# netdata python.d.plugin configuration for web log
#
# 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.

# ----------------------------------------------------------------------
# PLUGIN CONFIGURATION
#
# 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, web_log also supports the following:
#
#     path: 'PATH'                        # the path to web server log file
#     path: 'PATH[0-9]*[0-9]'             # log files with date suffix are also supported
#     detailed_response_codes: yes/no     # default: yes. Additional chart where response codes are not grouped
#     detailed_response_aggregate: yes/no # default: yes. Not aggregated detailed response codes charts
#     all_time : yes/no                   # default: yes. All time unique client IPs chart (50000 addresses ~ 400KB)
#     filter:                             # filter with regex
#          include: 'REGEX'               # only those rows that matches the regex
#          exclude: 'REGEX'               # all rows except those that matches the regex
#     categories:                         # requests per url chart configuration
#          cacti: 'cacti.*'               # name(dimension): REGEX to match
#          observium: 'observium.*'       # name(dimension): REGEX to match
#          stub_status: 'stub_status'     # name(dimension): REGEX to match
#     user_defined:                       # requests per pattern in <user_defined> field (custom_log_format)
#          cacti: 'cacti.*'               # name(dimension): REGEX to match
#          observium: 'observium.*'       # name(dimension): REGEX to match
#          stub_status: 'stub_status'     # name(dimension): REGEX to match
#     custom_log_format:                  # define a custom log format
#          pattern: '(?P<address>[\da-f.:]+) -.*?"(?P<method>[A-Z]+) (?P<url>.*?)" (?P<code>[1-9]\d{2}) (?P<bytes_sent>\d+) (?P<resp_length>\d+) (?P<resp_time>\d+\.\d+) '
#          time_multiplier: 1000000       # type <int>/<float> - convert time to microseconds
#     histogram: [1,3,10,30,100, ...]      # type list of int - Cumulative histogram of response time in milli seconds

# ----------------------------------------------------------------------
# WEB SERVER CONFIGURATION
#
# Make sure the web server log directory and the web server log files
# can be read by user 'netdata'.
#
# To enable the timings chart and the requests size dimension, the
# web server needs to log them. This is how to add them:
#
# nginx:
#   log_format netdata '$remote_addr - $remote_user [$time_local] '
#                      '"$request" $status $body_bytes_sent '
#                      '$request_length $request_time $upstream_response_time '
#                      '"$http_referer" "$http_user_agent"';
#   access_log /var/log/nginx/access.log netdata;
#
# apache (you need mod_logio enabled):
#   LogFormat "%h %l %u %t \"%r\" %>s %O %I %D \"%{Referer}i\" \"%{User-Agent}i\"" vhost_netdata
#   LogFormat "%h %l %u %t \"%r\" %>s %O %I %D \"%{Referer}i\" \"%{User-Agent}i\"" netdata
#   CustomLog "/var/log/apache2/access.log" netdata

# ----------------------------------------------------------------------
# VHOST AND PORT
# if your want to graph the request/sec per virtual host and per port (to check the number of requests in http vs https)

# in apache : (%v gives the hostname, %p the port number)
#  LogFormat "%v %p %h %t \"%r\" %>s %O %I %D \"%{Referer}i\" \"%{User-Agent}i\"" vhost_netdata
#
# and in this file in apache_vhosts_log section, add :
#  custom_log_format:
#     pattern: '(?P<vhost>[a-zA-Z\d.-_]+) (?P<port>\d+) (?P<address>[\da-f.:]+) \[.*\] "(?P<method>[A-Z]+)[^"]*" (?P<code>[1-9]\d{2}) (?P<bytes_sent>\d+) (?P<resp_length>\d+) (?P<resp_time>\d+)'

# in nginx: ($host or $http_host give the hostname, $server_port the port number)
#   log_format netdatavhost '$host $server_port $remote_addr - $remote_user [$time_local] '
#                      '"$request" $status $body_bytes_sent '
#                      '$request_length $request_time $upstream_response_time '
#                      '"$http_referer" "$http_user_agent"';
#
#   access_log /var/log/nginx/access.log netdatavhost;
#
#   be aware that the access_log directive in a server{} block overwrites the one in http{}, if your vhosts have individual log
#   files, you have to specify the general netdata log in each vhost as a second access_log statement.
#
# and in this file in nginx_log section, add :
#  custom_log_format:
#     pattern: '(?P<vhost>[a-zA-Z\d.-_\[\]]+) (?P<port>\d+) (?P<address>[\da-f.:]+) .* "(?P<method>[A-Z]+)[^"]*" (?P<code>[1-9]\d{2}) (?P<bytes_sent>\d+) (?P<resp_length>\d+) (?P<resp_time>\d+)'

# ----------------------------------------------------------------------
# AUTO-DETECTION JOBS
# only one of them per web server will run (when they have the same name)


# -------------------------------------------
# nginx log on various distros

# debian, arch
nginx_log:
  name: 'nginx'
  path: '/var/log/nginx/access.log'

# gentoo
nginx_log2:
  name: 'nginx'
  path: '/var/log/nginx/localhost.access_log'


# -------------------------------------------
# apache log on various distros

# debian
apache_log:
  name: 'apache'
  path: '/var/log/apache2/access.log'

# gentoo
apache_log2:
  name: 'apache'
  path: '/var/log/apache2/access_log'

# arch
apache_log3:
  name: 'apache'
  path: '/var/log/httpd/access_log'

# debian
apache_vhosts_log:
  name: 'apache_vhosts'
  path: '/var/log/apache2/other_vhosts_access.log'


# -------------------------------------------
# gunicorn log on various distros

gunicorn_log:
  name: 'gunicorn'
  path: '/var/log/gunicorn/access.log'

gunicorn_log2:
  name: 'gunicorn'
  path: '/var/log/gunicorn/gunicorn-access.log'

# -------------------------------------------
# Apache Cache
apache_cache:
  name: 'apache_cache'
  type: 'apache_cache'
  path: '/var/log/apache/cache.log'

apache2_cache:
  name: 'apache_cache'
  type: 'apache_cache'
  path: '/var/log/apache2/cache.log'

httpd_cache:
  name: 'apache_cache'
  type: 'apache_cache'
  path: '/var/log/httpd/cache.log'

# -------------------------------------------
# Squid

# debian/ubuntu
squid_log1:
  name: 'squid'
  type: 'squid'
  path: '/var/log/squid3/access.log'

#gentoo
squid_log2:
  name: 'squid'
  type: 'squid'
  path: '/var/log/squid/access.log'