diff options
Diffstat (limited to '')
| -rw-r--r-- | collectors/python.d.plugin/hddtemp/Makefile.inc | 13 | ||||
| l--------- | collectors/python.d.plugin/hddtemp/README.md | 1 | ||||
| -rw-r--r-- | collectors/python.d.plugin/hddtemp/hddtemp.chart.py | 99 | ||||
| -rw-r--r-- | collectors/python.d.plugin/hddtemp/hddtemp.conf | 95 | ||||
| -rw-r--r-- | collectors/python.d.plugin/hddtemp/integrations/hdd_temperature.md | 217 | ||||
| -rw-r--r-- | collectors/python.d.plugin/hddtemp/metadata.yaml | 163 |
6 files changed, 588 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/hddtemp/Makefile.inc b/collectors/python.d.plugin/hddtemp/Makefile.inc new file mode 100644 index 00000000..22852b64 --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/Makefile.inc @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +# THIS IS NOT A COMPLETE Makefile +# IT IS INCLUDED BY ITS PARENT'S Makefile.am +# IT IS REQUIRED TO REFERENCE ALL FILES RELATIVE TO THE PARENT + +# install these files +dist_python_DATA += hddtemp/hddtemp.chart.py +dist_pythonconfig_DATA += hddtemp/hddtemp.conf + +# do not install these files, but include them in the distribution +dist_noinst_DATA += hddtemp/README.md hddtemp/Makefile.inc + diff --git a/collectors/python.d.plugin/hddtemp/README.md b/collectors/python.d.plugin/hddtemp/README.md new file mode 120000 index 00000000..95c7593f --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/README.md @@ -0,0 +1 @@ +integrations/hdd_temperature.md
\ No newline at end of file diff --git a/collectors/python.d.plugin/hddtemp/hddtemp.chart.py b/collectors/python.d.plugin/hddtemp/hddtemp.chart.py new file mode 100644 index 00000000..6427aa18 --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/hddtemp.chart.py @@ -0,0 +1,99 @@ +# -*- coding: utf-8 -*- +# Description: hddtemp netdata python.d module +# Author: Pawel Krupa (paulfantom) +# Author: Ilya Mashchenko (ilyam8) +# SPDX-License-Identifier: GPL-3.0-or-later + + +import re +from copy import deepcopy + +from bases.FrameworkServices.SocketService import SocketService + +ORDER = [ + 'temperatures', +] + +CHARTS = { + 'temperatures': { + 'options': ['disks_temp', 'Disks Temperatures', 'Celsius', 'temperatures', 'hddtemp.temperatures', 'line'], + 'lines': [ + # lines are created dynamically in `check()` method + ]}} + +RE = re.compile(r'\/dev\/([^|]+)\|([^|]+)\|([0-9]+|SLP|UNK)\|') + + +class Disk: + def __init__(self, id_, name, temp): + self.id = id_.split('/')[-1] + self.name = name.replace(' ', '_') + self.temp = temp if temp.isdigit() else None + + def __repr__(self): + return self.id + + +class Service(SocketService): + def __init__(self, configuration=None, name=None): + SocketService.__init__(self, configuration=configuration, name=name) + self.order = ORDER + self.definitions = deepcopy(CHARTS) + self.do_only = self.configuration.get('devices') + self._keep_alive = False + self.request = "" + self.host = "127.0.0.1" + self.port = 7634 + + def get_disks(self): + r = self._get_raw_data() + + if not r: + return None + + m = RE.findall(r) + + if not m: + self.error("received data doesn't have needed records") + return None + + rv = [Disk(*d) for d in m] + self.debug('available disks: {0}'.format(rv)) + + if self.do_only: + return [v for v in rv if v.id in self.do_only] + return rv + + def get_data(self): + """ + Get data from TCP/IP socket + :return: dict + """ + + disks = self.get_disks() + + if not disks: + return None + + return dict((d.id, d.temp) for d in disks) + + def check(self): + """ + Parse configuration, check if hddtemp is available, and dynamically create chart lines data + :return: boolean + """ + self._parse_config() + disks = self.get_disks() + + if not disks: + return False + + for d in disks: + dim = [d.id] + self.definitions['temperatures']['lines'].append(dim) + + return True + + @staticmethod + def _check_raw_data(data): + return not bool(data) diff --git a/collectors/python.d.plugin/hddtemp/hddtemp.conf b/collectors/python.d.plugin/hddtemp/hddtemp.conf new file mode 100644 index 00000000..b2d7aef6 --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/hddtemp.conf @@ -0,0 +1,95 @@ +# netdata python.d.plugin configuration for hddtemp +# +# 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, hddtemp also supports the following: +# +# host: 'IP or HOSTNAME' # the host to connect to +# port: PORT # the port to connect to +# + +# By default this module will try to autodetect disks +# (autodetection works only for disk which names start with "sd"). +# However this can be overridden by setting variable `disks` to +# array of desired disks. Example for two disks: +# +# devices: +# - sda +# - sdb +# + +# ---------------------------------------------------------------------- +# AUTO-DETECTION JOBS +# only one of them will run (they have the same name) + +localhost: + name: 'local' + host: 'localhost' + port: 7634 + +localipv4: + name: 'local' + host: '127.0.0.1' + port: 7634 + +localipv6: + name: 'local' + host: '::1' + port: 7634 diff --git a/collectors/python.d.plugin/hddtemp/integrations/hdd_temperature.md b/collectors/python.d.plugin/hddtemp/integrations/hdd_temperature.md new file mode 100644 index 00000000..4a1504f0 --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/integrations/hdd_temperature.md @@ -0,0 +1,217 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/hddtemp/README.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/hddtemp/metadata.yaml" +sidebar_label: "HDD temperature" +learn_status: "Published" +learn_rel_path: "Data Collection/Hardware Devices and Sensors" +most_popular: False +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# HDD temperature + + +<img src="https://netdata.cloud/img/hard-drive.svg" width="150"/> + + +Plugin: python.d.plugin +Module: hddtemp + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This collector monitors disk temperatures. + + +It uses the `hddtemp` daemon to gather the metrics. + + +This collector is only supported on the following platforms: + +- Linux + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +By default, this collector will attempt to connect to the `hddtemp` daemon on `127.0.0.1:7634` + +#### 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 HDD temperature instance + +These metrics refer to the entire monitored application. + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| hddtemp.temperatures | a dimension per disk | Celsius | + + + +## Alerts + +There are no alerts configured by default for this integration. + + +## Setup + +### Prerequisites + +#### Run `hddtemp` in daemon mode + +You can execute `hddtemp` in TCP/IP daemon mode by using the `-d` argument. + +So running `hddtemp -d` would run the daemon, by default on port 7634. + + + +### Configuration + +#### File + +The configuration file name for this integration is `python.d/hddtemp.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/configure/nodes.md#the-netdata-config-directory). + +```bash +cd /etc/netdata 2>/dev/null || cd /opt/netdata/etc/netdata +sudo ./edit-config python.d/hddtemp.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. + +By default this collector will try to autodetect disks (autodetection works only for disk which names start with "sd"). However this can be overridden by setting the option `disks` to an array of desired disks. + + +<details><summary>Config options</summary> + +| Name | Description | Default | Required | +|:----|:-----------|:-------|:--------:| +| update_every | Sets the default data collection frequency. | 1 | 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. | local | no | +| devices | Array of desired disks to detect, in case their name doesn't start with `sd`. | | no | +| host | The IP or HOSTNAME to connect to. | localhost | yes | +| port | The port to connect to. | 7634 | no | + +</details> + +#### Examples + +##### Basic + +A basic example configuration. + +```yaml +localhost: + name: 'local' + host: '127.0.0.1' + port: 7634 + +``` +##### Custom disk names + +An example defining the disk names to detect. + +<details><summary>Config</summary> + +```yaml +localhost: + name: 'local' + host: '127.0.0.1' + port: 7634 + devices: + - customdisk1 + - customdisk2 + +``` +</details> + +##### 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: 7634 + +remote_job: + name : 'remote' + host : 'http://192.0.2.1:2812' + +``` +</details> + + + +## Troubleshooting + +### Debug Mode + +To troubleshoot issues with the `hddtemp` 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 hddtemp debug trace + ``` + + diff --git a/collectors/python.d.plugin/hddtemp/metadata.yaml b/collectors/python.d.plugin/hddtemp/metadata.yaml new file mode 100644 index 00000000..d8b56fc6 --- /dev/null +++ b/collectors/python.d.plugin/hddtemp/metadata.yaml @@ -0,0 +1,163 @@ +plugin_name: python.d.plugin +modules: + - meta: + plugin_name: python.d.plugin + module_name: hddtemp + monitored_instance: + name: HDD temperature + link: https://linux.die.net/man/8/hddtemp + categories: + - data-collection.hardware-devices-and-sensors + icon_filename: "hard-drive.svg" + related_resources: + integrations: + list: [] + info_provided_to_referring_integrations: + description: "" + keywords: + - hardware + - hdd temperature + - disk temperature + - temperature + most_popular: false + overview: + data_collection: + metrics_description: | + This collector monitors disk temperatures. + method_description: | + It uses the `hddtemp` daemon to gather the metrics. + supported_platforms: + include: + - Linux + exclude: [] + multi_instance: true + additional_permissions: + description: "" + default_behavior: + auto_detection: + description: By default, this collector will attempt to connect to the `hddtemp` daemon on `127.0.0.1:7634` + limits: + description: "" + performance_impact: + description: "" + setup: + prerequisites: + list: + - title: Run `hddtemp` in daemon mode + description: | + You can execute `hddtemp` in TCP/IP daemon mode by using the `-d` argument. + + So running `hddtemp -d` would run the daemon, by default on port 7634. + configuration: + file: + name: "python.d/hddtemp.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. + + By default this collector will try to autodetect disks (autodetection works only for disk which names start with "sd"). However this can be overridden by setting the option `disks` to an array of desired disks. + folding: + title: "Config options" + enabled: true + list: + - name: update_every + description: Sets the default data collection frequency. + default_value: 1 + 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: "local" + required: false + - name: devices + description: Array of desired disks to detect, in case their name doesn't start with `sd`. + default_value: "" + required: false + - name: host + description: The IP or HOSTNAME to connect to. + default_value: "localhost" + required: true + - name: port + description: The port to connect to. + default_value: 7634 + required: false + examples: + folding: + enabled: true + title: "Config" + list: + - name: Basic + description: A basic example configuration. + folding: + enabled: false + config: | + localhost: + name: 'local' + host: '127.0.0.1' + port: 7634 + - name: Custom disk names + description: An example defining the disk names to detect. + config: | + localhost: + name: 'local' + host: '127.0.0.1' + port: 7634 + devices: + - customdisk1 + - customdisk2 + - 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: 7634 + + remote_job: + name : 'remote' + host : 'http://192.0.2.1:2812' + troubleshooting: + problems: + list: [] + alerts: [] + metrics: + folding: + title: Metrics + enabled: false + description: "" + availability: [] + scopes: + - name: global + description: "These metrics refer to the entire monitored application." + labels: [] + metrics: + - name: hddtemp.temperatures + description: Disk Temperatures + unit: "Celsius" + chart_type: line + dimensions: + - name: a dimension per disk |