summaryrefslogtreecommitdiffstats
path: root/health/health.d/web_log.conf
blob: 127c9a9c6ab21485608d61d363aa64b9363bd9a4 (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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
# make sure we can collect web log data

 template: last_collected_secs
       on: web_log.response_codes
    class: Web Server
component: Web log
     type: Latency
 families: *
     calc: $now - $last_collected_t
    units: seconds ago
    every: 10s
     warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
     crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
    delay: down 5m multiplier 1.5 max 1h
     info: number of seconds since the last successful data collection
       to: webmaster


# -----------------------------------------------------------------------------
# high level response code alarms

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: 1m_requests
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned
     calc: ($this == 0)?(1):($this)
    units: requests
    every: 10s
     info: number of HTTP requests in the last minute

 template: 1m_successful
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned of successful_requests
     calc: $this * 100 / $1m_requests
    units: %
    every: 10s
     warn: ($1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 95 ) : ( 85 )) ) : ( 0 )
     crit: ($1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 85 ) : ( 75 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)
       to: webmaster

 template: 1m_redirects
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned of redirects
     calc: $this * 100 / $1m_requests
    units: %
    every: 10s
     warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING ) ? (  1 ) : ( 20 )) ) : ( 0 )
     crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 20 ) : ( 30 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of redirection HTTP requests over the last minute (3xx except 304)
       to: webmaster

 template: 1m_bad_requests
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of bad_requests
     calc: $this * 100 / $1m_requests
    units: %
    every: 10s
     warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 10 ) : ( 30 )) ) : ( 0 )
     crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 30 ) : ( 50 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of client error HTTP requests over the last minute (4xx except 401)
       to: webmaster

 template: 1m_internal_errors
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of server_errors
     calc: $this * 100 / $1m_requests
    units: %
    every: 10s
     warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 1 ) : ( 2 )) ) : ( 0 )
     crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of server error HTTP requests over the last minute (5xx)
       to: webmaster

# unmatched lines

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_total_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: 1m_total_requests
       on: web_log.response_codes
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned
     calc: ($this == 0)?(1):($this)
    units: requests
    every: 10s
     info: number of HTTP requests over the last minute

 template: 1m_unmatched
       on: web_log.response_codes
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of unmatched
     calc: $this * 100 / $1m_total_requests
    units: %
    every: 10s
     warn: ($1m_total_requests > 120) ? ($this > 1) : ( 0 )
    delay: up 1m down 5m multiplier 1.5 max 1h
     info: percentage of unparsed log lines over the last minute
       to: webmaster

# -----------------------------------------------------------------------------
# web slow

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: 10m_response_time
       on: web_log.response_time
    class: System
component: Web log
     type: Latency
 families: *
   lookup: average -10m unaligned of avg
    units: ms
    every: 30s
     info: average HTTP response time over the last 10 minutes

 template: web_slow
       on: web_log.response_time
    class: Web Server
component: Web log
     type: Latency
 families: *
   lookup: average -1m unaligned of avg
    units: ms
    every: 10s
    green: 500
      red: 1000
     warn: ($1m_requests > 120) ? ($this > $green && $this > ($10m_response_time * 2) ) : ( 0 )
     crit: ($1m_requests > 120) ? ($this > $red   && $this > ($10m_response_time * 4) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
     info: average HTTP response time over the last minute
  options: no-clear-notification
       to: webmaster

# -----------------------------------------------------------------------------
# web too many or too few requests

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $5m_successful_old > 120
#
# i.e. when there were at least 120 requests during the 5 minutes starting
#      at -10m and ending at -5m

 template: 5m_successful_old
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: average -5m at -5m unaligned of successful_requests
    units: requests/s
    every: 30s
     info: average number of successful HTTP requests for the 5 minutes starting 10 minutes ago

 template: 5m_successful
       on: web_log.response_statuses
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: average -5m unaligned of successful_requests
    units: requests/s
    every: 30s
     info: average number of successful HTTP requests over the last 5 minutes

 template: 5m_requests_ratio
       on: web_log.response_codes
    class: Web Server
component: Web log
     type: Workload
 families: *
     calc: ($5m_successful_old > 0)?($5m_successful * 100 / $5m_successful_old):(100)
    units: %
    every: 30s
     warn: ($5m_successful_old > 120) ? ($this > 200 OR $this < 50) : (0)
     crit: ($5m_successful_old > 120) ? ($this > 400 OR $this < 25) : (0)
    delay: down 15m multiplier 1.5 max 1h
  options: no-clear-notification
     info: ratio of successful HTTP requests over the last 5 minutes, \
           compared with the previous 5 minutes \
           (clear notification for this alarm will not be sent)
       to: webmaster



# ---------------------------------------------------GO-VERSION---------------------------------------------------------

# make sure we can collect web log data

 template: web_log_last_collected_secs
       on: web_log.requests
    class: Web Server
component: Web log
     type: Latency
 families: *
     calc: $now - $last_collected_t
    units: seconds ago
    every: 10s
     warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
     crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
    delay: down 5m multiplier 1.5 max 1h
     info: number of seconds since the last successful data collection
       to: webmaster

# unmatched lines

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_total_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: web_log_1m_total_requests
       on: web_log.requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned
     calc: ($this == 0)?(1):($this)
    units: requests
    every: 10s
     info: number of HTTP requests in the last minute

 template: web_log_1m_unmatched
       on: web_log.excluded_requests
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of unmatched
     calc: $this * 100 / $web_log_1m_total_requests
    units: %
    every: 10s
     warn: ($web_log_1m_total_requests > 120) ? ($this > 1) : ( 0 )
    delay: up 1m down 5m multiplier 1.5 max 1h
     info: percentage of unparsed log lines over the last minute
       to: webmaster

# -----------------------------------------------------------------------------
# high level response code alarms

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: web_log_1m_requests
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned
     calc: ($this == 0)?(1):($this)
    units: requests
    every: 10s
     info: number of HTTP requests in the last minute

 template: web_log_1m_successful
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned of success
     calc: $this * 100 / $web_log_1m_requests
    units: %
    every: 10s
     warn: ($web_log_1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 95 ) : ( 85 )) ) : ( 0 )
     crit: ($web_log_1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 85 ) : ( 75 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)
       to: webmaster

 template: web_log_1m_redirects
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: sum -1m unaligned of redirect
     calc: $this * 100 / $web_log_1m_requests
    units: %
    every: 10s
     warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING ) ? (  1 ) : ( 20 )) ) : ( 0 )
     crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 20 ) : ( 30 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of redirection HTTP requests over the last minute (3xx except 304)
       to: webmaster

 template: web_log_1m_bad_requests
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of bad
     calc: $this * 100 / $web_log_1m_requests
    units: %
    every: 10s
     warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 10 ) : ( 30 )) ) : ( 0 )
     crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 30 ) : ( 50 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of client error HTTP requests over the last minute (4xx except 401)
       to: webmaster

 template: web_log_1m_internal_errors
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Errors
 families: *
   lookup: sum -1m unaligned of error
     calc: $this * 100 / $web_log_1m_requests
    units: %
    every: 10s
     warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 1 ) : ( 2 )) ) : ( 0 )
     crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
    delay: up 2m down 15m multiplier 1.5 max 1h
     info: ratio of server error HTTP requests over the last minute (5xx)
       to: webmaster

# -----------------------------------------------------------------------------
# web slow

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $1m_requests > 120
#
# i.e. when there are at least 120 requests during the last minute

 template: web_log_10m_response_time
       on: web_log.request_processing_time
    class: System
component: Web log
     type: Latency
 families: *
   lookup: average -10m unaligned of avg
    units: ms
    every: 30s
     info: average HTTP response time over the last 10 minutes

 template: web_log_web_slow
       on: web_log.request_processing_time
    class: Web Server
component: Web log
     type: Latency
 families: *
   lookup: average -1m unaligned of avg
    units: ms
    every: 10s
    green: 500
      red: 1000
     warn: ($web_log_1m_requests > 120) ? ($this > $green && $this > ($web_log_10m_response_time * 2) ) : ( 0 )
     crit: ($web_log_1m_requests > 120) ? ($this > $red   && $this > ($web_log_10m_response_time * 4) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
     info: average HTTP response time over the last 1 minute
  options: no-clear-notification
       to: webmaster

# -----------------------------------------------------------------------------
# web too many or too few requests

# the following alarms trigger only when there are enough data.
# we assume there are enough data when:
#
#  $5m_successful_old > 120
#
# i.e. when there were at least 120 requests during the 5 minutes starting
#      at -10m and ending at -5m

 template: web_log_5m_successful_old
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: average -5m at -5m unaligned of success
    units: requests/s
    every: 30s
     info: average number of successful HTTP requests for the 5 minutes starting 10 minutes ago

 template: web_log_5m_successful
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
   lookup: average -5m unaligned of success
    units: requests/s
    every: 30s
     info: average number of successful HTTP requests over the last 5 minutes

 template: web_log_5m_requests_ratio
       on: web_log.type_requests
    class: Web Server
component: Web log
     type: Workload
 families: *
     calc: ($web_log_5m_successful_old > 0)?($web_log_5m_successful * 100 / $web_log_5m_successful_old):(100)
    units: %
    every: 30s
     warn: ($web_log_5m_successful_old > 120) ? ($this > 200 OR $this < 50) : (0)
     crit: ($web_log_5m_successful_old > 120) ? ($this > 400 OR $this < 25) : (0)
    delay: down 15m multiplier 1.5 max 1h
  options: no-clear-notification
     info: ratio of successful HTTP requests over over the last 5 minutes, \
           compared with the previous 5 minutes \
           (clear notification for this alarm will not be sent)
       to: webmaster