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
|
---
## https://awesome-prometheus-alerts.grep.to/rules#host-and-hardware
prometheus_server_rules_node_extra: []
prometheus_server_rules_node:
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 2m
labels:
severity: warning
annotations:
summary: Host out of memory (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Node memory is filling up (< 10% left)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostMemoryUnderMemoryPressure
expr: rate(node_vmstat_pgmajfault[1m]) > 1000
for: 2m
labels:
severity: warning
annotations:
summary: Host memory under memory pressure (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostMemoryHardwareCorrupted
expr: node_memory_HardwareCorrupted_bytes > 0
labels:
severity: warning
annotations:
summary: Host memory is corrupted (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The node reports {{ '{{' }} $value {{ '}}' }} bytes of corrupted memory.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostOutOfDiskSpace
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!~"(tmpfs|nfs4?|cifs)"} == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of disk space (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Disk is almost full (< 10% left)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostDiskWillFillIn24Hours
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"(tmpfs|nfs4?|cifs)"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host disk will fill in 24 hours (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostOutOfInodes
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of inodes (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostInodesWillFillIn24Hours
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host inodes will fill in 24 hours (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostUnusualDiskReadLatency
expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.2 and rate(node_disk_reads_completed_total[1m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk read latency (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostUnusualDiskWriteLatency
expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.2 and rate(node_disk_writes_completed_total[1m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk write latency (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostHighCpuLoad
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
for: 20m
labels:
severity: warning
annotations:
summary: Host high CPU load (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "CPU load is > 80%\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostCpuStealNoisyNeighbor
expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU steal noisy neighbor (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostSystemdNotRunning
expr: node_systemd_system_running == 0
for: 0m
labels:
severity: warning
annotations:
summary: Host systemd is not in running state (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "systemd is not in running state.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostSystemdServiceCrashed
expr: node_systemd_unit_state{state="failed"} == 1
for: 0m
labels:
severity: warning
annotations:
summary: Host systemd service crashed (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The systemd service unit {{ '{{' }} $labels.name {{ '}}' }} is in failed state.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 85
for: 5m
labels:
severity: warning
annotations:
summary: Host physical component too hot (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Physical hardware component too hot\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNodeOvertemperatureAlarm
expr: node_hwmon_temp_crit_alarm_celsius == 1
for: 0m
labels:
severity: critical
annotations:
summary: Host node overtemperature alarm (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Physical node temperature alarm triggered\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostRaidArrayGotInactive
expr: node_md_state{state="inactive"} > 0
for: 0m
labels:
severity: critical
annotations:
summary: Host RAID array got inactive (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "RAID array {{ '{{' }} $labels.device {{ '}}' }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostRaidDiskFailure
expr: node_md_disks{state="failed"} > 0
for: 2m
labels:
severity: warning
annotations:
summary: Host RAID disk failure (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "At least one device in RAID array on {{ '{{' }} $labels.instance {{ '}}' }} failed. Array {{ '{{' }} $labels.md_device {{ '}}' }} needs attention and possibly a disk swap\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host OOM kill detected (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "OOM kill detected\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostEdacCorrectableErrorsDetected
expr: increase(node_edac_correctable_errors_total[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host EDAC Correctable Errors detected (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has had {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} correctable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostEdacUncorrectableErrorsDetected
expr: node_edac_uncorrectable_errors_total > 0
for: 0m
labels:
severity: critical
annotations:
summary: Host EDAC Uncorrectable Errors detected (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has had {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNetworkReceiveErrors
expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Receive Errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} interface {{ '{{' }} $labels.device {{ '}}' }} has encountered {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} receive errors in the last five minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNetworkTransmitErrors
expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Transmit Errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} interface {{ '{{' }} $labels.device {{ '}}' }} has encountered {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} transmit errors in the last five minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNetworkInterfaceSaturated
expr: (rate(node_network_receive_bytes_total{device!~"^(tap|vnet).*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^(tap|vnet).*"}[1m])) / node_network_speed_bytes{device!~"^(tap|vnet).*"} > 0.95
for: 20m
labels:
severity: warning
annotations:
summary: Host Network Interface Saturated (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The network interface \"{{ '{{' }} $labels.device {{ '}}' }}\" on \"{{ '{{' }} $labels.instance {{ '}}' }}\" is getting overloaded.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostConntrackLimit
expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
for: 5m
labels:
severity: warning
annotations:
summary: Host conntrack limit (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The number of conntrack is approching limit\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNetworkBondDegraded
expr: (node_bonding_active - node_bonding_slaves) != 0
for: 1m
labels:
severity: warning
annotations:
title: Bond is degraded on (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Bond \"{{ '{{' }} $labels.master {{ '}}' }}\" on \"{{ '{{' }} $labels.instance {{ '}}' }}\" is degraded\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostClockSkew
expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
for: 2m
labels:
severity: warning
annotations:
summary: Host clock skew (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Clock skew detected. Clock is out of sync.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostClockNotSynchronising
expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
for: 2m
labels:
severity: warning
annotations:
summary: Host clock not synchronising (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Clock not synchronising.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: ZpoolStateDegraded
expr: node_zfs_zpool_state{state="degraded"} == 1
for: 0m
labels:
severity: warning
annotations:
summary: ZFS zpool is degraded (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The ZFS zpool {{ '{{' }} $labels.zpool {{ '}}' }} is degraded.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: ZpoolStateFaulted
expr: node_zfs_zpool_state{state="faulted"} == 1
for: 0m
labels:
severity: critical
annotations:
summary: ZFS zpool is faulted (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The ZFS zpool {{ '{{' }} $labels.zpool {{ '}}' }} is faulted.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
### textfile-collectors
- alert: NodeTextfileScrapeFailed
expr: node_textfile_scrape_error != 0
for: 0m
labels:
severity: warning
annotations:
summary: Scraping metrics from textfiles failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The textfile collector failed to scrape at least one file\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: NodeTextfileMetricsOutdated
expr: (time() - node_textfile_mtime_seconds{file!~".*/(git-fsck-|syncoid-pull-).*.prom"}) > 3600
for: 0m
labels:
severity: warning
annotations:
summary: Metrics from a textfile collector are too old (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The exported values from textfile {{ '{{' }} $labels.file {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }} are {{ '{{' }} $value {{ '}}' }} seconds old.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
## textfile-collector: apt_info
- alert: AptUpgradesPending
expr: sum by (instance) (apt_upgrades_pending) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host has upgradeable packages (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has {{ '{{' }} $value {{ '}}' }} upgradable packages.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: AptAutoremovePending
expr: sum by (instance) (apt_autoremove_pending) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host has packages that can be autoremoved (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has {{ '{{' }} $value {{ '}}' }} packages that can be autoremoved.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostNeedsRebooting
expr: node_reboot_required > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host must be rebootet (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "Host {{ '{{' }} $labels.instance {{ '}}' }} must be rebootet for security uppdates to take effect.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
## textfile-collector: deleted-libraries
- alert: DeletedLibraryInUse
expr: node_processes_linking_deleted_libraries
for: 2m
labels:
severity: warning
annotations:
summary: Some processes still use a deleted library (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The deleted library {{ '{{' }} $labels.library_name {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }} is still in use by {{ '{{' }} $value {{ '}}' }} processes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
## textfile-collector: smartmon
- alert: SmartmonDeviceUnhealthy
expr: smartmon_device_smart_healthy == 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disks are unhealthy (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports unhealthy device {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonDeviceErrors
expr: smartmon_device_errors > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk reports S.M.A.R.T. errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports errors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
# selection of S.M.A.R.T. metrics based on: https://www.backblaze.com/blog/hard-drive-smart-stats/
- alert: SmartmonReallocatedSectorsCount
expr: delta(smartmon_attr_raw_value{name="reallocated_sector_ct"}[72h]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports reallocated sectors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports reallocated sectors within last 72 hours for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonReallocatedSectorsCountHigh
expr: smartmon_attr_raw_value{name="reallocated_sector_ct"} > 100
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports more than 100 reallocated sectors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports more than 100 reallocated sectors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonReportedUncorrectableErrors
expr: delta(smartmon_attr_raw_value{name="reported_uncorrect"}[72h]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports uncorrectable errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports uncorrectable errors within last 72 hours for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonCommandTimeouts
expr: delta(smartmon_attr_raw_value{name="command_timeout"}[72h]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports command timeouts (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports command timeouts within last 72 hours for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonCurrentPendingSectors
expr: smartmon_attr_raw_value{name="current_pending_sector"} > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports current pending sectors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports current pending sectors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonOfflineUncorrectable
expr: smartmon_attr_raw_value{name="offline_uncorrectable"} > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports offline uncorrectable errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports offline uncorrectable errors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonNVMEMediaErrors
expr: delta(smartmon_media_errors_total[72h]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports NVMe media errors. (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports NVMe media errors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SmartmonNVMEPercentageUsed
expr: smartmon_percentage_used_ratio > 80
for: 0m
labels:
severity: warning
annotations:
summary: Host disk S.M.A.R.T. reports worn out disk. (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports NVMe high usage of device {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be completely worn out soon.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
## syncoid-pull scripts
- alert: SyncoidPullJobTooLongAgo
expr: time() - syncoid_pull_run > (24 * 3600)
for: 0m
labels:
severity: warning
annotations:
summary: The last syncoid pull job was too long ago (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The last syncoid-based backup job of {{ '{{' }} $labels.instance {{ '}}' }} from {{ '{{' }} $labels.backup_server {{ '}}' }} ran more then 24 hours ago.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: SyncoidPullJobFailed
expr: syncoid_pull_exit_code != 0
for: 0m
labels:
severity: warning
annotations:
summary: The last syncoid pull job failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The last syncoid-based backup job of {{ '{{' }} $labels.instance {{ '}}' }} from {{ '{{' }} $labels.backup_server {{ '}}' }} has failed.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
|
