diff options
Diffstat (limited to '')
-rw-r--r-- | collectors/python.d.plugin/puppet/Makefile.inc | 13 | ||||
-rw-r--r-- | collectors/python.d.plugin/puppet/README.md | 48 | ||||
-rw-r--r-- | collectors/python.d.plugin/puppet/puppet.chart.py | 121 | ||||
-rw-r--r-- | collectors/python.d.plugin/puppet/puppet.conf | 98 |
4 files changed, 280 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/puppet/Makefile.inc b/collectors/python.d.plugin/puppet/Makefile.inc new file mode 100644 index 000000000..fe94b9254 --- /dev/null +++ b/collectors/python.d.plugin/puppet/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 += puppet/puppet.chart.py +dist_pythonconfig_DATA += puppet/puppet.conf + +# do not install these files, but include them in the distribution +dist_noinst_DATA += puppet/README.md puppet/Makefile.inc + diff --git a/collectors/python.d.plugin/puppet/README.md b/collectors/python.d.plugin/puppet/README.md new file mode 100644 index 000000000..8304c831e --- /dev/null +++ b/collectors/python.d.plugin/puppet/README.md @@ -0,0 +1,48 @@ +# puppet + +Monitor status of Puppet Server and Puppet DB. + +Following charts are drawn: + +1. **JVM Heap** + * committed (allocated from OS) + * used (actual use) +2. **JVM Non-Heap** + * committed (allocated from OS) + * used (actual use) +3. **CPU Usage** + * execution + * GC (taken by garbage collection) +4. **File Descriptors** + * max + * used + + +### configuration + +```yaml +puppetdb: + url: 'https://fqdn.example.com:8081' + tls_cert_file: /path/to/client.crt + tls_key_file: /path/to/client.key + autodetection_retry: 1 + retries: 3600 + +puppetserver: + url: 'https://fqdn.example.com:8140' + autodetection_retry: 1 + retries: 3600 +``` + +When no configuration is given then `https://fqdn.example.com:8140` is +tried without any retries. + +### notes + +* Exact Fully Qualified Domain Name of the node should be used. +* Usually Puppet Server/DB startup time is VERY long. So, there should + be quite reasonable retry count. +* Secure PuppetDB config may require client certificate. Not applies + to default PuppetDB configuration though. + +--- diff --git a/collectors/python.d.plugin/puppet/puppet.chart.py b/collectors/python.d.plugin/puppet/puppet.chart.py new file mode 100644 index 000000000..5c8e48bd9 --- /dev/null +++ b/collectors/python.d.plugin/puppet/puppet.chart.py @@ -0,0 +1,121 @@ +# -*- coding: utf-8 -*- +# Description: puppet netdata python.d module +# Author: Andrey Galkin <andrey@futoin.org> (andvgal) +# SPDX-License-Identifier: GPL-3.0-or-later +# +# This module should work both with OpenSource and PE versions +# of PuppetServer and PuppetDB. +# +# NOTE: PuppetDB may be configured to require proper TLS +# client certificate for security reasons. Use tls_key_file +# and tls_cert_file options then. +# + +from bases.FrameworkServices.UrlService import UrlService +from json import loads +import socket + +update_every = 5 +priority = 60000 +# very long clojure-based service startup time +retries = 180 + +MB = 1048576 +CPU_SCALE = 1000 +ORDER = [ + 'jvm_heap', + 'jvm_nonheap', + 'cpu', + 'fd_open', +] +CHARTS = { + 'jvm_heap': { + 'options': [None, 'JVM Heap', 'MB', 'resources', 'puppet.jvm', 'area'], + 'lines': [ + ['jvm_heap_committed', 'committed', 'absolute', 1, MB], + ['jvm_heap_used', 'used', 'absolute', 1, MB], + ], + 'variables': [ + ['jvm_heap_max'], + ['jvm_heap_init'], + ], + }, + 'jvm_nonheap': { + 'options': [None, 'JVM Non-Heap', 'MB', 'resources', 'puppet.jvm', 'area'], + 'lines': [ + ['jvm_nonheap_committed', 'committed', 'absolute', 1, MB], + ['jvm_nonheap_used', 'used', 'absolute', 1, MB], + ], + 'variables': [ + ['jvm_nonheap_max'], + ['jvm_nonheap_init'], + ], + }, + 'cpu': { + 'options': [None, 'CPU usage', 'percentage', 'resources', 'puppet.cpu', 'stacked'], + 'lines': [ + ['cpu_time', 'execution', 'absolute', 1, CPU_SCALE], + ['gc_time', 'GC', 'absolute', 1, CPU_SCALE], + ] + }, + 'fd_open': { + 'options': [None, 'File Descriptors', 'descriptors', 'resources', 'puppet.fdopen', 'line'], + 'lines': [ + ['fd_used', 'used', 'absolute'], + ], + 'variables': [ + ['fd_max'], + ], + }, +} + + +class Service(UrlService): + def __init__(self, configuration=None, name=None): + UrlService.__init__(self, configuration=configuration, name=name) + self.url = 'https://{0}:8140'.format(socket.getfqdn()) + self.order = ORDER + self.definitions = CHARTS + + def _get_data(self): + # NOTE: there are several ways to retrieve data + # 1. Only PE versions: + # https://puppet.com/docs/pe/2018.1/api_status/status_api_metrics_endpoints.html + # 2. Inidividual Metrics API (JMX): + # https://puppet.com/docs/pe/2018.1/api_status/metrics_api.html + # 3. Extended status at debug level: + # https://puppet.com/docs/pe/2018.1/api_status/status_api_json_endpoints.html + # + # For sake of simplicity and efficiency the status one is used.. + + raw_data = self._get_raw_data(self.url + '/status/v1/services?level=debug') + + if raw_data is None: + return None + + raw_data = loads(raw_data) + data = {} + + try: + try: + jvm_metrics = raw_data['status-service']['status']['experimental']['jvm-metrics'] + except KeyError: + jvm_metrics = raw_data['status-service']['status']['jvm-metrics'] + + heap_mem = jvm_metrics['heap-memory'] + non_heap_mem = jvm_metrics['non-heap-memory'] + + for k in ['max', 'committed', 'used', 'init']: + data['jvm_heap_'+k] = heap_mem[k] + data['jvm_nonheap_'+k] = non_heap_mem[k] + + fd_open = jvm_metrics['file-descriptors'] + data['fd_max'] = fd_open['max'] + data['fd_used'] = fd_open['used'] + + data['cpu_time'] = int(jvm_metrics['cpu-usage'] * CPU_SCALE) + data['gc_time'] = int(jvm_metrics['gc-cpu-usage'] * CPU_SCALE) + except KeyError: + pass + + return data or None diff --git a/collectors/python.d.plugin/puppet/puppet.conf b/collectors/python.d.plugin/puppet/puppet.conf new file mode 100644 index 000000000..991bfabed --- /dev/null +++ b/collectors/python.d.plugin/puppet/puppet.conf @@ -0,0 +1,98 @@ +# netdata python.d.plugin configuration for Puppet Server and Puppet DB +# +# 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 + +# retries sets the number of retries to be made in case of failures. +# If unset, the default for python.d.plugin is used. +# Attempts to restore the service are made once every update_every +# and only if the module has collected values in the past. +# retries: 60 + +# 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 +# retries: 60 # the JOB's number of restoration attempts +# autodetection_retry: 0 # the JOB's re-check interval in seconds +# +# These configuration comes from UrlService base: +# url: # HTTP or HTTPS URL +# tls_verify: False # Control HTTPS server certificate verification +# tls_ca_file: # Optional CA (bundle) file to use +# tls_cert_file: # Optional client certificate file +# tls_key_file: # Optional client key file +# +# ---------------------------------------------------------------------- +# AUTO-DETECTION JOBS +# only one of them will run (they have the same name) +# puppet: +# url: 'https://<FQDN>:8140' +# + +# +# Production configuration should look like below. +# +# NOTE: usually Puppet Server/DB startup time is VERY long. So, there should +# be quite reasonable retry count. +# +# NOTE: secure PuppetDB config may require client certificate. +# Not applies to default PuppetDB configuration though. +# +# puppetdb: +# url: 'https://fqdn.example.com:8081' +# tls_cert_file: /path/to/client.crt +# tls_key_file: /path/to/client.key +# autodetection_retry: 1 +# retries: 3600 +# +# puppetserver: +# url: 'https://fqdn.example.com:8140' +# autodetection_retry: 1 +# retries: 3600 +# |