diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 11:19:16 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 12:07:37 +0000 |
commit | b485aab7e71c1625cfc27e0f92c9509f42378458 (patch) | |
tree | ae9abe108601079d1679194de237c9a435ae5b55 /src/collectors/python.d.plugin/boinc | |
parent | Adding upstream version 1.44.3. (diff) | |
download | netdata-b485aab7e71c1625cfc27e0f92c9509f42378458.tar.xz netdata-b485aab7e71c1625cfc27e0f92c9509f42378458.zip |
Adding upstream version 1.45.3+dfsg.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/collectors/python.d.plugin/boinc')
l--------- | src/collectors/python.d.plugin/boinc/README.md | 1 | ||||
-rw-r--r-- | src/collectors/python.d.plugin/boinc/boinc.chart.py | 168 | ||||
-rw-r--r-- | src/collectors/python.d.plugin/boinc/boinc.conf | 66 | ||||
-rw-r--r-- | src/collectors/python.d.plugin/boinc/integrations/boinc.md | 204 | ||||
-rw-r--r-- | src/collectors/python.d.plugin/boinc/metadata.yaml | 198 |
5 files changed, 637 insertions, 0 deletions
diff --git a/src/collectors/python.d.plugin/boinc/README.md b/src/collectors/python.d.plugin/boinc/README.md new file mode 120000 index 000000000..22c10ca17 --- /dev/null +++ b/src/collectors/python.d.plugin/boinc/README.md @@ -0,0 +1 @@ +integrations/boinc.md
\ No newline at end of file diff --git a/src/collectors/python.d.plugin/boinc/boinc.chart.py b/src/collectors/python.d.plugin/boinc/boinc.chart.py new file mode 100644 index 000000000..a31eda1c2 --- /dev/null +++ b/src/collectors/python.d.plugin/boinc/boinc.chart.py @@ -0,0 +1,168 @@ +# -*- coding: utf-8 -*- +# Description: BOINC netdata python.d module +# Author: Austin S. Hemmelgarn (Ferroin) +# SPDX-License-Identifier: GPL-3.0-or-later + +import socket + +from bases.FrameworkServices.SimpleService import SimpleService +from third_party import boinc_client + +ORDER = [ + 'tasks', + 'states', + 'sched_states', + 'process_states', +] + +CHARTS = { + 'tasks': { + 'options': [None, 'Overall Tasks', 'tasks', 'boinc', 'boinc.tasks', 'line'], + 'lines': [ + ['total', 'Total', 'absolute', 1, 1], + ['active', 'Active', 'absolute', 1, 1] + ] + }, + 'states': { + 'options': [None, 'Tasks per State', 'tasks', 'boinc', 'boinc.states', 'line'], + 'lines': [ + ['new', 'New', 'absolute', 1, 1], + ['downloading', 'Downloading', 'absolute', 1, 1], + ['downloaded', 'Ready to Run', 'absolute', 1, 1], + ['comperror', 'Compute Errors', 'absolute', 1, 1], + ['uploading', 'Uploading', 'absolute', 1, 1], + ['uploaded', 'Uploaded', 'absolute', 1, 1], + ['aborted', 'Aborted', 'absolute', 1, 1], + ['upload_failed', 'Failed Uploads', 'absolute', 1, 1] + ] + }, + 'sched_states': { + 'options': [None, 'Tasks per Scheduler State', 'tasks', 'boinc', 'boinc.sched', 'line'], + 'lines': [ + ['uninit_sched', 'Uninitialized', 'absolute', 1, 1], + ['preempted', 'Preempted', 'absolute', 1, 1], + ['scheduled', 'Scheduled', 'absolute', 1, 1] + ] + }, + 'process_states': { + 'options': [None, 'Tasks per Process State', 'tasks', 'boinc', 'boinc.process', 'line'], + 'lines': [ + ['uninit_proc', 'Uninitialized', 'absolute', 1, 1], + ['executing', 'Executing', 'absolute', 1, 1], + ['suspended', 'Suspended', 'absolute', 1, 1], + ['aborting', 'Aborted', 'absolute', 1, 1], + ['quit', 'Quit', 'absolute', 1, 1], + ['copy_pending', 'Copy Pending', 'absolute', 1, 1] + ] + } +} + +# A simple template used for pre-loading the return dictionary to make +# the _get_data() method simpler. +_DATA_TEMPLATE = { + 'total': 0, + 'active': 0, + 'new': 0, + 'downloading': 0, + 'downloaded': 0, + 'comperror': 0, + 'uploading': 0, + 'uploaded': 0, + 'aborted': 0, + 'upload_failed': 0, + 'uninit_sched': 0, + 'preempted': 0, + 'scheduled': 0, + 'uninit_proc': 0, + 'executing': 0, + 'suspended': 0, + 'aborting': 0, + 'quit': 0, + 'copy_pending': 0 +} + +# Map task states to dimensions +_TASK_MAP = { + boinc_client.ResultState.NEW: 'new', + boinc_client.ResultState.FILES_DOWNLOADING: 'downloading', + boinc_client.ResultState.FILES_DOWNLOADED: 'downloaded', + boinc_client.ResultState.COMPUTE_ERROR: 'comperror', + boinc_client.ResultState.FILES_UPLOADING: 'uploading', + boinc_client.ResultState.FILES_UPLOADED: 'uploaded', + boinc_client.ResultState.ABORTED: 'aborted', + boinc_client.ResultState.UPLOAD_FAILED: 'upload_failed' +} + +# Map scheduler states to dimensions +_SCHED_MAP = { + boinc_client.CpuSched.UNINITIALIZED: 'uninit_sched', + boinc_client.CpuSched.PREEMPTED: 'preempted', + boinc_client.CpuSched.SCHEDULED: 'scheduled', +} + +# Maps process states to dimensions +_PROC_MAP = { + boinc_client.Process.UNINITIALIZED: 'uninit_proc', + boinc_client.Process.EXECUTING: 'executing', + boinc_client.Process.SUSPENDED: 'suspended', + boinc_client.Process.ABORT_PENDING: 'aborted', + boinc_client.Process.QUIT_PENDING: 'quit', + boinc_client.Process.COPY_PENDING: 'copy_pending' +} + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + SimpleService.__init__(self, configuration=configuration, name=name) + self.order = ORDER + self.definitions = CHARTS + self.host = self.configuration.get('host', 'localhost') + self.port = self.configuration.get('port', 0) + self.password = self.configuration.get('password', '') + self.client = boinc_client.BoincClient(host=self.host, port=self.port, passwd=self.password) + self.alive = False + + def check(self): + return self.connect() + + def connect(self): + self.client.connect() + self.alive = self.client.connected and self.client.authorized + return self.alive + + def reconnect(self): + # The client class itself actually disconnects existing + # connections when it is told to connect, so we don't need to + # explicitly disconnect when we're just trying to reconnect. + return self.connect() + + def is_alive(self): + if not self.alive: + return self.reconnect() + return True + + def _get_data(self): + if not self.is_alive(): + return None + + data = dict(_DATA_TEMPLATE) + + try: + results = self.client.get_tasks() + except socket.error: + self.error('Connection is dead') + self.alive = False + return None + + for task in results: + data['total'] += 1 + data[_TASK_MAP[task.state]] += 1 + try: + if task.active_task: + data['active'] += 1 + data[_SCHED_MAP[task.scheduler_state]] += 1 + data[_PROC_MAP[task.active_task_state]] += 1 + except AttributeError: + pass + + return data or None diff --git a/src/collectors/python.d.plugin/boinc/boinc.conf b/src/collectors/python.d.plugin/boinc/boinc.conf new file mode 100644 index 000000000..16edf55c4 --- /dev/null +++ b/src/collectors/python.d.plugin/boinc/boinc.conf @@ -0,0 +1,66 @@ +# netdata python.d.plugin configuration for boinc +# +# This file is in YaML format. Generally the format is: +# +# name: value +# +# There are 2 sections: +# - global variables +# - one or more JOBS +# +# JOBS allow you to collect values from multiple sources. +# Each source will have its own set of charts. +# +# JOB parameters have to be indented (using spaces only, example below). + +# ---------------------------------------------------------------------- +# Global Variables +# These variables set the defaults for all JOBs, however each JOB +# may define its own, overriding the defaults. + +# update_every sets the default data collection frequency. +# If unset, the python.d.plugin default is used. +# update_every: 1 + +# priority controls the order of charts at the netdata dashboard. +# Lower numbers move the charts towards the top of the page. +# If unset, the default for python.d.plugin is used. +# priority: 60000 + +# penalty indicates whether to apply penalty to update_every in case of failures. +# Penalty will increase every 5 failed updates in a row. Maximum penalty is 10 minutes. +# penalty: yes + +# autodetection_retry sets the job re-check interval in seconds. +# The job is not deleted if check fails. +# Attempts to start the job are made once every autodetection_retry. +# This feature is disabled by default. +# autodetection_retry: 0 + +# ---------------------------------------------------------------------- +# JOBS (data collection sources) +# +# The default JOBS share the same *name*. JOBS with the same name +# are mutually exclusive. Only one of them will be allowed running at +# any time. This allows autodetection to try several alternatives and +# pick the one that works. +# +# Any number of jobs is supported. +# +# All python.d.plugin JOBS (for all its modules) support a set of +# predefined parameters. These are: +# +# job_name: +# name: myname # the JOB's name as it will appear at the +# # dashboard (by default is the job_name) +# # JOBs sharing a name are mutually exclusive +# update_every: 1 # the JOB's data collection frequency +# priority: 60000 # the JOB's order on the dashboard +# penalty: yes # the JOB's penalty +# autodetection_retry: 0 # the JOB's re-check interval in seconds +# +# Additionally to the above, boinc also supports the following: +# +# hostname: localhost # The host running the BOINC client +# port: 31416 # The remote GUI RPC port for BOINC +# password: '' # The remote GUI RPC password diff --git a/src/collectors/python.d.plugin/boinc/integrations/boinc.md b/src/collectors/python.d.plugin/boinc/integrations/boinc.md new file mode 100644 index 000000000..bfd1f7198 --- /dev/null +++ b/src/collectors/python.d.plugin/boinc/integrations/boinc.md @@ -0,0 +1,204 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/boinc/README.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/boinc/metadata.yaml" +sidebar_label: "BOINC" +learn_status: "Published" +learn_rel_path: "Collecting Metrics/Distributed Computing Systems" +most_popular: False +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# BOINC + + +<img src="https://netdata.cloud/img/bolt.svg" width="150"/> + + +Plugin: python.d.plugin +Module: boinc + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This collector monitors task counts for the Berkeley Open Infrastructure Networking Computing (BOINC) distributed computing client. + +It uses the same RPC interface that the BOINC monitoring GUI does. + +This collector is supported on all platforms. + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +By default, the module will try to auto-detect the password to the RPC interface by looking in `/var/lib/boinc` for this file (this is the location most Linux distributions use for a system-wide BOINC installation), so things may just work without needing configuration for a local system. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per BOINC instance + +These metrics refer to the entire monitored application. + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| boinc.tasks | Total, Active | tasks | +| boinc.states | New, Downloading, Ready to Run, Compute Errors, Uploading, Uploaded, Aborted, Failed Uploads | tasks | +| boinc.sched | Uninitialized, Preempted, Scheduled | tasks | +| boinc.process | Uninitialized, Executing, Suspended, Aborted, Quit, Copy Pending | tasks | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ boinc_total_tasks ](https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf) | boinc.tasks | average number of total tasks over the last 10 minutes | +| [ boinc_active_tasks ](https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf) | boinc.tasks | average number of active tasks over the last 10 minutes | +| [ boinc_compute_errors ](https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf) | boinc.states | average number of compute errors over the last 10 minutes | +| [ boinc_upload_errors ](https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf) | boinc.states | average number of failed uploads over the last 10 minutes | + + +## Setup + +### Prerequisites + +#### Boinc RPC interface + +BOINC requires use of a password to access it's RPC interface. You can find this password in the `gui_rpc_auth.cfg` file in your BOINC directory. + + +### Configuration + +#### File + +The configuration file name for this integration is `python.d/boinc.conf`. + + +You can edit the configuration file using the `edit-config` script from the +Netdata [config directory](https://github.com/netdata/netdata/blob/master/docs/netdata-agent/configuration.md#the-netdata-config-directory). + +```bash +cd /etc/netdata 2>/dev/null || cd /opt/netdata/etc/netdata +sudo ./edit-config python.d/boinc.conf +``` +#### Options + +There are 2 sections: + +* Global variables +* One or more JOBS that can define multiple different instances to monitor. + +The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values. + +Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition. + +Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified. + + +<details><summary>Config options</summary> + +| Name | Description | Default | Required | +|:----|:-----------|:-------|:--------:| +| update_every | Sets the default data collection frequency. | 5 | no | +| priority | Controls the order of charts at the netdata dashboard. | 60000 | no | +| autodetection_retry | Sets the job re-check interval in seconds. | 0 | no | +| penalty | Indicates whether to apply penalty to update_every in case of failures. | yes | no | +| name | Job name. This value will overwrite the `job_name` value. JOBS with the same name are mutually exclusive. Only one of them will be allowed running at any time. This allows autodetection to try several alternatives and pick the one that works. | | no | +| hostname | Define a hostname where boinc is running. | localhost | no | +| port | The port of boinc RPC interface. | | no | +| password | Provide a password to connect to a boinc RPC interface. | | no | + +</details> + +#### Examples + +##### Configuration of a remote boinc instance + +A basic JOB configuration for a remote boinc instance + +```yaml +remote: + hostname: '1.2.3.4' + port: 1234 + password: 'some-password' + +``` +##### Multi-instance + +> **Note**: When you define multiple jobs, their names must be unique. + +Collecting metrics from local and remote instances. + + +<details><summary>Config</summary> + +```yaml +localhost: + name: 'local' + host: '127.0.0.1' + port: 1234 + password: 'some-password' + +remote_job: + name: 'remote' + host: '192.0.2.1' + port: 1234 + password: some-other-password + +``` +</details> + + + +## Troubleshooting + +### Debug Mode + +To troubleshoot issues with the `boinc` collector, run the `python.d.plugin` with the debug option enabled. The output +should give you clues as to why the collector isn't working. + +- Navigate to the `plugins.d` directory, usually at `/usr/libexec/netdata/plugins.d/`. If that's not the case on + your system, open `netdata.conf` and look for the `plugins` setting under `[directories]`. + + ```bash + cd /usr/libexec/netdata/plugins.d/ + ``` + +- Switch to the `netdata` user. + + ```bash + sudo -u netdata -s + ``` + +- Run the `python.d.plugin` to debug the collector: + + ```bash + ./python.d.plugin boinc debug trace + ``` + + diff --git a/src/collectors/python.d.plugin/boinc/metadata.yaml b/src/collectors/python.d.plugin/boinc/metadata.yaml new file mode 100644 index 000000000..9448cbe0f --- /dev/null +++ b/src/collectors/python.d.plugin/boinc/metadata.yaml @@ -0,0 +1,198 @@ +plugin_name: python.d.plugin +modules: + - meta: + plugin_name: python.d.plugin + module_name: boinc + monitored_instance: + name: BOINC + link: "https://boinc.berkeley.edu/" + categories: + - data-collection.distributed-computing-systems + icon_filename: "bolt.svg" + related_resources: + integrations: + list: [] + info_provided_to_referring_integrations: + description: "" + keywords: + - boinc + - distributed + most_popular: false + overview: + data_collection: + metrics_description: "This collector monitors task counts for the Berkeley Open Infrastructure Networking Computing (BOINC) distributed computing client." + method_description: "It uses the same RPC interface that the BOINC monitoring GUI does." + supported_platforms: + include: [] + exclude: [] + multi_instance: true + additional_permissions: + description: "" + default_behavior: + auto_detection: + description: "By default, the module will try to auto-detect the password to the RPC interface by looking in `/var/lib/boinc` for this file (this is the location most Linux distributions use for a system-wide BOINC installation), so things may just work without needing configuration for a local system." + limits: + description: "" + performance_impact: + description: "" + setup: + prerequisites: + list: + - title: "Boinc RPC interface" + description: BOINC requires use of a password to access it's RPC interface. You can find this password in the `gui_rpc_auth.cfg` file in your BOINC directory. + configuration: + file: + name: python.d/boinc.conf + options: + description: | + There are 2 sections: + + * Global variables + * One or more JOBS that can define multiple different instances to monitor. + + The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values. + + Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition. + + Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified. + folding: + title: "Config options" + enabled: true + list: + - name: update_every + description: Sets the default data collection frequency. + default_value: 5 + required: false + - name: priority + description: Controls the order of charts at the netdata dashboard. + default_value: 60000 + required: false + - name: autodetection_retry + description: Sets the job re-check interval in seconds. + default_value: 0 + required: false + - name: penalty + description: Indicates whether to apply penalty to update_every in case of failures. + default_value: yes + required: false + - name: name + description: Job name. This value will overwrite the `job_name` value. JOBS with the same name are mutually exclusive. Only one of them will be allowed running at any time. This allows autodetection to try several alternatives and pick the one that works. + default_value: "" + required: false + - name: hostname + description: Define a hostname where boinc is running. + default_value: "localhost" + required: false + - name: port + description: The port of boinc RPC interface. + default_value: "" + required: false + - name: password + description: Provide a password to connect to a boinc RPC interface. + default_value: "" + required: false + examples: + folding: + enabled: true + title: "Config" + list: + - name: Configuration of a remote boinc instance + description: A basic JOB configuration for a remote boinc instance + folding: + enabled: false + config: | + remote: + hostname: '1.2.3.4' + port: 1234 + password: 'some-password' + - name: Multi-instance + description: | + > **Note**: When you define multiple jobs, their names must be unique. + + Collecting metrics from local and remote instances. + config: | + localhost: + name: 'local' + host: '127.0.0.1' + port: 1234 + password: 'some-password' + + remote_job: + name: 'remote' + host: '192.0.2.1' + port: 1234 + password: some-other-password + troubleshooting: + problems: + list: [] + alerts: + - name: boinc_total_tasks + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf + metric: boinc.tasks + info: average number of total tasks over the last 10 minutes + os: "*" + - name: boinc_active_tasks + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf + metric: boinc.tasks + info: average number of active tasks over the last 10 minutes + os: "*" + - name: boinc_compute_errors + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf + metric: boinc.states + info: average number of compute errors over the last 10 minutes + os: "*" + - name: boinc_upload_errors + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/boinc.conf + metric: boinc.states + info: average number of failed uploads over the last 10 minutes + os: "*" + metrics: + folding: + title: Metrics + enabled: false + description: "" + availability: [] + scopes: + - name: global + description: "These metrics refer to the entire monitored application." + labels: [] + metrics: + - name: boinc.tasks + description: Overall Tasks + unit: "tasks" + chart_type: line + dimensions: + - name: Total + - name: Active + - name: boinc.states + description: Tasks per State + unit: "tasks" + chart_type: line + dimensions: + - name: New + - name: Downloading + - name: Ready to Run + - name: Compute Errors + - name: Uploading + - name: Uploaded + - name: Aborted + - name: Failed Uploads + - name: boinc.sched + description: Tasks per Scheduler State + unit: "tasks" + chart_type: line + dimensions: + - name: Uninitialized + - name: Preempted + - name: Scheduled + - name: boinc.process + description: Tasks per Process State + unit: "tasks" + chart_type: line + dimensions: + - name: Uninitialized + - name: Executing + - name: Suspended + - name: Aborted + - name: Quit + - name: Copy Pending |