INFO SEARCH metrics

Only Application metrics are listed here. These are kept compatible across releases. Developer metrics are hidden unless search.info-developer-visible is set to yes, and may change or be removed in any release without notice.

Some metrics are reported only when they apply. The coordinator_* metrics appear only when the module is loaded with --use-coordinator. Metrics ending in _latency_usec additionally appear only after at least one sample has been recorded.

Valkey prefixes each field with search_ and each section with search_ in INFO output, so compatibility_usage appears as search_compatibility_usage in section search_compatibility.

Metric NameSectionUnitDescription
compatibility_usagecompatibilityStringComma-separated label=count list of legacy behaviors used because search.emulate-release is below the release that fixed them (see below)
coordinator_bytes_incoordinatorBytesTotal size (in bytes) of incoming gRPC response messages received by the coordinator client from remote nodes
coordinator_bytes_outcoordinatorBytesTotal size (in bytes) of outgoing gRPC request messages sent by the coordinator client to remote nodes
coordinator_client_get_global_metadata_failure_countcoordinatorCountCount of failed client requests to get global metadata
coordinator_client_get_global_metadata_failure_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for failed client metadata requests
coordinator_client_get_global_metadata_success_countcoordinatorCountCount of successful client requests to get global metadata
coordinator_client_get_global_metadata_success_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for successful client metadata requests
coordinator_client_search_index_partition_failure_countcoordinatorCountCount of failed client searches on index partitions
coordinator_client_search_index_partition_failure_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for failed partition searches
coordinator_client_search_index_partition_success_countcoordinatorCountCount of successful client searches on index partitions
coordinator_client_search_index_partition_success_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for successful partition searches
coordinator_server_get_global_metadata_failure_countcoordinatorCountCount of failed server requests to get global metadata
coordinator_server_get_global_metadata_failure_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for failed server metadata requests
coordinator_server_get_global_metadata_success_countcoordinatorCountCount of successful server requests to get global metadata
coordinator_server_get_global_metadata_success_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for successful server metadata requests
coordinator_server_listening_portcoordinatorPortThe port number the coordinator server is listening on
coordinator_server_search_index_partition_cpu_time_useccoordinatorMicrosecondsCumulative CPU time (in microseconds) spent handling remote query operations on this node
coordinator_server_search_index_partition_failure_countcoordinatorCountCount of failed server searches on index partitions
coordinator_server_search_index_partition_failure_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for failed server partition searches
coordinator_server_search_index_partition_success_countcoordinatorCountCount of successful server searches on index partitions
coordinator_server_search_index_partition_success_latency_useccoordinatorMicrosecondsLatency distribution (in microseconds) for successful server partition searches
coordinator_threads_cpu_time_seccoordinatorSecondsCumulative CPU time consumed by coordinator (gRPC) threads
hnsw_add_exceptions_counthnswlibCountCount of exceptions during HNSW vector additions
hnsw_create_exceptions_counthnswlibCountCount of exceptions during HNSW vector creation
hnsw_modify_exceptions_counthnswlibCountCount of exceptions during HNSW vector modifications
hnsw_remove_exceptions_counthnswlibCountCount of exceptions during HNSW vector removals
hnsw_search_exceptions_counthnswlibCountCount of exceptions during HNSW vector searches
number_of_attributesindex_statsCountTotal count of all attributes across all search indexes
number_of_indexesindex_statsCountTotal number of search indexes
num_cursorscursorsCountNumber of open cursors created by WITHCURSOR
total_active_write_threadsindex_statsCountNumber of active writer threads (0 if suspended, otherwise the writer thread pool size)
total_indexed_documentsindex_statsCountTotal number of indexed documents across all search indexes
background_indexing_statusindexingStringBackground indexing status: IN_PROGRESS or NO_ACTIVITY
flat_vector_index_search_latency_useclatencyMicrosecondsLatency distribution (in microseconds) for flat vector index searches
hnsw_vector_index_search_latency_useclatencyMicrosecondsLatency distribution (in microseconds) for HNSW vector index searches
index_reclaimable_memorymemoryBytesTrack memory that can be reclaimed after vector deletions
used_memory_bytesmemoryBytesTotal memory used by the module (in bytes)
used_memory_humanmemoryStringTotal memory used by the module (in human readable format)
successful_requests_countqueryCountTotal count of successful query requests
failure_requests_countqueryCountTotal count of failed query requests
hybrid_requests_countqueryCountCount of KNN queries that also have a non-vector filter, for example @color:{red}=>[KNN 10 @vec $v], including an FT.HYBRID VSIM arm with FILTER. It does not count FT.HYBRID commands as such
nonvector_requests_countqueryCountNumber of requests that are exclusively non-vector search queries, including vector range (VECTOR_RANGE) queries and the SEARCH arm of FT.HYBRID
vector_requests_countqueryCountNumber of KNN queries without a filter, for example *=>[KNN 10 @vec $v]. An FT.HYBRID VSIM arm without FILTER is not counted
inline_filtering_requests_countqueryCountCount of queries using inline filtering
prefiltering_requests_countqueryCountCount of queries using pre-filtering
result_record_dropped_countqueryCountTracks records dropped when FT.SEARCH results exceed configured limits
vector_range_results_fetched_limited_countqueryCountCount of VECTOR_RANGE queries whose results were truncated on this shard. See Result limit.
rdb_load_failure_cntrdbCountNumber of failed RDB load operations
rdb_load_success_cntrdbCountNumber of successful RDB load operations
rdb_save_failure_cntrdbCountNumber of failed RDB save operations
rdb_save_success_cntrdbCountNumber of successful RDB save operations
string_interning_store_sizestring_interningCountNumber of unique strings in the interning store
query_queue_sizethread-poolCountCurrent size of the reader thread pool queue
reader_resumed_cntthread-poolCountNumber of times the reader worker thread pool was resumed
used_read_cputhread-poolPercentAverage CPU percentage used by reader threads (returns -1 if unavailable)
used_write_cputhread-poolPercentAverage CPU percentage used by writer threads (returns -1 if unavailable)
worker_pool_suspend_cntthread-poolCountNumber of times the worker thread pool was suspended
writer_queue_sizethread-poolCountCurrent size of the writer thread pool queue
writer_resumed_cntthread-poolCountNumber of times the writer worker thread pool was resumed
writer_suspension_expired_cntthread-poolCountNumber of times writer suspension expired due to timeout
vector_registry_dedup_cntvector_registryCountCount of vector updates that reused an already registered copy of an identical vector
vector_registry_entry_cntvector_registryCountNumber of vectors currently tracked by the vector registry
vector_registry_pending_unshare_cntvector_registryCountNumber of vectors queued to stop being shared with the engine, after their index was dropped
vector_registry_shared_externally_cntvector_registryCountCount of vectors successfully shared with the engine's hash field, so only one copy is kept in memory
vector_registry_shared_externally_errorsvector_registryCountCount of failed attempts to share a vector with the engine's hash field
vector_registry_sharing_activevector_registryBoolean1 if vector memory sharing with the engine is enabled, otherwise 0

Compatibility counters

The compatibility_usage metric is a comma-separated list of label=count pairs. Each count is how often a legacy, incompatible behavior was used because search.emulate-release is set below the release that fixed it. See Compatibility Defects for the full list of labels and what each one changes. The metric is always reported; a label appears in the list only after its legacy behavior is first used, and an absent label has a count of 0.