XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 17:07:24 +08:00
Code Issues Projects Releases Packages Wiki Activity

Adding alerts for criteo/cassandra_exporter

Browse source
This commit is contained in:
Samuel Berthe 2020-03-07 18:51:34 +01:00
parent 75a17a79be
commit b97ece8c69
No known key found for this signature in database
GPG key ID: 9D7813625412A946
1 changed files with 51 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
_data/rules.yml
View file

@ -376,9 +376,60 @@ services:
- name: Cassandra
exporters:
- name: instaclustr/cassandra-exporter
doc_url: https://github.com/instaclustr/cassandra-exporter
rules:
- name: criteo/cassandra_exporter
doc_url: https://github.com/criteo/cassandra_exporter
rules:
- name: Cassandra hints count
description: Cassandra hints count was changed to {{ $value | printf "%.0f" }} on {{ $labels.instance }} some nodes may go down
query: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:storage:totalhints:count"}[1m]) > 3'
severity: critical
- name: Cassandra compaction task pending
description: Many Cassandra compaction tasks are pending. You might need to increase I/O capacity by adding nodes to the cluster.
query: 'avg_over_time(cassandra_stats{name="org:apache:cassandra:metrics:compaction:pendingtasks:value"}[30m]) > 100'
severity: warning
- name: Cassandra viewwrite latency
description: High viewwrite latency on {{ $labels.instance }} cassandra node
query: 'cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:viewwrite:viewwritelatency:99thpercentile",service="cas"} > 100000'
severity: warning
- name: Cassandra cool hacker
description: Increase of Cassandra authentication failures
query: 'irate(cassandra_stats{name="org:apache:cassandra:metrics:client:authfailure:count"}[1m]) > 5'
severity: warning
- name: Cassandra node down
description: Cassandra node down
query: 'sum(cassandra_stats{name="org:apache:cassandra:net:failuredetector:downendpointcount"}) by (service,group,cluster,env) > 0'
severity: critical
- name: Cassandra commitlog pending tasks
description: Unexpected number of Cassandra commitlog pending tasks
query: 'cassandra_stats{name="org:apache:cassandra:metrics:commitlog:pendingtasks:value"} > 15'
severity: warning
- name: Cassandra compaction executor blocked tasks
description: Some Cassandra compaction executor tasks are blocked
query: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:compactionexecutor:currentlyblockedtasks:count"} > 0'
severity: warning
- name: Cassandra flush writer blocked tasks
description: Some Cassandra flush writer tasks are blocked
query: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:memtableflushwriter:currentlyblockedtasks:count"} > 0'
severity: warning
- name: Cassandra repair pending tasks
description: Some Cassandra repair tasks are pending
query: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:antientropystage:pendingtasks:value"} > 2'
severity: warning
- name: Cassandra repair blocked tasks
description: Some Cassandra repair tasks are blocked
query: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:antientropystage:currentlyblockedtasks:count"} > 0'
severity: warning
- name: Cassandra connection timeouts total
description: Some connection between nodes are ending in timeout
query: 'rate(cassandra_stats{name="org:apache:cassandra:metrics:connection:totaltimeouts:count"}[1m]) > 5'
severity: critical
- name: Cassandra storage exceptions
description: Something is going wrong with cassandra storage
query: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:storage:exceptions:count"}[1m]) > 1'
severity: critical
- name: Apache
exporters: