Description: Number of spillable operator instances that triggered at least one spill, broken down by storage backend (local, remote). Incremented once per operator instance at the first flush callback.
Description: Cumulative wall-clock time spent in write-side spill IO (block append and flush), broken down by storage backend. Useful for tracking write-side spill performance.
Description: Cumulative wall-clock time spent in read-side spill IO (block reads during restore), broken down by storage backend. Useful for tracking read-side spill performance.
Description: Whether this FE failed to initialize Ranger audit. 1 means authorization still works but this FE writes no Ranger audit event until it is restarted with a fixed audit configuration; the FE log names the destination that failed. 0 otherwise. A common cause is an audit destination that the FE does not ship: only the file and solr Ranger audit destinations are available.
Description: Ratio of external table scan thread time slices used by each resource group to the total used by all resource groups. This is an average value over the time interval between two metric retrievals.
Description: Ratio of pipeline thread time slices used by each resource group to the total used by all resource groups. This is an average value over the time interval between two metric retrievals.
Description: Execution time accumulated by each level of the pipeline driver queue of each resource group, divided by the factor of the level. The level label is the level, from 0 to 7, and a driver moves to a higher level as it runs longer. The next driver is taken from the non-empty level with the smallest value. When a level turns from empty to non-empty, its value is raised to at least the value of the level scheduled last. To keep values within the numeric range, all levels and the scheduling watermark occasionally subtract a common time origin. This gauge can decrease during that rebase; the cumulative ready-wait and schedule-count counters are preserved.
Description: Cumulative number of drivers taken from each level of the pipeline driver queue of each resource group. This counter includes draining resource-group versions and retains their final totals after removal. Updating, deleting, or recreating a group with the same name preserves the total within the BE/CN process.
Description: Cumulative time that the drivers taken from each level of the pipeline driver queue of each resource group waited in the ready queue. Like the schedule-count counter, it includes draining versions and preserves totals across group updates, deletion, and recreation with the same name within the BE/CN process. Divide its increase by the increase of resource_group_driver_queue_level_schedule_count to get the average wait of the level.
Description: Estimated number of CPU cores currently in use by each resource group. This is an average value over the time interval between two metric retrievals.
Description: Ratio of internal table scan thread time slices used by each resource group to the total used by all resource groups. This is an average value over the time interval between two metric retrievals.