diff options
Diffstat (limited to '')
| -rw-r--r-- | health/health.d/postgres.conf | 228 |
1 files changed, 228 insertions, 0 deletions
diff --git a/health/health.d/postgres.conf b/health/health.d/postgres.conf new file mode 100644 index 00000000..de4c0078 --- /dev/null +++ b/health/health.d/postgres.conf @@ -0,0 +1,228 @@ +# you can disable an alarm notification by setting the 'to' line to: silent + + template: postgres_total_connection_utilization + on: postgres.connections_utilization + class: Utilization + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of used + units: % + every: 1m + warn: $this > (($status >= $WARNING) ? (70) : (80)) + crit: $this > (($status == $CRITICAL) ? (80) : (90)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL connection utilization + info: Average total connection utilization over the last minute + to: dba + + template: postgres_acquired_locks_utilization + on: postgres.locks_utilization + class: Utilization + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of used + units: % + every: 1m + warn: $this > (($status >= $WARNING) ? (15) : (20)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL acquired locks utilization + info: Average acquired locks utilization over the last minute + to: dba + + template: postgres_txid_exhaustion_perc + on: postgres.txid_exhaustion_perc + class: Utilization + type: Database +component: PostgreSQL + hosts: * + calc: $txid_exhaustion + units: % + every: 1m + warn: $this > 90 + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL TXID exhaustion + info: Percent towards TXID wraparound + to: dba + +# Database alarms + + template: postgres_db_cache_io_ratio + on: postgres.db_cache_io_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of miss + calc: 100 - $this + units: % + every: 1m + warn: $this < (($status >= $WARNING) ? (70) : (60)) + crit: $this < (($status == $CRITICAL) ? (60) : (50)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL DB ${label:database} cache hit ratio + info: Average cache hit ratio in db ${label:database} over the last minute + to: dba + + template: postgres_db_transactions_rollback_ratio + on: postgres.db_transactions_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -5m unaligned of rollback + units: % + every: 1m + warn: $this > (($status >= $WARNING) ? (0) : (2)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL DB ${label:database} aborted transactions + info: Average aborted transactions percentage in db ${label:database} over the last five minutes + to: dba + + template: postgres_db_deadlocks_rate + on: postgres.db_deadlocks_rate + class: Errors + type: Database +component: PostgreSQL + hosts: * + lookup: sum -1m unaligned of deadlocks + units: deadlocks + every: 1m + warn: $this > (($status >= $WARNING) ? (0) : (10)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL DB ${label:database} deadlocks rate + info: Number of deadlocks detected in db ${label:database} in the last minute + to: dba + +# Table alarms + + template: postgres_table_cache_io_ratio + on: postgres.table_cache_io_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of miss + calc: 100 - $this + units: % + every: 1m + warn: $this < (($status >= $WARNING) ? (70) : (60)) + crit: $this < (($status == $CRITICAL) ? (60) : (50)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} cache hit ratio + info: Average cache hit ratio in db ${label:database} table ${label:table} over the last minute + to: dba + + template: postgres_table_index_cache_io_ratio + on: postgres.table_index_cache_io_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of miss + calc: 100 - $this + units: % + every: 1m + warn: $this < (($status >= $WARNING) ? (70) : (60)) + crit: $this < (($status == $CRITICAL) ? (60) : (50)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} index cache hit ratio + info: Average index cache hit ratio in db ${label:database} table ${label:table} over the last minute + to: dba + + template: postgres_table_toast_cache_io_ratio + on: postgres.table_toast_cache_io_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of miss + calc: 100 - $this + units: % + every: 1m + warn: $this < (($status >= $WARNING) ? (70) : (60)) + crit: $this < (($status == $CRITICAL) ? (60) : (50)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} toast cache hit ratio + info: Average TOAST hit ratio in db ${label:database} table ${label:table} over the last minute + to: dba + + template: postgres_table_toast_index_cache_io_ratio + on: postgres.table_toast_index_cache_io_ratio + class: Workload + type: Database +component: PostgreSQL + hosts: * + lookup: average -1m unaligned of miss + calc: 100 - $this + units: % + every: 1m + warn: $this < (($status >= $WARNING) ? (70) : (60)) + crit: $this < (($status == $CRITICAL) ? (60) : (50)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} index toast hit ratio + info: average index TOAST hit ratio in db ${label:database} table ${label:table} over the last minute + to: dba + + template: postgres_table_bloat_size_perc + on: postgres.table_bloat_size_perc + class: Errors + type: Database +component: PostgreSQL + hosts: * + calc: ($table_size > (1024 * 1024 * 100)) ? ($bloat) : (0) + units: % + every: 1m + warn: $this > (($status >= $WARNING) ? (60) : (70)) + crit: $this > (($status == $CRITICAL) ? (70) : (80)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} bloat size + info: Bloat size percentage in db ${label:database} table ${label:table} + to: dba + + template: postgres_table_last_autovacuum_time + on: postgres.table_autovacuum_since_time + class: Errors + type: Database +component: PostgreSQL + hosts: !* + calc: $time + units: seconds + every: 1m + warn: $this != nan AND $this > (60 * 60 * 24 * 7) + summary: PostgreSQL table ${label:table} db ${label:database} last autovacuum + info: Time elapsed since db ${label:database} table ${label:table} was vacuumed by the autovacuum daemon + to: dba + + template: postgres_table_last_autoanalyze_time + on: postgres.table_autoanalyze_since_time + class: Errors + type: Database +component: PostgreSQL + hosts: !* + calc: $time + units: seconds + every: 1m + warn: $this != nan AND $this > (60 * 60 * 24 * 7) + summary: PostgreSQL table ${label:table} db ${label:database} last autoanalyze + info: Time elapsed since db ${label:database} table ${label:table} was analyzed by the autovacuum daemon + to: dba + +# Index alarms + + template: postgres_index_bloat_size_perc + on: postgres.index_bloat_size_perc + class: Errors + type: Database +component: PostgreSQL + hosts: * + calc: ($index_size > (1024 * 1024 * 10)) ? ($bloat) : (0) + units: % + every: 1m + warn: $this > (($status >= $WARNING) ? (60) : (70)) + crit: $this > (($status == $CRITICAL) ? (70) : (80)) + delay: down 15m multiplier 1.5 max 1h + summary: PostgreSQL table ${label:table} db ${label:database} index bloat size + info: Bloat size percentage in db ${label:database} table ${label:table} index ${label:index} + to: dba |