diff options
Diffstat (limited to '')
-rw-r--r-- | src/health/health.d/clickhouse.conf | 140 |
1 files changed, 140 insertions, 0 deletions
diff --git a/src/health/health.d/clickhouse.conf b/src/health/health.d/clickhouse.conf new file mode 100644 index 000000000..e24f71830 --- /dev/null +++ b/src/health/health.d/clickhouse.conf @@ -0,0 +1,140 @@ +# you can disable an alarm notification by setting the 'to' line to: silent + + template: clickhouse_restarted + on: clickhouse.uptime + class: Error + type: Database +component: ClickHouse + calc: $uptime + units: seconds + every: 10s + warn: $this > 1 AND $this < 180 + summary: ClickHouse restart detected + info: ClickHouse has recently been restarted + to: silent + + template: clickhouse_queries_preempted + on: clickhouse.queries_preempted + class: Workload + type: Database +component: ClickHouse + lookup: max -1m unaligned + units: preempted_queries + every: 10s + warn: $this > 0 + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse preempted queries detected + info: ClickHouse has queries that are stopped and waiting due to priority setting + to: dba + + template: clickhouse_long_running_query + on: clickhouse.longest_running_query_time + class: Latency + type: Database +component: ClickHouse + lookup: max -1m unaligned + units: seconds + every: 10s + warn: $this > (($status >= $WARNING) ? (300) : (600)) + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse long-running query detected + info: ClickHouse has a long-running query exceeding the threshold + to: dba + + template: clickhouse_rejected_inserts + on: clickhouse.rejected_inserts + class: Workload + type: Database +component: ClickHouse + lookup: sum -1m unaligned + units: rejected_inserts + every: 10s + warn: $this > 0 + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse rejected INSERT queries detected + info: ClickHouse has INSERT queries that are rejected due to high number of active data parts for partition in a MergeTree + to: dba + + template: clickhouse_delayed_inserts + on: clickhouse.delayed_inserts + class: Workload + type: Database +component: ClickHouse + lookup: sum -1m unaligned + units: delayed_inserts + every: 10s + warn: $this > 0 + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse delayed INSERT queries detected + info: ClickHouse has INSERT queries that are throttled due to high number of active data parts for partition in a MergeTree + to: silent + + template: clickhouse_replication_lag + on: clickhouse.replicas_max_absolute_delay + class: Workload + type: Database +component: ClickHouse + lookup: avg -1m unaligned + units: seconds + every: 10s + warn: $this > (($status >= $WARNING) ? (250) : (300)) + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse high replication lag detected + info: ClickHouse is experiencing replication lag greater than 5 minutes + to: dba + + template: clickhouse_replicated_readonly_tables + on: clickhouse.replicated_readonly_tables + class: Error + type: Database +component: ClickHouse + lookup: max -1m unaligned + units: readonly_tables + every: 10s + warn: $this > 0 + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse replicated tables in readonly state detected + info: ClickHouse has replicated tables in readonly state due to ZooKeeper session loss/startup without ZooKeeper configured + to: dba + + template: clickhouse_max_part_count_for_partition + on: clickhouse.max_part_count_for_partition + class: Workload + type: Database +component: ClickHouse + lookup: avg -1m unaligned + units: parts + every: 10s + warn: $this > (($status >= $WARNING) ? (200) : (300)) + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse high parts/partition detected + info: ClickHouse high number of parts per partition + to: dba + + template: clickhouse_distributed_connections_failures + on: clickhouse.distributed_connections_fail_exhausted_retries + class: Error + type: Database +component: ClickHouse + lookup: sum -1m unaligned + units: failures + every: 10s + warn: $this > 0 + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse distributed connections failures detected + info: ClickHouse has failed distributed connections after exhausting all retry attempts + to: dba + + template: clickhouse_distributed_files_to_insert + on: clickhouse.distributed_files_to_insert + class: Workload + type: Database +component: ClickHouse + lookup: max -1m unaligned + units: files + every: 10s + warn: $this > (($status >= $WARNING) ? (40) : (80)) + delay: down 5m multiplier 1.5 max 1h + summary: ClickHouse high files to insert detected + info: ClickHouse high number of pending files to process for asynchronous insertion into Distributed tables + to: silent |