summaryrefslogtreecommitdiffstats
path: root/conf.d/python.d/web_log.conf
blob: c185f8d8505d94e8a1f2abadf338ab847c7ce5c2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
# 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

# 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.

# ----------------------------------------------------------------------
# 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
#     retries: 60             # the JOB's number of restoration attempts
#     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> - 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

# ----------------------------------------------------------------------
# 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'