Use the operator's credentials to connect to the ClickHouse instance and run health checks: * Access point is available (use chi level service) * Distributed query check: SELECT count() FROM cluster('all-sharded', cluster('all-sharded', system.one)) * Zookeeper check -- run only if zookeeper is a part of CHI spec.configuration: SELECT count() FROM `system`.`zookeeper` WHERE `path` = '/' * No readonly replicas: SELECT max(`value`) FROM cluster('{cluster}', `system`.`metrics`) WHERE `metric` = 'ReadonlyReplica' * No delayed inserts: SELECT `value` FROM `system`.`metrics` WHERE `metric` = 'DelayedInserts' * Healthy schema: MaxPartCountForPartition: >150 yellow, >300 red: select value from system.asynchronous_metrics where metric='MaxPartCountForPartition' Provide some kind of warning if the health checks are failing.
Use the operator's credentials to connect to the ClickHouse instance and run health checks:
SELECT count() FROM cluster('all-sharded', cluster('all-sharded', system.one))
SELECT count() FROM
system.zookeeperWHEREpath= '/'SELECT max(
value) FROM cluster('{cluster}',system.metrics) WHEREmetric= 'ReadonlyReplica'SELECT
valueFROMsystem.metricsWHEREmetric= 'DelayedInserts'select value from system.asynchronous_metrics where metric='MaxPartCountForPartition'
Provide some kind of warning if the health checks are failing.