Scylla integration metrics

The official Datadog integration for monitoring Scylla. It collects 504 metrics.

Definitions as of 2026-08-05

Official summary

Track cluster resources, latencies, health, and much more.

Metric types

count (occurrences in the interval): 394
gauge (value at a point in time): 110

Metrics

Descriptions are the official definitions, unedited.

Metric	Type	Unit
`scylla.alien.receive_batch_queue_length`Current receive batch queue length	gauge	-
`scylla.alien.total_received_messages`Total number of received messages	count	-
`scylla.alien.total_sent_messages`Total number of sent messages	count	-
`scylla.batchlog_manager.total_write_replay_attempts`Counts write operations issued in a batchlog replay flow. The high value of this metric indicates that we have a long batch replay list.	count	write
`scylla.cache.active_reads`number of currently active reads	gauge	read
`scylla.cache.bytes_total`total size of memory for the cache	gauge	byte
`scylla.cache.bytes_used`current bytes used by the cache out of the total size of memory	gauge	byte
`scylla.cache.concurrent_misses_same_key`total number of operation with misses same key	count	miss
`scylla.cache.dummy_row_hits`total number of dummy rows touched by reads in cache	count	-
`scylla.cache.mispopulations`number of entries not inserted by reads	count	-
`scylla.cache.partition_evictions`total number of evicted partitions	count	eviction
`scylla.cache.partition_hits`number of partitions needed by reads and found in cache	count	hit
`scylla.cache.partition_insertions`total number of partitions added to cache	count	-
`scylla.cache.partition_merges`total number of partitions merged	count	-
`scylla.cache.partition_misses`number of partitions needed by reads and missing in cache	count	miss
`scylla.cache.partition_removals`total number of invalidated partitions	count	-
`scylla.cache.partitions`total number of cached partitions	gauge	-
`scylla.cache.pinned_dirty_memory_overload`amount of pinned bytes that we tried to unpin over the limit. This should sit constantly at 0; and any number different than 0 is indicative of a bug	count	byte
`scylla.cache.range_tombstone_reads`total amount of range tombstones processed during read	count	-
`scylla.cache.reads`number of started reads	count	get
`scylla.cache.reads_with_misses`number of reads which had to read from sstables	count	read
`scylla.cache.row_evictions`total number of rows evicted from cache	count	eviction
`scylla.cache.row_hits`total number of rows needed by reads and found in cache	count	hit
`scylla.cache.row_insertions`total number of rows added to cache	count	set
`scylla.cache.row_misses`total number of rows needed by reads and missing in cache	count	miss
`scylla.cache.row_removals`total number of invalidated rows	count	eviction
`scylla.cache.row_tombstone_reads`total amount of row tombstones processed during read	count	-
`scylla.cache.rows`total number of cached rows	gauge	row
`scylla.cache.rows_compacted_with_tombstones`Number of rows scanned during write of a tombstone for the purpose of compaction in cache	count	-
`scylla.cache.rows_dropped_by_tombstones`Number of rows dropped in cache by a tombstone write	count	-
`scylla.cache.rows_dropped_from_memtable`total number of rows in memtables which were dropped during cache update on memtable flush	count	row
`scylla.cache.rows_merged_from_memtable`total number of rows in memtables which were merged with existing rows during cache update on memtable flush	count	row
`scylla.cache.rows_processed_from_memtable`total number of rows in memtables which were processed during cache update on memtable flush	count	row
`scylla.cache.sstable_partition_skips`number of times sstable reader was fast forwarded across partitions	count	-
`scylla.cache.sstable_reader_recreations`number of times sstable reader was recreated due to memtable flush	count	-
`scylla.cache.sstable_row_skips`number of times sstable reader was fast forwarded within a partition	count	row
`scylla.cache.static_row_insertions`total number of static rows added to cache	count	row
`scylla.cdc.operations_failed`number of failed CDC operations	count	-
`scylla.cdc.operations_on_clustering_row_performed_failed`number of failed CDC operations that processed a clustering_row	count	-
`scylla.cdc.operations_on_clustering_row_performed_total`number of total CDC operations that processed a clustering_row	count	-
`scylla.cdc.operations_on_list_performed_failed`number of failed CDC operations that processed a list	count	-
`scylla.cdc.operations_on_list_performed_total`number of total CDC operations that processed a list	count	-
`scylla.cdc.operations_on_map_performed_failed`number of failed CDC operations that processed a map	count	-
`scylla.cdc.operations_on_map_performed_total`number of total CDC operations that processed a map	count	-
`scylla.cdc.operations_on_partition_delete_performed_failed`number of failed CDC operations that processed a partition_delete	count	-
`scylla.cdc.operations_on_partition_delete_performed_total`number of total CDC operations that processed a partition_delete	count	-
`scylla.cdc.operations_on_range_tombstone_performed_failed`number of failed CDC operations that processed a range_tombstone	count	-
`scylla.cdc.operations_on_range_tombstone_performed_total`number of total CDC operations that processed a range_tombstone	count	-
`scylla.cdc.operations_on_row_delete_performed_failed`number of failed CDC operations that processed a row_delete	count	-
`scylla.cdc.operations_on_row_delete_performed_total`number of total CDC operations that processed a row_delete	count	-
`scylla.cdc.operations_on_set_performed_failed`number of failed CDC operations that processed a set	count	-
`scylla.cdc.operations_on_set_performed_total`number of total CDC operations that processed a set	count	-
`scylla.cdc.operations_on_static_row_performed_failed`number of failed CDC operations that processed a static_row	count	-
`scylla.cdc.operations_on_static_row_performed_total`number of total CDC operations that processed a static_row	count	-
`scylla.cdc.operations_on_udt_performed_failed`number of failed CDC operations that processed a udt	count	-
`scylla.cdc.operations_on_udt_performed_total`number of total CDC operations that processed a udt	count	-
`scylla.cdc.operations_total`number of total CDC operations	count	-
`scylla.cdc.operations_with_postimage_failed`number of failed operations that included postimage	count	-
`scylla.cdc.operations_with_postimage_total`number of total operations that included postimage	count	-
`scylla.cdc.operations_with_preimage_failed`number of failed operations that included preimage	count	-
`scylla.cdc.operations_with_preimage_total`number of total operations that included preimage	count	-
`scylla.cdc.preimage_selects_failed`number of failed preimage queries performed	count	-
`scylla.cdc.preimage_selects_total`number of total preimage queries performed	count	-
`scylla.commitlog.active_allocations`Current number of active allocations.	gauge	-
`scylla.commitlog.alloc`Counts a number of times a new mutation has been added to a segment. Divide bytes_written by this value to get the average number of bytes per mutation written to the disk.	count	-
`scylla.commitlog.allocating_segments`Holds the number of not closed segments that still have some free space. This value should not get too high.	gauge	-
`scylla.commitlog.blocked_on_new_segment`Number of allocations blocked on acquiring new segment.	gauge	-
`scylla.commitlog.bytes_flush_requested`Counts number of bytes requested to be flushed (persisted).	count	-
`scylla.commitlog.bytes_released`Counts number of bytes released from disk. (Deleted/recycled)	count	-
`scylla.commitlog.bytes_written`Counts a number of bytes written to the disk. Divide this value by "alloc" to get the average number of bytes per mutation written to the disk.	count	byte
`scylla.commitlog.cycle`Counts a number of commitlog write cycles - when the data is written from the internal memory buffer to the disk.	count	-
`scylla.commitlog.disk_active_bytes`Holds size of disk space in bytes used for data so far. A too high value indicates that we have some bottleneck in the writing to sstables path.	gauge	-
`scylla.commitlog.disk_slack_end_bytes`Holds size of disk space in bytes unused because of segment switching (end slack). A too high value indicates that we do not write enough data to each segment.	gauge	-
`scylla.commitlog.disk_total_bytes`Holds a size of disk space in bytes used for data so far. A too high value indicates that we have some bottleneck in the writing to sstables path.	gauge	byte
`scylla.commitlog.flush`Counts a number of times the flush() method was called for a file.	count	-
`scylla.commitlog.flush_limit_exceeded`Counts a number of times a flush limit was exceeded. A non-zero value indicates that there are too many pending flush operations (see pending_flushes) and some of them will be blocked till the total amount of pending flush operations drops below 5.	count	-
`scylla.commitlog.memory_buffer_bytes`Holds the total number of bytes in internal memory buffers.	gauge	byte
`scylla.commitlog.pending_allocations`Holds a number of currently pending allocations. A non-zero value indicates that we have a bottleneck in the disk write flow.	gauge	-
`scylla.commitlog.pending_flushes`Holds a number of currently pending flushes. See the related flush_limit_exceeded metric.	gauge	-
`scylla.commitlog.requests_blocked_memory`Counts a number of requests blocked due to memory pressure. A non-zero value indicates that the commitlog memory quota is not enough to serve the required amount of requests.	count	request
`scylla.commitlog.segments`Holds the current number of segments.	gauge	-
`scylla.commitlog.slack`Counts a number of unused bytes written to the disk due to disk segment alignment.	count	byte
`scylla.commitlog.unused_segments`Holds the current number of unused segments. A non-zero value indicates that the disk write path became temporary slow.	gauge	-
`scylla.compaction.manager_backlog`Holds the sum of compaction backlog for all tables in the system.	gauge	-
`scylla.compaction_manager.compactions`Holds the number of currently active compactions.	gauge	-
`scylla.compaction_manager.completed_compactions`Holds the number of completed compaction tasks.	count	-
`scylla.compaction_manager.failed_compactions`Holds the number of failed compaction tasks.	count	-
`scylla.compaction_manager.normalized_backlog`Holds the sum of normalized compaction backlog for all tables in the system. Backlog is normalized by dividing backlog by shard's available memory.	gauge	-
`scylla.compaction_manager.pending_compactions`Holds the number of compaction tasks waiting for an opportunity to run.	gauge	-
`scylla.compaction_manager.postponed_compactions`Holds the number of tables with postponed compaction.	gauge	-
`scylla.compaction_manager.validation_errors`Holds the number of encountered validation errors.	count	-
`scylla.cql.authorized_prepared_statements_cache_evictions`Counts a number of authenticated prepared statements cache entries evictions.	count	-
`scylla.cql.authorized_prepared_statements_cache_size`A number of entries in the authenticated prepared statements cache.	gauge	-
`scylla.cql.batches`Counts a total number of CQL BATCH requests.	count	-
`scylla.cql.batches_pure_logged`Counts a total number of LOGGED batches that were executed as LOGGED batches.	count	-
`scylla.cql.batches_pure_unlogged`Counts a total number of UNLOGGED batches that were executed as UNLOGGED batches.	count	-
`scylla.cql.batches_unlogged_from_logged`Counts a total number of LOGGED batches that were executed as UNLOGGED batches.	count	-
`scylla.cql.deletes`Counts a total number of CQL DELETE requests.	count	-
`scylla.cql.deletes_per_ks`Counts the number of CQL DELETE requests executed on particular keyspaces. Label who' indicates where the reqs come from (clients or DB internals)	count	-
`scylla.cql.filtered_read_requests`Counts a total number of CQL read requests that required ALLOW FILTERING. See filtered_rows_read_total to compare how many rows needed to be filtered.	count	-
`scylla.cql.filtered_rows_dropped_total`Counts a number of rows read during CQL requests that required ALLOW FILTERING and dropped by the filter. Number similar to filtered_rows_read_total indicates that filtering is not accurate and might cause performance degradation.	count	row
`scylla.cql.filtered_rows_matched_total`Counts a number of rows read during CQL requests that required ALLOW FILTERING and accepted by the filter. Number similar to filtered_rows_read_total indicates that filtering is accurate.	count	row
`scylla.cql.filtered_rows_read_total`Counts a total number of rows read during CQL requests that required ALLOW FILTERING. See filtered_rows_matched_total and filtered_rows_dropped_total for information how accurate filtering queries are.	count	row
`scylla.cql.inserts`Counts a total number of CQL INSERT requests.	count	-
`scylla.cql.inserts_per_ks`Counts the number of CQL INSERT requests executed on particular keyspaces. Label who' indicates where the reqs come from (clients or DB internals).	count	-
`scylla.cql.prepared_cache_evictions`Counts a number of prepared statements cache entries evictions.	count	eviction
`scylla.cql.prepared_cache_memory_footprint`Size (in bytes) of the prepared statements cache.	gauge	byte
`scylla.cql.prepared_cache_size`A number of entries in the prepared statements cache.	gauge	-
`scylla.cql.reads`Counts a total number of CQL read requests.	count	read
`scylla.cql.reads_per_ks`Counts the number of CQL SELECT requests executed on particular keyspaces. Label who' indicates where the reqs come from (clients or DB internals)	count	-
`scylla.cql.reverse_queries`Counts number of CQL SELECT requests with ORDER BY DESC.	count	query
`scylla.cql.rows_read`Counts a total number of rows read during CQL requests.	count	row
`scylla.cql.secondary_index_creates`Counts a total number of CQL CREATE INDEX requests.	count	query
`scylla.cql.secondary_index_drops`Counts a total number of CQL DROP INDEX requests.	count	query
`scylla.cql.secondary_index_reads`Counts a total number of CQL read requests performed using secondary indexes.	count	query
`scylla.cql.secondary_index_rows_read`Counts a total number of rows read during CQL requests performed using secondary indexes.	count	row
`scylla.cql.select_allow_filtering`Counts the number of SELECT query executions with ALLOW FILTERING option.	count	-
`scylla.cql.select_bypass_caches`Counts the number of SELECT query executions with BYPASS CACHE option.	count	-
`scylla.cql.select_parallelized`Counts the number of parallelized aggregation SELECT query executions.	count	-
`scylla.cql.select_partition_range_scan`Counts the number of SELECT query executions requiring partition range scan.	count	-
`scylla.cql.select_partition_range_scan_no_bypass_cache`Counts the number of SELECT query executions requiring partition range scan without BYPASS CACHE option.	count	-
`scylla.cql.statements_in_batches`Counts a total number of sub-statements in CQL BATCH requests.	count	query
`scylla.cql.unpaged_select_queries`Counts number of unpaged CQL SELECT requests.	count	query
`scylla.cql.unpaged_select_queries_per_ks`Counts the number of unpaged CQL SELECT requests against particular keyspaces.	count	-
`scylla.cql.unprivileged_entries_evictions_on_size`Counts a number of evictions of prepared statements from the prepared statements cache after they have been used only once. An increasing counter suggests the user may be preparing a different statement for each request instead of reusing the same prepared statement with parameters.	count	-
`scylla.cql.updates`Counts a total number of CQL UPDATE requests.	count	query
`scylla.cql.updates_per_ks`Counts the number of CQL UPDATE requests executed on particular keyspaces. Label who' indicates where the reqs come from (clients or DB internals)	count	-
`scylla.cql.user_prepared_auth_cache_footprint`Size (in bytes) of the authenticated prepared statements cache.	gauge	byte
`scylla.database.active_reads`Holds the number of currently active read operations.	gauge	read
`scylla.database.active_reads_memory_consumption`Holds the amount of memory consumed by currently active read operations. If this value gets close to 2474639 we are likely to start dropping new read requests. In that case sstable_read_queue_overloads is going to get a non-zero value.	gauge	byte
`scylla.database.clustering_filter_count`Counts bloom filter invocations.	count	-
`scylla.database.clustering_filter_fast_path_count`Counts number of times bloom filtering short cut to include all sstables when only one full range was specified.	count	-
`scylla.database.clustering_filter_sstables_checked`Counts sstables checked after applying the bloom filter. High value indicates that bloom filter is not very efficient.	count	-
`scylla.database.clustering_filter_surviving_sstables`Counts sstables that survived the clustering key filtering. High value indicates that bloom filter is not very efficient and still have to access a lot of sstables to get data.	count	-
`scylla.database.counter_cell_lock_acquisition`The number of acquired counter cell locks.	count	-
`scylla.database.counter_cell_lock_pending`The number of counter updates waiting for a lock.	gauge	-
`scylla.database.disk_reads`Holds the number of currently active disk read operations.	gauge	-
`scylla.database.dropped_view_updates`Counts the number of view updates that have been dropped due to cluster overload.	count	-
`scylla.database.large_partition_exceeding_threshold`Number of large partitions exceeding compaction_large_partition_warning_threshold_mb. Large partitions have performance impact and should be avoided; check the documentation for details.	count	-
`scylla.database.multishard_query_failed_reader_saves`The number of times the saving of a shard reader failed.	count	-
`scylla.database.multishard_query_failed_reader_stops`The number of times the stopping of a shard reader failed.	count	-
`scylla.database.multishard_query_unpopped_bytes`The total number of bytes that were extracted from the shard reader but were unconsumed by the query and moved back into the reader.	count	byte
`scylla.database.multishard_query_unpopped_fragments`The total number of fragments that were extracted from the shard reader but were unconsumed by the query and moved back into the reader.	count	-
`scylla.database.paused_reads`The number of currently active reads that are temporarily paused.	gauge	read
`scylla.database.paused_reads_permit_based_evictions`The number of paused reads evicted to free up permits. Permits are required for new reads to start; and the database will evict paused reads (if any) to be able to admit new ones; if there is a shortage of permits.	count	eviction
`scylla.database.querier_cache_drops`Counts querier cache lookups that found a cached querier but had to drop it due to position mismatch	count	eviction
`scylla.database.querier_cache_lookups`Counts querier cache lookups (paging queries)	count	get
`scylla.database.querier_cache_memory_based_evictions`Counts querier cache entries that were evicted because the memory usage of the cached queriers were above the limit.	count	eviction
`scylla.database.querier_cache_misses`Counts querier cache lookups that failed to find a cached querier	count	miss
`scylla.database.querier_cache_population`The number of entries currently in the querier cache.	gauge	-
`scylla.database.querier_cache_resource_based_evictions`Counts querier cache entries that were evicted to free up resources (limited by reader concurrency limits) necessary to create new readers.	count	eviction
`scylla.database.querier_cache_time_based_evictions`Counts querier cache entries that timed out and were evicted.	count	eviction
`scylla.database.queued_reads`Holds the number of currently queued read operations.	gauge	read
`scylla.database.reads_shed_due_to_overload`The number of reads shed because the admission queue reached its max capacity. When the queue is full, excessive reads are shed to avoid overload.	count	-
`scylla.database.requests_blocked_memory`Holds the number of requests blocked due to reaching the memory quota (27839692B). Non-zero value indicates that our bottleneck is memory and more specifically - the memory quota allocated for the "database" component.	count	request
`scylla.database.requests_blocked_memory_current`Holds the current number of requests blocked due to reaching the memory quota (27839692B). Non-zero value indicates that our bottleneck is memory and more specifically - the memory quota allocated for the "database" component.	gauge	request
`scylla.database.schema_changed`The number of times the schema changed	count	-
`scylla.database.short_data_queries`The rate of data queries (data or digest reads) that returned less rows than requested due to result size limiting.	count	query
`scylla.database.short_mutation_queries`The rate of mutation queries that returned less rows than requested due to result size limiting.	count	query
`scylla.database.sstable_read_queue_overloads`Counts the number of times the sstable read queue was overloaded. A non-zero value indicates that we have to drop read requests because they arrive faster than we can serve them.	count	-
`scylla.database.sstables_read`Holds the number of currently read sstables.	gauge	-
`scylla.database.total_reads`Counts the total number of successful reads on this shard.	count	read
`scylla.database.total_reads_failed`Counts the total number of failed read operations. Add the total_reads to this value to get the total amount of reads issued on this shard.	count	read
`scylla.database.total_reads_rate_limited`Counts read operations which were rejected on the replica side because the per-partition limit was reached.	count	-
`scylla.database.total_result_bytes`Holds the current amount of memory used for results.	gauge	byte
`scylla.database.total_view_updates_failed_local`Total number of view updates generated for tables and failed to be applied locally.	count	-
`scylla.database.total_view_updates_failed_remote`Total number of view updates generated for tables and failed to be sent to remote replicas.	count	-
`scylla.database.total_view_updates_pushed_local`Total number of view updates generated for tables and applied locally.	count	-
`scylla.database.total_view_updates_pushed_remote`Total number of view updates generated for tables and sent to remote replicas.	count	-
`scylla.database.total_writes`Counts the total number of successful write operations performed by this shard.	count	write
`scylla.database.total_writes_failed`Counts the total number of failed write operations. A sum of this value plus total_writes represents a total amount of writes attempted on this shard.	count	write
`scylla.database.total_writes_rate_limited`Counts write operations which were rejected on the replica side because the per-partition limit was reached.	count	-
`scylla.database.total_writes_timedout`Counts write operations failed due to a timeout. A positive value is a sign of storage being overloaded.	count	write
`scylla.database.view_building_paused`Counts the number of times view building process was paused (e.g. due to node unavailability).	count	-
`scylla.database.view_update_backlog`Holds the current size in bytes of the pending view updates for all tables	count	byte
`scylla.execution_stages.function_calls_enqueued`Counts function calls added to execution stages queues	count	-
`scylla.execution_stages.function_calls_executed`Counts function calls executed by execution stages	count	-
`scylla.execution_stages.tasks_preempted`Counts tasks which were preempted before execution all queued operations	count	-
`scylla.execution_stages.tasks_scheduled`Counts tasks scheduled by execution stages	count	-
`scylla.forward_service.requests_dispatched_to_other_nodes`how many forward requests were dispatched to other nodes	count	-
`scylla.forward_service.requests_dispatched_to_own_shards`how many forward requests were dispatched to local shards	count	-
`scylla.forward_service.requests_executed`how many forward requests were executed	count	-
`scylla.gossip.heart_beat`Heartbeat of the current Node.	count	-
`scylla.gossip.live`How many live nodes the current node sees	gauge	-
`scylla.gossip.unreachable`How many unreachable nodes the current node sees	gauge	-
`scylla.hints.for_views_manager_corrupted_files`Number of hints files that were discarded during sending because the file was corrupted.	count	file
`scylla.hints.for_views_manager_discarded`Number of hints that were discarded during sending (too old; schema changed; etc.).	count	-
`scylla.hints.for_views_manager_dropped`Number of dropped hints.	count	-
`scylla.hints.for_views_manager_errors`Number of errors during hints writes.	count	error
`scylla.hints.for_views_manager_pending_drains`Number of tasks waiting in the queue for draining hints	gauge	-
`scylla.hints.for_views_manager_pending_sends`Number of tasks waiting in the queue for sending a hint	gauge	-
`scylla.hints.for_views_manager_sent`Number of sent hints.	count	-
`scylla.hints.for_views_manager_size_of_hints_in_progress`Size of hinted mutations that are scheduled to be written.	gauge	-
`scylla.hints.for_views_manager_written`Number of successfully written hints.	count	-
`scylla.hints.manager_corrupted_files`Number of hints files that were discarded during sending because the file was corrupted.	count	-
`scylla.hints.manager_discarded`Number of hints that were discarded during sending (too old; schema changed; etc.).	count	-
`scylla.hints.manager_dropped`Number of dropped hints.	count	-
`scylla.hints.manager_errors`Number of errors during hints writes.	count	error
`scylla.hints.manager_pending_drains`Number of tasks waiting in the queue for draining hints	gauge	-
`scylla.hints.manager_pending_sends`Number of tasks waiting in the queue for sending a hint	gauge	-
`scylla.hints.manager_sent`Number of sent hints.	count	-
`scylla.hints.manager_size_of_hints_in_progress`Size of hinted mutations that are scheduled to be written.	gauge	-
`scylla.hints.manager_written`Number of successfully written hints.	count	-
`scylla.httpd.connections_current`The current number of open connections	gauge	connection
`scylla.httpd.connections_total`The total number of connections opened	count	connection
`scylla.httpd.read_errors`The total number of errors while reading http requests	count	error
`scylla.httpd.reply_errors`The total number of errors while replying to http	count	error
`scylla.httpd.requests_served`The total number of http requests served	count	request
`scylla.io_queue.adjusted_consumption`Consumed disk capacity units adjusted for class shares and idling preemption	count	-
`scylla.io_queue.consumption`Accumulated disk capacity units consumed by this class; an increment per-second rate indicates full utilization	count	-
`scylla.io_queue.delay`total delay time in the queue	gauge	-
`scylla.io_queue.disk_queue_length`Number of requests in the disk	gauge	-
`scylla.io_queue.queue_length`Number of requests in the queue	gauge	request
`scylla.io_queue.shares`current amount of shares	gauge	-
`scylla.io_queue.starvation_time_sec`Total time spent starving for disk	count	-
`scylla.io_queue.total_bytes`Total bytes passed in the queue	count	byte
`scylla.io_queue.total_delay_sec`Total time spent in the queue	count	-
`scylla.io_queue.total_exec_sec`Total time spent in disk	count	-
`scylla.io_queue.total_operations`Total bytes passed in the queue	count	byte
`scylla.io_queue.total_read_bytes`Total read bytes passed in the queue	count	-
`scylla.io_queue.total_read_ops`Total read operations passed in the queue	count	-
`scylla.io_queue.total_split_bytes`Total number of bytes split	count	-
`scylla.io_queue.total_split_ops`Total number of requests split	count	-
`scylla.io_queue.total_write_bytes`Total write bytes passed in the queue	count	-
`scylla.io_queue.total_write_ops`Total write operations passed in the queue	count	-
`scylla.lsa.free_space`Holds a current amount of free memory that is under lsa control.	gauge	byte
`scylla.lsa.large_objects_total_space_bytes`Holds a current size of allocated non-LSA memory.	gauge	byte
`scylla.lsa.memory_allocated`Counts number of bytes which were requested from LSA allocator.	count	byte
`scylla.lsa.memory_compacted`Counts number of bytes which were copied as part of segment compaction.	count	byte
`scylla.lsa.memory_evicted`Counts number of bytes which were evicted.	count	-
`scylla.lsa.memory_freed`Counts number of bytes which were requested to be freed in LSA.	count	-
`scylla.lsa.non_lsa_used_space_bytes`Holds a current amount of used non-LSA memory.	gauge	byte
`scylla.lsa.occupancy`Holds a current portion (in percents) of the used memory.	gauge	percent
`scylla.lsa.segments_compacted`Counts a number of compacted segments.	count	-
`scylla.lsa.segments_migrated`Counts a number of migrated segments.	count	-
`scylla.lsa.small_objects_total_space_bytes`Holds a current size of "small objects" memory region in bytes.	gauge	byte
`scylla.lsa.small_objects_used_space_bytes`Holds a current amount of used "small objects" memory in bytes.	gauge	byte
`scylla.lsa.total_space_bytes`Holds a current size of allocated memory in bytes.	gauge	byte
`scylla.lsa.used_space_bytes`Holds a current amount of used memory in bytes.	gauge	byte
`scylla.memory.allocated_memory`Allocated memory size in bytes	count	byte
`scylla.memory.cross_cpu_free_operations`Total number of cross cpu free	count	-
`scylla.memory.dirty_bytes`Holds the current size of all ("regular"; "system" and "streaming") non-free memory in bytes: used memory + released memory that hasn't been returned to a free memory pool yet. Total memory size minus this value represents the amount of available memory. If this value minus virtual_dirty_bytes is too high then this means that the dirty memory eviction lags behind.	gauge	byte
`scylla.memory.free_memory`Free memory size in bytes	count	byte
`scylla.memory.free_operations`Total number of free operations	count	-
`scylla.memory.malloc_failed`Total count of failed memory allocations	count	-
`scylla.memory.malloc_live_objects`Number of live objects	gauge	-
`scylla.memory.malloc_operations`Total number of malloc operations	count	-
`scylla.memory.reclaims_operations`Total reclaims operations	count	-
`scylla.memory.regular_dirty_bytes`Holds the current size of a all non-free memory in bytes: used memory + released memory that hasn't been returned to a free memory pool yet. Total memory size minus this value represents the amount of available memory. If this value minus virtual_dirty_bytes is too high then this means that the dirty memory eviction lags behind.	gauge	byte
`scylla.memory.regular_virtual_dirty_bytes`Holds the size of used memory in bytes. Compare it to "dirty_bytes" to see how many memory is wasted (neither used nor available).	gauge	byte
`scylla.memory.streaming_dirty_bytes`Holds the current size of a all non-free memory in bytes: used memory + released memory that hasn't been returned to a free memory pool yet. Total memory size minus this value represents the amount of available memory. If this value minus virtual_dirty_bytes is too high then this means that the dirty memory eviction lags behind.	gauge	byte
`scylla.memory.streaming_virtual_dirty_bytes`Holds the size of used memory in bytes. Compare it to "dirty_bytes" to see how many memory is wasted (neither used nor available).	gauge	byte
`scylla.memory.system_dirty_bytes`Holds the current size of a all non-free memory in bytes: used memory + released memory that hasn't been returned to a free memory pool yet. Total memory size minus this value represents the amount of available memory. If this value minus virtual_dirty_bytes is too high then this means that the dirty memory eviction lags behind.	gauge	byte
`scylla.memory.system_virtual_dirty_bytes`Holds the size of used memory in bytes. Compare it to "dirty_bytes" to see how many memory is wasted (neither used nor available).	gauge	byte
`scylla.memory.total_memory`Total memory size in bytes	count	byte
`scylla.memory.virtual_dirty_bytes`Holds the size of all ("regular"; "system" and "streaming") used memory in bytes. Compare it to "dirty_bytes" to see how many memory is wasted (neither used nor available).	gauge	byte
`scylla.memtables.failed_flushes`Holds the number of failed memtable flushes. High value in this metric may indicate a permanent failure to flush a memtable.	gauge	-
`scylla.memtables.pending_flushes`Holds the current number of memtables that are currently being flushed to sstables. High value in this metric may be an indication of storage being a bottleneck.	gauge	-
`scylla.memtables.pending_flushes_bytes`Holds the current number of bytes in memtables that are currently being flushed to sstables. High value in this metric may be an indication of storage being a bottleneck.	gauge	byte
`scylla.node.operation_mode`The operation mode of the current node. UNKNOWN = 0; STARTING = 1; JOINING = 2; NORMAL = 3; LEAVING = 4; DECOMMISSIONED = 5; DRAINING = 6; DRAINED = 7; MOVING = 8	gauge	-
`scylla.node.ops_finished_percentage`Finished percentage of node operation on this shard	gauge	-
`scylla.per_partition.rate_limiter_allocations`Number of times a entry was allocated over an empty/expired entry.	count	-
`scylla.per_partition.rate_limiter_failed_allocations`Number of times the rate limiter gave up trying to allocate.	count	-
`scylla.per_partition.rate_limiter_load_factor`Current load factor of the hash table (upper bound, may be overestimated).	gauge	-
`scylla.per_partition.rate_limiter_probe_count`Number of probes made during lookups.	count	-
`scylla.per_partition.rate_limiter_successful_lookups`Number of times a lookup returned an already allocated entry.	count	-
`scylla.query_processor.queries`Counts queries by consistency level.	count	query
`scylla.query_processor.statements_prepared`Counts a total number of parsed CQL requests.	count	-
`scylla.raft.add_entries`	count	byte
`scylla.raft.applied_entries`	count	byte
`scylla.raft.group0_status`	count	byte
`scylla.raft.in_memory_log_size`	count	byte
`scylla.raft.messages_received`	count	byte
`scylla.raft.messages_sent`	count	byte
`scylla.raft.persisted_log_entriespersisted_log_entries`	count	byte
`scylla.raft.polls`	count	byte
`scylla.raft.queue_entries_for_apply`	count	byte
`scylla.raft.sm_load_snapshot`	count	byte
`scylla.raft.snapshots_taken`	count	byte
`scylla.raft.store_snapshot`	count	byte
`scylla.raft.store_term_and_vote`	count	byte
`scylla.raft.truncate_persisted_log`	count	byte
`scylla.raft.waiter_awaiken`	count	byte
`scylla.raft.waiter_dropped`	count	byte
`scylla.reactor.abandoned_failed_futures`Total number of abandoned failed futures, futures destroyed while still containing an exception	count	-
`scylla.reactor.aio_bytes_read`Total aio-reads bytes	count	byte
`scylla.reactor.aio_bytes_write`Total aio-writes bytes	count	byte
`scylla.reactor.aio_errors`Total aio errors	count	error
`scylla.reactor.aio_outsizes`Total number of aio operations that exceed IO limit	count	-
`scylla.reactor.aio_reads`Total aio-reads operations	count	read
`scylla.reactor.aio_writes`Total aio-writes operations	count	write
`scylla.reactor.cpp_exceptions`Total number of C++ exceptions	count	-
`scylla.reactor.cpu_busy_ms`Total cpu busy time in milliseconds	count	millisecond
`scylla.reactor.cpu_steal_time_ms`Total steal time; the time in which some other process was running while Seastar was not trying to run (not sleeping).Because this is in userspace; some time that could be legitimally thought as steal time is not accounted as such. For example; if we are sleeping and can wake up but the kernel hasn't woken us up yet.	count	millisecond
`scylla.reactor.fstream_read_bytes`Counts bytes read from disk file streams. A high rate indicates high disk activity. Divide by fstream_reads to determine average read size.	count	byte
`scylla.reactor.fstream_read_bytes_blocked`Counts the number of bytes read from disk that could not be satisfied from read-ahead buffers; and had to block. Indicates short streams; or incorrect read ahead configuration.	count	byte
`scylla.reactor.fstream_reads`Counts reads from disk file streams. A high rate indicates high disk activity. Contrast with other fstream_read* counters to locate bottlenecks.	count	read
`scylla.reactor.fstream_reads_ahead_bytes_discarded`Counts the number of buffered bytes that were read ahead of time and were discarded because they were not needed; wasting disk bandwidth. Indicates over-eager read ahead configuration.	count	byte
`scylla.reactor.fstream_reads_aheads_discarded`Counts the number of times a buffer that was read ahead of time and was discarded because it was not needed; wasting disk bandwidth. Indicates over-eager read ahead configuration.	count	-
`scylla.reactor.fstream_reads_blocked`Counts the number of times a disk read could not be satisfied from read-ahead buffers; and had to block. Indicates short streams; or incorrect read ahead configuration.	count	-
`scylla.reactor.fsyncs`Total number of fsync operations	count	-
`scylla.reactor.io_queue_requests`Number of requests in the io queue	gauge	request
`scylla.reactor.io_threaded_fallbacks`Total number of io-threaded-fallbacks operations	count	-
`scylla.reactor.logging_failures`Total number of logging failures	count	-
`scylla.reactor.polls`Number of times pollers were executed	count	-
`scylla.reactor.tasks_pending`Number of pending tasks in the queue	gauge	task
`scylla.reactor.tasks_processed`Total tasks processed	count	task
`scylla.reactor.timers_pending`Number of tasks in the timer-pending queue	count	task
`scylla.reactor.utilization`CPU utilization	gauge	percent
`scylla.repair.row_from_disk_bytes`	count	byte
`scylla.repair.row_from_disk_nr`	count	byte
`scylla.repair.rx_hashes_nr`	count	byte
`scylla.repair.rx_row_bytes`	count	byte
`scylla.repair.rx_row_nr`	count	byte
`scylla.repair.tx_hashes_nr`	count	byte
`scylla.repair.tx_row_bytes`	count	byte
`scylla.repair.tx_row_nr`	count	byte
`scylla.scheduler.queue_length`Size of backlog on this queue; in tasks; indicates whether the queue is busy and/or contended	gauge	-
`scylla.scheduler.runtime_ms`Accumulated runtime of this task queue; an increment rate of 1000ms per second indicates full utilization	count	millisecond
`scylla.scheduler.shares`Shares allocated to this queue	gauge	-
`scylla.scheduler.starvetime_ms`Accumulated starvation time of this task queue; an increment rate of 1000ms per second indicates the scheduler feels really bad	count	-
`scylla.scheduler.tasks_processed`Count of tasks executing on this queue; indicates together with runtime_ms indicates length of tasks	count	-
`scylla.scheduler.time_spent_on_task_quota_violations_ms`Total amount in milliseconds we were in violation of the task quota	count	millisecond
`scylla.scheduler.waittime_ms`Accumulated waittime of this task queue; an increment rate of 1000ms per second indicates queue is waiting for something (e.g. IO)	count	-
`scylla.schema_commitlog.active_allocations`	count	byte
`scylla.schema_commitlog.alloc`	count	byte
`scylla.schema_commitlog.allocating_segments`	count	byte
`scylla.schema_commitlog.blocked_on_new_segment`	count	byte
`scylla.schema_commitlog.bytes_flush_requested`	count	byte
`scylla.schema_commitlog.bytes_released`	count	byte
`scylla.schema_commitlog.bytes_written`	count	byte
`scylla.schema_commitlog.cycle`	count	byte
`scylla.schema_commitlog.disk_active_bytes`	count	byte
`scylla.schema_commitlog.disk_slack_end_bytes`	count	byte
`scylla.schema_commitlog.disk_total_bytes`	count	byte
`scylla.schema_commitlog.flush`	count	byte
`scylla.schema_commitlog.flush_limit_exceeded`	count	byte
`scylla.schema_commitlog.memory_buffer_bytes`	count	byte
`scylla.schema_commitlog.pending_allocations`	count	byte
`scylla.schema_commitlog.pending_flushes`	count	byte
`scylla.schema_commitlog.requests_blocked_memory`	count	byte
`scylla.schema_commitlog.segments`	count	byte
`scylla.schema_commitlog.slack`	count	byte
`scylla.schema_commitlog.unused_segments`	count	byte
`scylla.sstables.bloom_filter_memory_size`Bloom filter memory usage in bytes.	gauge	-
`scylla.sstables.capped_local_deletion_time`Was local deletion time capped at maximum allowed value in Statistics	count	time
`scylla.sstables.capped_tombstone_deletion_time`Was partition tombstone deletion time capped at maximum allowed value	count	time
`scylla.sstables.cell_tombstone_writes`Number of cell tombstones written	count	-
`scylla.sstables.cell_writes`Number of cells written	count	-
`scylla.sstables.currently_open_for_reading`Number of sstables currently open for reading	gauge	-
`scylla.sstables.currently_open_for_writing`Number of sstables currently open for writing	gauge	-
`scylla.sstables.index_page_blocks`Index page requests which needed to wait due to page not being loaded yet	count	request
`scylla.sstables.index_page_cache_bytes`Total number of bytes cached in the index page cache	gauge	-
`scylla.sstables.index_page_cache_bytes_in_std`Total number of bytes in temporary buffers which live in the std allocator	gauge	-
`scylla.sstables.index_page_cache_evictions`Total number of index page cache pages which have been evicted	count	-
`scylla.sstables.index_page_cache_hits`Index page cache requests which were served from cache	count	-
`scylla.sstables.index_page_cache_misses`Index page cache requests which had to perform I/O	count	-
`scylla.sstables.index_page_cache_populations`Total number of index page cache pages which were inserted into the cache	count	-
`scylla.sstables.index_page_evictions`Index pages which got evicted from memory	count	-
`scylla.sstables.index_page_hits`Index page requests which could be satisfied without waiting	count	request
`scylla.sstables.index_page_misses`Index page requests which initiated a read from disk	count	request
`scylla.sstables.index_page_populations`Index pages which got populated into memory	count	-
`scylla.sstables.index_page_used_bytes`Amount of bytes used by index pages in memory	gauge	-
`scylla.sstables.partition_reads`Number of partitions read	count	read
`scylla.sstables.partition_seeks`Number of partitions seeked	count	-
`scylla.sstables.partition_writes`Number of partitions written	count	write
`scylla.sstables.pi_auto_scale_events`Number of promoted index auto-scaling events	count	-
`scylla.sstables.pi_cache_block_count`Number of promoted index blocks currently cached	gauge	-
`scylla.sstables.pi_cache_bytes`Number of bytes currently used by cached promoted index blocks	gauge	-
`scylla.sstables.pi_cache_evictions`Number of promoted index blocks which got evicted	count	-
`scylla.sstables.pi_cache_hits_l0`Number of requests for promoted index block in state l0 which didn't have to go to the page cache	count	-
`scylla.sstables.pi_cache_hits_l1`Number of requests for promoted index block in state l1 which didn't have to go to the page cache	count	-
`scylla.sstables.pi_cache_hits_l2`Number of requests for promoted index block in state l2 which didn't have to go to the page cache	count	-
`scylla.sstables.pi_cache_misses_l0`Number of requests for promoted index block in state l0 which had to go to the page cache	count	-
`scylla.sstables.pi_cache_misses_l1`Number of requests for promoted index block in state l1 which had to go to the page cache	count	-
`scylla.sstables.pi_cache_misses_l2`Number of requests for promoted index block in state l2 which had to go to the page cache	count	-
`scylla.sstables.pi_cache_populations`Number of promoted index blocks which got inserted	count	-
`scylla.sstables.range_partition_reads`Number of partition range flat mutation reads	count	read
`scylla.sstables.range_tombstone_reads`Number of range tombstones read	count	-
`scylla.sstables.range_tombstone_writes`Number of range tombstones written	count	-
`scylla.sstables.row_reads`Number of rows read	count	row
`scylla.sstables.row_tombstone_reads`Number of row tombstones read	count	-
`scylla.sstables.row_writes`Number of clustering rows written	count	row
`scylla.sstables.single_partition_reads`Number of single partition flat mutation reads	count	read
`scylla.sstables.sstable_partition_reads`Number of whole sstable flat mutation reads	count	read
`scylla.sstables.static_row_writes`Number of static rows written	count	row
`scylla.sstables.tombstone_writes`Number of tombstones written	count	-
`scylla.sstables.total_deleted`Counter of deleted sstables	count	-
`scylla.sstables.total_open_for_reading`Counter of sstables open for reading	count	-
`scylla.sstables.total_open_for_writing`Counter of sstables open for writing	count	-
`scylla.stall.detector_reported`Total number of reported stalls, look in the traces for the exact reason	count	-
`scylla.storage.proxy.coordinator_background_read_repairs`number of background read repairs	count	read
`scylla.storage.proxy.coordinator_background_reads`number of currently pending background read requests	gauge	read
`scylla.storage.proxy.coordinator_background_replica_writes_failed_local_node`number of replica writes that timed out or failed after CL was reachedon a local Node	count	-
`scylla.storage.proxy.coordinator_background_write_bytes`number of bytes in pending background write requests	count	byte
`scylla.storage.proxy.coordinator_background_writes`number of currently pending background write requests	gauge	write
`scylla.storage.proxy.coordinator_background_writes_failed`number of write requests that failed after CL was reached	count	write
`scylla.storage.proxy.coordinator_canceled_read_repairs`number of global read repairs canceled due to a concurrent write	count	read
`scylla.storage.proxy.coordinator_cas_background`	count	byte
`scylla.storage.proxy.coordinator_cas_dropped_prune`	count	byte
`scylla.storage.proxy.coordinator_cas_failed_read_round_optimization`	count	byte
`scylla.storage.proxy.coordinator_cas_foreground`	count	byte
`scylla.storage.proxy.coordinator_cas_prune`	count	byte
`scylla.storage.proxy.coordinator_cas_read_contention`	count	byte
`scylla.storage.proxy.coordinator_cas_read_latency`	count	byte
`scylla.storage.proxy.coordinator_cas_read_latency_summary`	count	byte
`scylla.storage.proxy.coordinator_cas_read_timouts`	count	byte
`scylla.storage.proxy.coordinator_cas_read_unavailable`	count	byte
`scylla.storage.proxy.coordinator_cas_read_unfinished_commit`	count	byte
`scylla.storage.proxy.coordinator_cas_total_operations`	count	byte
`scylla.storage.proxy.coordinator_cas_write_condition_not_met`	count	byte
`scylla.storage.proxy.coordinator_cas_write_contention`	count	byte
`scylla.storage.proxy.coordinator_cas_write_latency`	count	byte
`scylla.storage.proxy.coordinator_cas_write_latency_summary`	count	byte
`scylla.storage.proxy.coordinator_cas_write_timeout_due_to_uncertainty`	count	byte
`scylla.storage.proxy.coordinator_cas_write_timeouts`	count	byte
`scylla.storage.proxy.coordinator_cas_write_unavailable`	count	byte
`scylla.storage.proxy.coordinator_cas_write_unfinished_commit`	count	byte
`scylla.storage.proxy.coordinator_completed_reads_local_node`number of data read requests that completed on a local Node	count	read
`scylla.storage.proxy.coordinator_completed_reads_remote_node`	count	byte
`scylla.storage.proxy.coordinator_current_throttled_base_writes`number of currently throttled base replica write requests	gauge	write
`scylla.storage.proxy.coordinator_current_throttled_writes`number of currently throttled write requests	gauge	write
`scylla.storage.proxy.coordinator_foreground_read_repair`number of foreground read repairs	count	read
`scylla.storage.proxy.coordinator_foreground_reads`number of currently pending foreground read requests	gauge	read
`scylla.storage.proxy.coordinator_foreground_writes`number of currently pending foreground write requests	gauge	write
`scylla.storage.proxy.coordinator_last_mv_flow_control_delay`delay (in seconds) added for MV flow control in the last request	gauge	second
`scylla.storage.proxy.coordinator_queued_write_bytes`number of bytes in pending write requests	count	byte
`scylla.storage.proxy.coordinator_range_timeouts`number of range read operations failed due to a timeout	count	error
`scylla.storage.proxy.coordinator_range_unavailable`number of range read operations failed due to an "unavailable" error	count	error
`scylla.storage.proxy.coordinator_read_errors_local_node`number of data read requests that failed on a local Node	count	error
`scylla.storage.proxy.coordinator_read_latency.count`The general read latency histogram	count	read
`scylla.storage.proxy.coordinator_read_latency.sum`The general read latency histogram	gauge	read
`scylla.storage.proxy.coordinator_read_latency_summary`	count	byte
`scylla.storage.proxy.coordinator_read_rate_limited`	count	byte
`scylla.storage.proxy.coordinator_read_repair_write_attempts_local_node`number of write operations in a read repair context on a local Node	count	write
`scylla.storage.proxy.coordinator_read_repair_write_attempts_remote_node`	count	byte
`scylla.storage.proxy.coordinator_read_retries`number of read retry attempts	count	read
`scylla.storage.proxy.coordinator_read_timeouts`number of read request failed due to a timeout	count	error
`scylla.storage.proxy.coordinator_read_unavailable`number read requests failed due to an "unavailable" error	count	error
`scylla.storage.proxy.coordinator_reads_coordinator_outside_replica_se`	count	byte
`scylla.storage.proxy.coordinator_reads_local_node`number of data read requests on a local Node	count	read
`scylla.storage.proxy.coordinator_reads_remote_node`	count	byte
`scylla.storage.proxy.coordinator_speculative_data_reads`number of speculative data read requests that were sent	count	read
`scylla.storage.proxy.coordinator_speculative_digest_reads`number of speculative digest read requests that were sent	count	read
`scylla.storage.proxy.coordinator_throttled_writes`number of throttled write requests	count	write
`scylla.storage.proxy.coordinator_total_write_attempts_local_node`total number of write requests on a local Node	count	write
`scylla.storage.proxy.coordinator_total_write_attempts_remote_node`	count	byte
`scylla.storage.proxy.coordinator_write_errors_local_node`number of write requests that failed on a local Node	count	error
`scylla.storage.proxy.coordinator_write_latency.count`The general write latency histogram	count	write
`scylla.storage.proxy.coordinator_write_latency.sum`The general write latency histogram	gauge	write
`scylla.storage.proxy.coordinator_write_latency_summary`	count	byte
`scylla.storage.proxy.coordinator_write_rate_limited`	count	byte
`scylla.storage.proxy.coordinator_write_timeouts`number of write request failed due to a timeout	count	error
`scylla.storage.proxy.coordinator_write_unavailable`number write requests failed due to an "unavailable" error	count	error
`scylla.storage.proxy.coordinator_writes_coordinator_outside_replica_set`	count	byte
`scylla.storage.proxy.coordinator_writes_failed_due_to_too_many_in_flight_hints`	count	byte
`scylla.storage.proxy.replica_cas_dropped_prune`	count	byte
`scylla.storage.proxy.replica_cross_shard_ops`number of operations that crossed a shard boundary	count	-
`scylla.storage.proxy.replica_forwarded_mutations`number of mutations forwarded to other replica Nodes	count	-
`scylla.storage.proxy.replica_forwarding_errors`number of errors during forwarding mutations to other replica Nodes	count	error
`scylla.storage.proxy.replica_reads`number of remote data read requests this Node received	count	read
`scylla.storage.proxy.replica_received_counter_updates`number of counter updates received by this node acting as an update leader	count	-
`scylla.storage.proxy.replica_received_mutations`number of mutations received by a replica Node	count	-
`scylla.streaming.finished_percentage`Finished percentage of node operation on this shard	gauge	-
`scylla.streaming.total_incoming_bytes`Total number of bytes received on this shard.	count	byte
`scylla.streaming.total_outgoing_bytes`Total number of bytes sent on this shard.	count	byte
`scylla.thrift.current_connections`Holds a current number of opened Thrift connections.	gauge	connection
`scylla.thrift.served`Rate of serving Thrift requests.	count	-
`scylla.thrift.thrift_connections`Rate of creation of new Thrift connections.	count	connection
`scylla.tracing.active_sessions`Holds a number of a currently active tracing sessions.	gauge	-
`scylla.tracing.cached_records`Holds a number of tracing records cached in the tracing sessions that are not going to be written in the next write event. If sum of this metric; pending_for_write_records and flushing_records is close to 11000 we are likely to start dropping tracing records.	gauge	-
`scylla.tracing.dropped_records`Counts a number of dropped records due to too many pending records. High value indicates that backend is saturated with the rate with which new tracing records are created.	count	-
`scylla.tracing.dropped_sessions`Counts a number of dropped sessions due to too many pending sessions/records. High value indicates that backend is saturated with the rate with which new tracing records are created.	count	-
`scylla.tracing.flushing_records`Holds a number of tracing records that currently being written to the I/O backend. If sum of this metric; cached_records and pending_for_write_records is close to 11000 we are likely to start dropping tracing records.	gauge	-
`scylla.tracing.keyspace_helper_bad_column_family_errors`Counts a number of times write failed due to one of the tables in the system_traces keyspace has an incompatible schema. One error may result one or more tracing records to be lost. Non-zero value indicates that the administrator has to take immediate steps to fix the corresponding schema. The appropriate error message will be printed in the syslog.	count	error
`scylla.tracing.keyspace_helper_tracing_errors`Counts a number of errors during writing to a system_traces keyspace. One error may cause one or more tracing records to be lost.	count	error
`scylla.tracing.pending_for_write_records`Holds a number of tracing records that are going to be written in the next write event. If sum of this metric; cached_records and flushing_records is close to 11000 we are likely to start dropping tracing records.	gauge	-
`scylla.tracing.trace_errors`Counts a number of trace records dropped due to an error (e.g. OOM).	count	error
`scylla.tracing.trace_records_count`This metric is a rate of tracing records generation.	count	-
`scylla.transport.auth_responses`Counts the total number of received CQL AUTH messages.	count	-
`scylla.transport.batch_requests`Counts the total number of received CQL BATCH messages.	count	-
`scylla.transport.cql_connections`Counts a number of client connections.	count	connection
`scylla.transport.cql_errors_total`Counts the total number of returned CQL errors.	count	-
`scylla.transport.current_connections`Holds a current number of client connections.	gauge	connection
`scylla.transport.execute_requests`Counts the total number of received CQL EXECUTE messages.	count	-
`scylla.transport.options_requests`Counts the total number of received CQL OPTIONS messages.	count	-
`scylla.transport.prepare_requests`Counts the total number of received CQL PREPARE messages.	count	-
`scylla.transport.query_requests`Counts the total number of received CQL QUERY messages.	count	-
`scylla.transport.register_requests`Counts the total number of received CQL REGISTER messages.	count	-
`scylla.transport.requests_blocked_memory`Holds an incrementing counter with the requests that ever blocked due to reaching the memory quota limit (12373196B). The first derivative of this value shows how often we block due to memory exhaustion in the "CQL transport" component.	count	request
`scylla.transport.requests_blocked_memory_current`Holds the number of requests that are currently blocked due to reaching the memory quota limit (12373196B). Non-zero value indicates that our bottleneck is memory and more specifically - the memory quota allocated for the "CQL transport" component.	gauge	request
`scylla.transport.requests_memory_available`Holds the amount of available memory for admitting new requests (max is 219571814B).Zero value indicates that our bottleneck is memory and more specifically - the memory quota allocated for the CQL transport component.	gauge	-
`scylla.transport.requests_served`Counts a number of served requests.	count	request
`scylla.transport.requests_serving`Holds a number of requests that are being processed right now.	gauge	request
`scylla.transport.requests_shed`Holds an incrementing counter with the requests that were shed due to overload (threshold configured via max_concurrent_requests_per_shard). The first derivative of this value shows how often we shed requests due to overload in the CQL transport component.	count	-
`scylla.transport.startups`Counts the total number of received CQL STARTUP messages.	count	-
`scylla.view.builder_builds_in_progress`Number of currently active view builds.	gauge	-
`scylla.view.builder_pending_bookkeeping_ops`Number of tasks waiting to perform bookkeeping operations	gauge	-
`scylla.view.builder_steps_failed`Number of failed build steps.	count	-
`scylla.view.builder_steps_performed`Number of performed build steps.	count	-
`scylla.view.update_generator_pending_registrations`Number of tasks waiting to register staging sstables	gauge	-
`scylla.view.update_generator_queued_batches_count`Number of sets of sstables queued for view update generation	gauge	-
`scylla.view.update_generator_sstables_pending_work`Number of bytes remaining to be processed from SSTables for view updates	gauge	-
`scylla.view.update_generator_sstables_to_move_count`Number of sets of sstables which are already processed and wait to be moved from their staging directory	gauge	-

Official documentation

Official documentation for the Scylla integration

Metric names and descriptions are the official Datadog integration definitions (Copyright Datadog, Inc., BSD-3-Clause), reproduced unedited. The full license terms are on the About page.

Official summary

Metric types

Metrics

Official documentation

Related products

Other Caching integrations