, connect to a data collecting server + + if (unlikely(sock == -1)) { + size_t reconnects = 0; + + sock = connect_to_one_of( + instance->config.destination, connector_specific_config->default_port, &timeout, &reconnects, NULL, 0); +#ifdef ENABLE_HTTPS + if (exporting_tls_is_enabled(instance->config.type, options) && sock != -1) { + if (netdata_exporting_ctx) { + if (sock_delnonblock(sock) < 0) + error("Exporting cannot remove the non-blocking flag from socket %d", sock); + + if (connector_specific_data->conn == NULL) { + connector_specific_data->conn = SSL_new(netdata_exporting_ctx); + if (connector_specific_data->conn == NULL) { + error("Failed to allocate SSL structure to socket %d.", sock); + connector_specific_data->flags = NETDATA_SSL_NO_HANDSHAKE; + } + } else { + SSL_clear(connector_specific_data->conn); + } + + if (connector_specific_data->conn) { + if (SSL_set_fd(connector_specific_data->conn, sock) != 1) { + error("Failed to set the socket to the SSL on socket fd %d.", sock); + connector_specific_data->flags = NETDATA_SSL_NO_HANDSHAKE; + } else { + connector_specific_data->flags = NETDATA_SSL_HANDSHAKE_COMPLETE; + SSL_set_connect_state(connector_specific_data->conn); + int err = SSL_connect(connector_specific_data->conn); + if (err != 1) { + err = SSL_get_error(connector_specific_data->conn, err); + error( + "SSL cannot connect with the server: %s ", + ERR_error_string((long)SSL_get_error(connector_specific_data->conn, err), NULL)); + connector_specific_data->flags = NETDATA_SSL_NO_HANDSHAKE; + } else { + info("Exporting established a SSL connection."); + + struct timeval tv; + tv.tv_sec = timeout.tv_sec / 4; + tv.tv_usec = 0; + + if (!tv.tv_sec) + tv.tv_sec = 2; + + if (setsockopt(sock, SOL_SOCKET, SO_RCVTIMEO, (const char *)&tv, sizeof(tv))) + error("Cannot set timeout to socket %d, this can block communication", sock); + } + } + } + } + } +#endif + + stats->reconnects += reconnects; + } + + if (unlikely(instance->engine->exit)) + break; + + // ------------------------------------------------------------------------ + // if we are connected, send our buffer to the data collecting server + + failures = 0; + + if (likely(sock != -1)) { + simple_connector_send_buffer( + &sock, + &failures, + instance, + connector_specific_data->header, + connector_specific_data->buffer, + buffered_metrics); + } else { + error("EXPORTING: failed to update '%s'", instance->config.destination); + stats->transmission_failures++; + + // increment the counter we check for data loss + failures++; + } + + if (!failures) { + connector_specific_data->first_buffer->buffered_metrics = + connector_specific_data->first_buffer->buffered_bytes = connector_specific_data->first_buffer->used = 0; + connector_specific_data->first_buffer = connector_specific_data->first_buffer->next; + } + + if (unlikely(instance->engine->exit)) + break; + + if (send_stats) { + uv_mutex_lock(&instance->mutex); + + stats->buffered_metrics = connector_specific_data->total_buffered_metrics; + + send_internal_metrics(instance); + + stats->buffered_metrics = 0; + + // reset the internal monitoring chart counters + connector_specific_data->total_buffered_metrics = + stats->buffered_bytes = + stats->receptions = + stats->received_bytes = + stats->sent_metrics = + stats->sent_bytes = + stats->transmission_successes = + stats->transmission_failures = + stats->reconnects = + stats->data_lost_events = + stats->lost_metrics = + stats->lost_bytes = 0; + + uv_mutex_unlock(&instance->mutex); + } + +#ifdef UNIT_TESTING + return; +#endif + } + +#if ENABLE_PROMETHEUS_REMOTE_WRITE + if (instance->config.type == EXPORTING_CONNECTOR_TYPE_PROMETHEUS_REMOTE_WRITE) + clean_prometheus_remote_write(instance); +#endif + + simple_connector_cleanup(instance); +} diff --git a/exporting/send_internal_metrics.c b/exporting/send_internal_metrics.c new file mode 100644 index 000000000..defb8d047 --- /dev/null +++ b/exporting/send_internal_metrics.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "exporting_engine.h" + +/** + * Create a chart for the main exporting thread CPU usage + * + * @param st_rusage the thead CPU usage chart + * @param rd_user a dimension for user CPU usage + * @param rd_system a dimension for system CPU usage + */ +void create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_system) +{ + if (*st_rusage && *rd_user && *rd_system) + return; + + *st_rusage = rrdset_create_localhost( + "netdata", "exporting_main_thread_cpu", NULL, "exporting", "exporting_cpu_usage", "Netdata Main Exporting Thread CPU Usage", + "milliseconds/s", "exporting", NULL, 130600, localhost->rrd_update_every, RRDSET_TYPE_STACKED); + + *rd_user = rrddim_add(*st_rusage, "user", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL); + *rd_system = rrddim_add(*st_rusage, "system", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL); +} + +/** + * Send the main exporting thread CPU usage + * + * @param st_rusage a thead CPU usage chart + * @param rd_user a dimension for user CPU usage + * @param rd_system a dimension for system CPU usage + */ +void send_main_rusage(RRDSET *st_rusage, RRDDIM *rd_user, RRDDIM *rd_system) +{ + struct rusage thread; + getrusage(RUSAGE_THREAD, &thread); + + if (likely(st_rusage->counter_done)) + rrdset_next(st_rusage); + + rrddim_set_by_pointer(st_rusage, rd_user, thread.ru_utime.tv_sec * 1000000ULL + thread.ru_utime.tv_usec); + rrddim_set_by_pointer(st_rusage, rd_system, thread.ru_stime.tv_sec * 1000000ULL + thread.ru_stime.tv_usec); + + rrdset_done(st_rusage); +} + +/** + * Send internal metrics for an instance + * + * Send performance metrics for the operation of exporting engine itself to the Netdata database. + * + * @param instance an instance data structure. + */ +void send_internal_metrics(struct instance *instance) +{ + struct stats *stats = &instance->stats; + + // ------------------------------------------------------------------------ + // create charts for monitoring the exporting operations + + if (!stats->initialized) { + char id[RRD_ID_LENGTH_MAX + 1]; + BUFFER *family = buffer_create(0); + + buffer_sprintf(family, "exporting_%s", instance->config.name); + + snprintf(id, RRD_ID_LENGTH_MAX, "exporting_%s_metrics", instance->config.name); + netdata_fix_chart_id(id); + + stats->st_metrics = rrdset_create_localhost( + "netdata", id, NULL, buffer_tostring(family), "exporting_buffer", "Netdata Buffered Metrics", "metrics", "exporting", NULL, + 130610, instance->config.update_every, RRDSET_TYPE_LINE); + + stats->rd_buffered_metrics = rrddim_add(stats->st_metrics, "buffered", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_lost_metrics = rrddim_add(stats->st_metrics, "lost", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_sent_metrics = rrddim_add(stats->st_metrics, "sent", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + + // ------------------------------------------------------------------------ + + snprintf(id, RRD_ID_LENGTH_MAX, "exporting_%s_bytes", instance->config.name); + netdata_fix_chart_id(id); + + stats->st_bytes = rrdset_create_localhost( + "netdata", id, NULL, buffer_tostring(family), "exporting_data_size", "Netdata Exporting Data Size", "KiB", "exporting", NULL, + 130620, instance->config.update_every, RRDSET_TYPE_AREA); + + stats->rd_buffered_bytes = rrddim_add(stats->st_bytes, "buffered", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE); + stats->rd_lost_bytes = rrddim_add(stats->st_bytes, "lost", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE); + stats->rd_sent_bytes = rrddim_add(stats->st_bytes, "sent", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE); + stats->rd_received_bytes = rrddim_add(stats->st_bytes, "received", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE); + + // ------------------------------------------------------------------------ + + snprintf(id, RRD_ID_LENGTH_MAX, "exporting_%s_ops", instance->config.name); + netdata_fix_chart_id(id); + + stats->st_ops = rrdset_create_localhost( + "netdata", id, NULL, buffer_tostring(family), "exporting_operations", "Netdata Exporting Operations", "operations", "exporting", + NULL, 130630, instance->config.update_every, RRDSET_TYPE_LINE); + + stats->rd_transmission_successes = rrddim_add(stats->st_ops, "write", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_data_lost_events = rrddim_add(stats->st_ops, "discard", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_reconnects = rrddim_add(stats->st_ops, "reconnect", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_transmission_failures = rrddim_add(stats->st_ops, "failure", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + stats->rd_receptions = rrddim_add(stats->st_ops, "read", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + + // ------------------------------------------------------------------------ + + snprintf(id, RRD_ID_LENGTH_MAX, "exporting_%s_thread_cpu", instance->config.name); + netdata_fix_chart_id(id); + + stats->st_rusage = rrdset_create_localhost( + "netdata", id, NULL, buffer_tostring(family), "exporting_instance", "Netdata Exporting Instance Thread CPU Usage", + "milliseconds/s", "exporting", NULL, 130640, instance->config.update_every, RRDSET_TYPE_STACKED); + + stats->rd_user = rrddim_add(stats->st_rusage, "user", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL); + stats->rd_system = rrddim_add(stats->st_rusage, "system", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL); + + buffer_free(family); + + stats->initialized = 1; + } + + // ------------------------------------------------------------------------ + // update the monitoring charts + + if (likely(stats->st_metrics->counter_done)) + rrdset_next(stats->st_metrics); + + rrddim_set_by_pointer(stats->st_metrics, stats->rd_buffered_metrics, stats->buffered_metrics); + rrddim_set_by_pointer(stats->st_metrics, stats->rd_lost_metrics, stats->lost_metrics); + rrddim_set_by_pointer(stats->st_metrics, stats->rd_sent_metrics, stats->sent_metrics); + + rrdset_done(stats->st_metrics); + + // ------------------------------------------------------------------------ + + if (likely(stats->st_bytes->counter_done)) + rrdset_next(stats->st_bytes); + + rrddim_set_by_pointer(stats->st_bytes, stats->rd_buffered_bytes, stats->buffered_bytes); + rrddim_set_by_pointer(stats->st_bytes, stats->rd_lost_bytes, stats->lost_bytes); + rrddim_set_by_pointer(stats->st_bytes, stats->rd_sent_bytes, stats->sent_bytes); + rrddim_set_by_pointer(stats->st_bytes, stats->rd_received_bytes, stats->received_bytes); + + rrdset_done(stats->st_bytes); + + // ------------------------------------------------------------------------ + + if (likely(stats->st_ops->counter_done)) + rrdset_next(stats->st_ops); + + rrddim_set_by_pointer(stats->st_ops, stats->rd_transmission_successes, stats->transmission_successes); + rrddim_set_by_pointer(stats->st_ops, stats->rd_data_lost_events, stats->data_lost_events); + rrddim_set_by_pointer(stats->st_ops, stats->rd_reconnects, stats->reconnects); + rrddim_set_by_pointer(stats->st_ops, stats->rd_transmission_failures, stats->transmission_failures); + rrddim_set_by_pointer(stats->st_ops, stats->rd_receptions, stats->receptions); + + rrdset_done(stats->st_ops); + + // ------------------------------------------------------------------------ + + struct rusage thread; + getrusage(RUSAGE_THREAD, &thread); + + if (likely(stats->st_rusage->counter_done)) + rrdset_next(stats->st_rusage); + + rrddim_set_by_pointer(stats->st_rusage, stats->rd_user, thread.ru_utime.tv_sec * 1000000ULL + thread.ru_utime.tv_usec); + rrddim_set_by_pointer(stats->st_rusage, stats->rd_system, thread.ru_stime.tv_sec * 1000000ULL + thread.ru_stime.tv_usec); + + rrdset_done(stats->st_rusage); +} diff --git a/exporting/tests/Makefile.am b/exporting/tests/Makefile.am new file mode 100644 index 000000000..babdcf0df --- /dev/null +++ b/exporting/tests/Makefile.am @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in diff --git a/exporting/tests/exporting_doubles.c b/exporting/tests/exporting_doubles.c new file mode 100644 index 000000000..3c73e0327 --- /dev/null +++ b/exporting/tests/exporting_doubles.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "test_exporting_engine.h" + +struct engine *__real_read_exporting_config(); +struct engine *__wrap_read_exporting_config() +{ + function_called(); + return mock_ptr_type(struct engine *); +} + +struct engine *__mock_read_exporting_config() +{ + struct engine *engine = calloc(1, sizeof(struct engine)); + engine->config.hostname = strdupz("test_engine_host"); + engine->config.update_every = 3; + + + engine->instance_root = calloc(1, sizeof(struct instance)); + struct instance *instance = engine->instance_root; + instance->engine = engine; + instance->config.type = EXPORTING_CONNECTOR_TYPE_GRAPHITE; + instance->config.name = strdupz("instance_name"); + instance->config.destination = strdupz("localhost"); + instance->config.prefix = strdupz("netdata"); + instance->config.hostname = strdupz("test-host"); + instance->config.update_every = 1; + instance->config.buffer_on_failures = 10; + instance->config.timeoutms = 10000; + instance->config.charts_pattern = simple_pattern_create("*", NULL, SIMPLE_PATTERN_EXACT); + instance->config.hosts_pattern = simple_pattern_create("*", NULL, SIMPLE_PATTERN_EXACT); + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + + return engine; +} + +int __real_init_connectors(struct engine *engine); +int __wrap_init_connectors(struct engine *engine) +{ + function_called(); + check_expected_ptr(engine); + return mock_type(int); +} + +int __real_mark_scheduled_instances(struct engine *engine); +int __wrap_mark_scheduled_instances(struct engine *engine) +{ + function_called(); + check_expected_ptr(engine); + return mock_type(int); +} + +calculated_number __real_exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp); +calculated_number __wrap_exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp) +{ + (void)instance; + (void)rd; + + *last_timestamp = 15052; + + function_called(); + return mock_type(calculated_number); +} + +int __real_prepare_buffers(struct engine *engine); +int __wrap_prepare_buffers(struct engine *engine) +{ + function_called(); + check_expected_ptr(engine); + return mock_type(int); +} + +void __wrap_create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_system) +{ + function_called(); + check_expected_ptr(st_rusage); + check_expected_ptr(rd_user); + check_expected_ptr(rd_system); +} + +void __wrap_send_main_rusage(RRDSET *st_rusage, RRDDIM *rd_user, RRDDIM *rd_system) +{ + function_called(); + check_expected_ptr(st_rusage); + check_expected_ptr(rd_user); + check_expected_ptr(rd_system); +} + +int __wrap_send_internal_metrics(struct instance *instance) +{ + function_called(); + check_expected_ptr(instance); + return mock_type(int); +} + +int __wrap_rrdhost_is_exportable(struct instance *instance, RRDHOST *host) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(host); + return mock_type(int); +} + +int __wrap_rrdset_is_exportable(struct instance *instance, RRDSET *st) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(st); + return mock_type(int); +} + +int __mock_start_batch_formatting(struct instance *instance) +{ + function_called(); + check_expected_ptr(instance); + return mock_type(int); +} + +int __mock_start_host_formatting(struct instance *instance, RRDHOST *host) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(host); + return mock_type(int); +} + +int __mock_start_chart_formatting(struct instance *instance, RRDSET *st) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(st); + return mock_type(int); +} + +int __mock_metric_formatting(struct instance *instance, RRDDIM *rd) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(rd); + return mock_type(int); +} + +int __mock_end_chart_formatting(struct instance *instance, RRDSET *st) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(st); + return mock_type(int); +} + +int __mock_end_host_formatting(struct instance *instance, RRDHOST *host) +{ + function_called(); + check_expected_ptr(instance); + check_expected_ptr(host); + return mock_type(int); +} + +int __mock_end_batch_formatting(struct instance *instance) +{ + function_called(); + check_expected_ptr(instance); + return mock_type(int); +} + +int __wrap_simple_connector_end_batch(struct instance *instance) +{ + function_called(); + check_expected_ptr(instance); + return mock_type(int); +} + +#if ENABLE_PROMETHEUS_REMOTE_WRITE +void *__wrap_init_write_request() +{ + function_called(); + return mock_ptr_type(void *); +} + +void __wrap_add_host_info( + void *write_request_p, + const char *name, const char *instance, const char *application, const char *version, const int64_t timestamp) +{ + function_called(); + check_expected_ptr(write_request_p); + check_expected_ptr(name); + check_expected_ptr(instance); + check_expected_ptr(application); + check_expected_ptr(version); + check_expected(timestamp); +} + +void __wrap_add_label(void *write_request_p, char *key, char *value) +{ + function_called(); + check_expected_ptr(write_request_p); + check_expected_ptr(key); + check_expected_ptr(value); +} + +void __wrap_add_metric( + void *write_request_p, + const char *name, const char *chart, const char *family, const char *dimension, + const char *instance, const double value, const int64_t timestamp) +{ + function_called(); + check_expected_ptr(write_request_p); + check_expected_ptr(name); + check_expected_ptr(chart); + check_expected_ptr(family); + check_expected_ptr(dimension); + check_expected_ptr(instance); + check_expected(value); + check_expected(timestamp); +} +#endif // ENABLE_PROMETHEUS_REMOTE_WRITE + +#if HAVE_KINESIS +void __wrap_aws_sdk_init() +{ + function_called(); +} + +void __wrap_kinesis_init( + void *kinesis_specific_data_p, const char *region, const char *access_key_id, const char *secret_key, + const long timeout) +{ + function_called(); + check_expected_ptr(kinesis_specific_data_p); + check_expected_ptr(region); + check_expected_ptr(access_key_id); + check_expected_ptr(secret_key); + check_expected(timeout); +} + +void __wrap_kinesis_put_record( + void *kinesis_specific_data_p, const char *stream_name, const char *partition_key, const char *data, + size_t data_len) +{ + function_called(); + check_expected_ptr(kinesis_specific_data_p); + check_expected_ptr(stream_name); + check_expected_ptr(partition_key); + check_expected_ptr(data); + check_expected_ptr(data); + check_expected(data_len); +} + +int __wrap_kinesis_get_result(void *request_outcomes_p, char *error_message, size_t *sent_bytes, size_t *lost_bytes) +{ + function_called(); + check_expected_ptr(request_outcomes_p); + check_expected_ptr(error_message); + check_expected_ptr(sent_bytes); + check_expected_ptr(lost_bytes); + return mock_type(int); +} +#endif // HAVE_KINESIS + +#if ENABLE_EXPORTING_PUBSUB +int __wrap_pubsub_init( + void *pubsub_specific_data_p, char *error_message, const char *destination, const char *credentials_file, + const char *project_id, const char *topic_id) +{ + function_called(); + check_expected_ptr(pubsub_specific_data_p); + check_expected_ptr(error_message); + check_expected_ptr(destination); + check_expected_ptr(credentials_file); + check_expected_ptr(project_id); + check_expected_ptr(topic_id); + return mock_type(int); +} + +int __wrap_pubsub_add_message(void *pubsub_specific_data_p, char *data) +{ + function_called(); + check_expected_ptr(pubsub_specific_data_p); + check_expected_ptr(data); + return mock_type(int); +} + +int __wrap_pubsub_publish( + void *pubsub_specific_data_p, char *error_message, size_t buffered_metrics, size_t buffered_bytes) +{ + function_called(); + check_expected_ptr(pubsub_specific_data_p); + check_expected_ptr(error_message); + check_expected(buffered_metrics); + check_expected(buffered_bytes); + return mock_type(int); +} + +int __wrap_pubsub_get_result( + void *pubsub_specific_data_p, char *error_message, + size_t *sent_metrics, size_t *sent_bytes, size_t *lost_metrics, size_t *lost_bytes) +{ + function_called(); + check_expected_ptr(pubsub_specific_data_p); + check_expected_ptr(error_message); + check_expected_ptr(sent_metrics); + check_expected_ptr(sent_bytes); + check_expected_ptr(lost_metrics); + check_expected_ptr(lost_bytes); + return mock_type(int); +} +#endif // ENABLE_EXPORTING_PUBSUB + +#if HAVE_MONGOC +void __wrap_mongoc_init() +{ + function_called(); +} + +mongoc_uri_t * __wrap_mongoc_uri_new_with_error (const char *uri_string, bson_error_t *error) +{ + function_called(); + check_expected_ptr(uri_string); + check_expected_ptr(error); + return mock_ptr_type(mongoc_uri_t *); +} + +int32_t __wrap_mongoc_uri_get_option_as_int32(const mongoc_uri_t *uri, const char *option, int32_t fallback) +{ + function_called(); + check_expected_ptr(uri); + check_expected_ptr(option); + check_expected(fallback); + return mock_type(int32_t); +} + +bool __wrap_mongoc_uri_set_option_as_int32 (const mongoc_uri_t *uri, const char *option, int32_t value) +{ + function_called(); + check_expected_ptr(uri); + check_expected_ptr(option); + check_expected(value); + return mock_type(bool); +} + +mongoc_client_t * __wrap_mongoc_client_new_from_uri (const mongoc_uri_t *uri) +{ + function_called(); + check_expected_ptr(uri); + return mock_ptr_type(mongoc_client_t *); +} + +bool __wrap_mongoc_client_set_appname (mongoc_client_t *client, const char *appname) +{ + function_called(); + check_expected_ptr(client); + check_expected_ptr(appname); + return mock_type(bool); +} + +mongoc_collection_t * +__wrap_mongoc_client_get_collection(mongoc_client_t *client, const char *db, const char *collection) +{ + function_called(); + check_expected_ptr(client); + check_expected_ptr(db); + check_expected_ptr(collection); + return mock_ptr_type(mongoc_collection_t *); +} + +void __wrap_mongoc_uri_destroy (mongoc_uri_t *uri) +{ + function_called(); + check_expected_ptr(uri); +} + +bool __wrap_mongoc_collection_insert_many( + mongoc_collection_t *collection, + const bson_t **documents, + size_t n_documents, + const bson_t *opts, + bson_t *reply, + bson_error_t *error) +{ + function_called(); + check_expected_ptr(collection); + check_expected_ptr(documents); + check_expected(n_documents); + check_expected_ptr(opts); + check_expected_ptr(reply); + check_expected_ptr(error); + return mock_type(bool); +} +#endif // HAVE_MONGOC diff --git a/exporting/tests/exporting_fixtures.c b/exporting/tests/exporting_fixtures.c new file mode 100644 index 000000000..00bb0ed0f --- /dev/null +++ b/exporting/tests/exporting_fixtures.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "test_exporting_engine.h" + +int setup_configured_engine(void **state) +{ + struct engine *engine = __mock_read_exporting_config(); + engine->instance_root->data_is_ready = 1; + + *state = engine; + + return 0; +} + +int teardown_configured_engine(void **state) +{ + struct engine *engine = *state; + + struct instance *instance = engine->instance_root; + free((void *)instance->config.destination); + free((void *)instance->config.name); + free((void *)instance->config.prefix); + free((void *)instance->config.hostname); + simple_pattern_free(instance->config.charts_pattern); + simple_pattern_free(instance->config.hosts_pattern); + free(instance); + + free((void *)engine->config.hostname); + free(engine); + + return 0; +} + +int setup_rrdhost() +{ + localhost = calloc(1, sizeof(RRDHOST)); + + localhost->rrd_update_every = 1; + + localhost->tags = strdupz("TAG1=VALUE1 TAG2=VALUE2"); + + struct label *label = calloc(1, sizeof(struct label)); + label->key = strdupz("key1"); + label->value = strdupz("value1"); + label->label_source = LABEL_SOURCE_NETDATA_CONF; + localhost->labels.head = label; + + label = calloc(1, sizeof(struct label)); + label->key = strdupz("key2"); + label->value = strdupz("value2"); + label->label_source = LABEL_SOURCE_AUTO; + localhost->labels.head->next = label; + + localhost->rrdset_root = calloc(1, sizeof(RRDSET)); + RRDSET *st = localhost->rrdset_root; + st->rrdhost = localhost; + strcpy(st->id, "chart_id"); + st->name = strdupz("chart_name"); + st->flags |= RRDSET_FLAG_ENABLED; + st->rrd_memory_mode |= RRD_MEMORY_MODE_SAVE; + st->update_every = 1; + + localhost->rrdset_root->dimensions = calloc(1, sizeof(RRDDIM)); + RRDDIM *rd = localhost->rrdset_root->dimensions; + rd->rrdset = st; + rd->id = strdupz("dimension_id"); + rd->name = strdupz("dimension_name"); + rd->last_collected_value = 123000321; + rd->last_collected_time.tv_sec = 15051; + rd->collections_counter++; + rd->next = NULL; + + rd->state = calloc(1, sizeof(*rd->state)); + rd->state->query_ops.oldest_time = __mock_rrddim_query_oldest_time; + rd->state->query_ops.latest_time = __mock_rrddim_query_latest_time; + rd->state->query_ops.init = __mock_rrddim_query_init; + rd->state->query_ops.is_finished = __mock_rrddim_query_is_finished; + rd->state->query_ops.next_metric = __mock_rrddim_query_next_metric; + rd->state->query_ops.finalize = __mock_rrddim_query_finalize; + + return 0; +} + +int teardown_rrdhost() +{ + RRDDIM *rd = localhost->rrdset_root->dimensions; + free((void *)rd->name); + free((void *)rd->id); + free(rd->state); + free(rd); + + RRDSET *st = localhost->rrdset_root; + free((void *)st->name); + free(st); + + free(localhost->labels.head->next->key); + free(localhost->labels.head->next->value); + free(localhost->labels.head->next); + free(localhost->labels.head->key); + free(localhost->labels.head->value); + free(localhost->labels.head); + + free((void *)localhost->tags); + free(localhost); + + return 0; +} + +int setup_initialized_engine(void **state) +{ + setup_configured_engine(state); + + struct engine *engine = *state; + init_connectors_in_tests(engine); + + setup_rrdhost(); + + return 0; +} + +int teardown_initialized_engine(void **state) +{ + struct engine *engine = *state; + + teardown_rrdhost(); + buffer_free(engine->instance_root->labels); + buffer_free(engine->instance_root->buffer); + teardown_configured_engine(state); + + return 0; +} + +int setup_prometheus(void **state) +{ + (void)state; + + prometheus_exporter_instance = calloc(1, sizeof(struct instance)); + + setup_rrdhost(); + + prometheus_exporter_instance->config.update_every = 10; + + prometheus_exporter_instance->config.options |= + EXPORTING_OPTION_SEND_NAMES | EXPORTING_OPTION_SEND_CONFIGURED_LABELS | EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + prometheus_exporter_instance->config.charts_pattern = simple_pattern_create("*", NULL, SIMPLE_PATTERN_EXACT); + prometheus_exporter_instance->config.hosts_pattern = simple_pattern_create("*", NULL, SIMPLE_PATTERN_EXACT); + + return 0; +} + +int teardown_prometheus(void **state) +{ + (void)state; + + teardown_rrdhost(); + + simple_pattern_free(prometheus_exporter_instance->config.charts_pattern); + simple_pattern_free(prometheus_exporter_instance->config.hosts_pattern); + free(prometheus_exporter_instance); + + return 0; +} diff --git a/exporting/tests/netdata_doubles.c b/exporting/tests/netdata_doubles.c new file mode 100644 index 000000000..f4da7769f --- /dev/null +++ b/exporting/tests/netdata_doubles.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "test_exporting_engine.h" + +// Use memomy allocation functions guarded by CMocka in strdupz +const char *__wrap_strdupz(const char *s) +{ + char *duplicate = malloc(sizeof(char) * (strlen(s) + 1)); + strcpy(duplicate, s); + + return duplicate; +} + +time_t __wrap_now_realtime_sec(void) +{ + function_called(); + return mock_type(time_t); +} + +void __wrap_uv_thread_set_name_np(uv_thread_t ut, const char* name) +{ + (void)ut; + (void)name; + + function_called(); +} + +void __wrap_info_int(const char *file, const char *function, const unsigned long line, const char *fmt, ...) +{ + (void)file; + (void)function; + (void)line; + + function_called(); + + va_list args; + + va_start(args, fmt); + vsnprintf(log_line, MAX_LOG_LINE, fmt, args); + va_end(args); +} + +int __wrap_connect_to_one_of( + const char *destination, + int default_port, + struct timeval *timeout, + size_t *reconnects_counter, + char *connected_to, + size_t connected_to_size) +{ + (void)timeout; + + function_called(); + + check_expected(destination); + check_expected_ptr(default_port); + // TODO: check_expected_ptr(timeout); + check_expected(reconnects_counter); + check_expected(connected_to); + check_expected(connected_to_size); + + return mock_type(int); +} + +void __rrdhost_check_rdlock(RRDHOST *host, const char *file, const char *function, const unsigned long line) +{ + (void)host; + (void)file; + (void)function; + (void)line; +} + +void __rrdset_check_rdlock(RRDSET *st, const char *file, const char *function, const unsigned long line) +{ + (void)st; + (void)file; + (void)function; + (void)line; +} + +void __rrd_check_rdlock(const char *file, const char *function, const unsigned long line) +{ + (void)file; + (void)function; + (void)line; +} + +RRDSET *rrdset_create_custom( + RRDHOST *host, + const char *type, + const char *id, + const char *name, + const char *family, + const char *context, + const char *title, + const char *units, + const char *plugin, + const char *module, + long priority, + int update_every, + RRDSET_TYPE chart_type, + RRD_MEMORY_MODE memory_mode, + long history_entries) +{ + check_expected_ptr(host); + check_expected_ptr(type); + check_expected_ptr(id); + check_expected_ptr(name); + check_expected_ptr(family); + check_expected_ptr(context); + UNUSED(title); + check_expected_ptr(units); + check_expected_ptr(plugin); + check_expected_ptr(module); + check_expected(priority); + check_expected(update_every); + check_expected(chart_type); + UNUSED(memory_mode); + UNUSED(history_entries); + + function_called(); + + return mock_ptr_type(RRDSET *); +} + +void rrdset_next_usec(RRDSET *st, usec_t microseconds) +{ + check_expected_ptr(st); + UNUSED(microseconds); + + function_called(); +} + +void rrdset_done(RRDSET *st) +{ + check_expected_ptr(st); + + function_called(); +} + +RRDDIM *rrddim_add_custom( + RRDSET *st, + const char *id, + const char *name, + collected_number multiplier, + collected_number divisor, + RRD_ALGORITHM algorithm, + RRD_MEMORY_MODE memory_mode) +{ + check_expected_ptr(st); + UNUSED(id); + check_expected_ptr(name); + check_expected(multiplier); + check_expected(divisor); + check_expected(algorithm); + UNUSED(memory_mode); + + function_called(); + + return NULL; +} + +collected_number rrddim_set_by_pointer(RRDSET *st, RRDDIM *rd, collected_number value) +{ + check_expected_ptr(st); + UNUSED(rd); + UNUSED(value); + + function_called(); + + return 0; +} + +const char *rrd_memory_mode_name(RRD_MEMORY_MODE id) +{ + (void)id; + return RRD_MEMORY_MODE_NONE_NAME; +} + +calculated_number rrdvar2number(RRDVAR *rv) +{ + (void)rv; + return 0; +} + +int foreach_host_variable_callback(RRDHOST *host, int (*callback)(RRDVAR *rv, void *data), void *data) +{ + (void)host; + (void)callback; + (void)data; + return 0; +} + +void rrdset_update_heterogeneous_flag(RRDSET *st) +{ + (void)st; +} + +time_t __mock_rrddim_query_oldest_time(RRDDIM *rd) +{ + (void)rd; + + function_called(); + return mock_type(time_t); +} + +time_t __mock_rrddim_query_latest_time(RRDDIM *rd) +{ + (void)rd; + + function_called(); + return mock_type(time_t); +} + +void __mock_rrddim_query_init(RRDDIM *rd, struct rrddim_query_handle *handle, time_t start_time, time_t end_time) +{ + (void)rd; + (void)handle; + + function_called(); + check_expected(start_time); + check_expected(end_time); +} + +int __mock_rrddim_query_is_finished(struct rrddim_query_handle *handle) +{ + (void)handle; + + function_called(); + return mock_type(int); +} + +storage_number __mock_rrddim_query_next_metric(struct rrddim_query_handle *handle, time_t *current_time) +{ + (void)handle; + (void)current_time; + + function_called(); + return mock_type(storage_number); +} + +void __mock_rrddim_query_finalize(struct rrddim_query_handle *handle) +{ + (void)handle; + + function_called(); +} diff --git a/exporting/tests/system_doubles.c b/exporting/tests/system_doubles.c new file mode 100644 index 000000000..ca85800c0 --- /dev/null +++ b/exporting/tests/system_doubles.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "test_exporting_engine.h" + +void __wrap_uv_thread_create(uv_thread_t thread, void (*worker)(void *arg), void *arg) +{ + function_called(); + + check_expected_ptr(thread); + check_expected_ptr(worker); + check_expected_ptr(arg); +} + +void __wrap_uv_mutex_lock(uv_mutex_t *mutex) +{ + (void)mutex; +} + +void __wrap_uv_mutex_unlock(uv_mutex_t *mutex) +{ + (void)mutex; +} + +void __wrap_uv_cond_signal(uv_cond_t *cond_var) +{ + (void)cond_var; +} + +void __wrap_uv_cond_wait(uv_cond_t *cond_var, uv_mutex_t *mutex) +{ + (void)cond_var; + (void)mutex; +} + +ssize_t __wrap_recv(int sockfd, void *buf, size_t len, int flags) +{ + function_called(); + + check_expected(sockfd); + check_expected_ptr(buf); + check_expected(len); + check_expected(flags); + + char *mock_string = "Test recv"; + strcpy(buf, mock_string); + + return strlen(mock_string); +} + +ssize_t __wrap_send(int sockfd, const void *buf, size_t len, int flags) +{ + function_called(); + + check_expected(sockfd); + check_expected_ptr(buf); + check_expected_ptr(buf); + check_expected(len); + check_expected(flags); + + return strlen(buf); +} diff --git a/exporting/tests/test_exporting_engine.c b/exporting/tests/test_exporting_engine.c new file mode 100644 index 000000000..774d1a265 --- /dev/null +++ b/exporting/tests/test_exporting_engine.c @@ -0,0 +1,1939 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "test_exporting_engine.h" +#include "libnetdata/required_dummies.h" + +RRDHOST *localhost; +netdata_rwlock_t rrd_rwlock; + +// global variables needed by read_exporting_config() +struct config netdata_config; +char *netdata_configured_user_config_dir = "."; +char *netdata_configured_stock_config_dir = "."; +char *netdata_configured_hostname = "test_global_host"; + +char log_line[MAX_LOG_LINE + 1]; + +BACKEND_OPTIONS global_backend_options = 0; +const char *global_backend_source = "average"; +const char *global_backend_prefix = "netdata"; + +void init_connectors_in_tests(struct engine *engine) +{ + expect_function_call(__wrap_now_realtime_sec); + will_return(__wrap_now_realtime_sec, 2); + + expect_function_call(__wrap_uv_thread_create); + + expect_value(__wrap_uv_thread_create, thread, &engine->instance_root->thread); + expect_value(__wrap_uv_thread_create, worker, simple_connector_worker); + expect_value(__wrap_uv_thread_create, arg, engine->instance_root); + + expect_function_call(__wrap_uv_thread_set_name_np); + + assert_int_equal(__real_init_connectors(engine), 0); + + assert_int_equal(engine->now, 2); + assert_int_equal(engine->instance_root->after, 2); +} + +static void test_exporting_engine(void **state) +{ + struct engine *engine = *state; + + expect_function_call(__wrap_read_exporting_config); + will_return(__wrap_read_exporting_config, engine); + + expect_function_call(__wrap_init_connectors); + expect_memory(__wrap_init_connectors, engine, engine, sizeof(struct engine)); + will_return(__wrap_init_connectors, 0); + + expect_function_call(__wrap_create_main_rusage_chart); + expect_not_value(__wrap_create_main_rusage_chart, st_rusage, NULL); + expect_not_value(__wrap_create_main_rusage_chart, rd_user, NULL); + expect_not_value(__wrap_create_main_rusage_chart, rd_system, NULL); + + expect_function_call(__wrap_now_realtime_sec); + will_return(__wrap_now_realtime_sec, 2); + + expect_function_call(__wrap_mark_scheduled_instances); + expect_memory(__wrap_mark_scheduled_instances, engine, engine, sizeof(struct engine)); + will_return(__wrap_mark_scheduled_instances, 1); + + expect_function_call(__wrap_prepare_buffers); + expect_memory(__wrap_prepare_buffers, engine, engine, sizeof(struct engine)); + will_return(__wrap_prepare_buffers, 0); + + expect_function_call(__wrap_send_main_rusage); + expect_value(__wrap_send_main_rusage, st_rusage, NULL); + expect_value(__wrap_send_main_rusage, rd_user, NULL); + expect_value(__wrap_send_main_rusage, rd_system, NULL); + + void *ptr = malloc(sizeof(struct netdata_static_thread)); + assert_ptr_equal(exporting_main(ptr), NULL); + assert_int_equal(engine->now, 2); + free(ptr); +} + +static void test_read_exporting_config(void **state) +{ + struct engine *engine = __mock_read_exporting_config(); // TODO: use real read_exporting_config() function + *state = engine; + + assert_ptr_not_equal(engine, NULL); + assert_string_equal(engine->config.hostname, "test_engine_host"); + assert_int_equal(engine->config.update_every, 3); + assert_int_equal(engine->instance_num, 0); + + + struct instance *instance = engine->instance_root; + assert_ptr_not_equal(instance, NULL); + assert_ptr_equal(instance->next, NULL); + assert_ptr_equal(instance->engine, engine); + assert_int_equal(instance->config.type, EXPORTING_CONNECTOR_TYPE_GRAPHITE); + assert_string_equal(instance->config.destination, "localhost"); + assert_string_equal(instance->config.prefix, "netdata"); + assert_int_equal(instance->config.update_every, 1); + assert_int_equal(instance->config.buffer_on_failures, 10); + assert_int_equal(instance->config.timeoutms, 10000); + assert_true(simple_pattern_matches(instance->config.charts_pattern, "any_chart")); + assert_true(simple_pattern_matches(instance->config.hosts_pattern, "anyt_host")); + assert_int_equal(instance->config.options, EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES); + + teardown_configured_engine(state); +} + +static void test_init_connectors(void **state) +{ + struct engine *engine = *state; + + init_connectors_in_tests(engine); + + assert_int_equal(engine->instance_num, 1); + + struct instance *instance = engine->instance_root; + + assert_ptr_equal(instance->next, NULL); + assert_int_equal(instance->index, 0); + + struct simple_connector_config *connector_specific_config = instance->config.connector_specific_config; + assert_int_equal(connector_specific_config->default_port, 2003); + + assert_ptr_equal(instance->worker, simple_connector_worker); + assert_ptr_equal(instance->start_batch_formatting, NULL); + assert_ptr_equal(instance->start_host_formatting, format_host_labels_graphite_plaintext); + assert_ptr_equal(instance->start_chart_formatting, NULL); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_graphite_plaintext); + assert_ptr_equal(instance->end_chart_formatting, NULL); + assert_ptr_equal(instance->end_host_formatting, flush_host_labels); + + BUFFER *buffer = instance->buffer; + assert_ptr_not_equal(buffer, NULL); + buffer_sprintf(buffer, "%s", "graphite test"); + assert_string_equal(buffer_tostring(buffer), "graphite test"); +} + +static void test_init_graphite_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_graphite_instance(instance), 0); + assert_int_equal( + ((struct simple_connector_config *)(instance->config.connector_specific_config))->default_port, 2003); + freez(instance->config.connector_specific_config); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_graphite_plaintext); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_graphite_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_graphite_plaintext); +} + +static void test_init_json_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_json_instance(instance), 0); + assert_int_equal( + ((struct simple_connector_config *)(instance->config.connector_specific_config))->default_port, 5448); + freez(instance->config.connector_specific_config); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_json_plaintext); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_json_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_json_plaintext); +} + +static void test_init_opentsdb_telnet_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_opentsdb_telnet_instance(instance), 0); + assert_int_equal( + ((struct simple_connector_config *)(instance->config.connector_specific_config))->default_port, 4242); + freez(instance->config.connector_specific_config); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_opentsdb_telnet); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_opentsdb_telnet_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_opentsdb_telnet); +} + +static void test_init_opentsdb_http_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_opentsdb_http_instance(instance), 0); + assert_int_equal( + ((struct simple_connector_config *)(instance->config.connector_specific_config))->default_port, 4242); + freez(instance->config.connector_specific_config); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_opentsdb_http); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + assert_int_equal(init_opentsdb_http_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_opentsdb_http); +} + +static void test_mark_scheduled_instances(void **state) +{ + struct engine *engine = *state; + + assert_int_equal(__real_mark_scheduled_instances(engine), 1); + + struct instance *instance = engine->instance_root; + assert_int_equal(instance->scheduled, 1); + assert_int_equal(instance->before, 2); +} + +static void test_rrdhost_is_exportable(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + expect_function_call(__wrap_info_int); + + assert_ptr_equal(localhost->exporting_flags, NULL); + + assert_int_equal(__real_rrdhost_is_exportable(instance, localhost), 1); + + assert_string_equal(log_line, "enabled exporting of host 'localhost' for instance 'instance_name'"); + + assert_ptr_not_equal(localhost->exporting_flags, NULL); + assert_int_equal(localhost->exporting_flags[0], RRDHOST_FLAG_BACKEND_SEND); +} + +static void test_false_rrdhost_is_exportable(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + simple_pattern_free(instance->config.hosts_pattern); + instance->config.hosts_pattern = simple_pattern_create("!*", NULL, SIMPLE_PATTERN_EXACT); + + expect_function_call(__wrap_info_int); + + assert_ptr_equal(localhost->exporting_flags, NULL); + + assert_int_equal(__real_rrdhost_is_exportable(instance, localhost), 0); + + assert_string_equal(log_line, "disabled exporting of host 'localhost' for instance 'instance_name'"); + + assert_ptr_not_equal(localhost->exporting_flags, NULL); + assert_int_equal(localhost->exporting_flags[0], RRDHOST_FLAG_BACKEND_DONT_SEND); +} + +static void test_rrdset_is_exportable(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + RRDSET *st = localhost->rrdset_root; + + assert_ptr_equal(st->exporting_flags, NULL); + + assert_int_equal(__real_rrdset_is_exportable(instance, st), 1); + + assert_ptr_not_equal(st->exporting_flags, NULL); + assert_int_equal(st->exporting_flags[0], RRDSET_FLAG_BACKEND_SEND); +} + +static void test_false_rrdset_is_exportable(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + RRDSET *st = localhost->rrdset_root; + + simple_pattern_free(instance->config.charts_pattern); + instance->config.charts_pattern = simple_pattern_create("!*", NULL, SIMPLE_PATTERN_EXACT); + + assert_ptr_equal(st->exporting_flags, NULL); + + assert_int_equal(__real_rrdset_is_exportable(instance, st), 0); + + assert_ptr_not_equal(st->exporting_flags, NULL); + assert_int_equal(st->exporting_flags[0], RRDSET_FLAG_BACKEND_IGNORE); +} + +static void test_exporting_calculate_value_from_stored_data(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + RRDDIM *rd = localhost->rrdset_root->dimensions; + time_t timestamp; + + instance->after = 3; + instance->before = 10; + + expect_function_call(__mock_rrddim_query_oldest_time); + will_return(__mock_rrddim_query_oldest_time, 1); + + expect_function_call(__mock_rrddim_query_latest_time); + will_return(__mock_rrddim_query_latest_time, 2); + + expect_function_call(__mock_rrddim_query_init); + expect_value(__mock_rrddim_query_init, start_time, 1); + expect_value(__mock_rrddim_query_init, end_time, 2); + + expect_function_call(__mock_rrddim_query_is_finished); + will_return(__mock_rrddim_query_is_finished, 0); + expect_function_call(__mock_rrddim_query_next_metric); + will_return(__mock_rrddim_query_next_metric, pack_storage_number(27, SN_EXISTS)); + + expect_function_call(__mock_rrddim_query_is_finished); + will_return(__mock_rrddim_query_is_finished, 0); + expect_function_call(__mock_rrddim_query_next_metric); + will_return(__mock_rrddim_query_next_metric, pack_storage_number(45, SN_EXISTS)); + + expect_function_call(__mock_rrddim_query_is_finished); + will_return(__mock_rrddim_query_is_finished, 1); + + expect_function_call(__mock_rrddim_query_finalize); + + assert_int_equal(__real_exporting_calculate_value_from_stored_data(instance, rd, ×tamp), 36); +} + +static void test_prepare_buffers(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->start_batch_formatting = __mock_start_batch_formatting; + instance->start_host_formatting = __mock_start_host_formatting; + instance->start_chart_formatting = __mock_start_chart_formatting; + instance->metric_formatting = __mock_metric_formatting; + instance->end_chart_formatting = __mock_end_chart_formatting; + instance->end_host_formatting = __mock_end_host_formatting; + instance->end_batch_formatting = __mock_end_batch_formatting; + __real_mark_scheduled_instances(engine); + + expect_function_call(__mock_start_batch_formatting); + expect_value(__mock_start_batch_formatting, instance, instance); + will_return(__mock_start_batch_formatting, 0); + + expect_function_call(__wrap_rrdhost_is_exportable); + expect_value(__wrap_rrdhost_is_exportable, instance, instance); + expect_value(__wrap_rrdhost_is_exportable, host, localhost); + will_return(__wrap_rrdhost_is_exportable, 1); + + expect_function_call(__mock_start_host_formatting); + expect_value(__mock_start_host_formatting, instance, instance); + expect_value(__mock_start_host_formatting, host, localhost); + will_return(__mock_start_host_formatting, 0); + + RRDSET *st = localhost->rrdset_root; + expect_function_call(__wrap_rrdset_is_exportable); + expect_value(__wrap_rrdset_is_exportable, instance, instance); + expect_value(__wrap_rrdset_is_exportable, st, st); + will_return(__wrap_rrdset_is_exportable, 1); + + expect_function_call(__mock_start_chart_formatting); + expect_value(__mock_start_chart_formatting, instance, instance); + expect_value(__mock_start_chart_formatting, st, st); + will_return(__mock_start_chart_formatting, 0); + + RRDDIM *rd = localhost->rrdset_root->dimensions; + expect_function_call(__mock_metric_formatting); + expect_value(__mock_metric_formatting, instance, instance); + expect_value(__mock_metric_formatting, rd, rd); + will_return(__mock_metric_formatting, 0); + + expect_function_call(__mock_end_chart_formatting); + expect_value(__mock_end_chart_formatting, instance, instance); + expect_value(__mock_end_chart_formatting, st, st); + will_return(__mock_end_chart_formatting, 0); + + expect_function_call(__mock_end_host_formatting); + expect_value(__mock_end_host_formatting, instance, instance); + expect_value(__mock_end_host_formatting, host, localhost); + will_return(__mock_end_host_formatting, 0); + + expect_function_call(__mock_end_batch_formatting); + expect_value(__mock_end_batch_formatting, instance, instance); + will_return(__mock_end_batch_formatting, 0); + + assert_int_equal(__real_prepare_buffers(engine), 0); + + assert_int_equal(instance->stats.buffered_metrics, 1); + + // check with NULL functions + instance->start_batch_formatting = NULL; + instance->start_host_formatting = NULL; + instance->start_chart_formatting = NULL; + instance->metric_formatting = NULL; + instance->end_chart_formatting = NULL; + instance->end_host_formatting = NULL; + instance->end_batch_formatting = NULL; + assert_int_equal(__real_prepare_buffers(engine), 0); + + assert_int_equal(instance->scheduled, 0); + assert_int_equal(instance->after, 2); +} + +static void test_exporting_name_copy(void **state) +{ + (void)state; + + char *source_name = "test.name-with/special#characters_"; + char destination_name[RRD_ID_LENGTH_MAX + 1]; + + assert_int_equal(exporting_name_copy(destination_name, source_name, RRD_ID_LENGTH_MAX), 34); + assert_string_equal(destination_name, "test.name_with_special_characters_"); +} + +static void test_format_dimension_collected_graphite_plaintext(void **state) +{ + struct engine *engine = *state; + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_collected_graphite_plaintext(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "netdata.test-host.chart_name.dimension_name;TAG1=VALUE1 TAG2=VALUE2 123000321 15051\n"); +} + +static void test_format_dimension_stored_graphite_plaintext(void **state) +{ + struct engine *engine = *state; + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_stored_graphite_plaintext(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "netdata.test-host.chart_name.dimension_name;TAG1=VALUE1 TAG2=VALUE2 690565856.0000000 15052\n"); +} + +static void test_format_dimension_collected_json_plaintext(void **state) +{ + struct engine *engine = *state; + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_collected_json_plaintext(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "{\"prefix\":\"netdata\",\"hostname\":\"test-host\",\"host_tags\":\"TAG1=VALUE1 TAG2=VALUE2\"," + "\"chart_id\":\"chart_id\",\"chart_name\":\"chart_name\",\"chart_family\":\"(null)\"," + "\"chart_context\":\"(null)\",\"chart_type\":\"(null)\",\"units\":\"(null)\",\"id\":\"dimension_id\"," + "\"name\":\"dimension_name\",\"value\":123000321,\"timestamp\":15051}\n"); +} + +static void test_format_dimension_stored_json_plaintext(void **state) +{ + struct engine *engine = *state; + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_stored_json_plaintext(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "{\"prefix\":\"netdata\",\"hostname\":\"test-host\",\"host_tags\":\"TAG1=VALUE1 TAG2=VALUE2\"," + "\"chart_id\":\"chart_id\",\"chart_name\":\"chart_name\",\"chart_family\":\"(null)\"," \ + "\"chart_context\": \"(null)\",\"chart_type\":\"(null)\",\"units\": \"(null)\",\"id\":\"dimension_id\"," + "\"name\":\"dimension_name\",\"value\":690565856.0000000,\"timestamp\": 15052}\n"); +} + +static void test_format_dimension_collected_opentsdb_telnet(void **state) +{ + struct engine *engine = *state; + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_collected_opentsdb_telnet(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "put netdata.chart_name.dimension_name 15051 123000321 host=test-host TAG1=VALUE1 TAG2=VALUE2\n"); +} + +static void test_format_dimension_stored_opentsdb_telnet(void **state) +{ + struct engine *engine = *state; + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_stored_opentsdb_telnet(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "put netdata.chart_name.dimension_name 15052 690565856.0000000 host=test-host TAG1=VALUE1 TAG2=VALUE2\n"); +} + +static void test_format_dimension_collected_opentsdb_http(void **state) +{ + struct engine *engine = *state; + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_collected_opentsdb_http(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "{\"metric\":\"netdata.chart_name.dimension_name\"," + "\"timestamp\":15051," + "\"value\":123000321," + "\"tags\":{\"host\":\"test-host TAG1=VALUE1 TAG2=VALUE2\"}}"); +} + +static void test_format_dimension_stored_opentsdb_http(void **state) +{ + struct engine *engine = *state; + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + RRDDIM *rd = localhost->rrdset_root->dimensions; + assert_int_equal(format_dimension_stored_opentsdb_http(engine->instance_root, rd), 0); + assert_string_equal( + buffer_tostring(engine->instance_root->buffer), + "{\"metric\":\"netdata.chart_name.dimension_name\"," + "\"timestamp\":15052," + "\"value\":690565856.0000000," + "\"tags\":{\"host\":\"test-host TAG1=VALUE1 TAG2=VALUE2\"}}"); +} + +static void test_exporting_discard_response(void **state) +{ + struct engine *engine = *state; + + BUFFER *response = buffer_create(0); + buffer_sprintf(response, "Test response"); + + assert_int_equal(exporting_discard_response(response, engine->instance_root), 0); + assert_int_equal(buffer_strlen(response), 0); + + buffer_free(response); +} + +static void test_simple_connector_receive_response(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + + int sock = 1; + + expect_function_call(__wrap_recv); + expect_value(__wrap_recv, sockfd, 1); + expect_not_value(__wrap_recv, buf, 0); + expect_value(__wrap_recv, len, 4096); + expect_value(__wrap_recv, flags, MSG_DONTWAIT); + + simple_connector_receive_response(&sock, instance); + + assert_int_equal(stats->received_bytes, 9); + assert_int_equal(stats->receptions, 1); + assert_int_equal(sock, 1); +} + +static void test_simple_connector_send_buffer(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + + int sock = 1; + int failures = 3; + size_t buffered_metrics = 1; + BUFFER *header = buffer_create(0); + BUFFER *buffer = buffer_create(0); + buffer_strcat(header, "test header\n"); + buffer_strcat(buffer, "test buffer\n"); + + expect_function_call(__wrap_send); + expect_value(__wrap_send, sockfd, 1); + expect_value(__wrap_send, buf, buffer_tostring(header)); + expect_string(__wrap_send, buf, "test header\n"); + expect_value(__wrap_send, len, 12); + expect_value(__wrap_send, flags, MSG_NOSIGNAL); + + expect_function_call(__wrap_send); + expect_value(__wrap_send, sockfd, 1); + expect_value(__wrap_send, buf, buffer_tostring(buffer)); + expect_string(__wrap_send, buf, "test buffer\n"); + expect_value(__wrap_send, len, 12); + expect_value(__wrap_send, flags, MSG_NOSIGNAL); + + simple_connector_send_buffer(&sock, &failures, instance, header, buffer, buffered_metrics); + + assert_int_equal(failures, 0); + assert_int_equal(stats->transmission_successes, 1); + assert_int_equal(stats->sent_bytes, 12); + assert_int_equal(stats->sent_metrics, 1); + assert_int_equal(stats->transmission_failures, 0); + + assert_int_equal(buffer_strlen(buffer), 0); + + assert_int_equal(sock, 1); +} + +static void test_simple_connector_worker(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + + __real_mark_scheduled_instances(engine); + + struct simple_connector_data *simple_connector_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = simple_connector_data; + simple_connector_data->last_buffer = callocz(1, sizeof(struct simple_connector_buffer)); + simple_connector_data->first_buffer = simple_connector_data->last_buffer; + simple_connector_data->header = buffer_create(0); + simple_connector_data->buffer = buffer_create(0); + simple_connector_data->last_buffer->header = buffer_create(0); + simple_connector_data->last_buffer->buffer = buffer_create(0); + + buffer_sprintf(simple_connector_data->last_buffer->header, "test header"); + buffer_sprintf(simple_connector_data->last_buffer->buffer, "test buffer"); + + expect_function_call(__wrap_connect_to_one_of); + expect_string(__wrap_connect_to_one_of, destination, "localhost"); + expect_value(__wrap_connect_to_one_of, default_port, 2003); + expect_not_value(__wrap_connect_to_one_of, reconnects_counter, 0); + expect_value(__wrap_connect_to_one_of, connected_to, 0); + expect_value(__wrap_connect_to_one_of, connected_to_size, 0); + will_return(__wrap_connect_to_one_of, 2); + + expect_function_call(__wrap_send); + expect_value(__wrap_send, sockfd, 2); + expect_not_value(__wrap_send, buf, buffer_tostring(simple_connector_data->last_buffer->buffer)); + expect_string(__wrap_send, buf, "test header"); + expect_value(__wrap_send, len, 11); + expect_value(__wrap_send, flags, MSG_NOSIGNAL); + + expect_function_call(__wrap_send); + expect_value(__wrap_send, sockfd, 2); + expect_value(__wrap_send, buf, buffer_tostring(simple_connector_data->last_buffer->buffer)); + expect_string(__wrap_send, buf, "test buffer"); + expect_value(__wrap_send, len, 11); + expect_value(__wrap_send, flags, MSG_NOSIGNAL); + + expect_function_call(__wrap_send_internal_metrics); + expect_value(__wrap_send_internal_metrics, instance, instance); + will_return(__wrap_send_internal_metrics, 0); + + simple_connector_worker(instance); + + assert_int_equal(stats->buffered_metrics, 0); + assert_int_equal(stats->buffered_bytes, 0); + assert_int_equal(stats->received_bytes, 0); + assert_int_equal(stats->sent_bytes, 0); + assert_int_equal(stats->sent_metrics, 0); + assert_int_equal(stats->lost_metrics, 0); + assert_int_equal(stats->receptions, 0); + assert_int_equal(stats->transmission_successes, 0); + assert_int_equal(stats->transmission_failures, 0); + assert_int_equal(stats->data_lost_events, 0); + assert_int_equal(stats->lost_bytes, 0); + assert_int_equal(stats->reconnects, 0); +} + +static void test_sanitize_json_string(void **state) +{ + (void)state; + + char *src = "check \t\\\" string"; + char dst[19 + 1]; + + sanitize_json_string(dst, src, 19); + + assert_string_equal(dst, "check _\\\\\\\" string"); +} + +static void test_sanitize_graphite_label_value(void **state) +{ + (void)state; + + char *src = "check ;~ string"; + char dst[15 + 1]; + + sanitize_graphite_label_value(dst, src, 15); + + assert_string_equal(dst, "check____string"); +} + +static void test_sanitize_opentsdb_label_value(void **state) +{ + (void)state; + + char *src = "check \t\\\" #&$? -_./ string"; + char dst[26 + 1]; + + sanitize_opentsdb_label_value(dst, src, 26); + + assert_string_equal(dst, "check__________-_./_string"); +} + +static void test_format_host_labels_json_plaintext(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + assert_int_equal(format_host_labels_json_plaintext(instance, localhost), 0); + assert_string_equal(buffer_tostring(instance->labels), "\"labels\":{\"key1\":\"value1\",\"key2\":\"value2\"},"); +} + +static void test_format_host_labels_graphite_plaintext(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + assert_int_equal(format_host_labels_graphite_plaintext(instance, localhost), 0); + assert_string_equal(buffer_tostring(instance->labels), ";key1=value1;key2=value2"); +} + +static void test_format_host_labels_opentsdb_telnet(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + assert_int_equal(format_host_labels_opentsdb_telnet(instance, localhost), 0); + assert_string_equal(buffer_tostring(instance->labels), " key1=value1 key2=value2"); +} + +static void test_format_host_labels_opentsdb_http(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + assert_int_equal(format_host_labels_opentsdb_http(instance, localhost), 0); + assert_string_equal(buffer_tostring(instance->labels), ",\"key1\":\"value1\",\"key2\":\"value2\""); +} + +static void test_flush_host_labels(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->labels = buffer_create(12); + buffer_strcat(instance->labels, "check string"); + assert_int_equal(buffer_strlen(instance->labels), 12); + + assert_int_equal(flush_host_labels(instance, localhost), 0); + assert_int_equal(buffer_strlen(instance->labels), 0); +} + +static void test_create_main_rusage_chart(void **state) +{ + UNUSED(state); + + RRDSET *st_rusage = calloc(1, sizeof(RRDSET)); + RRDDIM *rd_user = NULL; + RRDDIM *rd_system = NULL; + + expect_function_call(rrdset_create_custom); + expect_value(rrdset_create_custom, host, localhost); + expect_string(rrdset_create_custom, type, "netdata"); + expect_string(rrdset_create_custom, id, "exporting_main_thread_cpu"); + expect_value(rrdset_create_custom, name, NULL); + expect_string(rrdset_create_custom, family, "exporting"); + expect_string(rrdset_create_custom, context, "exporting_cpu_usage"); + expect_string(rrdset_create_custom, units, "milliseconds/s"); + expect_string(rrdset_create_custom, plugin, "exporting"); + expect_value(rrdset_create_custom, module, NULL); + expect_value(rrdset_create_custom, priority, 130600); + expect_value(rrdset_create_custom, update_every, localhost->rrd_update_every); + expect_value(rrdset_create_custom, chart_type, RRDSET_TYPE_STACKED); + will_return(rrdset_create_custom, st_rusage); + + expect_function_calls(rrddim_add_custom, 2); + expect_value_count(rrddim_add_custom, st, st_rusage, 2); + expect_value_count(rrddim_add_custom, name, NULL, 2); + expect_value_count(rrddim_add_custom, multiplier, 1, 2); + expect_value_count(rrddim_add_custom, divisor, 1000, 2); + expect_value_count(rrddim_add_custom, algorithm, RRD_ALGORITHM_INCREMENTAL, 2); + + __real_create_main_rusage_chart(&st_rusage, &rd_user, &rd_system); + + free(st_rusage); +} + +static void test_send_main_rusage(void **state) +{ + UNUSED(state); + + RRDSET *st_rusage = calloc(1, sizeof(RRDSET)); + st_rusage->counter_done = 1; + + expect_function_call(rrdset_next_usec); + expect_value(rrdset_next_usec, st, st_rusage); + + expect_function_calls(rrddim_set_by_pointer, 2); + expect_value_count(rrddim_set_by_pointer, st, st_rusage, 2); + + expect_function_call(rrdset_done); + expect_value(rrdset_done, st, st_rusage); + + __real_send_main_rusage(st_rusage, NULL, NULL); + + free(st_rusage); +} + +static void test_send_internal_metrics(void **state) +{ + UNUSED(state); + + struct instance *instance = calloc(1, sizeof(struct instance)); + instance->config.name = (const char *)strdupz("test_instance"); + instance->config.update_every = 2; + + struct stats *stats = &instance->stats; + + stats->st_metrics = calloc(1, sizeof(RRDSET)); + stats->st_metrics->counter_done = 1; + stats->st_bytes = calloc(1, sizeof(RRDSET)); + stats->st_bytes->counter_done = 1; + stats->st_ops = calloc(1, sizeof(RRDSET)); + stats->st_ops->counter_done = 1; + stats->st_rusage = calloc(1, sizeof(RRDSET)); + stats->st_rusage->counter_done = 1; + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_create_custom); + expect_value(rrdset_create_custom, host, localhost); + expect_string(rrdset_create_custom, type, "netdata"); + expect_string(rrdset_create_custom, id, "exporting_test_instance_metrics"); + expect_value(rrdset_create_custom, name, NULL); + expect_string(rrdset_create_custom, family, "exporting_test_instance"); + expect_string(rrdset_create_custom, context, "exporting_buffer"); + expect_string(rrdset_create_custom, units, "metrics"); + expect_string(rrdset_create_custom, plugin, "exporting"); + expect_value(rrdset_create_custom, module, NULL); + expect_value(rrdset_create_custom, priority, 130610); + expect_value(rrdset_create_custom, update_every, 2); + expect_value(rrdset_create_custom, chart_type, RRDSET_TYPE_LINE); + will_return(rrdset_create_custom, stats->st_metrics); + + expect_function_calls(rrddim_add_custom, 3); + expect_value_count(rrddim_add_custom, st, stats->st_metrics, 3); + expect_value_count(rrddim_add_custom, name, NULL, 3); + expect_value_count(rrddim_add_custom, multiplier, 1, 3); + expect_value_count(rrddim_add_custom, divisor, 1, 3); + expect_value_count(rrddim_add_custom, algorithm, RRD_ALGORITHM_ABSOLUTE, 3); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_create_custom); + expect_value(rrdset_create_custom, host, localhost); + expect_string(rrdset_create_custom, type, "netdata"); + expect_string(rrdset_create_custom, id, "exporting_test_instance_bytes"); + expect_value(rrdset_create_custom, name, NULL); + expect_string(rrdset_create_custom, family, "exporting_test_instance"); + expect_string(rrdset_create_custom, context, "exporting_data_size"); + expect_string(rrdset_create_custom, units, "KiB"); + expect_string(rrdset_create_custom, plugin, "exporting"); + expect_value(rrdset_create_custom, module, NULL); + expect_value(rrdset_create_custom, priority, 130620); + expect_value(rrdset_create_custom, update_every, 2); + expect_value(rrdset_create_custom, chart_type, RRDSET_TYPE_AREA); + will_return(rrdset_create_custom, stats->st_bytes); + + expect_function_calls(rrddim_add_custom, 4); + expect_value_count(rrddim_add_custom, st, stats->st_bytes, 4); + expect_value_count(rrddim_add_custom, name, NULL, 4); + expect_value_count(rrddim_add_custom, multiplier, 1, 4); + expect_value_count(rrddim_add_custom, divisor, 1024, 4); + expect_value_count(rrddim_add_custom, algorithm, RRD_ALGORITHM_ABSOLUTE, 4); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_create_custom); + expect_value(rrdset_create_custom, host, localhost); + expect_string(rrdset_create_custom, type, "netdata"); + expect_string(rrdset_create_custom, id, "exporting_test_instance_ops"); + expect_value(rrdset_create_custom, name, NULL); + expect_string(rrdset_create_custom, family, "exporting_test_instance"); + expect_string(rrdset_create_custom, context, "exporting_operations"); + expect_string(rrdset_create_custom, units, "operations"); + expect_string(rrdset_create_custom, plugin, "exporting"); + expect_value(rrdset_create_custom, module, NULL); + expect_value(rrdset_create_custom, priority, 130630); + expect_value(rrdset_create_custom, update_every, 2); + expect_value(rrdset_create_custom, chart_type, RRDSET_TYPE_LINE); + will_return(rrdset_create_custom, stats->st_ops); + + expect_function_calls(rrddim_add_custom, 5); + expect_value_count(rrddim_add_custom, st, stats->st_ops, 5); + expect_value_count(rrddim_add_custom, name, NULL, 5); + expect_value_count(rrddim_add_custom, multiplier, 1, 5); + expect_value_count(rrddim_add_custom, divisor, 1, 5); + expect_value_count(rrddim_add_custom, algorithm, RRD_ALGORITHM_ABSOLUTE, 5); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_create_custom); + expect_value(rrdset_create_custom, host, localhost); + expect_string(rrdset_create_custom, type, "netdata"); + expect_string(rrdset_create_custom, id, "exporting_test_instance_thread_cpu"); + expect_value(rrdset_create_custom, name, NULL); + expect_string(rrdset_create_custom, family, "exporting_test_instance"); + expect_string(rrdset_create_custom, context, "exporting_instance"); + expect_string(rrdset_create_custom, units, "milliseconds/s"); + expect_string(rrdset_create_custom, plugin, "exporting"); + expect_value(rrdset_create_custom, module, NULL); + expect_value(rrdset_create_custom, priority, 130640); + expect_value(rrdset_create_custom, update_every, 2); + expect_value(rrdset_create_custom, chart_type, RRDSET_TYPE_STACKED); + will_return(rrdset_create_custom, stats->st_rusage); + + expect_function_calls(rrddim_add_custom, 2); + expect_value_count(rrddim_add_custom, st, stats->st_rusage, 2); + expect_value_count(rrddim_add_custom, name, NULL, 2); + expect_value_count(rrddim_add_custom, multiplier, 1, 2); + expect_value_count(rrddim_add_custom, divisor, 1000, 2); + expect_value_count(rrddim_add_custom, algorithm, RRD_ALGORITHM_INCREMENTAL, 2); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_next_usec); + expect_value(rrdset_next_usec, st, stats->st_metrics); + + expect_function_calls(rrddim_set_by_pointer, 3); + expect_value_count(rrddim_set_by_pointer, st, stats->st_metrics, 3); + + expect_function_call(rrdset_done); + expect_value(rrdset_done, st, stats->st_metrics); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_next_usec); + expect_value(rrdset_next_usec, st, stats->st_bytes); + + expect_function_calls(rrddim_set_by_pointer, 4); + expect_value_count(rrddim_set_by_pointer, st, stats->st_bytes, 4); + + expect_function_call(rrdset_done); + expect_value(rrdset_done, st, stats->st_bytes); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_next_usec); + expect_value(rrdset_next_usec, st, stats->st_ops); + + expect_function_calls(rrddim_set_by_pointer, 5); + expect_value_count(rrddim_set_by_pointer, st, stats->st_ops, 5); + + expect_function_call(rrdset_done); + expect_value(rrdset_done, st, stats->st_ops); + + // ------------------------------------------------------------------------ + + expect_function_call(rrdset_next_usec); + expect_value(rrdset_next_usec, st, stats->st_rusage); + + expect_function_calls(rrddim_set_by_pointer, 2); + expect_value_count(rrddim_set_by_pointer, st, stats->st_rusage, 2); + + expect_function_call(rrdset_done); + expect_value(rrdset_done, st, stats->st_rusage); + + // ------------------------------------------------------------------------ + + __real_send_internal_metrics(instance); + + free(stats->st_metrics); + free(stats->st_bytes); + free(stats->st_ops); + free(stats->st_rusage); + free((void *)instance->config.name); + free(instance); +} + +static void test_can_send_rrdset(void **state) +{ + (void)*state; + + assert_int_equal(can_send_rrdset(prometheus_exporter_instance, localhost->rrdset_root), 1); + + rrdset_flag_set(localhost->rrdset_root, RRDSET_FLAG_BACKEND_IGNORE); + assert_int_equal(can_send_rrdset(prometheus_exporter_instance, localhost->rrdset_root), 0); + rrdset_flag_clear(localhost->rrdset_root, RRDSET_FLAG_BACKEND_IGNORE); + + // TODO: test with a denying simple pattern + + rrdset_flag_set(localhost->rrdset_root, RRDSET_FLAG_OBSOLETE); + assert_int_equal(can_send_rrdset(prometheus_exporter_instance, localhost->rrdset_root), 0); + rrdset_flag_clear(localhost->rrdset_root, RRDSET_FLAG_OBSOLETE); + + localhost->rrdset_root->rrd_memory_mode = RRD_MEMORY_MODE_NONE; + prometheus_exporter_instance->config.options |= EXPORTING_SOURCE_DATA_AVERAGE; + assert_int_equal(can_send_rrdset(prometheus_exporter_instance, localhost->rrdset_root), 0); +} + +static void test_prometheus_name_copy(void **state) +{ + (void)*state; + + char destination_name[PROMETHEUS_ELEMENT_MAX + 1]; + assert_int_equal(prometheus_name_copy(destination_name, "test-name", PROMETHEUS_ELEMENT_MAX), 9); + + assert_string_equal(destination_name, "test_name"); +} + +static void test_prometheus_label_copy(void **state) +{ + (void)*state; + + char destination_name[PROMETHEUS_ELEMENT_MAX + 1]; + assert_int_equal(prometheus_label_copy(destination_name, "test\"\\\nlabel", PROMETHEUS_ELEMENT_MAX), 15); + + assert_string_equal(destination_name, "test\\\"\\\\\\\nlabel"); +} + +static void test_prometheus_units_copy(void **state) +{ + (void)*state; + + char destination_name[PROMETHEUS_ELEMENT_MAX + 1]; + assert_string_equal(prometheus_units_copy(destination_name, "test-units", PROMETHEUS_ELEMENT_MAX, 0), "_test_units"); + assert_string_equal(destination_name, "_test_units"); + + assert_string_equal(prometheus_units_copy(destination_name, "%", PROMETHEUS_ELEMENT_MAX, 0), "_percent"); + assert_string_equal(prometheus_units_copy(destination_name, "test-units/s", PROMETHEUS_ELEMENT_MAX, 0), "_test_units_persec"); + + assert_string_equal(prometheus_units_copy(destination_name, "KiB", PROMETHEUS_ELEMENT_MAX, 1), "_KB"); +} + +static void test_format_host_labels_prometheus(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + format_host_labels_prometheus(instance, localhost); + assert_string_equal(buffer_tostring(instance->labels), "key1=\"netdata\",key2=\"value2\""); +} + +static void rrd_stats_api_v1_charts_allmetrics_prometheus(void **state) +{ + (void)state; + + BUFFER *buffer = buffer_create(0); + + localhost->hostname = strdupz("test_hostname"); + localhost->rrdset_root->family = strdupz("test_family"); + localhost->rrdset_root->context = strdupz("test_context"); + + expect_function_call(__wrap_now_realtime_sec); + will_return(__wrap_now_realtime_sec, 2); + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + rrd_stats_api_v1_charts_allmetrics_prometheus_single_host(localhost, buffer, "test_server", "test_prefix", 0, 0); + + assert_string_equal( + buffer_tostring(buffer), + "netdata_info{instance=\"test_hostname\",application=\"(null)\",version=\"(null)\"} 1\n" + "netdata_host_tags_info{key1=\"value1\",key2=\"value2\"} 1\n" + "netdata_host_tags{key1=\"value1\",key2=\"value2\"} 1\n" + "test_prefix_test_context{chart=\"chart_id\",family=\"test_family\",dimension=\"dimension_id\"} 690565856.0000000\n"); + + buffer_flush(buffer); + + expect_function_call(__wrap_now_realtime_sec); + will_return(__wrap_now_realtime_sec, 2); + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + rrd_stats_api_v1_charts_allmetrics_prometheus_single_host( + localhost, buffer, "test_server", "test_prefix", 0, PROMETHEUS_OUTPUT_NAMES | PROMETHEUS_OUTPUT_TYPES); + + assert_string_equal( + buffer_tostring(buffer), + "netdata_info{instance=\"test_hostname\",application=\"(null)\",version=\"(null)\"} 1\n" + "netdata_host_tags_info{key1=\"value1\",key2=\"value2\"} 1\n" + "netdata_host_tags{key1=\"value1\",key2=\"value2\"} 1\n" + "# TYPE test_prefix_test_context gauge\n" + "test_prefix_test_context{chart=\"chart_name\",family=\"test_family\",dimension=\"dimension_name\"} 690565856.0000000\n"); + + buffer_flush(buffer); + + expect_function_call(__wrap_now_realtime_sec); + will_return(__wrap_now_realtime_sec, 2); + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + rrd_stats_api_v1_charts_allmetrics_prometheus_all_hosts(localhost, buffer, "test_server", "test_prefix", 0, 0); + + assert_string_equal( + buffer_tostring(buffer), + "netdata_info{instance=\"test_hostname\",application=\"(null)\",version=\"(null)\"} 1\n" + "netdata_host_tags_info{instance=\"test_hostname\",key1=\"value1\",key2=\"value2\"} 1\n" + "netdata_host_tags{instance=\"test_hostname\",key1=\"value1\",key2=\"value2\"} 1\n" + "test_prefix_test_context{chart=\"chart_id\",family=\"test_family\",dimension=\"dimension_id\",instance=\"test_hostname\"} 690565856.0000000\n"); + + free(localhost->rrdset_root->context); + free(localhost->rrdset_root->family); + free(localhost->hostname); + buffer_free(buffer); +} + +#if ENABLE_PROMETHEUS_REMOTE_WRITE +static void test_init_prometheus_remote_write_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + expect_function_call(__wrap_init_write_request); + will_return(__wrap_init_write_request, 0xff); + + assert_int_equal(init_prometheus_remote_write_instance(instance), 0); + + assert_ptr_equal(instance->worker, simple_connector_worker); + assert_ptr_equal(instance->start_batch_formatting, NULL); + assert_ptr_equal(instance->start_host_formatting, format_host_prometheus_remote_write); + assert_ptr_equal(instance->start_chart_formatting, format_chart_prometheus_remote_write); + assert_ptr_equal(instance->metric_formatting, format_dimension_prometheus_remote_write); + assert_ptr_equal(instance->end_chart_formatting, NULL); + assert_ptr_equal(instance->end_host_formatting, NULL); + assert_ptr_equal(instance->end_batch_formatting, format_batch_prometheus_remote_write); + assert_ptr_equal(instance->prepare_header, prometheus_remote_write_prepare_header); + assert_ptr_equal(instance->check_response, process_prometheus_remote_write_response); + + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + struct prometheus_remote_write_specific_data *connector_specific_data = + (struct prometheus_remote_write_specific_data *)instance->connector_specific_data; + + assert_ptr_not_equal(instance->connector_specific_data, NULL); + assert_ptr_not_equal(connector_specific_data->write_request, NULL); + freez(instance->connector_specific_data); +} + +static void test_prometheus_remote_write_prepare_header(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + struct prometheus_remote_write_specific_config *connector_specific_config = + callocz(1, sizeof(struct prometheus_remote_write_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->remote_write_path = strdupz("/receive"); + + struct simple_connector_data *simple_connector_data = callocz(1, sizeof(struct simple_connector_data)); + instance->connector_specific_data = simple_connector_data; + simple_connector_data->last_buffer = callocz(1, sizeof(struct simple_connector_buffer)); + simple_connector_data->last_buffer->header = buffer_create(0); + simple_connector_data->last_buffer->buffer = buffer_create(0); + + buffer_sprintf(simple_connector_data->last_buffer->buffer, "test buffer"); + + prometheus_remote_write_prepare_header(instance); + + assert_string_equal( + buffer_tostring(simple_connector_data->last_buffer->header), + "POST /receive HTTP/1.1\r\n" + "Host: localhost\r\n" + "Accept: */*\r\n" + "Content-Encoding: snappy\r\n" + "Content-Type: application/x-protobuf\r\n" + "X-Prometheus-Remote-Write-Version: 0.1.0\r\n" + "Content-Length: 11\r\n" + "\r\n"); + + free(connector_specific_config->remote_write_path); + + buffer_free(simple_connector_data->last_buffer->header); + buffer_free(simple_connector_data->last_buffer->buffer); +} + +static void test_process_prometheus_remote_write_response(void **state) +{ + (void)state; + BUFFER *buffer = buffer_create(0); + + buffer_sprintf(buffer, "HTTP/1.1 200 OK\r\n"); + assert_int_equal(process_prometheus_remote_write_response(buffer, NULL), 0); + + buffer_free(buffer); +} + +static void test_format_host_prometheus_remote_write(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options |= EXPORTING_OPTION_SEND_CONFIGURED_LABELS; + instance->config.options |= EXPORTING_OPTION_SEND_AUTOMATIC_LABELS; + + struct simple_connector_data *simple_connector_data = mallocz(sizeof(struct simple_connector_data *)); + instance->connector_specific_data = simple_connector_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + mallocz(sizeof(struct prometheus_remote_write_specific_data *)); + simple_connector_data->connector_specific_data = (void *)connector_specific_data; + connector_specific_data->write_request = (void *)0xff; + + localhost->program_name = strdupz("test_program"); + localhost->program_version = strdupz("test_version"); + + expect_function_call(__wrap_add_host_info); + expect_value(__wrap_add_host_info, write_request_p, 0xff); + expect_string(__wrap_add_host_info, name, "netdata_info"); + expect_string(__wrap_add_host_info, instance, "test-host"); + expect_string(__wrap_add_host_info, application, "test_program"); + expect_string(__wrap_add_host_info, version, "test_version"); + expect_in_range( + __wrap_add_host_info, timestamp, now_realtime_usec() / USEC_PER_MS - 1000, now_realtime_usec() / USEC_PER_MS); + + expect_function_call(__wrap_add_label); + expect_value(__wrap_add_label, write_request_p, 0xff); + expect_string(__wrap_add_label, key, "key1"); + expect_string(__wrap_add_label, value, "value1"); + + expect_function_call(__wrap_add_label); + expect_value(__wrap_add_label, write_request_p, 0xff); + expect_string(__wrap_add_label, key, "key2"); + expect_string(__wrap_add_label, value, "value2"); + + assert_int_equal(format_host_prometheus_remote_write(instance, localhost), 0); + + freez(connector_specific_data); + freez(simple_connector_data); + free(localhost->program_name); + free(localhost->program_version); +} + +static void test_format_dimension_prometheus_remote_write(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + struct simple_connector_data *simple_connector_data = mallocz(sizeof(struct simple_connector_data *)); + instance->connector_specific_data = simple_connector_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + mallocz(sizeof(struct prometheus_remote_write_specific_data *)); + simple_connector_data->connector_specific_data = (void *)connector_specific_data; + connector_specific_data->write_request = (void *)0xff; + + RRDDIM *rd = localhost->rrdset_root->dimensions; + + expect_function_call(__wrap_exporting_calculate_value_from_stored_data); + will_return(__wrap_exporting_calculate_value_from_stored_data, pack_storage_number(27, SN_EXISTS)); + + expect_function_call(__wrap_add_metric); + expect_value(__wrap_add_metric, write_request_p, 0xff); + expect_string(__wrap_add_metric, name, "netdata_"); + expect_string(__wrap_add_metric, chart, ""); + expect_string(__wrap_add_metric, family, ""); + expect_string(__wrap_add_metric, dimension, "dimension_name"); + expect_string(__wrap_add_metric, instance, "test-host"); + expect_value(__wrap_add_metric, value, 0x292932e0); + expect_value(__wrap_add_metric, timestamp, 15052 * MSEC_PER_SEC); + + assert_int_equal(format_dimension_prometheus_remote_write(instance, rd), 0); +} + +static void test_format_batch_prometheus_remote_write(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + struct simple_connector_data *simple_connector_data = mallocz(sizeof(struct simple_connector_data *)); + instance->connector_specific_data = simple_connector_data; + struct prometheus_remote_write_specific_data *connector_specific_data = + mallocz(sizeof(struct prometheus_remote_write_specific_data *)); + simple_connector_data->connector_specific_data = (void *)connector_specific_data; + connector_specific_data->write_request = __real_init_write_request(); + + expect_function_call(__wrap_simple_connector_end_batch); + expect_value(__wrap_simple_connector_end_batch, instance, instance); + will_return(__wrap_simple_connector_end_batch, 0); + __real_add_host_info( + connector_specific_data->write_request, + "test_name", "test_instance", "test_application", "test_version", 15051); + + __real_add_label(connector_specific_data->write_request, "test_key", "test_value"); + + __real_add_metric( + connector_specific_data->write_request, + "test_name", "test chart", "test_family", "test_dimension", "test_instance", + 123000321, 15052); + + assert_int_equal(format_batch_prometheus_remote_write(instance), 0); + + BUFFER *buffer = instance->buffer; + assert_int_equal(buffer_strlen(buffer), 192); + + BUFFER *escaped_buffer = buffer_create(850); + size_t len = buffer_strlen(buffer); + char *ch = (char *)buffer_tostring(buffer); + for (; len > 0; ch++, len--) + buffer_sprintf(escaped_buffer, "\\%03o", (unsigned int)*ch); + assert_string_equal( + buffer_tostring(escaped_buffer), + "\\37777777641\\002\\120\\012\\37777777622\\001\\012\\025\\012\\010\\137\\137\\156\\141\\155\\145\\137\\137" + "\\022\\011\\164\\145\\163\\164\\005\\015\\064\\012\\031\\012\\010\\151\\156\\163\\164\\141\\156\\143\\145\\022" + "\\015\\005\\027\\021\\017\\100\\012\\037\\012\\013\\141\\160\\160\\154\\151\\143\\141\\164\\151\\157\\156\\022" + "\\020\\005\\036\\035\\022\\034\\012\\027\\012\\007\\166\\145\\162\\163\\001\\035\\000\\014\\005\\035\\015\\016" + "\\014\\012\\026\\012\\010\\005\\020\\020\\153\\145\\171\\022\\012\\005\\012\\040\\166\\141\\154\\165\\145\\022" + "\\014\\011\\000\\005\\001\\030\\37777777760\\077\\020\\37777777713\\165\\012\\37777777611\\142\\37777777625" + "\\000\\034\\023\\012\\005\\143\\150\\141\\162\\164\\011\\075\\000\\040\\005\\014\\054\\012\\025\\012\\006\\146" + "\\141\\155\\151\\154\\171\\022\\013\\005\\123\\011\\015\\040\\012\\033\\012\\011\\144\\151\\155\\145\\156\\005" + "\\37777777607\\000\\016\\005\\032\\025\\020\\000\\012\\146\\37777777736\\000\\064\\022\\014\\011\\000\\000\\000" + "\\004\\130\\123\\37777777635\\101\\020\\37777777714\\165"); + + buffer_free(escaped_buffer); + protocol_buffers_shutdown(); +} +#endif // ENABLE_PROMETHEUS_REMOTE_WRITE + +#if HAVE_KINESIS +static void test_init_aws_kinesis_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + + struct aws_kinesis_specific_config *connector_specific_config = + callocz(1, sizeof(struct aws_kinesis_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->stream_name = strdupz("test_stream"); + connector_specific_config->auth_key_id = strdupz("test_auth_key_id"); + connector_specific_config->secure_key = strdupz("test_secure_key"); + + expect_function_call(__wrap_aws_sdk_init); + expect_function_call(__wrap_kinesis_init); + expect_not_value(__wrap_kinesis_init, kinesis_specific_data_p, NULL); + expect_string(__wrap_kinesis_init, region, "localhost"); + expect_string(__wrap_kinesis_init, access_key_id, "test_auth_key_id"); + expect_string(__wrap_kinesis_init, secret_key, "test_secure_key"); + expect_value(__wrap_kinesis_init, timeout, 10000); + + assert_int_equal(init_aws_kinesis_instance(instance), 0); + + assert_ptr_equal(instance->worker, aws_kinesis_connector_worker); + assert_ptr_equal(instance->start_batch_formatting, NULL); + assert_ptr_equal(instance->start_host_formatting, format_host_labels_json_plaintext); + assert_ptr_equal(instance->start_chart_formatting, NULL); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_json_plaintext); + assert_ptr_equal(instance->end_chart_formatting, NULL); + assert_ptr_equal(instance->end_host_formatting, flush_host_labels); + assert_ptr_equal(instance->end_batch_formatting, NULL); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + assert_ptr_not_equal(instance->connector_specific_data, NULL); + freez(instance->connector_specific_data); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + + expect_function_call(__wrap_kinesis_init); + expect_not_value(__wrap_kinesis_init, kinesis_specific_data_p, NULL); + expect_string(__wrap_kinesis_init, region, "localhost"); + expect_string(__wrap_kinesis_init, access_key_id, "test_auth_key_id"); + expect_string(__wrap_kinesis_init, secret_key, "test_secure_key"); + expect_value(__wrap_kinesis_init, timeout, 10000); + + assert_int_equal(init_aws_kinesis_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_json_plaintext); + + free(connector_specific_config->stream_name); + free(connector_specific_config->auth_key_id); + free(connector_specific_config->secure_key); +} + +static void test_aws_kinesis_connector_worker(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + BUFFER *buffer = instance->buffer; + + __real_mark_scheduled_instances(engine); + + expect_function_call(__wrap_rrdhost_is_exportable); + expect_value(__wrap_rrdhost_is_exportable, instance, instance); + expect_value(__wrap_rrdhost_is_exportable, host, localhost); + will_return(__wrap_rrdhost_is_exportable, 1); + + RRDSET *st = localhost->rrdset_root; + expect_function_call(__wrap_rrdset_is_exportable); + expect_value(__wrap_rrdset_is_exportable, instance, instance); + expect_value(__wrap_rrdset_is_exportable, st, st); + will_return(__wrap_rrdset_is_exportable, 1); + + expect_function_call(__wrap_simple_connector_end_batch); + expect_value(__wrap_simple_connector_end_batch, instance, instance); + will_return(__wrap_simple_connector_end_batch, 0); + __real_prepare_buffers(engine); + + struct aws_kinesis_specific_config *connector_specific_config = + callocz(1, sizeof(struct aws_kinesis_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->stream_name = strdupz("test_stream"); + connector_specific_config->auth_key_id = strdupz("test_auth_key_id"); + connector_specific_config->secure_key = strdupz("test_secure_key"); + + struct aws_kinesis_specific_data *connector_specific_data = callocz(1, sizeof(struct aws_kinesis_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + expect_function_call(__wrap_kinesis_put_record); + expect_not_value(__wrap_kinesis_put_record, kinesis_specific_data_p, NULL); + expect_string(__wrap_kinesis_put_record, stream_name, "test_stream"); + expect_string(__wrap_kinesis_put_record, partition_key, "netdata_0"); + expect_value(__wrap_kinesis_put_record, data, buffer_tostring(buffer)); + // The buffer is prepared by Graphite exporting connector + expect_string( + __wrap_kinesis_put_record, data, + "netdata.test-host.chart_name.dimension_name;TAG1=VALUE1 TAG2=VALUE2 123000321 15051\n"); + expect_value(__wrap_kinesis_put_record, data_len, 84); + + expect_function_call(__wrap_kinesis_get_result); + expect_value(__wrap_kinesis_get_result, request_outcomes_p, NULL); + expect_not_value(__wrap_kinesis_get_result, error_message, NULL); + expect_not_value(__wrap_kinesis_get_result, sent_bytes, NULL); + expect_not_value(__wrap_kinesis_get_result, lost_bytes, NULL); + will_return(__wrap_kinesis_get_result, 0); + + expect_function_call(__wrap_send_internal_metrics); + expect_value(__wrap_send_internal_metrics, instance, instance); + will_return(__wrap_send_internal_metrics, 0); + + aws_kinesis_connector_worker(instance); + + assert_int_equal(stats->buffered_metrics, 0); + assert_int_equal(stats->buffered_bytes, 84); + assert_int_equal(stats->received_bytes, 0); + assert_int_equal(stats->sent_bytes, 84); + assert_int_equal(stats->sent_metrics, 1); + assert_int_equal(stats->lost_metrics, 0); + assert_int_equal(stats->receptions, 1); + assert_int_equal(stats->transmission_successes, 1); + assert_int_equal(stats->transmission_failures, 0); + assert_int_equal(stats->data_lost_events, 0); + assert_int_equal(stats->lost_bytes, 0); + assert_int_equal(stats->reconnects, 0); + + free(connector_specific_config->stream_name); + free(connector_specific_config->auth_key_id); + free(connector_specific_config->secure_key); +} +#endif // HAVE_KINESIS + +#if ENABLE_EXPORTING_PUBSUB +static void test_init_pubsub_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + + struct pubsub_specific_config *connector_specific_config = + callocz(1, sizeof(struct pubsub_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->credentials_file = strdupz("/test/credentials/file"); + connector_specific_config->project_id = strdupz("test_project_id"); + connector_specific_config->topic_id = strdupz("test_topic_id"); + + expect_function_call(__wrap_pubsub_init); + expect_not_value(__wrap_pubsub_init, pubsub_specific_data_p, NULL); + expect_string(__wrap_pubsub_init, destination, "localhost"); + expect_string(__wrap_pubsub_init, error_message, ""); + expect_string(__wrap_pubsub_init, credentials_file, "/test/credentials/file"); + expect_string(__wrap_pubsub_init, project_id, "test_project_id"); + expect_string(__wrap_pubsub_init, topic_id, "test_topic_id"); + will_return(__wrap_pubsub_init, 0); + + assert_int_equal(init_pubsub_instance(instance), 0); + + assert_ptr_equal(instance->worker, pubsub_connector_worker); + assert_ptr_equal(instance->start_batch_formatting, NULL); + assert_ptr_equal(instance->start_host_formatting, format_host_labels_json_plaintext); + assert_ptr_equal(instance->start_chart_formatting, NULL); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_json_plaintext); + assert_ptr_equal(instance->end_chart_formatting, NULL); + assert_ptr_equal(instance->end_host_formatting, flush_host_labels); + assert_ptr_equal(instance->end_batch_formatting, NULL); + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + assert_ptr_not_equal(instance->connector_specific_data, NULL); + freez(instance->connector_specific_data); + + instance->config.options = EXPORTING_SOURCE_DATA_AVERAGE | EXPORTING_OPTION_SEND_NAMES; + + expect_function_call(__wrap_pubsub_init); + expect_not_value(__wrap_pubsub_init, pubsub_specific_data_p, NULL); + expect_string(__wrap_pubsub_init, destination, "localhost"); + expect_string(__wrap_pubsub_init, error_message, ""); + expect_string(__wrap_pubsub_init, credentials_file, "/test/credentials/file"); + expect_string(__wrap_pubsub_init, project_id, "test_project_id"); + expect_string(__wrap_pubsub_init, topic_id, "test_topic_id"); + will_return(__wrap_pubsub_init, 0); + + assert_int_equal(init_pubsub_instance(instance), 0); + assert_ptr_equal(instance->metric_formatting, format_dimension_stored_json_plaintext); + + free(connector_specific_config->credentials_file); + free(connector_specific_config->project_id); + free(connector_specific_config->topic_id); +} + +static void test_pubsub_connector_worker(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + + __real_mark_scheduled_instances(engine); + + expect_function_call(__wrap_rrdhost_is_exportable); + expect_value(__wrap_rrdhost_is_exportable, instance, instance); + expect_value(__wrap_rrdhost_is_exportable, host, localhost); + will_return(__wrap_rrdhost_is_exportable, 1); + + RRDSET *st = localhost->rrdset_root; + expect_function_call(__wrap_rrdset_is_exportable); + expect_value(__wrap_rrdset_is_exportable, instance, instance); + expect_value(__wrap_rrdset_is_exportable, st, st); + will_return(__wrap_rrdset_is_exportable, 1); + + expect_function_call(__wrap_simple_connector_end_batch); + expect_value(__wrap_simple_connector_end_batch, instance, instance); + will_return(__wrap_simple_connector_end_batch, 0); + __real_prepare_buffers(engine); + + struct pubsub_specific_config *connector_specific_config = + callocz(1, sizeof(struct pubsub_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->credentials_file = strdupz("/test/credentials/file"); + connector_specific_config->project_id = strdupz("test_project_id"); + connector_specific_config->topic_id = strdupz("test_topic_id"); + + struct pubsub_specific_data *connector_specific_data = callocz(1, sizeof(struct pubsub_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + expect_function_call(__wrap_pubsub_add_message); + expect_not_value(__wrap_pubsub_add_message, pubsub_specific_data_p, NULL); + // The buffer is prepared by Graphite exporting connector + expect_string( + __wrap_pubsub_add_message, data, + "netdata.test-host.chart_name.dimension_name;TAG1=VALUE1 TAG2=VALUE2 123000321 15051\n"); + will_return(__wrap_pubsub_add_message, 0); + + expect_function_call(__wrap_pubsub_publish); + expect_not_value(__wrap_pubsub_publish, pubsub_specific_data_p, NULL); + expect_string(__wrap_pubsub_publish, error_message, ""); + expect_value(__wrap_pubsub_publish, buffered_metrics, 1); + expect_value(__wrap_pubsub_publish, buffered_bytes, 84); + will_return(__wrap_pubsub_publish, 0); + + expect_function_call(__wrap_pubsub_get_result); + expect_not_value(__wrap_pubsub_get_result, pubsub_specific_data_p, NULL); + expect_not_value(__wrap_pubsub_get_result, error_message, NULL); + expect_not_value(__wrap_pubsub_get_result, sent_metrics, NULL); + expect_not_value(__wrap_pubsub_get_result, sent_bytes, NULL); + expect_not_value(__wrap_pubsub_get_result, lost_metrics, NULL); + expect_not_value(__wrap_pubsub_get_result, lost_bytes, NULL); + will_return(__wrap_pubsub_get_result, 0); + + expect_function_call(__wrap_send_internal_metrics); + expect_value(__wrap_send_internal_metrics, instance, instance); + will_return(__wrap_send_internal_metrics, 0); + + pubsub_connector_worker(instance); + + assert_int_equal(stats->buffered_metrics, 0); + assert_int_equal(stats->buffered_bytes, 84); + assert_int_equal(stats->received_bytes, 0); + assert_int_equal(stats->sent_bytes, 84); + assert_int_equal(stats->sent_metrics, 0); + assert_int_equal(stats->lost_metrics, 0); + assert_int_equal(stats->receptions, 1); + assert_int_equal(stats->transmission_successes, 1); + assert_int_equal(stats->transmission_failures, 0); + assert_int_equal(stats->data_lost_events, 0); + assert_int_equal(stats->lost_bytes, 0); + assert_int_equal(stats->reconnects, 0); + + free(connector_specific_config->credentials_file); + free(connector_specific_config->project_id); + free(connector_specific_config->topic_id); +} +#endif // ENABLE_EXPORTING_PUBSUB + +#if HAVE_MONGOC +static void test_init_mongodb_instance(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + instance->config.options = EXPORTING_SOURCE_DATA_AS_COLLECTED | EXPORTING_OPTION_SEND_NAMES; + + struct mongodb_specific_config *connector_specific_config = callocz(1, sizeof(struct mongodb_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->database = strdupz("test_database"); + connector_specific_config->collection = strdupz("test_collection"); + instance->config.buffer_on_failures = 10; + + expect_function_call(__wrap_mongoc_init); + expect_function_call(__wrap_mongoc_uri_new_with_error); + expect_string(__wrap_mongoc_uri_new_with_error, uri_string, "localhost"); + expect_not_value(__wrap_mongoc_uri_new_with_error, error, NULL); + will_return(__wrap_mongoc_uri_new_with_error, 0xf1); + + expect_function_call(__wrap_mongoc_uri_get_option_as_int32); + expect_value(__wrap_mongoc_uri_get_option_as_int32, uri, 0xf1); + expect_string(__wrap_mongoc_uri_get_option_as_int32, option, MONGOC_URI_SOCKETTIMEOUTMS); + expect_value(__wrap_mongoc_uri_get_option_as_int32, fallback, 1000); + will_return(__wrap_mongoc_uri_get_option_as_int32, 1000); + + expect_function_call(__wrap_mongoc_uri_set_option_as_int32); + expect_value(__wrap_mongoc_uri_set_option_as_int32, uri, 0xf1); + expect_string(__wrap_mongoc_uri_set_option_as_int32, option, MONGOC_URI_SOCKETTIMEOUTMS); + expect_value(__wrap_mongoc_uri_set_option_as_int32, value, 1000); + will_return(__wrap_mongoc_uri_set_option_as_int32, true); + + expect_function_call(__wrap_mongoc_client_new_from_uri); + expect_value(__wrap_mongoc_client_new_from_uri, uri, 0xf1); + will_return(__wrap_mongoc_client_new_from_uri, 0xf2); + + expect_function_call(__wrap_mongoc_client_set_appname); + expect_value(__wrap_mongoc_client_set_appname, client, 0xf2); + expect_string(__wrap_mongoc_client_set_appname, appname, "netdata"); + will_return(__wrap_mongoc_client_set_appname, true); + + expect_function_call(__wrap_mongoc_client_get_collection); + expect_value(__wrap_mongoc_client_get_collection, client, 0xf2); + expect_string(__wrap_mongoc_client_get_collection, db, "test_database"); + expect_string(__wrap_mongoc_client_get_collection, collection, "test_collection"); + will_return(__wrap_mongoc_client_get_collection, 0xf3); + + expect_function_call(__wrap_mongoc_uri_destroy); + expect_value(__wrap_mongoc_uri_destroy, uri, 0xf1); + + assert_int_equal(init_mongodb_instance(instance), 0); + + assert_ptr_equal(instance->worker, mongodb_connector_worker); + assert_ptr_equal(instance->start_batch_formatting, NULL); + assert_ptr_equal(instance->start_host_formatting, format_host_labels_json_plaintext); + assert_ptr_equal(instance->start_chart_formatting, NULL); + assert_ptr_equal(instance->metric_formatting, format_dimension_collected_json_plaintext); + assert_ptr_equal(instance->end_chart_formatting, NULL); + assert_ptr_equal(instance->end_host_formatting, flush_host_labels); + assert_ptr_equal(instance->end_batch_formatting, format_batch_mongodb); + assert_ptr_equal(instance->prepare_header, NULL); + assert_ptr_equal(instance->check_response, NULL); + + assert_ptr_not_equal(instance->buffer, NULL); + buffer_free(instance->buffer); + + assert_ptr_not_equal(instance->connector_specific_data, NULL); + + struct mongodb_specific_data *connector_specific_data = + (struct mongodb_specific_data *)instance->connector_specific_data; + size_t number_of_buffers = 1; + struct bson_buffer *current_buffer = connector_specific_data->first_buffer; + while (current_buffer->next != connector_specific_data->first_buffer) { + current_buffer = current_buffer->next; + number_of_buffers++; + if (number_of_buffers == (size_t)(instance->config.buffer_on_failures + 1)) { + number_of_buffers = 0; + break; + } + } + assert_int_equal(number_of_buffers, 9); + + free(connector_specific_config->database); + free(connector_specific_config->collection); +} + +static void test_format_batch_mongodb(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + struct stats *stats = &instance->stats; + + struct mongodb_specific_data *connector_specific_data = mallocz(sizeof(struct mongodb_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + + struct bson_buffer *current_buffer = callocz(1, sizeof(struct bson_buffer)); + connector_specific_data->first_buffer = current_buffer; + connector_specific_data->first_buffer->next = current_buffer; + connector_specific_data->last_buffer = current_buffer; + + BUFFER *buffer = buffer_create(0); + buffer_sprintf(buffer, "{ \"metric\": \"test_metric\" }\n"); + instance->buffer = buffer; + stats->buffered_metrics = 1; + + assert_int_equal(format_batch_mongodb(instance), 0); + + assert_int_equal(connector_specific_data->last_buffer->documents_inserted, 1); + assert_int_equal(buffer_strlen(buffer), 0); + + size_t len; + char *str = bson_as_canonical_extended_json(connector_specific_data->last_buffer->insert[0], &len); + assert_string_equal(str, "{ \"metric\" : \"test_metric\" }"); + + freez(str); + buffer_free(buffer); +} + +static void test_mongodb_connector_worker(void **state) +{ + struct engine *engine = *state; + struct instance *instance = engine->instance_root; + + struct mongodb_specific_config *connector_specific_config = callocz(1, sizeof(struct mongodb_specific_config)); + instance->config.connector_specific_config = connector_specific_config; + connector_specific_config->database = strdupz("test_database"); + + struct mongodb_specific_data *connector_specific_data = callocz(1, sizeof(struct mongodb_specific_data)); + instance->connector_specific_data = (void *)connector_specific_data; + connector_specific_config->collection = strdupz("test_collection"); + + struct bson_buffer *buffer = callocz(1, sizeof(struct bson_buffer)); + buffer->documents_inserted = 1; + connector_specific_data->first_buffer = buffer; + connector_specific_data->first_buffer->next = buffer; + + connector_specific_data->first_buffer->insert = callocz(1, sizeof(bson_t *)); + bson_error_t bson_error; + connector_specific_data->first_buffer->insert[0] = + bson_new_from_json((const uint8_t *)"{ \"test_key\" : \"test_value\" }", -1, &bson_error); + + connector_specific_data->client = mongoc_client_new("mongodb://localhost"); + connector_specific_data->collection = + __real_mongoc_client_get_collection(connector_specific_data->client, "test_database", "test_collection"); + + expect_function_call(__wrap_mongoc_collection_insert_many); + expect_value(__wrap_mongoc_collection_insert_many, collection, connector_specific_data->collection); + expect_value(__wrap_mongoc_collection_insert_many, documents, connector_specific_data->first_buffer->insert); + expect_value(__wrap_mongoc_collection_insert_many, n_documents, 1); + expect_value(__wrap_mongoc_collection_insert_many, opts, NULL); + expect_value(__wrap_mongoc_collection_insert_many, reply, NULL); + expect_not_value(__wrap_mongoc_collection_insert_many, error, NULL); + will_return(__wrap_mongoc_collection_insert_many, true); + + expect_function_call(__wrap_send_internal_metrics); + expect_value(__wrap_send_internal_metrics, instance, instance); + will_return(__wrap_send_internal_metrics, 0); + + mongodb_connector_worker(instance); + + assert_ptr_equal(connector_specific_data->first_buffer->insert, NULL); + assert_int_equal(connector_specific_data->first_buffer->documents_inserted, 0); + assert_ptr_equal(connector_specific_data->first_buffer, connector_specific_data->first_buffer->next); + + struct stats *stats = &instance->stats; + assert_int_equal(stats->buffered_metrics, 0); + assert_int_equal(stats->buffered_bytes, 0); + assert_int_equal(stats->received_bytes, 0); + assert_int_equal(stats->sent_bytes, 30); + assert_int_equal(stats->sent_metrics, 1); + assert_int_equal(stats->lost_metrics, 0); + assert_int_equal(stats->receptions, 1); + assert_int_equal(stats->transmission_successes, 1); + assert_int_equal(stats->transmission_failures, 0); + assert_int_equal(stats->data_lost_events, 0); + assert_int_equal(stats->lost_bytes, 0); + assert_int_equal(stats->reconnects, 0); + + free(connector_specific_config->database); + free(connector_specific_config->collection); +} +#endif // HAVE_MONGOC + +int main(void) +{ + const struct CMUnitTest tests[] = { + cmocka_unit_test_setup_teardown(test_exporting_engine, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test(test_read_exporting_config), + cmocka_unit_test_setup_teardown(test_init_connectors, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_init_graphite_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_init_json_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_init_opentsdb_telnet_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_init_opentsdb_http_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_mark_scheduled_instances, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_rrdhost_is_exportable, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_false_rrdhost_is_exportable, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_rrdset_is_exportable, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_false_rrdset_is_exportable, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_exporting_calculate_value_from_stored_data, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown(test_prepare_buffers, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test(test_exporting_name_copy), + cmocka_unit_test_setup_teardown( + test_format_dimension_collected_graphite_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_stored_graphite_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_collected_json_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_stored_json_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_collected_opentsdb_telnet, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_stored_opentsdb_telnet, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_collected_opentsdb_http, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_stored_opentsdb_http, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_exporting_discard_response, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_simple_connector_receive_response, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_simple_connector_send_buffer, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_simple_connector_worker, setup_initialized_engine, teardown_initialized_engine), + }; + + const struct CMUnitTest label_tests[] = { + cmocka_unit_test(test_sanitize_json_string), + cmocka_unit_test(test_sanitize_graphite_label_value), + cmocka_unit_test(test_sanitize_opentsdb_label_value), + cmocka_unit_test_setup_teardown( + test_format_host_labels_json_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_host_labels_graphite_plaintext, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_host_labels_opentsdb_telnet, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_host_labels_opentsdb_http, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown(test_flush_host_labels, setup_initialized_engine, teardown_initialized_engine), + }; + + int test_res = cmocka_run_group_tests_name("exporting_engine", tests, NULL, NULL) + + cmocka_run_group_tests_name("labels_in_exporting_engine", label_tests, NULL, NULL); + + const struct CMUnitTest internal_metrics_tests[] = { + cmocka_unit_test_setup_teardown(test_create_main_rusage_chart, setup_rrdhost, teardown_rrdhost), + cmocka_unit_test(test_send_main_rusage), + cmocka_unit_test(test_send_internal_metrics), + }; + + test_res += cmocka_run_group_tests_name("internal_metrics", internal_metrics_tests, NULL, NULL); + + const struct CMUnitTest prometheus_web_api_tests[] = { + cmocka_unit_test_setup_teardown(test_can_send_rrdset, setup_prometheus, teardown_prometheus), + cmocka_unit_test_setup_teardown(test_prometheus_name_copy, setup_prometheus, teardown_prometheus), + cmocka_unit_test_setup_teardown(test_prometheus_label_copy, setup_prometheus, teardown_prometheus), + cmocka_unit_test_setup_teardown(test_prometheus_units_copy, setup_prometheus, teardown_prometheus), + cmocka_unit_test_setup_teardown( + test_format_host_labels_prometheus, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + rrd_stats_api_v1_charts_allmetrics_prometheus, setup_prometheus, teardown_prometheus), + }; + + test_res += cmocka_run_group_tests_name("prometheus_web_api", prometheus_web_api_tests, NULL, NULL); + +#if ENABLE_PROMETHEUS_REMOTE_WRITE + const struct CMUnitTest prometheus_remote_write_tests[] = { + cmocka_unit_test_setup_teardown( + test_init_prometheus_remote_write_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_prometheus_remote_write_prepare_header, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test(test_process_prometheus_remote_write_response), + cmocka_unit_test_setup_teardown( + test_format_host_prometheus_remote_write, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_dimension_prometheus_remote_write, setup_initialized_engine, teardown_initialized_engine), + cmocka_unit_test_setup_teardown( + test_format_batch_prometheus_remote_write, setup_initialized_engine, teardown_initialized_engine), + }; + + test_res += cmocka_run_group_tests_name( + "prometheus_remote_write_exporting_connector", prometheus_remote_write_tests, NULL, NULL); +#endif + +#if HAVE_KINESIS + const struct CMUnitTest kinesis_tests[] = { + cmocka_unit_test_setup_teardown( + test_init_aws_kinesis_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_aws_kinesis_connector_worker, setup_initialized_engine, teardown_initialized_engine), + }; + + test_res += cmocka_run_group_tests_name("kinesis_exporting_connector", kinesis_tests, NULL, NULL); +#endif + +#if ENABLE_EXPORTING_PUBSUB + const struct CMUnitTest pubsub_tests[] = { + cmocka_unit_test_setup_teardown( + test_init_pubsub_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_pubsub_connector_worker, setup_initialized_engine, teardown_initialized_engine), + }; + + test_res += cmocka_run_group_tests_name("pubsub_exporting_connector", pubsub_tests, NULL, NULL); +#endif + +#if HAVE_MONGOC + const struct CMUnitTest mongodb_tests[] = { + cmocka_unit_test_setup_teardown( + test_init_mongodb_instance, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_format_batch_mongodb, setup_configured_engine, teardown_configured_engine), + cmocka_unit_test_setup_teardown( + test_mongodb_connector_worker, setup_configured_engine, teardown_configured_engine), + }; + + test_res += cmocka_run_group_tests_name("mongodb_exporting_connector", mongodb_tests, NULL, NULL); +#endif + + return test_res; +} diff --git a/exporting/tests/test_exporting_engine.h b/exporting/tests/test_exporting_engine.h new file mode 100644 index 000000000..800be1b99 --- /dev/null +++ b/exporting/tests/test_exporting_engine.h @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef TEST_EXPORTING_ENGINE_H +#define TEST_EXPORTING_ENGINE_H 1 + +#include "libnetdata/libnetdata.h" + +#include "exporting/exporting_engine.h" +#include "exporting/graphite/graphite.h" +#include "exporting/json/json.h" +#include "exporting/opentsdb/opentsdb.h" + +#if ENABLE_PROMETHEUS_REMOTE_WRITE +#include "exporting/prometheus/remote_write/remote_write.h" +#endif + +#if HAVE_KINESIS +#include "exporting/aws_kinesis/aws_kinesis.h" +#endif + +#if ENABLE_EXPORTING_PUBSUB +#include "exporting/pubsub/pubsub.h" +#endif + +#if HAVE_MONGOC +#include "exporting/mongodb/mongodb.h" +#endif + +#include +#include +#include +#include +#include + +#define MAX_LOG_LINE 1024 +extern char log_line[]; + +// ----------------------------------------------------------------------- +// doubles for Netdata functions + +const char *__wrap_strdupz(const char *s); +void __wrap_info_int(const char *file, const char *function, const unsigned long line, const char *fmt, ...); +int __wrap_connect_to_one_of( + const char *destination, + int default_port, + struct timeval *timeout, + size_t *reconnects_counter, + char *connected_to, + size_t connected_to_size); +void __rrdhost_check_rdlock(RRDHOST *host, const char *file, const char *function, const unsigned long line); +void __rrdset_check_rdlock(RRDSET *st, const char *file, const char *function, const unsigned long line); +void __rrd_check_rdlock(const char *file, const char *function, const unsigned long line); +time_t __mock_rrddim_query_oldest_time(RRDDIM *rd); +time_t __mock_rrddim_query_latest_time(RRDDIM *rd); +void __mock_rrddim_query_init(RRDDIM *rd, struct rrddim_query_handle *handle, time_t start_time, time_t end_time); +int __mock_rrddim_query_is_finished(struct rrddim_query_handle *handle); +storage_number __mock_rrddim_query_next_metric(struct rrddim_query_handle *handle, time_t *current_time); +void __mock_rrddim_query_finalize(struct rrddim_query_handle *handle); + +// ----------------------------------------------------------------------- +// wraps for system functions + +void __wrap_uv_thread_create(uv_thread_t thread, void (*worker)(void *arg), void *arg); +void __wrap_uv_mutex_lock(uv_mutex_t *mutex); +void __wrap_uv_mutex_unlock(uv_mutex_t *mutex); +void __wrap_uv_cond_signal(uv_cond_t *cond_var); +void __wrap_uv_cond_wait(uv_cond_t *cond_var, uv_mutex_t *mutex); +ssize_t __wrap_recv(int sockfd, void *buf, size_t len, int flags); +ssize_t __wrap_send(int sockfd, const void *buf, size_t len, int flags); + +// ----------------------------------------------------------------------- +// doubles and originals for exporting engine functions + +struct engine *__real_read_exporting_config(); +struct engine *__wrap_read_exporting_config(); +struct engine *__mock_read_exporting_config(); + +int __real_init_connectors(struct engine *engine); +int __wrap_init_connectors(struct engine *engine); + +int __real_mark_scheduled_instances(struct engine *engine); +int __wrap_mark_scheduled_instances(struct engine *engine); + +calculated_number __real_exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp); +calculated_number __wrap_exporting_calculate_value_from_stored_data( + struct instance *instance, + RRDDIM *rd, + time_t *last_timestamp); + +int __real_prepare_buffers(struct engine *engine); +int __wrap_prepare_buffers(struct engine *engine); + +void __real_create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_system); +void __wrap_create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_system); + +void __real_send_main_rusage(RRDSET *st_rusage, RRDDIM *rd_user, RRDDIM *rd_system); +void __wrap_send_main_rusage(RRDSET *st_rusage, RRDDIM *rd_user, RRDDIM *rd_system); + +int __real_send_internal_metrics(struct instance *instance); +int __wrap_send_internal_metrics(struct instance *instance); + +int __real_rrdhost_is_exportable(struct instance *instance, RRDHOST *host); +int __wrap_rrdhost_is_exportable(struct instance *instance, RRDHOST *host); + +int __real_rrdset_is_exportable(struct instance *instance, RRDSET *st); +int __wrap_rrdset_is_exportable(struct instance *instance, RRDSET *st); + +int __mock_start_batch_formatting(struct instance *instance); +int __mock_start_host_formatting(struct instance *instance, RRDHOST *host); +int __mock_start_chart_formatting(struct instance *instance, RRDSET *st); +int __mock_metric_formatting(struct instance *instance, RRDDIM *rd); +int __mock_end_chart_formatting(struct instance *instance, RRDSET *st); +int __mock_end_host_formatting(struct instance *instance, RRDHOST *host); +int __mock_end_batch_formatting(struct instance *instance); + +int __wrap_simple_connector_end_batch(struct instance *instance); + +#if ENABLE_PROMETHEUS_REMOTE_WRITE +void *__real_init_write_request(); +void *__wrap_init_write_request(); + +void __real_add_host_info( + void *write_request_p, + const char *name, const char *instance, const char *application, const char *version, const int64_t timestamp); +void __wrap_add_host_info( + void *write_request_p, + const char *name, const char *instance, const char *application, const char *version, const int64_t timestamp); + +void __real_add_label(void *write_request_p, char *key, char *value); +void __wrap_add_label(void *write_request_p, char *key, char *value); + +void __real_add_metric( + void *write_request_p, + const char *name, const char *chart, const char *family, const char *dimension, + const char *instance, const double value, const int64_t timestamp); +void __wrap_add_metric( + void *write_request_p, + const char *name, const char *chart, const char *family, const char *dimension, + const char *instance, const double value, const int64_t timestamp); +#endif /* ENABLE_PROMETHEUS_REMOTE_WRITE */ + +#if HAVE_KINESIS +void __wrap_aws_sdk_init(); +void __wrap_kinesis_init( + void *kinesis_specific_data_p, const char *region, const char *access_key_id, const char *secret_key, + const long timeout); +void __wrap_kinesis_put_record( + void *kinesis_specific_data_p, const char *stream_name, const char *partition_key, const char *data, + size_t data_len); +int __wrap_kinesis_get_result(void *request_outcomes_p, char *error_message, size_t *sent_bytes, size_t *lost_bytes); +#endif /* HAVE_KINESIS */ + +#if ENABLE_EXPORTING_PUBSUB +int __wrap_pubsub_init( + void *pubsub_specific_data_p, char *error_message, const char *destination, const char *credentials_file, + const char *project_id, const char *topic_id); +int __wrap_pubsub_add_message(void *pubsub_specific_data_p, char *data); +int __wrap_pubsub_publish( + void *pubsub_specific_data_p, char *error_message, size_t buffered_metrics, size_t buffered_bytes); +int __wrap_pubsub_get_result( + void *pubsub_specific_data_p, char *error_message, + size_t *sent_metrics, size_t *sent_bytes, size_t *lost_metrics, size_t *lost_bytes); +#endif /* ENABLE_EXPORTING_PUBSUB */ + +#if HAVE_MONGOC +void __wrap_mongoc_init(); +mongoc_uri_t *__wrap_mongoc_uri_new_with_error(const char *uri_string, bson_error_t *error); +int32_t __wrap_mongoc_uri_get_option_as_int32(const mongoc_uri_t *uri, const char *option, int32_t fallback); +bool __wrap_mongoc_uri_set_option_as_int32(const mongoc_uri_t *uri, const char *option, int32_t value); +mongoc_client_t *__wrap_mongoc_client_new_from_uri(const mongoc_uri_t *uri); +bool __wrap_mongoc_client_set_appname(mongoc_client_t *client, const char *appname); +mongoc_collection_t * +__wrap_mongoc_client_get_collection(mongoc_client_t *client, const char *db, const char *collection); +mongoc_collection_t * +__real_mongoc_client_get_collection(mongoc_client_t *client, const char *db, const char *collection); +void __wrap_mongoc_uri_destroy(mongoc_uri_t *uri); +bool __wrap_mongoc_collection_insert_many( + mongoc_collection_t *collection, + const bson_t **documents, + size_t n_documents, + const bson_t *opts, + bson_t *reply, + bson_error_t *error); +#endif /* HAVE_MONGOC */ + +// ----------------------------------------------------------------------- +// fixtures + +int setup_configured_engine(void **state); +int teardown_configured_engine(void **state); +int setup_rrdhost(); +int teardown_rrdhost(); +int setup_initialized_engine(void **state); +int teardown_initialized_engine(void **state); +int setup_prometheus(void **state); +int teardown_prometheus(void **state); + +void init_connectors_in_tests(struct engine *engine); + +#endif /* TEST_EXPORTING_ENGINE_H */ -- cgit v1.2.3