diff --git a/_data/rules.yml b/_data/rules.yml index 86edb23..b91c594 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -197,7 +197,7 @@ groups: severity: critical - name: Host RAID disk failure description: 'At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap' - query: 'node_md_disks{state="fail"} > 0' + query: 'node_md_disks{state="failed"} > 0' severity: warning - name: Host kernel version deviations description: Different kernel versions are running @@ -239,8 +239,9 @@ groups: severity: warning - name: Container Memory usage description: Container Memory usage is above 80% - query: "(sum(container_memory_usage_bytes) BY (instance, name) / sum(container_spec_memory_limit_bytes) BY (instance, name) * 100) > 80" + query: "(sum(container_memory_working_set_bytes) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80" severity: warning + comments: See https://medium.com/faun/how-much-is-too-much-the-linux-oomkiller-and-used-memory-d32186f29c9d - name: Container Volume usage description: Container Volume usage is above 80% query: "(1 - (sum(container_fs_inodes_free) BY (instance) / sum(container_fs_inodes_total) BY (instance)) * 100) > 80"