diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 14:31:17 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 14:31:17 +0000 |
commit | 8020f71afd34d7696d7933659df2d763ab05542f (patch) | |
tree | 2fdf1b5447ffd8bdd61e702ca183e814afdcb4fc /collectors/python.d.plugin/varnish | |
parent | Initial commit. (diff) | |
download | netdata-upstream.tar.xz netdata-upstream.zip |
Adding upstream version 1.37.1.upstream/1.37.1upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'collectors/python.d.plugin/varnish')
-rw-r--r-- | collectors/python.d.plugin/varnish/Makefile.inc | 13 | ||||
-rw-r--r-- | collectors/python.d.plugin/varnish/README.md | 65 | ||||
-rw-r--r-- | collectors/python.d.plugin/varnish/varnish.chart.py | 385 | ||||
-rw-r--r-- | collectors/python.d.plugin/varnish/varnish.conf | 66 |
4 files changed, 529 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/varnish/Makefile.inc b/collectors/python.d.plugin/varnish/Makefile.inc new file mode 100644 index 0000000..2469b05 --- /dev/null +++ b/collectors/python.d.plugin/varnish/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 += varnish/varnish.chart.py +dist_pythonconfig_DATA += varnish/varnish.conf + +# do not install these files, but include them in the distribution +dist_noinst_DATA += varnish/README.md varnish/Makefile.inc + diff --git a/collectors/python.d.plugin/varnish/README.md b/collectors/python.d.plugin/varnish/README.md new file mode 100644 index 0000000..018905f --- /dev/null +++ b/collectors/python.d.plugin/varnish/README.md @@ -0,0 +1,65 @@ +<!-- +title: "Varnish Cache monitoring with Netdata" +custom_edit_url: https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/varnish/README.md +sidebar_label: "Varnish Cache" +--> + +# Varnish Cache monitoring with Netdata + +Provides HTTP accelerator global, Backends (VBE) and Storages (SMF, SMA, MSE) statistics using `varnishstat` tool. + +Note that both, Varnish-Cache (free and open source) and Varnish-Plus (Commercial/Enterprise version), are supported. + +## Requirements + +- `netdata` user must be a member of the `varnish` group + +## Charts + +This module produces the following charts: + +- Connections Statistics in `connections/s` +- Client Requests in `requests/s` +- All History Hit Rate Ratio in `percent` +- Current Poll Hit Rate Ratio in `percent` +- Expired Objects in `expired/s` +- Least Recently Used Nuked Objects in `nuked/s` +- Number Of Threads In All Pools in `pools` +- Threads Statistics in `threads/s` +- Current Queue Length in `requests` +- Backend Connections Statistics in `connections/s` +- Requests To The Backend in `requests/s` +- ESI Statistics in `problems/s` +- Memory Usage in `MiB` +- Uptime in `seconds` + +For every backend (VBE): + +- Backend Response Statistics in `kilobits/s` + +For every storage (SMF, SMA, or MSE): + +- Storage Usage in `KiB` +- Storage Allocated Objects + +## Configuration + +Edit the `python.d/varnish.conf` configuration file using `edit-config` from the Netdata [config +directory](/docs/configure/nodes.md), which is typically at `/etc/netdata`. + +```bash +cd /etc/netdata # Replace this path with your Netdata config directory, if different +sudo ./edit-config python.d/varnish.conf +``` + +Only one parameter is supported: + +```yaml +instance_name: 'name' +``` + +The name of the `varnishd` instance to get logs from. If not specified, the host name is used. + +--- + + diff --git a/collectors/python.d.plugin/varnish/varnish.chart.py b/collectors/python.d.plugin/varnish/varnish.chart.py new file mode 100644 index 0000000..506ad02 --- /dev/null +++ b/collectors/python.d.plugin/varnish/varnish.chart.py @@ -0,0 +1,385 @@ +# -*- coding: utf-8 -*- +# Description: varnish netdata python.d module +# Author: ilyam8 +# SPDX-License-Identifier: GPL-3.0-or-later + +import re + +from bases.FrameworkServices.ExecutableService import ExecutableService +from bases.collection import find_binary + +ORDER = [ + 'session_connections', + 'client_requests', + 'all_time_hit_rate', + 'current_poll_hit_rate', + 'cached_objects_expired', + 'cached_objects_nuked', + 'threads_total', + 'threads_statistics', + 'threads_queue_len', + 'backend_connections', + 'backend_requests', + 'esi_statistics', + 'memory_usage', + 'uptime' +] + +CHARTS = { + 'session_connections': { + 'options': [None, 'Connections Statistics', 'connections/s', + 'client metrics', 'varnish.session_connection', 'line'], + 'lines': [ + ['sess_conn', 'accepted', 'incremental'], + ['sess_dropped', 'dropped', 'incremental'] + ] + }, + 'client_requests': { + 'options': [None, 'Client Requests', 'requests/s', + 'client metrics', 'varnish.client_requests', 'line'], + 'lines': [ + ['client_req', 'received', 'incremental'] + ] + }, + 'all_time_hit_rate': { + 'options': [None, 'All History Hit Rate Ratio', 'percentage', 'cache performance', + 'varnish.all_time_hit_rate', 'stacked'], + 'lines': [ + ['cache_hit', 'hit', 'percentage-of-absolute-row'], + ['cache_miss', 'miss', 'percentage-of-absolute-row'], + ['cache_hitpass', 'hitpass', 'percentage-of-absolute-row']] + }, + 'current_poll_hit_rate': { + 'options': [None, 'Current Poll Hit Rate Ratio', 'percentage', 'cache performance', + 'varnish.current_poll_hit_rate', 'stacked'], + 'lines': [ + ['cache_hit', 'hit', 'percentage-of-incremental-row'], + ['cache_miss', 'miss', 'percentage-of-incremental-row'], + ['cache_hitpass', 'hitpass', 'percentage-of-incremental-row'] + ] + }, + 'cached_objects_expired': { + 'options': [None, 'Expired Objects', 'expired/s', 'cache performance', + 'varnish.cached_objects_expired', 'line'], + 'lines': [ + ['n_expired', 'objects', 'incremental'] + ] + }, + 'cached_objects_nuked': { + 'options': [None, 'Least Recently Used Nuked Objects', 'nuked/s', 'cache performance', + 'varnish.cached_objects_nuked', 'line'], + 'lines': [ + ['n_lru_nuked', 'objects', 'incremental'] + ] + }, + 'threads_total': { + 'options': [None, 'Number Of Threads In All Pools', 'number', 'thread related metrics', + 'varnish.threads_total', 'line'], + 'lines': [ + ['threads', None, 'absolute'] + ] + }, + 'threads_statistics': { + 'options': [None, 'Threads Statistics', 'threads/s', 'thread related metrics', + 'varnish.threads_statistics', 'line'], + 'lines': [ + ['threads_created', 'created', 'incremental'], + ['threads_failed', 'failed', 'incremental'], + ['threads_limited', 'limited', 'incremental'] + ] + }, + 'threads_queue_len': { + 'options': [None, 'Current Queue Length', 'requests', 'thread related metrics', + 'varnish.threads_queue_len', 'line'], + 'lines': [ + ['thread_queue_len', 'in queue'] + ] + }, + 'backend_connections': { + 'options': [None, 'Backend Connections Statistics', 'connections/s', 'backend metrics', + 'varnish.backend_connections', 'line'], + 'lines': [ + ['backend_conn', 'successful', 'incremental'], + ['backend_unhealthy', 'unhealthy', 'incremental'], + ['backend_reuse', 'reused', 'incremental'], + ['backend_toolate', 'closed', 'incremental'], + ['backend_recycle', 'recycled', 'incremental'], + ['backend_fail', 'failed', 'incremental'] + ] + }, + 'backend_requests': { + 'options': [None, 'Requests To The Backend', 'requests/s', 'backend metrics', + 'varnish.backend_requests', 'line'], + 'lines': [ + ['backend_req', 'sent', 'incremental'] + ] + }, + 'esi_statistics': { + 'options': [None, 'ESI Statistics', 'problems/s', 'esi related metrics', 'varnish.esi_statistics', 'line'], + 'lines': [ + ['esi_errors', 'errors', 'incremental'], + ['esi_warnings', 'warnings', 'incremental'] + ] + }, + 'memory_usage': { + 'options': [None, 'Memory Usage', 'MiB', 'memory usage', 'varnish.memory_usage', 'stacked'], + 'lines': [ + ['memory_free', 'free', 'absolute', 1, 1 << 20], + ['memory_allocated', 'allocated', 'absolute', 1, 1 << 20]] + }, + 'uptime': { + 'lines': [ + ['uptime', None, 'absolute'] + ], + 'options': [None, 'Uptime', 'seconds', 'uptime', 'varnish.uptime', 'line'] + } +} + + +def backend_charts_template(name): + order = [ + '{0}_response_statistics'.format(name), + ] + + charts = { + order[0]: { + 'options': [None, 'Backend "{0}"'.format(name), 'kilobits/s', 'backend response statistics', + 'varnish.backend', 'area'], + 'lines': [ + ['{0}_beresp_hdrbytes'.format(name), 'header', 'incremental', 8, 1000], + ['{0}_beresp_bodybytes'.format(name), 'body', 'incremental', -8, 1000] + ] + }, + } + + return order, charts + + +def storage_charts_template(name): + order = [ + 'storage_{0}_usage'.format(name), + 'storage_{0}_alloc_objs'.format(name) + ] + + charts = { + order[0]: { + 'options': [None, 'Storage "{0}" Usage'.format(name), 'KiB', 'storage usage', 'varnish.storage_usage', 'stacked'], + 'lines': [ + ['{0}.g_space'.format(name), 'free', 'absolute', 1, 1 << 10], + ['{0}.g_bytes'.format(name), 'allocated', 'absolute', 1, 1 << 10] + ] + }, + order[1]: { + 'options': [None, 'Storage "{0}" Allocated Objects'.format(name), 'objects', 'storage usage', 'varnish.storage_alloc_objs', 'line'], + 'lines': [ + ['{0}.g_alloc'.format(name), 'allocated', 'absolute'] + ] + } + } + + return order, charts + + +VARNISHSTAT = 'varnishstat' + +re_version = re.compile(r'varnish-(?:plus-)?(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)') + + +class VarnishVersion: + def __init__(self, major, minor, patch): + self.major = major + self.minor = minor + self.patch = patch + + def __str__(self): + return '{0}.{1}.{2}'.format(self.major, self.minor, self.patch) + + +class Parser: + _backend_new = re.compile(r'VBE.([\d\w_.]+)\(.*?\).(beresp[\w_]+)\s+(\d+)') + _backend_old = re.compile(r'VBE\.[\d\w-]+\.([\w\d_-]+).(beresp[\w_]+)\s+(\d+)') + _default = re.compile(r'([A-Z]+\.)?([\d\w_.]+)\s+(\d+)') + + def __init__(self): + self.re_default = None + self.re_backend = None + + def init(self, data): + data = ''.join(data) + parsed_main = Parser._default.findall(data) + if parsed_main: + self.re_default = Parser._default + + parsed_backend = Parser._backend_new.findall(data) + if parsed_backend: + self.re_backend = Parser._backend_new + else: + parsed_backend = Parser._backend_old.findall(data) + if parsed_backend: + self.re_backend = Parser._backend_old + + def server_stats(self, data): + return self.re_default.findall(''.join(data)) + + def backend_stats(self, data): + return self.re_backend.findall(''.join(data)) + + +class Service(ExecutableService): + def __init__(self, configuration=None, name=None): + ExecutableService.__init__(self, configuration=configuration, name=name) + self.order = ORDER + self.definitions = CHARTS + self.instance_name = configuration.get('instance_name') + self.parser = Parser() + self.command = None + self.collected_vbe = set() + self.collected_storages = set() + + def create_command(self): + varnishstat = find_binary(VARNISHSTAT) + + if not varnishstat: + self.error("can't locate '{0}' binary or binary is not executable by user netdata".format(VARNISHSTAT)) + return False + + command = [varnishstat, '-V'] + reply = self._get_raw_data(stderr=True, command=command) + if not reply: + self.error( + "no output from '{0}'. Is varnish running? Not enough privileges?".format(' '.join(self.command))) + return False + + ver = parse_varnish_version(reply) + if not ver: + self.error("failed to parse reply from '{0}', used regex :'{1}', reply : {2}".format( + ' '.join(command), re_version.pattern, reply)) + return False + + if self.instance_name: + self.command = [varnishstat, '-1', '-n', self.instance_name] + else: + self.command = [varnishstat, '-1'] + + if ver.major > 4: + self.command.extend(['-t', '1']) + + self.info("varnish version: {0}, will use command: '{1}'".format(ver, ' '.join(self.command))) + + return True + + def check(self): + if not self.create_command(): + return False + + # STDOUT is not empty + reply = self._get_raw_data() + if not reply: + self.error("no output from '{0}'. Is it running? Not enough privileges?".format(' '.join(self.command))) + return False + + self.parser.init(reply) + + # Output is parsable + if not self.parser.re_default: + self.error('cant parse the output...') + return False + + return True + + def get_data(self): + """ + Format data received from shell command + :return: dict + """ + raw = self._get_raw_data() + if not raw: + return None + + data = dict() + server_stats = self.parser.server_stats(raw) + if not server_stats: + return None + + stats = dict((param, value) for _, param, value in server_stats) + data.update(stats) + + self.get_vbe_backends(data, raw) + self.get_storages(server_stats) + + # varnish 5 uses default.g_bytes and default.g_space + data['memory_allocated'] = data.get('s0.g_bytes') or data.get('default.g_bytes') + data['memory_free'] = data.get('s0.g_space') or data.get('default.g_space') + + return data + + def get_vbe_backends(self, data, raw): + if not self.parser.re_backend: + return + stats = self.parser.backend_stats(raw) + if not stats: + return + + for (name, param, value) in stats: + data['_'.join([name, param])] = value + if name in self.collected_vbe: + continue + self.collected_vbe.add(name) + self.add_backend_charts(name) + + def get_storages(self, server_stats): + # Storage types: + # - SMF: File Storage + # - SMA: Malloc Storage + # - MSE: Massive Storage Engine (Varnish-Plus only) + # + # Stats example: + # [('SMF.', 'ssdStorage.c_req', '47686'), + # ('SMF.', 'ssdStorage.c_fail', '0'), + # ('SMF.', 'ssdStorage.c_bytes', '668102656'), + # ('SMF.', 'ssdStorage.c_freed', '140980224'), + # ('SMF.', 'ssdStorage.g_alloc', '39753'), + # ('SMF.', 'ssdStorage.g_bytes', '527122432'), + # ('SMF.', 'ssdStorage.g_space', '53159968768'), + # ('SMF.', 'ssdStorage.g_smf', '40130'), + # ('SMF.', 'ssdStorage.g_smf_frag', '311'), + # ('SMF.', 'ssdStorage.g_smf_large', '66')] + storages = [name for typ, name, _ in server_stats if typ.startswith(('SMF', 'SMA', 'MSE')) and name.endswith('g_space')] + if not storages: + return + for storage in storages: + storage = storage.split('.')[0] + if storage in self.collected_storages: + continue + self.collected_storages.add(storage) + self.add_storage_charts(storage) + + def add_backend_charts(self, backend_name): + self.add_charts(backend_name, backend_charts_template) + + def add_storage_charts(self, storage_name): + self.add_charts(storage_name, storage_charts_template) + + def add_charts(self, name, charts_template): + order, charts = charts_template(name) + + for chart_name in order: + params = [chart_name] + charts[chart_name]['options'] + dimensions = charts[chart_name]['lines'] + + new_chart = self.charts.add_chart(params) + for dimension in dimensions: + new_chart.add_dimension(dimension) + + +def parse_varnish_version(lines): + m = re_version.search(lines[0]) + if not m: + return None + + m = m.groupdict() + return VarnishVersion( + int(m['major']), + int(m['minor']), + int(m['patch']), + ) diff --git a/collectors/python.d.plugin/varnish/varnish.conf b/collectors/python.d.plugin/varnish/varnish.conf new file mode 100644 index 0000000..54bfe4d --- /dev/null +++ b/collectors/python.d.plugin/varnish/varnish.conf @@ -0,0 +1,66 @@ +# netdata python.d.plugin configuration for varnish +# +# 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, varnish also supports the following: +# +# instance_name: 'name' # the name of the varnishd instance to get logs from. If not specified, the host name is used. +# +# ---------------------------------------------------------------------- |