diff options
author | Christian Pointner <equinox@spreadspace.org> | 2022-07-08 22:09:57 +0200 |
---|---|---|
committer | Christian Pointner <equinox@spreadspace.org> | 2022-07-08 22:09:57 +0200 |
commit | c08fc5f358cdea44499e93bb9ac9b746d90646a0 (patch) | |
tree | 7107423bb105cdd98302037459c8073fa365664c /roles/monitoring/prometheus/server/defaults | |
parent | emc-xx: lvm volume for /srv/cache (diff) |
prometheus: increase level for read/write latency alert
Diffstat (limited to 'roles/monitoring/prometheus/server/defaults')
-rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index 4d146119..0715befc 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -74,7 +74,7 @@ prometheus_server_rules_node: 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]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0 + 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: 2m labels: severity: warning @@ -83,7 +83,7 @@ prometheus_server_rules_node: 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]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0 + 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: 2m labels: severity: warning |