diff options
Diffstat (limited to '')
| -rw-r--r-- | collectors/python.d.plugin/alarms/Makefile.inc | 13 | ||||
| -rw-r--r-- | collectors/python.d.plugin/alarms/README.md | 66 | ||||
| -rw-r--r-- | collectors/python.d.plugin/alarms/alarms.chart.py | 95 | ||||
| -rw-r--r-- | collectors/python.d.plugin/alarms/alarms.conf | 60 |
4 files changed, 234 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/alarms/Makefile.inc b/collectors/python.d.plugin/alarms/Makefile.inc new file mode 100644 index 0000000..c2de117 --- /dev/null +++ b/collectors/python.d.plugin/alarms/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 += alarms/alarms.chart.py +dist_pythonconfig_DATA += alarms/alarms.conf + +# do not install these files, but include them in the distribution +dist_noinst_DATA += alarms/README.md alarms/Makefile.inc + diff --git a/collectors/python.d.plugin/alarms/README.md b/collectors/python.d.plugin/alarms/README.md new file mode 100644 index 0000000..8dc666f --- /dev/null +++ b/collectors/python.d.plugin/alarms/README.md @@ -0,0 +1,66 @@ +<!-- +title: "Alarms" +custom_edit_url: https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/alarms/README.md +--> + +# Alarms - graphing Netdata alarm states over time + +This collector creates an 'Alarms' menu with one line plot showing alarm states over time. Alarm states are mapped to integer values according to the below default mapping. Any alarm status types not in this mapping will be ignored (Note: This mapping can be changed by editing the `status_map` in the `alarms.conf` file). If you would like to learn more about the different alarm statuses check out the docs [here](https://learn.netdata.cloud/docs/agent/health/reference#alarm-statuses). + +``` +{ + 'CLEAR': 0, + 'WARNING': 1, + 'CRITICAL': 2 +} +``` + +## Charts + +Below is an example of the chart produced when running `stress-ng --all 2` for a few minutes. You can see the various warning and critical alarms raised. + + + +## Configuration + +Enable the collector and [restart Netdata](/docs/configure/start-stop-restart.md). + +```bash +cd /etc/netdata/ +sudo ./edit-config python.d.conf +# Set `alarms: no` to `alarms: yes` +sudo systemctl restart netdata +``` + +If needed, edit the `python.d/alarms.conf` configuration file using `edit-config` from the your agent's [config +directory](/docs/configure/nodes.md), which is usually at `/etc/netdata`. + +```bash +cd /etc/netdata # Replace this path with your Netdata config directory, if different +sudo ./edit-config python.d/alarms.conf +``` + +The `alarms` specific part of the `alarms.conf` file should look like this: + +```yaml +# what url to pull data from +local: + url: 'http://127.0.0.1:19999/api/v1/alarms?all' + # define how to map alarm status to numbers for the chart + status_map: + CLEAR: 0 + WARNING: 1 + CRITICAL: 2 + # set to true to include a chart with calculated alarm values over time + collect_alarm_values: false + # define the type of chart for plotting status over time e.g. 'line' or 'stacked' + alarm_status_chart_type: 'line' + # a "," separated list of words you want to filter alarm names for. For example 'cpu,load' would filter for only + # alarms with "cpu" or "load" in alarm name. Default includes all. + alarm_contains_words: '' + # a "," separated list of words you want to exclude based on alarm name. For example 'cpu,load' would exclude + # all alarms with "cpu" or "load" in alarm name. Default excludes None. + alarm_excludes_words: '' +``` + +It will default to pulling all alarms at each time step from the Netdata rest api at `http://127.0.0.1:19999/api/v1/alarms?all` diff --git a/collectors/python.d.plugin/alarms/alarms.chart.py b/collectors/python.d.plugin/alarms/alarms.chart.py new file mode 100644 index 0000000..d194273 --- /dev/null +++ b/collectors/python.d.plugin/alarms/alarms.chart.py @@ -0,0 +1,95 @@ +# -*- coding: utf-8 -*- +# Description: alarms netdata python.d module +# Author: andrewm4894 +# SPDX-License-Identifier: GPL-3.0-or-later + +from json import loads + +from bases.FrameworkServices.UrlService import UrlService + +update_every = 10 +disabled_by_default = True + + +def charts_template(sm, alarm_status_chart_type='line'): + order = [ + 'alarms', + 'values' + ] + + mappings = ', '.join(['{0}={1}'.format(k, v) for k, v in sm.items()]) + charts = { + 'alarms': { + 'options': [None, 'Alarms ({0})'.format(mappings), 'status', 'status', 'alarms.status', alarm_status_chart_type], + 'lines': [], + 'variables': [ + ['alarms_num'], + ] + }, + 'values': { + 'options': [None, 'Alarm Values', 'value', 'value', 'alarms.value', 'line'], + 'lines': [], + } + } + return order, charts + + +DEFAULT_STATUS_MAP = {'CLEAR': 0, 'WARNING': 1, 'CRITICAL': 2} +DEFAULT_URL = 'http://127.0.0.1:19999/api/v1/alarms?all' +DEFAULT_COLLECT_ALARM_VALUES = False +DEFAULT_ALARM_STATUS_CHART_TYPE = 'line' +DEFAULT_ALARM_CONTAINS_WORDS = '' +DEFAULT_ALARM_EXCLUDES_WORDS = '' + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + self.sm = self.configuration.get('status_map', DEFAULT_STATUS_MAP) + self.alarm_status_chart_type = self.configuration.get('alarm_status_chart_type', DEFAULT_ALARM_STATUS_CHART_TYPE) + self.order, self.definitions = charts_template(self.sm, self.alarm_status_chart_type) + self.url = self.configuration.get('url', DEFAULT_URL) + self.collect_alarm_values = bool(self.configuration.get('collect_alarm_values', DEFAULT_COLLECT_ALARM_VALUES)) + self.collected_dims = {'alarms': set(), 'values': set()} + self.alarm_contains_words = self.configuration.get('alarm_contains_words', DEFAULT_ALARM_CONTAINS_WORDS) + self.alarm_contains_words_list = [alarm_contains_word.lstrip(' ').rstrip(' ') for alarm_contains_word in self.alarm_contains_words.split(',')] + self.alarm_excludes_words = self.configuration.get('alarm_excludes_words', DEFAULT_ALARM_EXCLUDES_WORDS) + self.alarm_excludes_words_list = [alarm_excludes_word.lstrip(' ').rstrip(' ') for alarm_excludes_word in self.alarm_excludes_words.split(',')] + + def _get_data(self): + raw_data = self._get_raw_data() + if raw_data is None: + return None + + raw_data = loads(raw_data) + alarms = raw_data.get('alarms', {}) + if self.alarm_contains_words != '': + alarms = {alarm_name: alarms[alarm_name] for alarm_name in alarms for alarm_contains_word in + self.alarm_contains_words_list if alarm_contains_word in alarm_name} + if self.alarm_excludes_words != '': + alarms = {alarm_name: alarms[alarm_name] for alarm_name in alarms for alarm_excludes_word in + self.alarm_excludes_words_list if alarm_excludes_word not in alarm_name} + + data = {a: self.sm[alarms[a]['status']] for a in alarms if alarms[a]['status'] in self.sm} + self.update_charts('alarms', data) + data['alarms_num'] = len(data) + + if self.collect_alarm_values: + data_values = {'{}_value'.format(a): alarms[a]['value'] * 100 for a in alarms if 'value' in alarms[a] and alarms[a]['value'] is not None} + self.update_charts('values', data_values, divisor=100) + data.update(data_values) + + return data + + def update_charts(self, chart, data, algorithm='absolute', multiplier=1, divisor=1): + if not self.charts: + return + + for dim in data: + if dim not in self.collected_dims[chart]: + self.collected_dims[chart].add(dim) + self.charts[chart].add_dimension([dim, dim, algorithm, multiplier, divisor]) + + for dim in list(self.collected_dims[chart]): + if dim not in data: + self.collected_dims[chart].remove(dim) + self.charts[chart].del_dimension(dim, hide=False) diff --git a/collectors/python.d.plugin/alarms/alarms.conf b/collectors/python.d.plugin/alarms/alarms.conf new file mode 100644 index 0000000..06d76c3 --- /dev/null +++ b/collectors/python.d.plugin/alarms/alarms.conf @@ -0,0 +1,60 @@ +# netdata python.d.plugin configuration for example +# +# 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: 10 + +# 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) + +# what url to pull data from +local: + url: 'http://127.0.0.1:19999/api/v1/alarms?all' + # define how to map alarm status to numbers for the chart + status_map: + CLEAR: 0 + WARNING: 1 + CRITICAL: 2 + # set to true to include a chart with calculated alarm values over time + collect_alarm_values: false + # define the type of chart for plotting status over time e.g. 'line' or 'stacked' + alarm_status_chart_type: 'line' + # a "," separated list of words you want to filter alarm names for. For example 'cpu,load' would filter for only + # alarms with "cpu" or "load" in alarm name. Default includes all. + alarm_contains_words: '' + # a "," separated list of words you want to exclude based on alarm name. For example 'cpu,load' would exclude + # all alarms with "cpu" or "load" in alarm name. Default excludes None. + alarm_excludes_words: '' |