diff --git a/postgres_mixin/alerts/alerts.libsonnet b/postgres_mixin/alerts/alerts.libsonnet new file mode 100644 index 00000000..7f70d8a8 --- /dev/null +++ b/postgres_mixin/alerts/alerts.libsonnet @@ -0,0 +1 @@ +(import 'postgres.libsonnet') diff --git a/postgres_mixin/alerts/alerts.yaml b/postgres_mixin/alerts/alerts.yaml deleted file mode 100644 index ff3d75a7..00000000 --- a/postgres_mixin/alerts/alerts.yaml +++ /dev/null @@ -1,57 +0,0 @@ ---- -groups: - - name: PostgreSQL - rules: - - alert: PostgreSQLMaxConnectionsReached - expr: sum(pg_stat_activity_count) by (instance) >= sum(pg_settings_max_connections) by (instance) - sum(pg_settings_superuser_reserved_connections) by (instance) - for: 1m - labels: - severity: email - annotations: - summary: "{{ $labels.instance }} has maxed out Postgres connections." - description: "{{ $labels.instance }} is exceeding the currently configured maximum Postgres connection limit (current value: {{ $value }}s). Services may be degraded - please take immediate action (you probably need to increase max_connections in the Docker image and re-deploy." - - - alert: PostgreSQLHighConnections - expr: sum(pg_stat_activity_count) by (instance) > (sum(pg_settings_max_connections) by (instance) - sum(pg_settings_superuser_reserved_connections) by (instance)) * 0.8 - for: 10m - labels: - severity: email - annotations: - summary: "{{ $labels.instance }} is over 80% of max Postgres connections." - description: "{{ $labels.instance }} is exceeding 80% of the currently configured maximum Postgres connection limit (current value: {{ $value }}s). Please check utilization graphs and confirm if this is normal service growth, abuse or an otherwise temporary condition or if new resources need to be provisioned (or the limits increased, which is mostly likely)." - - - alert: PostgreSQLDown - expr: pg_up != 1 - for: 1m - labels: - severity: email - annotations: - summary: "PostgreSQL is not processing queries: {{ $labels.instance }}" - description: "{{ $labels.instance }} is rejecting query requests from the exporter, and thus probably not allowing DNS requests to work either. User services should not be effected provided at least 1 node is still alive." - - - alert: PostgreSQLSlowQueries - expr: avg(rate(pg_stat_activity_max_tx_duration{datname!~"template.*"}[2m])) by (datname) > 2 * 60 - for: 2m - labels: - severity: email - annotations: - summary: "PostgreSQL high number of slow on {{ $labels.cluster }} for database {{ $labels.datname }} " - description: "PostgreSQL high number of slow queries {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }} " - - - alert: PostgreSQLQPS - expr: avg(irate(pg_stat_database_xact_commit{datname!~"template.*"}[5m]) + irate(pg_stat_database_xact_rollback{datname!~"template.*"}[5m])) by (datname) > 10000 - for: 5m - labels: - severity: email - annotations: - summary: "PostgreSQL high number of queries per second {{ $labels.cluster }} for database {{ $labels.datname }}" - description: "PostgreSQL high number of queries per second on {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }}" - - - alert: PostgreSQLCacheHitRatio - expr: avg(rate(pg_stat_database_blks_hit{datname!~"template.*"}[5m]) / (rate(pg_stat_database_blks_hit{datname!~"template.*"}[5m]) + rate(pg_stat_database_blks_read{datname!~"template.*"}[5m]))) by (datname) < 0.98 - for: 5m - labels: - severity: email - annotations: - summary: "PostgreSQL low cache hit rate on {{ $labels.cluster }} for database {{ $labels.datname }}" - description: "PostgreSQL low on cache hit rate on {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }}" diff --git a/postgres_mixin/alerts/postgres.libsonnet b/postgres_mixin/alerts/postgres.libsonnet new file mode 100644 index 00000000..d70f669d --- /dev/null +++ b/postgres_mixin/alerts/postgres.libsonnet @@ -0,0 +1,127 @@ +{ + prometheusAlerts+:: { + groups+: [ + { + name: 'PostgreSQL', + rules: [ + { + alert: 'PostgreSQLMaxConnectionsReached', + annotations: { + description: '{{ $labels.instance }} is exceeding the currently configured maximum Postgres connection limit (current value: {{ $value }}s). Services may be degraded - please take immediate action (you probably need to increase max_connections in the Docker image and re-deploy.', + summary: '{{ $labels.instance }} has maxed out Postgres connections.', + }, + expr: ||| + sum by (instance) (pg_stat_activity_count{%(postgresExporterSelector)s}) + >= + sum by (instance) (pg_settings_max_connections{%(postgresExporterSelector)s}) + - + sum by (instance) (pg_settings_superuser_reserved_connections{%(postgresExporterSelector)s}) + ||| % $._config, + 'for': '1m', + labels: { + severity: 'warning', + }, + }, + { + alert: 'PostgreSQLHighConnections', + annotations: { + description: '{{ $labels.instance }} is exceeding 80% of the currently configured maximum Postgres connection limit (current value: {{ $value }}s). Please check utilization graphs and confirm if this is normal service growth, abuse or an otherwise temporary condition or if new resources need to be provisioned (or the limits increased, which is mostly likely).', + summary: '{{ $labels.instance }} is over 80% of max Postgres connections.', + }, + expr: ||| + sum by (instance) (pg_stat_activity_count{%(postgresExporterSelector)s}) + > + ( + sum by (instance) (pg_settings_max_connections{%(postgresExporterSelector)s}) + - + sum by (instance) (pg_settings_superuser_reserved_connections{%(postgresExporterSelector)s}) + ) * 0.8 + ||| % $._config, + 'for': '10m', + labels: { + severity: 'warning', + }, + }, + { + alert: 'PostgreSQLDown', + annotations: { + description: '{{ $labels.instance }} is rejecting query requests from the exporter, and thus probably not allowing DNS requests to work either. User services should not be effected provided at least 1 node is still alive.', + summary: 'PostgreSQL is not processing queries: {{ $labels.instance }}', + }, + expr: 'pg_up{%(postgresExporterSelector)s} != 1' % $._config, + 'for': '1m', + labels: { + severity: 'warning', + }, + }, + { + alert: 'PostgreSQLSlowQueries', + annotations: { + description: 'PostgreSQL high number of slow queries {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }} ', + summary: 'PostgreSQL high number of slow on {{ $labels.cluster }} for database {{ $labels.datname }} ', + }, + expr: ||| + avg( + rate by (datname) ( + pg_stat_activity_max_tx_duration{datname!~"template.*",%(postgresExporterSelector)s}[2m] + ) + ) > 2 * 60 + ||| % $._config, + 'for': '2m', + labels: { + severity: 'warning', + }, + }, + { + alert: 'PostgreSQLQPS', + annotations: { + description: 'PostgreSQL high number of queries per second on {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }}', + summary: 'PostgreSQL high number of queries per second {{ $labels.cluster }} for database {{ $labels.datname }}', + }, + expr: ||| + avg by (datname) ( + irate( + pg_stat_database_xact_commit{datname!~"template.*",%(postgresExporterSelector)s}[5m] + ) + + + irate( + pg_stat_database_xact_rollback{datname!~"template.*",%(postgresExporterSelector)s}[5m] + ) + ) > 10000 + ||| % $._config, + 'for': '5m', + labels: { + severity: 'warning', + }, + }, + { + alert: 'PostgreSQLCacheHitRatio', + annotations: { + description: 'PostgreSQL low on cache hit rate on {{ $labels.cluster }} for database {{ $labels.datname }} with a value of {{ $value }}', + summary: 'PostgreSQL low cache hit rate on {{ $labels.cluster }} for database {{ $labels.datname }}', + }, + expr: ||| + avg by (datname) ( + rate(pg_stat_database_blks_hit{datname!~"template.*",%(postgresExporterSelector)s}[5m]) + / + ( + rate( + pg_stat_database_blks_hit{datname!~"template.*",%(postgresExporterSelector)s}[5m] + ) + + + rate( + pg_stat_database_blks_read{datname!~"template.*",%(postgresExporterSelector)s}[5m] + ) + ) + ) < 0.98 + ||| % $._config, + 'for': '5m', + labels: { + severity: 'warning', + }, + }, + ], + }, + ], + }, +} diff --git a/postgres_mixin/config.libsonnet b/postgres_mixin/config.libsonnet new file mode 100644 index 00000000..d7bd7ac1 --- /dev/null +++ b/postgres_mixin/config.libsonnet @@ -0,0 +1,5 @@ +{ + _config+:: { + postgresExporterSelector: '', + }, +} diff --git a/postgres_mixin/dashboards/dashboards.libsonnet b/postgres_mixin/dashboards/dashboards.libsonnet new file mode 100644 index 00000000..d55f1ef5 --- /dev/null +++ b/postgres_mixin/dashboards/dashboards.libsonnet @@ -0,0 +1,5 @@ +{ + grafanaDashboards+:: { + 'postgres-overview.json': (import 'postgres-overview.json'), + }, +} diff --git a/postgres_mixin/mixin.libsonnet b/postgres_mixin/mixin.libsonnet index 98c7ea7d..119d2cdd 100644 --- a/postgres_mixin/mixin.libsonnet +++ b/postgres_mixin/mixin.libsonnet @@ -1,13 +1,3 @@ -{ - grafanaDashboards: { - 'postgres-overview.json': (import 'dashboards/postgres-overview.json'), - }, - - // Helper function to ensure that we don't override other rules, by forcing - // the patching of the groups list, and not the overall rules object. - local importRules(rules) = { - groups+: std.native('parseYaml')(rules)[0].groups, - }, - - prometheusAlerts+: importRules(importstr 'alerts/alerts.yaml'), -} +(import 'alerts/alerts.libsonnet') + +(import 'dashboards/dashboards.libsonnet') + +(import 'config.libsonnet')