Overdue commit

roles/netdata/defaults/main.yml

@@ -0,0 +1 @@
+has_gpu: False

roles/netdata/files/netdata.repo

@@ -0,0 +1,21 @@
+[netdata]
+name=netdata
+baseurl=https://packagecloud.io/netdata/netdata/fedora/34/$basearch
+repo_gpgcheck=1
+gpgcheck=0
+enabled=1
+gpgkey=https://packagecloud.io/netdata/netdata/gpgkey
+sslverify=1
+sslcacert=/etc/pki/tls/certs/ca-bundle.crt
+metadata_expire=300
+
+[netdata-source]
+name=netdata-source
+baseurl=https://packagecloud.io/netdata/netdata/fedora/34/SRPMS
+repo_gpgcheck=1
+gpgcheck=0
+enabled=1
+gpgkey=https://packagecloud.io/netdata/netdata/gpgkey
+sslverify=1
+sslcacert=/etc/pki/tls/certs/ca-bundle.crt
+metadata_expire=300

roles/netdata/handlers/main.yml

@@ -0,0 +1,13 @@
+---
+- name: enable netdata
+  service: 
+    name: netdata
+    state: started
+    enabled: yes
+  become: yes
+
+- name: restart netdata
+  service: 
+    name: netdata
+    state: restarted
+  become: yes

roles/netdata/tasks/main.yml

@@ -0,0 +1,39 @@
+---
+
+- name: Add netdata repo
+  copy:
+    src: netdata.repo
+    mode: "0644"
+    dest: /etc/yum.repos.d/netdata.repo
+  become: yes
+
+- name: Install netdata
+  dnf:
+    name:
+    - netdata
+  notify: enable netdata
+  become: yes
+
+- name: Add netdata conf
+  template:
+    src: netdata.conf.j2
+    mode: "0644"
+    dest: /etc/netdata/netdata.conf
+  notify: restart netdata
+  become: yes
+
+- name: Add netdata python.d.conf
+  template:
+    src: python.d.conf.j2
+    mode: "0644"
+    dest: /etc/netdata/python.d.conf
+  notify: restart netdata
+  become: yes
+
+- name: Add netdata nvidia_smi.conf
+  template:
+    src: nvidia_smi.conf.j2
+    mode: "0644"
+    dest: /etc/netdata/python.d/nvidia_smi.conf
+  notify: restart netdata
+  become: yes

roles/netdata/templates/netdata.conf.j2

@@ -0,0 +1,36 @@
+# netdata configuration
+#
+# You can download the latest version of this file, using:
+#
+#  wget -O /etc/netdata/netdata.conf http://localhost:19999/netdata.conf
+# or
+#  curl -o /etc/netdata/netdata.conf http://localhost:19999/netdata.conf
+#
+# You can uncomment and change any of the options below.
+# The value shown in the commented settings, is the default value.
+#
+
+# global netdata configuration
+[global]
+    run as user = netdata
+
+    memory mode = ram
+
+    # the default database size - 1 hour
+    history = 3600
+
+    # some defaults to run netdata with least priority
+    process scheduling policy = idle
+    OOM score = 1000
+    
+    stock config directory = /etc/netdata/conf.d
+  
+[web]
+    web files owner = root
+    web files group = netdata
+    
+    # by default do not expose the netdata port
+    bind to = 0.0.0.0
+
+[health]
+    stock health configuration directory = /etc/netdata/conf.d/health.d

roles/netdata/templates/nvidia_smi.conf.j2

@@ -0,0 +1,72 @@
+# netdata python.d.plugin configuration for nvidia_smi
+#
+# 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, example also supports the following:
+#
+# loop_mode: yes/no                 # default is yes. If set to yes `nvidia-smi` is executed in a separate thread using `-l` option.
+# poll_seconds: SECONDS             # default is 1. Sets the frequency of seconds the nvidia-smi tool is polled in loop mode.
+# exclude_zero_memory_users: yes/no # default is no. Whether to collect users metrics with 0Mb memory allocation.
+#
+# ----------------------------------------------------------------------
+update_every : 5
+loop_mode    : yes
+poll_seconds : 5
+exclude_zero_memory_users : yes

roles/netdata/templates/python.d.conf.j2

@@ -0,0 +1,112 @@
+# netdata python.d.plugin configuration
+#
+# This file is in YaML format.
+# Generally the format is:
+#
+# name: value
+#
+
+# Enable / disable the whole python.d.plugin (all its modules)
+enabled: yes
+
+# ----------------------------------------------------------------------
+# Enable / Disable python.d.plugin modules
+#default_run: yes
+#
+# If "default_run" = "yes" the default for all modules is enabled (yes).
+# Setting any of these to "no" will disable it.
+#
+# If "default_run" = "no" the default for all modules is disabled (no).
+# Setting any of these to "yes" will enable it.
+
+# Enable / Disable explicit garbage collection (full collection run). Default is enabled.
+gc_run: yes
+
+# Garbage collection interval in seconds. Default is 300.
+gc_interval: 300
+
+# apache: yes
+
+# apache_cache has been replaced by web_log
+# adaptec_raid: yes
+# alarms: yes
+# am2320: yes
+# anomalies: no
+apache_cache: no
+# beanstalk: yes
+# bind_rndc: yes
+# boinc: yes
+# ceph: yes
+chrony: no
+# changefinder: no
+# couchdb: yes
+# dns_query_time: yes
+# dnsdist: yes
+# dockerd: yes
+# dovecot: yes
+# elasticsearch: yes
+# energid: yes
+
+# this is just an example
+example: no
+
+# exim: yes
+# fail2ban: yes
+# freeradius: yes
+# gearman: yes
+go_expvar: no
+
+# gunicorn_log has been replaced by web_log
+gunicorn_log: no
+# haproxy: yes
+# hddtemp: yes
+# httpcheck: yes
+hpssa: no
+# icecast: yes
+# ipfs: yes
+# isc_dhcpd: yes
+# litespeed: yes
+logind: no
+# megacli: yes
+# memcached: yes
+# mongodb: yes
+# monit: yes
+# mysql: yes
+# nginx: yes
+# nginx_plus: yes
+{% if has_gpu %}
+nvidia_smi: yes
+{% endif %}
+# nginx_log has been replaced by web_log
+nginx_log: no
+# nsd: yes
+# ntpd: yes
+# openldap: yes
+# oracledb: yes
+# ovpn_status_log: yes
+# phpfpm: yes
+# portcheck: yes
+# postfix: yes
+# postgres: yes
+# powerdns: yes
+# proxysql: yes
+# puppet: yes
+# rabbitmq: yes
+# redis: yes
+# rethinkdbs: yes
+# retroshare: yes
+# riakkv: yes
+# samba: yes
+sensors: yes
+# smartd_log: yes
+# spigotmc: yes
+# springboot: yes
+# squid: yes
+# traefik: yes
+# tomcat: yes
+# tor: yes
+# uwsgi: yes
+# varnish: yes
+# w1sensor: yes
+# web_log: yes
+# zscores: no