diff options
Diffstat (limited to 'src/collectors/python.d.plugin/bind_rndc')
5 files changed, 767 insertions, 0 deletions
diff --git a/src/collectors/python.d.plugin/bind_rndc/README.md b/src/collectors/python.d.plugin/bind_rndc/README.md new file mode 120000 index 000000000..03a182ae8 --- /dev/null +++ b/src/collectors/python.d.plugin/bind_rndc/README.md @@ -0,0 +1 @@ +integrations/isc_bind_rndc.md
\ No newline at end of file diff --git a/src/collectors/python.d.plugin/bind_rndc/bind_rndc.chart.py b/src/collectors/python.d.plugin/bind_rndc/bind_rndc.chart.py new file mode 100644 index 000000000..9d6c9fec7 --- /dev/null +++ b/src/collectors/python.d.plugin/bind_rndc/bind_rndc.chart.py @@ -0,0 +1,252 @@ +# -*- coding: utf-8 -*- +# Description: bind rndc netdata python.d module +# Author: ilyam8 +# SPDX-License-Identifier: GPL-3.0-or-later + +import os +from collections import defaultdict +from subprocess import Popen + +from bases.FrameworkServices.SimpleService import SimpleService +from bases.collection import find_binary + +update_every = 30 + +ORDER = [ + 'name_server_statistics', + 'incoming_queries', + 'outgoing_queries', + 'named_stats_size', +] + +CHARTS = { + 'name_server_statistics': { + 'options': [None, 'Name Server Statistics', 'stats', 'name server statistics', + 'bind_rndc.name_server_statistics', 'line'], + 'lines': [ + ['nms_requests', 'requests', 'incremental'], + ['nms_rejected_queries', 'rejected_queries', 'incremental'], + ['nms_success', 'success', 'incremental'], + ['nms_failure', 'failure', 'incremental'], + ['nms_responses', 'responses', 'incremental'], + ['nms_duplicate', 'duplicate', 'incremental'], + ['nms_recursion', 'recursion', 'incremental'], + ['nms_nxrrset', 'nxrrset', 'incremental'], + ['nms_nxdomain', 'nxdomain', 'incremental'], + ['nms_non_auth_answer', 'non_auth_answer', 'incremental'], + ['nms_auth_answer', 'auth_answer', 'incremental'], + ['nms_dropped_queries', 'dropped_queries', 'incremental'], + ]}, + 'incoming_queries': { + 'options': [None, 'Incoming Queries', 'queries', 'incoming queries', 'bind_rndc.incoming_queries', 'line'], + 'lines': [ + ]}, + 'outgoing_queries': { + 'options': [None, 'Outgoing Queries', 'queries', 'outgoing queries', 'bind_rndc.outgoing_queries', 'line'], + 'lines': [ + ]}, + 'named_stats_size': { + 'options': [None, 'Named Stats File Size', 'MiB', 'file size', 'bind_rndc.stats_size', 'line'], + 'lines': [ + ['stats_size', None, 'absolute', 1, 1 << 20] + ] + } +} + +NMS = { + 'nms_requests': [ + 'IPv4 requests received', + 'IPv6 requests received', + 'TCP requests received', + 'requests with EDNS(0) receive' + ], + 'nms_responses': [ + 'responses sent', + 'truncated responses sent', + 'responses with EDNS(0) sent', + 'requests with unsupported EDNS version received' + ], + 'nms_failure': [ + 'other query failures', + 'queries resulted in SERVFAIL' + ], + 'nms_auth_answer': ['queries resulted in authoritative answer'], + 'nms_non_auth_answer': ['queries resulted in non authoritative answer'], + 'nms_nxrrset': ['queries resulted in nxrrset'], + 'nms_success': ['queries resulted in successful answer'], + 'nms_nxdomain': ['queries resulted in NXDOMAIN'], + 'nms_recursion': ['queries caused recursion'], + 'nms_duplicate': ['duplicate queries received'], + 'nms_rejected_queries': [ + 'auth queries rejected', + 'recursive queries rejected' + ], + 'nms_dropped_queries': ['queries dropped'] +} + +STATS = ['Name Server Statistics', 'Incoming Queries', 'Outgoing Queries'] + + +class Service(SimpleService): + def __init__(self, configuration=None, name=None): + SimpleService.__init__(self, configuration=configuration, name=name) + self.order = ORDER + self.definitions = CHARTS + self.named_stats_path = self.configuration.get('named_stats_path', '/var/log/bind/named.stats') + self.rndc = find_binary('rndc') + self.data = dict( + nms_requests=0, + nms_responses=0, + nms_failure=0, + nms_auth=0, + nms_non_auth=0, + nms_nxrrset=0, + nms_success=0, + nms_nxdomain=0, + nms_recursion=0, + nms_duplicate=0, + nms_rejected_queries=0, + nms_dropped_queries=0, + ) + + def check(self): + if not self.rndc: + self.error('Can\'t locate "rndc" binary or binary is not executable by netdata') + return False + + if not (os.path.isfile(self.named_stats_path) and os.access(self.named_stats_path, os.R_OK)): + self.error('Cannot access file %s' % self.named_stats_path) + return False + + run_rndc = Popen([self.rndc, 'stats'], shell=False) + run_rndc.wait() + + if not run_rndc.returncode: + return True + self.error('Not enough permissions to run "%s stats"' % self.rndc) + return False + + def _get_raw_data(self): + """ + Run 'rndc stats' and read last dump from named.stats + :return: dict + """ + result = dict() + try: + current_size = os.path.getsize(self.named_stats_path) + run_rndc = Popen([self.rndc, 'stats'], shell=False) + run_rndc.wait() + + if run_rndc.returncode: + return None + with open(self.named_stats_path) as named_stats: + named_stats.seek(current_size) + result['stats'] = named_stats.readlines() + result['size'] = current_size + return result + except (OSError, IOError): + return None + + def _get_data(self): + """ + Parse data from _get_raw_data() + :return: dict + """ + + raw_data = self._get_raw_data() + + if raw_data is None: + return None + parsed = dict() + for stat in STATS: + parsed[stat] = parse_stats(field=stat, + named_stats=raw_data['stats']) + + self.data.update(nms_mapper(data=parsed['Name Server Statistics'])) + + for elem in zip(['Incoming Queries', 'Outgoing Queries'], ['incoming_queries', 'outgoing_queries']): + parsed_key, chart_name = elem[0], elem[1] + for dimension_id, value in queries_mapper(data=parsed[parsed_key], + add=chart_name[:9]).items(): + + if dimension_id not in self.data: + dimension = dimension_id.replace(chart_name[:9], '') + if dimension_id not in self.charts[chart_name]: + self.charts[chart_name].add_dimension([dimension_id, dimension, 'incremental']) + + self.data[dimension_id] = value + + self.data['stats_size'] = raw_data['size'] + return self.data + + +def parse_stats(field, named_stats): + """ + :param field: str: + :param named_stats: list: + :return: dict + + Example: + filed: 'Incoming Queries' + names_stats (list of lines): + ++ Incoming Requests ++ + 1405660 QUERY + 3 NOTIFY + ++ Incoming Queries ++ + 1214961 A + 75 NS + 2 CNAME + 2897 SOA + 35544 PTR + 14 MX + 5822 TXT + 145974 AAAA + 371 SRV + ++ Outgoing Queries ++ + ... + + result: + {'A', 1214961, 'NS': 75, 'CNAME': 2, 'SOA': 2897, ...} + """ + data = dict() + ns = iter(named_stats) + for line in ns: + if field not in line: + continue + while True: + try: + line = next(ns) + except StopIteration: + break + if '++' not in line: + if '[' in line: + continue + v, k = line.strip().split(' ', 1) + if k not in data: + data[k] = 0 + data[k] += int(v) + continue + break + break + return data + + +def nms_mapper(data): + """ + :param data: dict + :return: dict(defaultdict) + """ + result = defaultdict(int) + for k, v in NMS.items(): + for elem in v: + result[k] += data.get(elem, 0) + return result + + +def queries_mapper(data, add): + """ + :param data: dict + :param add: str + :return: dict + """ + return dict([(add + k, v) for k, v in data.items()]) diff --git a/src/collectors/python.d.plugin/bind_rndc/bind_rndc.conf b/src/collectors/python.d.plugin/bind_rndc/bind_rndc.conf new file mode 100644 index 000000000..84eaf0594 --- /dev/null +++ b/src/collectors/python.d.plugin/bind_rndc/bind_rndc.conf @@ -0,0 +1,108 @@ +# netdata python.d.plugin configuration for bind_rndc +# +# 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, bind_rndc also supports the following: +# +# named_stats_path: 'path to named.stats' # Default: '/var/log/bind/named.stats' +#------------------------------------------------------------------------------------------------------------------ +# Important Information +# +# BIND appends logs at EVERY RUN. It is NOT RECOMMENDED to set update_every below 30 sec. +# It is STRONGLY RECOMMENDED to create a bind-rndc.conf file for logrotate. +# +# To set up your BIND to dump stats do the following: +# +# 1. Add to 'named.conf.options' options {}: +# statistics-file "/var/log/bind/named.stats"; +# +# 2. Create bind/ directory in /var/log +# cd /var/log/ && mkdir bind +# +# 3. Change owner of directory to 'bind' user +# chown bind bind/ +# +# 4. RELOAD (NOT restart) BIND +# systemctl reload bind9.service +# +# 5. Run as a root 'rndc stats' to dump (BIND will create named.stats in new directory) +# +# To allow Netdata to run 'rndc stats' change '/etc/bind/rndc.key' group to netdata +# chown :netdata rndc.key +# +# Last, BUT NOT least, is to create bind-rndc.conf in logrotate.d/: +# +# /var/log/bind/named.stats { +# +# daily +# rotate 4 +# compress +# delaycompress +# create 0644 bind bind +# missingok +# postrotate +# rndc reload > /dev/null +# endscript +# } +# +# To test your logrotate conf file run as root: +# logrotate /etc/logrotate.d/bind-rndc -d (debug dry-run mode) +# +# ---------------------------------------------------------------------- diff --git a/src/collectors/python.d.plugin/bind_rndc/integrations/isc_bind_rndc.md b/src/collectors/python.d.plugin/bind_rndc/integrations/isc_bind_rndc.md new file mode 100644 index 000000000..0607e47da --- /dev/null +++ b/src/collectors/python.d.plugin/bind_rndc/integrations/isc_bind_rndc.md @@ -0,0 +1,215 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/bind_rndc/README.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/bind_rndc/metadata.yaml" +sidebar_label: "ISC Bind (RNDC)" +learn_status: "Published" +learn_rel_path: "Collecting Metrics/DNS and DHCP Servers" +most_popular: False +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# ISC Bind (RNDC) + + +<img src="https://netdata.cloud/img/isc.png" width="150"/> + + +Plugin: python.d.plugin +Module: bind_rndc + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +Monitor ISCBind (RNDC) performance for optimal DNS server operations. Monitor query rates, response times, and error rates to ensure reliable DNS service delivery. + +This collector uses the `rndc` tool to dump (named.stats) statistics then read them to gather Bind Name Server summary performance metrics. + +This collector is supported on all platforms. + +This collector only supports collecting metrics from a single instance of this integration. + + +### Default Behavior + +#### Auto-Detection + +If no configuration is given, the collector will attempt to read named.stats file at `/var/log/bind/named.stats` + +#### 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 ISC Bind (RNDC) instance + +These metrics refer to the entire monitored application. + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| bind_rndc.name_server_statistics | requests, rejected_queries, success, failure, responses, duplicate, recursion, nxrrset, nxdomain, non_auth_answer, auth_answer, dropped_queries | stats | +| bind_rndc.incoming_queries | a dimension per incoming query type | queries | +| bind_rndc.outgoing_queries | a dimension per outgoing query type | queries | +| bind_rndc.stats_size | stats_size | MiB | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ bind_rndc_stats_file_size ](https://github.com/netdata/netdata/blob/master/src/health/health.d/bind_rndc.conf) | bind_rndc.stats_size | BIND statistics-file size | + + +## Setup + +### Prerequisites + +#### Minimum bind version and permissions + +Version of bind must be >=9.6 and the Netdata user must have permissions to run `rndc stats` + +#### Setup log rotate for bind stats + +BIND appends logs at EVERY RUN. It is NOT RECOMMENDED to set `update_every` below 30 sec. +It is STRONGLY RECOMMENDED to create a `bind-rndc.conf` file for logrotate. + +To set up BIND to dump stats do the following: + +1. Add to 'named.conf.options' options {}: +`statistics-file "/var/log/bind/named.stats";` + +2. Create bind/ directory in /var/log: +`cd /var/log/ && mkdir bind` + +3. Change owner of directory to 'bind' user: +`chown bind bind/` + +4. RELOAD (NOT restart) BIND: +`systemctl reload bind9.service` + +5. Run as a root 'rndc stats' to dump (BIND will create named.stats in new directory) + +To allow Netdata to run 'rndc stats' change '/etc/bind/rndc.key' group to netdata: +`chown :netdata rndc.key` + +Last, BUT NOT least, is to create bind-rndc.conf in logrotate.d/: +``` +/var/log/bind/named.stats { + + daily + rotate 4 + compress + delaycompress + create 0644 bind bind + missingok + postrotate + rndc reload > /dev/null + endscript +} +``` +To test your logrotate conf file run as root: +`logrotate /etc/logrotate.d/bind-rndc -d (debug dry-run mode)` + + + +### Configuration + +#### File + +The configuration file name for this integration is `python.d/bind_rndc.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/bind_rndc.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 | +| named_stats_path | Path to the named stats, after being dumped by `nrdc` | /var/log/bind/named.stats | no | + +</details> + +#### Examples + +##### Local bind stats + +Define a local path to bind stats file + +```yaml +local: + named_stats_path: '/var/log/bind/named.stats' + +``` + + +## Troubleshooting + +### Debug Mode + +To troubleshoot issues with the `bind_rndc` 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 bind_rndc debug trace + ``` + + diff --git a/src/collectors/python.d.plugin/bind_rndc/metadata.yaml b/src/collectors/python.d.plugin/bind_rndc/metadata.yaml new file mode 100644 index 000000000..8cbbbed15 --- /dev/null +++ b/src/collectors/python.d.plugin/bind_rndc/metadata.yaml @@ -0,0 +1,191 @@ +plugin_name: python.d.plugin +modules: + - meta: + plugin_name: python.d.plugin + module_name: bind_rndc + monitored_instance: + name: ISC Bind (RNDC) + link: "https://www.isc.org/bind/" + categories: + - data-collection.dns-and-dhcp-servers + icon_filename: "isc.png" + related_resources: + integrations: + list: [] + info_provided_to_referring_integrations: + description: "" + keywords: + - dns + - bind + - server + most_popular: false + overview: + data_collection: + metrics_description: "Monitor ISCBind (RNDC) performance for optimal DNS server operations. Monitor query rates, response times, and error rates to ensure reliable DNS service delivery." + method_description: "This collector uses the `rndc` tool to dump (named.stats) statistics then read them to gather Bind Name Server summary performance metrics." + supported_platforms: + include: [] + exclude: [] + multi_instance: false + additional_permissions: + description: "" + default_behavior: + auto_detection: + description: "If no configuration is given, the collector will attempt to read named.stats file at `/var/log/bind/named.stats`" + limits: + description: "" + performance_impact: + description: "" + setup: + prerequisites: + list: + - title: "Minimum bind version and permissions" + description: "Version of bind must be >=9.6 and the Netdata user must have permissions to run `rndc stats`" + - title: "Setup log rotate for bind stats" + description: | + BIND appends logs at EVERY RUN. It is NOT RECOMMENDED to set `update_every` below 30 sec. + It is STRONGLY RECOMMENDED to create a `bind-rndc.conf` file for logrotate. + + To set up BIND to dump stats do the following: + + 1. Add to 'named.conf.options' options {}: + `statistics-file "/var/log/bind/named.stats";` + + 2. Create bind/ directory in /var/log: + `cd /var/log/ && mkdir bind` + + 3. Change owner of directory to 'bind' user: + `chown bind bind/` + + 4. RELOAD (NOT restart) BIND: + `systemctl reload bind9.service` + + 5. Run as a root 'rndc stats' to dump (BIND will create named.stats in new directory) + + To allow Netdata to run 'rndc stats' change '/etc/bind/rndc.key' group to netdata: + `chown :netdata rndc.key` + + Last, BUT NOT least, is to create bind-rndc.conf in logrotate.d/: + ``` + /var/log/bind/named.stats { + + daily + rotate 4 + compress + delaycompress + create 0644 bind bind + missingok + postrotate + rndc reload > /dev/null + endscript + } + ``` + To test your logrotate conf file run as root: + `logrotate /etc/logrotate.d/bind-rndc -d (debug dry-run mode)` + configuration: + file: + name: python.d/bind_rndc.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: named_stats_path + description: Path to the named stats, after being dumped by `nrdc` + default_value: "/var/log/bind/named.stats" + required: false + examples: + folding: + enabled: false + title: "Config" + list: + - name: Local bind stats + description: Define a local path to bind stats file + config: | + local: + named_stats_path: '/var/log/bind/named.stats' + troubleshooting: + problems: + list: [] + alerts: + - name: bind_rndc_stats_file_size + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/bind_rndc.conf + metric: bind_rndc.stats_size + info: BIND statistics-file size + metrics: + folding: + title: Metrics + enabled: false + description: "" + availability: [] + scopes: + - name: global + description: "These metrics refer to the entire monitored application." + labels: [] + metrics: + - name: bind_rndc.name_server_statistics + description: Name Server Statistics + unit: "stats" + chart_type: line + dimensions: + - name: requests + - name: rejected_queries + - name: success + - name: failure + - name: responses + - name: duplicate + - name: recursion + - name: nxrrset + - name: nxdomain + - name: non_auth_answer + - name: auth_answer + - name: dropped_queries + - name: bind_rndc.incoming_queries + description: Incoming queries + unit: "queries" + chart_type: line + dimensions: + - name: a dimension per incoming query type + - name: bind_rndc.outgoing_queries + description: Outgoing queries + unit: "queries" + chart_type: line + dimensions: + - name: a dimension per outgoing query type + - name: bind_rndc.stats_size + description: Named Stats File Size + unit: "MiB" + chart_type: line + dimensions: + - name: stats_size |