github-mirrors/VictoriaMetrics
1
0
Fork 0
mirror of https://github.com/VictoriaMetrics/VictoriaMetrics.git synced 2024-11-21 14:44:00 +00:00
Code Issues Projects Releases Packages Wiki Activity

alerts: inverse grouping in vmagent alerts (#5429)

Browse source 
Aggregations with by() have one sideeffect, that any custom labels you add to hosts are dropped too which can be used for alerts routing.

Therefore, some good practice could be to use without() instead, with labels, like without(path) , or without(url) to get same aggregations but with any external labels left intact.
This commit is contained in:
7840vz 2023-12-11 17:01:29 +03:00 committed by GitHub
parent 51df2248f0
commit 75196d7234
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
deployment/docker/alerts-vmagent.yml
View file

@ -10,7 +10,7 @@ groups:
concurrency: 2
rules:
- alert: PersistentQueueIsDroppingData
expr: sum(increase(vm_persistentqueue_bytes_dropped_total[5m])) by (job, instance) > 0
expr: sum(increase(vm_persistentqueue_bytes_dropped_total[5m])) without (path) > 0
for: 10m
labels:
severity: critical
@ -21,7 +21,7 @@ groups:
on instance {{ $labels.instance }} for the last 10m."
- alert: RejectedRemoteWriteDataBlocksAreDropped
expr: sum(increase(vmagent_remotewrite_packets_dropped_total[5m])) by (job, instance) > 0
expr: sum(increase(vmagent_remotewrite_packets_dropped_total[5m])) without (url) > 0
for: 15m
labels:
severity: warning
@ -31,7 +31,7 @@ groups:
remote-write server data blocks. Check the logs to find the reason for rejects."
- alert: TooManyScrapeErrors
expr: sum(increase(vm_promscrape_scrapes_failed_total[5m])) by (job, instance) > 0
expr: increase(vm_promscrape_scrapes_failed_total[5m]) > 0
for: 15m
labels:
severity: warning
@ -41,9 +41,9 @@ groups:
- alert: TooManyWriteErrors
expr: |
(sum(increase(vm_ingestserver_request_errors_total[5m])) by (job, instance)
(sum(increase(vm_ingestserver_request_errors_total[5m])) without (name,net,type)
+
sum(increase(vmagent_http_request_errors_total[5m])) by (job, instance)) > 0
sum(increase(vmagent_http_request_errors_total[5m])) without (path,protocol)) > 0
for: 15m
labels:
severity: warning
@ -52,7 +52,7 @@ groups:
summary: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} responds with errors to write requests for last 15m."
- alert: TooManyRemoteWriteErrors
expr: sum(rate(vmagent_remotewrite_retries_count_total[5m])) by(job, instance, url) > 0
expr: rate(vmagent_remotewrite_retries_count_total[5m]) > 0
for: 15m
labels:
severity: warning
@ -65,9 +65,9 @@ groups:
- alert: RemoteWriteConnectionIsSaturated
expr: |
(
sum(rate(vmagent_remotewrite_send_duration_seconds_total[5m])) by(job, instance, url)
rate(vmagent_remotewrite_send_duration_seconds_total[5m])
/
max(vmagent_remotewrite_queues) by(job, instance, url)
vmagent_remotewrite_queues
) > 0.9
for: 15m
labels: