Skip to content

Commit 5103808

Browse files
author
Muhammad Shahzeb
committed
Fix labels; make fmt
1 parent 3a5d179 commit 5103808

File tree

2 files changed

+16
-54
lines changed

2 files changed

+16
-54
lines changed

postgres_mixin/alerts/postgres.libsonnet

Lines changed: 15 additions & 53 deletions
Original file line numberDiff line numberDiff line change
@@ -174,9 +174,7 @@
174174
expr: 'rate(pg_xlog_position_bytes{asserts_env!=""}[5m]) < 200000',
175175
'for': '5m',
176176
labels: {
177-
asserts_severity: 'critical',
178-
asserts_entity_type: 'Service',
179-
asserts_alert_category: 'failure',
177+
severity: 'critical',
180178
},
181179
},
182180
{
@@ -188,9 +186,7 @@
188186
expr: 'rate(pg_xlog_position_bytes{asserts_env!=""}[2m]) > 36700160 and on (instance, asserts_env, asserts_site) (pg_replication_is_replica{asserts_env!=""} == 0)',
189187
'for': '10m',
190188
labels: {
191-
asserts_severity: 'critical',
192-
asserts_entity_type: 'Service',
193-
asserts_alert_category: 'failure',
189+
severity: 'critical',
194190
},
195191
},
196192
{
@@ -202,9 +198,7 @@
202198
expr: 'pg_stat_replication_pg_xlog_location_diff{asserts_env!=""} != 0',
203199
'for': '5m',
204200
labels: {
205-
asserts_severity: 'critical',
206-
asserts_entity_type: 'Service',
207-
asserts_alert_category: 'failure',
201+
severity: 'critical',
208202
},
209203
},
210204
{
@@ -216,9 +210,7 @@
216210
expr: '(pg_replication_lag{asserts_env!=""} > 3600) and on (instance) (pg_replication_is_replica{asserts_env!=""} == 1)',
217211
'for': '5m',
218212
labels: {
219-
asserts_severity: 'warning',
220-
asserts_entity_type: 'Service',
221-
asserts_alert_category: 'failure',
213+
severity: 'warning',
222214
},
223215
},
224216
{
@@ -230,9 +222,7 @@
230222
expr: '(pg_xlog_position_bytes{asserts_env!=""} and pg_replication_is_replica{asserts_env!=""} == 0) - on (job, service, asserts_env, asserts_site) group_right(instance) (pg_xlog_position_bytes{asserts_env!=""} and pg_replication_is_replica{asserts_env!=""} == 1) > 1e+09',
231223
'for': '5m',
232224
labels: {
233-
asserts_severity: 'critical',
234-
asserts_entity_type: 'Service',
235-
asserts_alert_category: 'failure',
225+
severity: 'critical',
236226
},
237227
},
238228
{
@@ -244,9 +234,7 @@
244234
expr: 'pg_replication_slots_active{asserts_env!=""} == 0',
245235
'for': '30m',
246236
labels: {
247-
asserts_severity: 'critical',
248-
asserts_entity_type: 'Service',
249-
asserts_alert_category: 'failure',
237+
severity: 'critical',
250238
},
251239
},
252240
{
@@ -258,9 +246,7 @@
258246
expr: 'pg_replication_slots_xmin_age{asserts_env!="", slot_name =~ "^repmgr_slot_[0-9]+"} > 20000',
259247
'for': '30m',
260248
labels: {
261-
asserts_severity: 'critical',
262-
asserts_entity_type: 'Service',
263-
asserts_alert_category: 'failure',
249+
severity: 'critical',
264250
},
265251
},
266252
{
@@ -271,9 +257,7 @@
271257
},
272258
expr: 'pg_replication_is_replica{asserts_env!=""} and changes(pg_replication_is_replica{asserts_env!=""}[1m]) > 0',
273259
labels: {
274-
asserts_severity: 'warning',
275-
asserts_entity_type: 'Service',
276-
asserts_alert_category: 'failure',
260+
severity: 'warning',
277261
},
278262
},
279263
{
@@ -285,9 +269,7 @@
285269
expr: 'pg_exporter_last_scrape_error{asserts_env!=""} > 0',
286270
'for': '30m',
287271
labels: {
288-
asserts_severity: 'critical',
289-
asserts_entity_type: 'Service',
290-
asserts_alert_category: 'failure',
272+
severity: 'critical',
291273
},
292274
},
293275
{
@@ -299,9 +281,7 @@
299281
expr: '(sum without(relname) (pg_stat_user_tables_n_dead_tup{asserts_env!="", db_name!~"template.*|^$"}) > 10000) / ((sum without(relname) (pg_stat_user_tables_n_live_tup{asserts_env!="", db_name!~"template.*|^$"}) + sum without(relname)(pg_stat_user_tables_n_dead_tup{asserts_env!="", db_name!~"template.*|^$"})) > 0) >= 0.1 unless on(instance, asserts_env, asserts_site) (pg_replication_is_replica{asserts_env!=""} == 1)',
300282
'for': '5m',
301283
labels: {
302-
asserts_severity: 'warning',
303-
asserts_entity_type: 'Service',
304-
asserts_alert_category: 'failure',
284+
severity: 'warning',
305285
},
306286
},
307287
{
@@ -313,9 +293,7 @@
313293
expr: 'group without(pod, instance)(timestamp(pg_stat_user_tables_n_dead_tup{asserts_env!=""} > pg_stat_user_tables_n_live_tup{asserts_env!=""} * on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_vacuum_scale_factor{asserts_env!=""} + on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_vacuum_threshold{asserts_env!=""})) < time() - 36000',
314294
'for': '30m',
315295
labels: {
316-
asserts_severity: 'critical',
317-
asserts_entity_type: 'Service',
318-
asserts_alert_category: 'failure',
296+
severity: 'critical',
319297
},
320298
},
321299
{
@@ -324,20 +302,9 @@
324302
description: '{{ $labels.instance }} table has not been analyzed recently, which might lead to inefficient query planning.',
325303
summary: 'PostgreSQL table not analyzed.',
326304
},
327-
expr: '
328-
group without(pod, instance)(
329-
timestamp(
330-
pg_stat_user_tables_n_dead_tup{asserts_env!=""} >
331-
pg_stat_user_tables_n_live_tup{asserts_env!=""}
332-
* on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_analyze_scale_factor{asserts_env!=""}
333-
+ on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_analyze_threshold{asserts_env!=""}
334-
)
335-
-
336-
pg_stat_user_tables_last_autoanalyze{asserts_env!=""}
337-
> 24 * 60 * 60
338-
)',
305+
expr: '\n group without(pod, instance)(\n timestamp(\n pg_stat_user_tables_n_dead_tup{asserts_env!=""} >\n pg_stat_user_tables_n_live_tup{asserts_env!=""}\n * on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_analyze_scale_factor{asserts_env!=""}\n + on(asserts_env, asserts_site, namespace, job, service, instance, server) group_left pg_settings_autovacuum_analyze_threshold{asserts_env!=""}\n )\n -\n pg_stat_user_tables_last_autoanalyze{asserts_env!=""}\n > 24 * 60 * 60\n )',
339306
labels: {
340-
asserts_severity: 'warning',
307+
severity: 'warning',
341308
asserts_entity_type: 'DataSource',
342309
asserts_alert_category: 'failure',
343310
},
@@ -348,15 +315,10 @@
348315
description: '{{ $labels.instance }} is requesting too many checkpoints, which may lead to performance degradation.',
349316
summary: 'PostgreSQL too many checkpoints requested.',
350317
},
351-
expr:'
352-
rate(pg_stat_bgwriter_checkpoints_timed_total{asserts_env!=""}[5m]) /
353-
(rate(pg_stat_bgwriter_checkpoints_timed_total{asserts_env!=""}[5m]) + rate(pg_stat_bgwriter_checkpoints_req_total{asserts_env!=""}[5m]))
354-
< 0.5',
318+
expr: '\n rate(pg_stat_bgwriter_checkpoints_timed_total{asserts_env!=""}[5m]) /\n (rate(pg_stat_bgwriter_checkpoints_timed_total{asserts_env!=""}[5m]) + rate(pg_stat_bgwriter_checkpoints_req_total{asserts_env!=""}[5m]))\n < 0.5',
355319
'for': '5m',
356320
labels: {
357-
asserts_severity: 'warning',
358-
asserts_entity_type: 'Service',
359-
asserts_alert_category: 'failure',
321+
severity: 'warning',
360322
},
361323
},
362324
],

postgres_mixin/dashboards/dashboards.libsonnet

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,4 +2,4 @@
22
grafanaDashboards+:: {
33
'postgres-overview.json': (import 'postgres-overview.json'),
44
},
5-
}
5+
}

0 commit comments

Comments
 (0)