Adding upstream version 1.44.3.upstream/1.44.3upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 547 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 00000000..c2de1172
--- /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 120000
index 00000000..85759ae6
--- /dev/null
+++ b/collectors/python.d.plugin/alarms/README.md
@@ -0,0 +1 @@
+integrations/netdata_agent_alarms.md
\ No newline at end of file
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 00000000..d1942735
--- /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 00000000..06d76c3b
--- /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: ''
diff --git a/collectors/python.d.plugin/alarms/integrations/netdata_agent_alarms.md b/collectors/python.d.plugin/alarms/integrations/netdata_agent_alarms.md
new file mode 100644
index 00000000..9fb69878
--- /dev/null
+++ b/collectors/python.d.plugin/alarms/integrations/netdata_agent_alarms.md
@@ -0,0 +1,201 @@
+<!--startmeta
+custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/alarms/README.md"
+meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/alarms/metadata.yaml"
+sidebar_label: "Netdata Agent alarms"
+learn_status: "Published"
+learn_rel_path: "Data Collection/Other"
+most_popular: False
+message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE"
+endmeta-->
+
+# Netdata Agent alarms
+
+Plugin: python.d.plugin
+Module: alarms
+
+<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" />
+
+## Overview
+
+This collector creates an 'Alarms' menu with one line plot of `alarms.status`.
+
+
+Alarm status is read from the Netdata agent rest api [`/api/v1/alarms?all`](https://learn.netdata.cloud/api#/alerts/alerts1).
+
+
+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
+
+It discovers instances of Netdata running on localhost, and gathers metrics from `http://127.0.0.1:19999/api/v1/alarms?all`. `CLEAR` status is mapped to `0`, `WARNING` to `1` and `CRITICAL` to `2`. Also, by default all alarms produced will be monitored.
+
+
+#### 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 Netdata Agent alarms instance
+
+These metrics refer to the entire monitored application.
+
+
+This scope has no labels.
+
+Metrics:
+
+| Metric | Dimensions | Unit |
+|:------|:----------|:----|
+| alarms.status | a dimension per alarm representing the latest status of the alarm. | status |
+| alarms.values | a dimension per alarm representing the latest collected value of the alarm. | value |
+
+
+
+## Alerts
+
+There are no alerts configured by default for this integration.
+
+
+## Setup
+
+### Prerequisites
+
+No action required.
+
+### Configuration
+
+#### File
+
+The configuration file name for this integration is `python.d/alarms.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/alarms.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 |
+|:----|:-----------|:-------|:--------:|
+| url | Netdata agent alarms endpoint to collect from. Can be local or remote so long as reachable by agent. | http://127.0.0.1:19999/api/v1/alarms?all | yes |
+| status_map | Mapping of alarm status to integer number that will be the metric value collected. | {"CLEAR": 0, "WARNING": 1, "CRITICAL": 2} | yes |
+| collect_alarm_values | set to true to include a chart with calculated alarm values over time. | no | yes |
+| alarm_status_chart_type | define the type of chart for plotting status over time e.g. 'line' or 'stacked'. | line | yes |
+| alarm_contains_words | 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. |  | yes |
+| alarm_excludes_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. |  | yes |
+| update_every | Sets the default data collection frequency. | 10 | 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 |
+
+</details>
+
+#### Examples
+
+##### Basic
+
+A basic example configuration.
+
+```yaml
+jobs:
+  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+
+```
+##### Advanced
+
+An advanced example configuration with multiple jobs collecting different subsets of alarms for plotting on different charts.
+"ML" job will collect status and values for all alarms with "ml_" in the name. Default job will collect status for all other alarms.
+
+
+<details><summary>Config</summary>
+
+```yaml
+ML:
+  update_every: 5
+  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+  status_map:
+    CLEAR: 0
+    WARNING: 1
+    CRITICAL: 2
+  collect_alarm_values: true
+  alarm_status_chart_type: 'stacked'
+  alarm_contains_words: 'ml_'
+
+Default:
+  update_every: 5
+  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+  status_map:
+    CLEAR: 0
+    WARNING: 1
+    CRITICAL: 2
+  collect_alarm_values: false
+  alarm_status_chart_type: 'stacked'
+  alarm_excludes_words: 'ml_'
+
+```
+</details>
+
+
+
+## Troubleshooting
+
+### Debug Mode
+
+To troubleshoot issues with the `alarms` 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 alarms debug trace
+  ```
+
+
diff --git a/collectors/python.d.plugin/alarms/metadata.yaml b/collectors/python.d.plugin/alarms/metadata.yaml
new file mode 100644
index 00000000..30a89778
--- /dev/null
+++ b/collectors/python.d.plugin/alarms/metadata.yaml
@@ -0,0 +1,177 @@
+plugin_name: python.d.plugin
+modules:
+  - meta:
+      plugin_name: python.d.plugin
+      module_name: alarms
+      monitored_instance:
+        name: Netdata Agent alarms
+        link: https://github.com/netdata/netdata/blob/master/collectors/python.d.plugin/alarms/README.md
+        categories:
+          - data-collection.other
+        icon_filename: ""
+      related_resources:
+        integrations:
+          list: []
+      info_provided_to_referring_integrations:
+        description: ""
+      keywords:
+        - alarms
+        - netdata
+      most_popular: false
+    overview:
+      data_collection:
+        metrics_description: |
+          This collector creates an 'Alarms' menu with one line plot of `alarms.status`.
+        method_description: |
+          Alarm status is read from the Netdata agent rest api [`/api/v1/alarms?all`](https://learn.netdata.cloud/api#/alerts/alerts1).
+      supported_platforms:
+        include: []
+        exclude: []
+      multi_instance: true
+      additional_permissions:
+        description: ""
+      default_behavior:
+        auto_detection:
+          description: |
+            It discovers instances of Netdata running on localhost, and gathers metrics from `http://127.0.0.1:19999/api/v1/alarms?all`. `CLEAR` status is mapped to `0`, `WARNING` to `1` and `CRITICAL` to `2`. Also, by default all alarms produced will be monitored.
+        limits:
+          description: ""
+        performance_impact:
+          description: ""
+    setup:
+      prerequisites:
+        list: []
+      configuration:
+        file:
+          name: python.d/alarms.conf
+          description: ""
+        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: url
+              description: Netdata agent alarms endpoint to collect from. Can be local or remote so long as reachable by agent.
+              default_value: http://127.0.0.1:19999/api/v1/alarms?all
+              required: true
+            - name: status_map
+              description: Mapping of alarm status to integer number that will be the metric value collected.
+              default_value: '{"CLEAR": 0, "WARNING": 1, "CRITICAL": 2}'
+              required: true
+            - name: collect_alarm_values
+              description: set to true to include a chart with calculated alarm values over time.
+              default_value: false
+              required: true
+            - name: alarm_status_chart_type
+              description: define the type of chart for plotting status over time e.g. 'line' or 'stacked'.
+              default_value: "line"
+              required: true
+            - name: alarm_contains_words
+              description: >
+                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.
+              default_value: ""
+              required: true
+            - name: alarm_excludes_words
+              description: >
+                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.
+              default_value: ""
+              required: true
+            - name: update_every
+              description: Sets the default data collection frequency.
+              default_value: 10
+              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
+        examples:
+          folding:
+            enabled: true
+            title: Config
+          list:
+            - name: Basic
+              folding:
+                enabled: false
+              description: A basic example configuration.
+              config: |
+                jobs:
+                  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+            - name: Advanced
+              folding:
+                enabled: true
+              description: |
+                An advanced example configuration with multiple jobs collecting different subsets of alarms for plotting on different charts.
+                "ML" job will collect status and values for all alarms with "ml_" in the name. Default job will collect status for all other alarms.
+              config: |
+                ML:
+                  update_every: 5
+                  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+                  status_map:
+                    CLEAR: 0
+                    WARNING: 1
+                    CRITICAL: 2
+                  collect_alarm_values: true
+                  alarm_status_chart_type: 'stacked'
+                  alarm_contains_words: 'ml_'
+                
+                Default:
+                  update_every: 5
+                  url: 'http://127.0.0.1:19999/api/v1/alarms?all'
+                  status_map:
+                    CLEAR: 0
+                    WARNING: 1
+                    CRITICAL: 2
+                  collect_alarm_values: false
+                  alarm_status_chart_type: 'stacked'
+                  alarm_excludes_words: 'ml_'
+    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: alarms.status
+              description: Alarms ({status mapping})
+              unit: "status"
+              chart_type: line
+              dimensions:
+                - name: a dimension per alarm representing the latest status of the alarm.
+            - name: alarms.values
+              description: Alarm Values
+              unit: "value"
+              chart_type: line
+              dimensions:
+                - name: a dimension per alarm representing the latest collected value of the alarm.