diff --git a/dist/rules/blackbox/blackbox-exporter.yml b/dist/rules/blackbox/blackbox-exporter.yml index 6d101db..7eb0a74 100644 --- a/dist/rules/blackbox/blackbox-exporter.yml +++ b/dist/rules/blackbox/blackbox-exporter.yml @@ -50,13 +50,13 @@ groups: summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }}) description: "SSL certificate expires in less than 20 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: BlackboxSslCertificateWillExpireSoon + - alert: BlackboxSslCertificateWillExpireVerySoon expr: '0 <= round((last_over_time(probe_ssl_earliest_cert_expiry[10m]) - time()) / 86400, 0.1) < 3' for: 0m labels: severity: critical annotations: - summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }}) + summary: Blackbox SSL certificate will expire very soon (instance {{ $labels.instance }}) description: "SSL certificate expires in less than 3 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" # For probe_ssl_earliest_cert_expiry to be exposed after expiration, you diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index 007b059..26898e6 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -51,14 +51,14 @@ groups: summary: Host unusual network throughput out (instance {{ $labels.instance }}) description: "Host transmit bandwidth is high (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: HostUnusualDiskReadRate + - alert: HostDiskIoUtilizationHigh expr: '(rate(node_disk_io_time_seconds_total[5m]) > .80)' for: 0m labels: severity: warning annotations: - summary: Host unusual disk read rate (instance {{ $labels.instance }}) - description: "Disk is too busy (IO wait > 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Host disk IO utilization high (instance {{ $labels.instance }}) + description: "Disk utilization is high (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" # Please add ignored mountpoints in node_exporter parameters like # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)". diff --git a/dist/rules/minio/embedded-exporter.yml b/dist/rules/minio/embedded-exporter.yml index ea55791..e0f53bd 100644 --- a/dist/rules/minio/embedded-exporter.yml +++ b/dist/rules/minio/embedded-exporter.yml @@ -24,7 +24,7 @@ groups: description: "Minio cluster node disk is offline\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: MinioDiskSpaceUsage - expr: 'disk_storage_available / disk_storage_total * 100 < 10' + expr: 'minio_cluster_capacity_raw_free_bytes / minio_cluster_capacity_raw_total_bytes * 100 < 10' for: 0m labels: severity: warning diff --git a/dist/rules/postgresql/postgres-exporter.yml b/dist/rules/postgresql/postgres-exporter.yml index 75e71b4..a8b5846 100644 --- a/dist/rules/postgresql/postgres-exporter.yml +++ b/dist/rules/postgresql/postgres-exporter.yml @@ -141,7 +141,7 @@ groups: description: "PostgreSQL dead tuples is too large\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: PostgresqlConfigurationChanged - expr: '{__name__=~"pg_settings_.*"} != ON(__name__, instance) {__name__=~"pg_settings_([^t]|t[^r]|tr[^a]|tra[^n]|tran[^s]|trans[^a]|transa[^c]|transac[^t]|transact[^i]|transacti[^o]|transactio[^n]|transaction[^_]|transaction_[^r]|transaction_r[^e]|transaction_re[^a]|transaction_rea[^d]|transaction_read[^_]|transaction_read_[^o]|transaction_read_o[^n]|transaction_read_on[^l]|transaction_read_onl[^y]).*"} OFFSET 5m' + expr: '{__name__=~"pg_settings_.*",__name__!="pg_settings_transaction_read_only"} != ON(__name__, instance) {__name__=~"pg_settings_.*",__name__!="pg_settings_transaction_read_only"} OFFSET 5m' for: 0m labels: severity: info @@ -153,7 +153,7 @@ groups: expr: 'sum(pg_stat_ssl_compression) > 0' for: 0m labels: - severity: critical + severity: warning annotations: summary: Postgresql SSL compression active (instance {{ $labels.instance }}) description: "Database allows connections with SSL compression enabled. This may add significant jitter in replication delay. Replicas should turn off SSL compression via `sslcompression=0` in `recovery.conf`.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"