-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathrules.yaml
297 lines (296 loc) · 13.3 KB
/
rules.yaml
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
apiVersion: v1
data:
kube-system-portworx.yaml: |
groups:
- name: portworx.rules
rules:
- alert: PortworxVolumeUsageCritical
annotations:
description: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is
over 80% used for more than 10 minutes.
summary: Portworx volume capacity is at {{$value}}% used.
expr: 100 * (px_volume_usage_bytes / px_volume_capacity_bytes) > 80
for: 5m
labels:
issue: Portworx volume {{$labels.volumeid}} usage on {{$labels.instance}} is
high.
severity: critical
- alert: PortworxVolumeUsage
annotations:
description: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is
over 70% used for more than 10 minutes.
summary: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (px_volume_usage_bytes / px_volume_capacity_bytes) > 70
for: 5m
labels:
issue: Portworx volume {{$labels.volumeid}} usage on {{$labels.instance}} is
critical.
severity: warning
- alert: PortworxVolumeWillFill
annotations:
description: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is
over 70% full and has been predicted to fill within 2 weeks.
summary: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is over
70% full and is predicted to fill within 2 weeks.
expr: (px_volume_usage_bytes / px_volume_capacity_bytes) > 0.7 and predict_linear(px_cluster_disk_available_bytes[1h],
14 * 86400) < 0
for: 10m
labels:
issue: Portworx volume {{$labels.volumeid}} on {{$labels.instance}} is predicted
to fill within 2 weeks.
severity: warning
- alert: PortworxVolumeNotInQuorum
annotations:
description: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is out of quorum. Please check all nodes with that volume replicas are online.
summary: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is out of quorum.
expr: px_volume_replication_status == 1
labels:
issue: Portworx volume out of quorum.
severity: warning
- alert: PortworxVolumeInResync
annotations:
description: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is in resync state.
summary: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is in resync state.
expr: px_volume_replication_status == 2
labels:
issue: Portworx volume in resync state.
severity: warning
- alert: PortworxVolumeDegraded
annotations:
description: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is in degraded state. Please check all nodes with that volume replicas are
online.
summary: Portworx volume {{$labels.volumeid}} from cluster {{$labels.cluster}}
is in degraded state.
expr: px_volume_replication_status == 3
labels:
issue: Portworx volume in degraded state.
severity: warning
- alert: PortworxStorageUsageCritical
annotations:
description: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is
over 80% used for more than 10 minutes.
summary: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (1 - px_cluster_disk_utilized_bytes / px_cluster_disk_total_bytes)
< 20
for: 5m
labels:
issue: Portworx storage {{$labels.volumeid}} usage on {{$labels.instance}} is
critical.
severity: critical
- alert: PortworxStorageUsage
annotations:
description: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is
over 70% used for more than 10 minutes.
summary: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (1 - (px_cluster_disk_utilized_bytes / px_cluster_disk_total_bytes))
< 30
for: 5m
labels:
issue: Portworx storage {{$labels.volumeid}} usage on {{$labels.instance}} is
critical.
severity: warning
- alert: PortworxStorageWillFill
annotations:
description: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is
over 70% full and has been predicted to fill within 2 weeks for more than
10 minutes.
summary: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is over
70% full and is predicted to fill within 2 weeks.
expr: (100 * (1 - (px_cluster_disk_utilized_bytes / px_cluster_disk_total_bytes)))
< 30 and predict_linear(px_cluster_disk_available_bytes[1h], 14 * 86400) < 0
for: 10m
labels:
issue: Portworx storage {{$labels.volumeid}} on {{$labels.instance}} is predicted
to fill within 2 weeks.
severity: warning
- alert: PortworxStorageNodeDown
annotations:
description: Portworx Storage Node has been offline for more than 5 minutes.
summary: Portworx Storage Node is Offline.
expr: max(px_cluster_status_nodes_storage_down) > 0
for: 5m
labels:
issue: Portworx Storage Node is Offline.
severity: critical
- alert: PortworxQuorumUnhealthy
annotations:
description: Portworx cluster Quorum Unhealthy for more than 5 minutes.
summary: Portworx Quorum Unhealthy.
expr: max(px_cluster_status_cluster_quorum) > 1
for: 5m
labels:
issue: Portworx Quorum Unhealthy.
severity: critical
- alert: PortworxMemberDown
annotations:
description: Portworx cluster member(s) has(have) been down for more than 5
minutes.
summary: Portworx cluster member(s) is(are) down.
expr: (max(px_cluster_status_cluster_size) - count(px_cluster_status_cluster_size))
> 0
for: 5m
labels:
issue: Portworx cluster member(s) is(are) down.
severity: critical
- alert: PXBackupError
annotations:
description: Failed to take backup for volume {{$labels.volumename}} with error
{{$labels.error_string}}.
summary: Failed to take backup for volume {{$labels.volumename}}.
expr: px_backup_stats_status == 2
labels:
issue: Cloudsnap backup error.
severity: warning
- alert: PXKvdbNodeViewUnhealthy
annotations:
description: Portworx node {{$labels.node_id}} from cluster {{$labels.cluster}}
is unable to talk to kvdb. Please check the KVDB health and node's connection
to KVDB.
summary: Portworx node {{$labels.node_id}} is unable to talk to kvdb.
expr: px_kvdb_health_state_node_view == 2
labels:
issue: Portworx node {{$labels.node_id}} is unable to talk to kvdb.
severity: critical
- alert: PXKvdbClusterViewUnhealthy
annotations:
description: Portworx node {{$labels.node_id}} from cluster {{$labels.cluster}}
is reporting that the cluster is unable to talk to kvdb. Please check KVDB
health and the node's connection to KVDB and the other nodes in the cluster.
summary: Portworx cluster {{$labels.cluster}} is unable to talk to kvdb.
expr: px_kvdb_health_state_cluster_view == 2
labels:
issue: Portworx cluster {{$labels.cluster}} is unable to talk to kvdb.
severity: critical
- name: Portworx PoolResize Alerts
rules:
- alert: PoolExpandSuccessful
annotations:
description: Pool {{$labels.POOL}} from node {{$labels.instance}}, from Portworx
cluster {{$labels.clusterid}} successfully expanded.
summary: Portworx pool {{$labels.POOL}} successfully expanded.
expr: px_alerts_poolexpandsuccessful == 1
labels:
issue: Portworx pool expand successful.
severity: warning
- alert: PoolExpandFailure
annotations:
description: Pool expansion for pool {{$labels.POOL}} from node {{$labels.instance}},
from Portworx cluster {{$labels.clusterid}} failed. Please check Portworx
alerts for more details.
summary: Pool expansion for pool {{$labels.POOL}} failed.
expr: px_alerts_poolexpandfailed == 1
labels:
issue: Portworx pool expand failure.
severity: critical
- name: Portworx VolumeResize Alerts
rules:
- alert: VolumeResizeSuccessful
annotations:
description: Portworx volume {{$labels.volumeid}} from cluster {{$labels.clusterid}}
successfully resized.
summary: Portworx volume {{$labels.volumeid}} successfully resized.
expr: px_alerts_volumeresizesuccessful == 1
labels:
issue: Portworx volume resize successful.
severity: warning
- alert: VolumeResizeDeferred
annotations:
description: Volume resize for volume {{$labels.volumeid}} from Portworx cluster
{{$labels.clusterid}} deferred. Please check Portworx alerts for more details.
summary: Volume resize for volume {{$labels.volumeid}} deferred.
expr: px_alerts_volumeresizedeferred == 1
labels:
issue: Portworx volume resize deferred.
severity: warning
- alert: VolumeResizeFailed
annotations:
description: Volume resize for volume {{$labels.volumeid}} from Portworx cluster
{{$labels.clusterid}} failed. Please check Portworx alerts for more details.
summary: Volume resize for volume {{$labels.volumeid}} failed.
expr: px_alerts_volumeresizefailed == 1
labels:
issue: Portworx volume resize failure.
severity: critical
- alert: PortworxPoolUsageCritical
annotations:
description: Portworx Pool {{$labels.POOL}} on {{$labels.instance}} is
over 80% used for more than 10 minutes.
summary: Portworx pool {{$labels.POOL}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (1 - px_pool_stats_used_bytes / px_pool_stats_total_bytes)
< 20
for: 5m
labels:
issue: Portworx pool {{$labels.POOL}} usage on {{$labels.instance}} is
critical.
severity: critical
- alert: PortworxPoolUsageMajor
annotations:
description: Portworx Pool {{$labels.POOL}} on {{$labels.instance}} is
over 75% used for more than 10 minutes.
summary: Portworx pool {{$labels.POOL}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (1 - px_pool_stats_used_bytes / px_pool_stats_total_bytes)
< 25
for 5m
labels:
issue: Portworx pool {{$labels.POOL}} usage on {{$labels.instance}} is
major.
severity: critical
- alert: PortworxPoolUsageWarning
annotations:
description: Portworx Pool {{$labels.POOL}} on {{$labels.instance}} is
over 70% used for more than 10 minutes.
summary: Portworx pool {{$labels.POOL}} on {{$labels.instance}} is at
{{$value}}% used.
expr: 100 * (1 - px_pool_stats_used_bytes / px_pool_stats_total_bytes)
< 30
for 5m
labels:
issue: Portworx pool {{$labels.POOL}} usage on {{$labels.instance}} is
on warning status.
severity: warning
- alert: PortworxPoolIsNotOnline
annotations:
description: Portworx pool {{$labels.POOL}} from cluster {{$labels.cluster}}
is not available.
summary: Portworx pool {{$labels.POOL}} from cluster {{$labels.cluster}}
is not available.
severity: critical
expr: px_pool_stats_pool_status != 1
- alert: PortworxPoolWriteLatency
annotations:
description: Portworx pool {{$labels.POOL}} write latency from cluster {{$labels.cluster}}
is greater than 2 seconds.
summary: Portworx pool {{$labels.POOL}} write latency from cluster {{$labels.cluster}}
is greater than 2 seconds.
severity: warning
expr: px_pool_stats_write_latency_seconds >= 2
- alert: PortworxPoolUsageWarningTest
annotations:
description: Portworx Pool {{$labels.POOL}} on {{$labels.instance}} is
over 70% used for more than 10 minutes.
summary: Portworx pool {{$labels.POOL}} on {{$labels.instance}} is at
{{$value}}% used. This is a test alert.
expr: 100 * (1 - px_pool_stats_used_bytes / px_pool_stats_total_bytes)
< 85
for 5m
labels:
issue: Portworx pool {{$labels.POOL}} usage on {{$labels.instance}} is
on warning status. This is a test alert.
severity: warning
kind: ConfigMap
metadata:
labels:
managed-by: prometheus-operator
prometheus-name: px-prometheus
name: prometheus-px-prometheus-rulefiles-0
namespace: kube-system