# Internal Metrics > For the complete documentation index, see [llms.txt](https://docs.redpanda.com/llms.txt). Component-specific: [streaming-full.txt](https://docs.redpanda.com/streaming-full.txt) --- title: Internal Metrics latest-redpanda-tag: v25.2.1 latest-console-tag: v3.7.3 latest-operator-version: v26.1.4 # EOL = End-of-Life (support lifecycle status) page-is-nearing-eol: "true" page-is-past-eol: "false" page-eol-date: July 31, 2026 latest-connect-version: 4.93.0 docname: internal-metrics-reference page-component-name: streaming page-version: "25.2" page-component-version: "25.2" page-component-title: Streaming page-relative-src-path: internal-metrics-reference.adoc page-edit-url: https://github.com/redpanda-data/docs/edit/v/25.2/modules/reference/pages/internal-metrics-reference.adoc description: Redpanda internal metrics for detailed analysis, debugging, and troubleshooting. page-git-created-date: "2023-05-30" page-git-modified-date: "2025-07-24" support-status: nearing end-of-life --- This section provides reference descriptions about the internal metrics exported from Redpanda’s `/metrics` endpoint. > 💡 **TIP** > > Use [/public\_metrics](https://docs.redpanda.com/streaming/25.2/reference/public-metrics-reference/) for your primary dashboards for monitoring system health. These metrics have low cardinality and are designed for customer consumption, with aggregated labels for better performance. **Public metrics use the `redpanda_` prefix.** > > Use [/metrics](./) for detailed analysis and debugging. These metrics can have high cardinality with thousands of series, providing granular operational insights. **Internal metrics use the `vectorized_` prefix.** > ❗ **IMPORTANT** > > In a live system, Redpanda metrics are exported only for features that are in use. For example, a metric for consumer groups is not exported when no groups are registered. > > To see the available internal metrics in your system, query the `/metrics` endpoint: > > ```bash > curl http://:9644/metrics | grep "[HELP|TYPE]" > ``` Internal metrics (`/metrics`) can generate thousands of metric series in production environments, so use them judiciously in monitoring systems to avoid performance issues. For alerting and dashboards, public metrics are preferable (`/public_metrics`) because they are optimized for lower cardinality. The [aggregate\_metrics](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#aggregate_metrics) cluster property controls internal metrics cardinality. When you enable this property, internal metrics combine labels (like shard) to reduce the number of series. Public metrics always combine labels, regardless of this setting. ## [](#vectorized_alien_receive_batch_queue_length)vectorized_alien_receive_batch_queue_length Indicates the current length of the alien receive batch queue. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_alien_total_received_messages)vectorized_alien_total_received_messages Tracks the cumulative number of alien messages that have been received. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_alien_total_sent_messages)vectorized_alien_total_sent_messages Tracks the cumulative number of alien messages that have been sent. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_application_build)vectorized_application_build Provides build details for Redpanda including the build revision, shard identifier, and version. **Type**: gauge **Labels**: - `revision` - `shard` - `version` * * * ## [](#vectorized_application_fips_mode)vectorized_application_fips_mode Indicates whether Redpanda is running in FIPS (Federal Information Processing Standards) mode. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_application_uptime)vectorized_application_uptime Reports the uptime of the Redpanda application in milliseconds. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_archival_upload_backlog_controller_backlog_size)vectorized_archival_upload_backlog_controller_backlog_size Shows the current backlog size in the archival upload controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_archival_upload_backlog_controller_error)vectorized_archival_upload_backlog_controller_error Reports the current error value (difference between set point and backlog size) in the archival upload controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_archival_upload_backlog_controller_shares)vectorized_archival_upload_backlog_controller_shares Represents the number of shares (or work units) output by the archival upload controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_authorization_result)vectorized_authorization_result Counts the total number of authorization results, broken down by result type. **Type**: counter **Labels**: - `type` * * * ## [](#vectorized_chunk_cache_available_size_bytes)vectorized_chunk_cache_available_size_bytes Measures the total size (in bytes) of all free segment appender chunks in the cache. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_chunk_cache_total_size_bytes)vectorized_chunk_cache_total_size_bytes Reports the total size (in bytes) of all segment appender chunks regardless of state. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_chunk_cache_wait_count)vectorized_chunk_cache_wait_count Counts how many times a request had to wait for a segment appender chunk to become available. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_client_active_downloads)vectorized_cloud_client_active_downloads Indicates the number of active GET requests to the object storage. **Type**: gauge **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_active_requests)vectorized_cloud_client_active_requests Reports the number of active HTTP requests (both PUT and GET) currently in progress. **Type**: gauge **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_active_uploads)vectorized_cloud_client_active_uploads Shows the number of active PUT requests currently executing. **Type**: gauge **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_all_requests)vectorized_cloud_client_all_requests Counts the total number of completed HTTP requests (includes both PUT and GET). **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_client_pool_utilization)vectorized_cloud_client_client_pool_utilization Measures the utilization of the object storage client pool as a percentage (0 means unused, 100 means fully utilized). **Type**: gauge **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_lease_duration)vectorized_cloud_client_lease_duration Provides a histogram of cloud client lease durations. **Type**: histogram * * * ## [](#vectorized_cloud_client_num_borrows)vectorized_cloud_client_num_borrows Counts how many times a shard has borrowed an object storage client from another shard. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_num_nosuchkey)vectorized_cloud_client_num_nosuchkey Counts the total number of NoSuchKey errors returned by the object storage provider. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_num_rpc_errors)vectorized_cloud_client_num_rpc_errors Counts the total number of REST API errors encountered from the object storage provider. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_num_slowdowns)vectorized_cloud_client_num_slowdowns Counts the total number of SlowDown errors received from the object storage provider. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_num_transport_errors)vectorized_cloud_client_num_transport_errors Counts the total number of transport errors (including TCP and TLS errors) from the object storage provider. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_total_downloads)vectorized_cloud_client_total_downloads Counts the total number of completed `GET` requests to object storage. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_total_inbound_bytes)vectorized_cloud_client_total_inbound_bytes Reports the total number of bytes received from object storage. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_total_outbound_bytes)vectorized_cloud_client_total_outbound_bytes Reports the total number of bytes sent to object storage. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_client_total_uploads)vectorized_cloud_client_total_uploads Counts the total number of completed PUT requests to object storage. **Type**: counter **Labels**: - `endpoint` - `region` - `shard` * * * ## [](#vectorized_cloud_storage_bytes_received)vectorized_cloud_storage_bytes_received Reports the total number of bytes received from object storage. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_bytes_sent)vectorized_cloud_storage_bytes_sent Reports the total number of bytes sent to object storage. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_cached_gets)vectorized_cloud_storage_cache_cached_gets Counts the number of cache get requests that were served from the cache. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_files)vectorized_cloud_storage_cache_files Indicates the current number of files stored in the object storage cache. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_gets)vectorized_cloud_storage_cache_gets Counts the total number of get requests directed at the object storage cache. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_in_progress_files)vectorized_cloud_storage_cache_in_progress_files Shows the current number of files that are in the process of being cached. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_puts)vectorized_cloud_storage_cache_puts Counts the total number of files successfully placed into the cache. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cache_size_bytes)vectorized_cloud_storage_cache_size_bytes Reports the current size of the object storage cache in bytes. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_client_acquisition_latency)vectorized_cloud_storage_client_acquisition_latency Provides a histogram of the latency experienced when acquiring a object storage client. **Type**: histogram * * * ## [](#vectorized_cloud_storage_cluster_metadata_manifest_downloads)vectorized_cloud_storage_cluster_metadata_manifest_downloads Counts the number of partition manifest downloads initiated by the cluster. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_cluster_metadata_manifest_uploads)vectorized_cloud_storage_cluster_metadata_manifest_uploads Counts the number of partition manifest uploads initiated by the cluster. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_controller_snapshot_failed_uploads)vectorized_cloud_storage_controller_snapshot_failed_uploads Counts the number of controller snapshot uploads that have failed. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_controller_snapshot_successful_uploads)vectorized_cloud_storage_controller_snapshot_successful_uploads Counts the number of successful controller snapshot uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_controller_snapshot_upload_backoff)vectorized_cloud_storage_controller_snapshot_upload_backoff Counts the number of times a backoff was applied during controller snapshot uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_download_backoff)vectorized_cloud_storage_download_backoff Counts how many times backoff was applied during log-segment downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_downloads)vectorized_cloud_storage_failed_downloads Counts the number of failed log-segment download attempts. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_index_downloads)vectorized_cloud_storage_failed_index_downloads Counts the number of failed attempts to download segment indices. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_index_uploads)vectorized_cloud_storage_failed_index_uploads Counts the number of failed attempts to upload segment indices. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_manifest_downloads)vectorized_cloud_storage_failed_manifest_downloads Counts the number of manifest download failures. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_manifest_uploads)vectorized_cloud_storage_failed_manifest_uploads Counts the number of manifest upload failures. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_failed_uploads)vectorized_cloud_storage_failed_uploads Counts the total number of failed log-segment upload attempts. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_index_downloads)vectorized_cloud_storage_index_downloads Counts the total number of segment index downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_index_uploads)vectorized_cloud_storage_index_uploads Counts the total number of segment index uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_manifest_download_backoff)vectorized_cloud_storage_manifest_download_backoff Counts how many times backoff was applied during manifest downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_manifest_upload_backoff)vectorized_cloud_storage_manifest_upload_backoff Counts how many times backoff was applied during manifest uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_partition_chunk_size)vectorized_cloud_storage_partition_chunk_size Reports the size (in bytes) of a chunk downloaded from object storage for a given partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `topic` * * * ## [](#vectorized_cloud_storage_partition_manifest_downloads)vectorized_cloud_storage_partition_manifest_downloads Counts the number of partition manifest downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_partition_manifest_uploads)vectorized_cloud_storage_partition_manifest_uploads Counts the number of (re)uploads for partition manifests. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_partition_read_bytes)vectorized_cloud_storage_partition_read_bytes Reports the total number of bytes read from a remote partition. **Type**: counter **Labels**: - `namespace` - `partition` - `topic` * * * ## [](#vectorized_cloud_storage_partition_read_records)vectorized_cloud_storage_partition_read_records Counts the total number of records read from a remote partition. **Type**: counter **Labels**: - `namespace` - `partition` - `topic` * * * ## [](#vectorized_cloud_storage_read_path_chunk_hydration_latency)vectorized_cloud_storage_read_path_chunk_hydration_latency Provides a histogram of the latency for hydrating individual chunks. **Type**: histogram * * * ## [](#vectorized_cloud_storage_read_path_chunks_hydrated)vectorized_cloud_storage_read_path_chunks_hydrated Counts the total number of chunks hydrated (note: some may later be evicted from the cache). **Type**: counter * * * ## [](#vectorized_cloud_storage_read_path_downloads_throttled_sum)vectorized_cloud_storage_read_path_downloads_throttled_sum Reports the cumulative time (in milliseconds) that downloads were throttled. **Type**: counter * * * ## [](#vectorized_cloud_storage_read_path_hydrations_in_progress)vectorized_cloud_storage_read_path_hydrations_in_progress Indicates the number of chunk hydrations currently in progress. **Type**: counter * * * ## [](#vectorized_cloud_storage_read_path_materialized_segments)vectorized_cloud_storage_read_path_materialized_segments Shows the current number of remote segments that have been materialized. **Type**: gauge * * * ## [](#vectorized_cloud_storage_read_path_readers)vectorized_cloud_storage_read_path_readers Indicates the current number of remote partition readers active. **Type**: gauge * * * ## [](#vectorized_cloud_storage_read_path_segment_readers)vectorized_cloud_storage_read_path_segment_readers Indicates the current number of remote segment readers active. **Type**: gauge * * * ## [](#vectorized_cloud_storage_read_path_spillover_manifest_bytes)vectorized_cloud_storage_read_path_spillover_manifest_bytes Reports the total memory (in bytes) used by spillover manifests. **Type**: gauge * * * ## [](#vectorized_cloud_storage_read_path_spillover_manifest_hydrated)vectorized_cloud_storage_read_path_spillover_manifest_hydrated Counts the number of times spillover manifests have been successfully cached. **Type**: counter * * * ## [](#vectorized_cloud_storage_read_path_spillover_manifest_instances)vectorized_cloud_storage_read_path_spillover_manifest_instances Shows the current number of spillover manifest instances stored in memory. **Type**: gauge * * * ## [](#vectorized_cloud_storage_read_path_spillover_manifest_latency)vectorized_cloud_storage_read_path_spillover_manifest_latency Provides a histogram of the latency for materializing spillover manifests. **Type**: histogram * * * ## [](#vectorized_cloud_storage_read_path_spillover_manifest_materialized)vectorized_cloud_storage_read_path_spillover_manifest_materialized Counts the number of times spillover manifests were loaded from the cache. **Type**: counter * * * ## [](#vectorized_cloud_storage_segment_download_latency)vectorized_cloud_storage_segment_download_latency Provides a histogram of the latency experienced during segment downloads. **Type**: histogram * * * ## [](#vectorized_cloud_storage_spillover_manifest_downloads)vectorized_cloud_storage_spillover_manifest_downloads Counts the number of spillover manifest downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_spillover_manifest_uploads)vectorized_cloud_storage_spillover_manifest_uploads Counts the number of spillover manifest (re)uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_successful_downloads)vectorized_cloud_storage_successful_downloads Counts the number of successful log-segment downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_successful_uploads)vectorized_cloud_storage_successful_uploads Counts the number of successful log-segment uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_topic_manifest_downloads)vectorized_cloud_storage_topic_manifest_downloads Counts the number of topic manifest downloads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_topic_manifest_uploads)vectorized_cloud_storage_topic_manifest_uploads Counts the number of topic manifest uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cloud_storage_upload_backoff)vectorized_cloud_storage_upload_backoff Counts the number of times backoff was applied during log-segment uploads. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cluster_controller_pending_partition_operations)vectorized_cluster_controller_pending_partition_operations Indicates the number of partitions with pending or ongoing operations at the controller level. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cluster_features_enterprise_license_expiry_sec)vectorized_cluster_features_enterprise_license_expiry_sec Reports the number of seconds remaining until the Enterprise Edition license expires. **Type**: gauge * * * ## [](#vectorized_cluster_partition_batches_produced)vectorized_cluster_partition_batches_produced Counts the total number of batches produced for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_bytes_fetched_from_follower_total)vectorized_cluster_partition_bytes_fetched_from_follower_total Reports the total number of bytes fetched from follower replicas (may exceed client-returned values). **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_bytes_fetched_total)vectorized_cluster_partition_bytes_fetched_total Reports the total number of bytes fetched (some may not be returned to the client). **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_bytes_produced_total)vectorized_cluster_partition_bytes_produced_total Counts the total number of bytes produced for a partition. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_cloud_storage_segments_metadata_bytes)vectorized_cluster_partition_cloud_storage_segments_metadata_bytes Reports the total number of bytes consumed by remote segments metadata for a partition. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_committed_offset)vectorized_cluster_partition_committed_offset Shows the committed offset for a partition (safely persisted across a majority of replicas). **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_end_offset)vectorized_cluster_partition_end_offset Reports the last offset stored on the current broker for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_high_watermark)vectorized_cluster_partition_high_watermark Indicates the high watermark (highest consumable offset) for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ### [](#vectorized_cluster_partition_iceberg_offsets_pending_commit)vectorized_cluster_partition_iceberg_offsets_pending_commit Reports the total number of offsets that are pending a commit to the Iceberg catalog. Lag is reported only on the leader, while followers report 0. -1 is reported if Iceberg is disabled. -2 indicates the lag is not yet computed. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ### [](#vectorized_cluster_partition_iceberg_offsets_pending_translation)vectorized_cluster_partition_iceberg_offsets_pending_translation Reports the total number of offsets that are pending translation to Iceberg. Lag is reported only on leader replicas, while followers report 0. -1 is reported if Iceberg is disabled. -2 indicates the lag is not yet computed. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_last_stable_offset)vectorized_cluster_partition_last_stable_offset Reports the last stable offset for a partition. A stable offset implies that the partition is fully caught up. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_leader)vectorized_cluster_partition_leader A flag indicating whether the current instance is the leader for the partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_leader_id)vectorized_cluster_partition_leader_id Reports the identifier of the current partition leader. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_moving_from_node)vectorized_cluster_partition_moving_from_node Indicates the number of partitions that are currently in the process of moving away from this broker. **Type**: gauge * * * ## [](#vectorized_cluster_partition_moving_to_node)vectorized_cluster_partition_moving_to_node Indicates the number of partitions that are currently moving to this broker. **Type**: gauge * * * ## [](#vectorized_cluster_partition_node_cancelling_movements)vectorized_cluster_partition_node_cancelling_movements Reports the number of partition movements being cancelled on this broker. **Type**: gauge * * * ## [](#vectorized_cluster_partition_num_with_broken_rack_constraint)vectorized_cluster_partition_num_with_broken_rack_constraint Counts the number of partitions that do not meet rack awareness constraints. **Type**: gauge * * * ## [](#vectorized_cluster_partition_records_fetched)vectorized_cluster_partition_records_fetched Counts the total number of records fetched from a partition. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_records_produced)vectorized_cluster_partition_records_produced Counts the total number of records produced to a partition. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_start_offset)vectorized_cluster_partition_start_offset Indicates the starting offset (raft snapshot offset) for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_partition_under_replicated_replicas)vectorized_cluster_partition_under_replicated_replicas Reports the number of under-replicated replicas for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_cluster_producer_state_manager_evicted_producers)vectorized_cluster_producer_state_manager_evicted_producers Counts the total number of producers that have been evicted. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_cluster_producer_state_manager_producer_manager_total_active_producers)vectorized_cluster_producer_state_manager_producer_manager_total_active_producers Reports the total number of active idempotent and transactional producers. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cluster_shard_placement_assigned_partitions)vectorized_cluster_shard_placement_assigned_partitions Indicates the number of partitions assigned to a particular shard. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cluster_shard_placement_hosted_partitions)vectorized_cluster_shard_placement_hosted_partitions Indicates the number of partitions hosted on a specific shard. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_cluster_shard_placement_partitions_to_reconcile)vectorized_cluster_shard_placement_partitions_to_reconcile Counts the number of partitions that require reconciliation of shard-local state. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_data_transforms_log_manager_buffer_usage_ratio)vectorized_data_transforms_log_manager_buffer_usage_ratio Reports the buffer usage ratio for the data transforms log manager. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_data_transforms_log_manager_write_errors_total)vectorized_data_transforms_log_manager_write_errors_total Counts the total number of write errors encountered by the transform log manager. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_debug_bundle_failed_generation_count)vectorized_debug_bundle_failed_generation_count Counts the total number of failed attempts to generate debug bundles. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_debug_bundle_last_failed_bundle_timestamp_seconds)vectorized_debug_bundle_last_failed_bundle_timestamp_seconds Reports the timestamp (in seconds since the epoch) of the last failed debug bundle generation. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_debug_bundle_last_successful_bundle_timestamp_seconds)vectorized_debug_bundle_last_successful_bundle_timestamp_seconds Reports the timestamp (in seconds since the epoch) of the last successful debug bundle generation. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_debug_bundle_successful_generation_count)vectorized_debug_bundle_successful_generation_count Counts the total number of successfully generated debug bundles. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_host_diskstats_discards)vectorized_host_diskstats_discards Reports the total number of discard operations initiated on the host disk. Discard operations free unused blocks and can affect disk longevity and performance. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_discards_merged)vectorized_host_diskstats_discards_merged Captures the number of discard operations that have been merged together, reducing overhead by consolidating multiple discard requests. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_discards_ms)vectorized_host_diskstats_discards_ms Measures the cumulative time in milliseconds spent on discard operations. This metric helps in understanding the performance impact of these operations on disk throughput. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_flushes)vectorized_host_diskstats_flushes Counts the number of flush operations performed by the host disk. Flushes ensure that buffered data is written to disk, which is important for data integrity. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_flushes_ms)vectorized_host_diskstats_flushes_ms Measures the total time in milliseconds spent on flush operations. Monitoring flush duration can indicate disk performance under heavy I/O workloads. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_io_in_progress)vectorized_host_diskstats_io_in_progress Shows the number of I/O operations currently in progress on the disk. This metric provides an insight into the active workload and concurrent operations. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_io_ms)vectorized_host_diskstats_io_ms Captures the cumulative time in milliseconds taken to complete I/O operations. This metric helps in assessing the responsiveness of disk operations under load. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_io_weighted_ms)vectorized_host_diskstats_io_weighted_ms Reports the weighted average time in milliseconds for I/O operations. Weighting factors in the duration and frequency of operations, offering a refined perspective on disk performance. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_reads)vectorized_host_diskstats_reads Counts the number of read operations executed by the host disk. Tracking read operations is useful for understanding disk usage patterns. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_reads_merged)vectorized_host_diskstats_reads_merged Indicates the number of merged read operations, where multiple reads are consolidated to optimize performance. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_reads_ms)vectorized_host_diskstats_reads_ms Measures the total time in milliseconds spent on read operations. This metric is useful for evaluating the efficiency of read processes under varying load conditions. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_sectors_discarded)vectorized_host_diskstats_sectors_discarded Reports the number of disk sectors discarded during discard operations. Monitoring this value can help in understanding the effectiveness and impact of discard commands on disk space. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_sectors_read)vectorized_host_diskstats_sectors_read Indicates the total number of sectors read from the disk. This metric is useful for assessing disk throughput and read performance. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_sectors_written)vectorized_host_diskstats_sectors_written Captures the total number of disk sectors written. This metric helps in monitoring the disk’s write activity and overall I/O load. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_writes)vectorized_host_diskstats_writes Counts the number of write operations performed on the disk. Tracking this metric can be useful for analyzing write-intensive workloads. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_writes_merged)vectorized_host_diskstats_writes_merged Reflects the number of merged write operations, where individual writes are combined to optimize disk utilization. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_diskstats_writes_ms)vectorized_host_diskstats_writes_ms Measures the total time in milliseconds taken by write operations. Monitoring this duration helps in evaluating the efficiency of disk writes. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `disk` - `shard` * * * ## [](#vectorized_host_netstat_bytes_received)vectorized_host_netstat_bytes_received Tracks the total number of bytes received on the host’s network interface. This metric helps in monitoring incoming network traffic for performance and capacity planning. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_host_netstat_bytes_sent)vectorized_host_netstat_bytes_sent Reports the total number of bytes sent from the host’s network interface. Monitoring outbound traffic can help in understanding network load and throughput. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_host_snmp_packets_received)vectorized_host_snmp_packets_received Indicates the number of SNMP packets received by the host. This metric is useful for tracking network management and monitoring activities. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_host_snmp_packets_sent)vectorized_host_snmp_packets_sent Counts the SNMP packets sent from the host, providing insight into outgoing SNMP communication which is useful for network monitoring systems. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_host_snmp_tcp_established)vectorized_host_snmp_tcp_established Measures the number of established TCP connections related to SNMP activity on the host. It aids in assessing the status and load of TCP-based SNMP communications. This metric is available only when the [`enable_host_metrics`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#enable_host_metrics) cluster property is set to `true`. **Type**: gauge **Labels**: - `shard` ## [](#vectorized_httpd_connections_current)vectorized_httpd_connections_current Indicates the current number of open HTTP connections. **Type**: gauge **Labels**: - `service` - `shard` * * * ## [](#vectorized_httpd_connections_total)vectorized_httpd_connections_total Counts the total number of HTTP connections opened. **Type**: counter **Labels**: - `service` - `shard` * * * ## [](#vectorized_httpd_read_errors)vectorized_httpd_read_errors Counts the total number of errors encountered while reading HTTP requests. **Type**: counter **Labels**: - `service` - `shard` * * * ## [](#vectorized_httpd_reply_errors)vectorized_httpd_reply_errors Counts the total number of errors encountered while sending HTTP responses. **Type**: counter **Labels**: - `service` - `shard` * * * ## [](#vectorized_httpd_requests_served)vectorized_httpd_requests_served Counts the total number of HTTP requests served. **Type**: counter **Labels**: - `service` - `shard` * * * ## [](#vectorized_internal_rpc_active_connections)vectorized_internal_rpc_active_connections Shows the current number of active internal RPC connections. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_connection_close_errors)vectorized_internal_rpc_connection_close_errors Counts the errors that occurred during the shutdown of internal RPC connections. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_connections_rejected)vectorized_internal_rpc_connections_rejected Counts the number of internal RPC connection attempts rejected due to open connection limits. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_connections_rejected_rate_limit)vectorized_internal_rpc_connections_rejected_rate_limit Counts the number of internal RPC connection attempts rejected due to rate limits. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_connections_wait_rate)vectorized_internal_rpc_connections_wait_rate Counts the number of internal RPC connections delayed due to rate limiting. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_connects)vectorized_internal_rpc_connects Counts the total number of accepted internal RPC connections. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_consumed_mem_bytes)vectorized_internal_rpc_consumed_mem_bytes Reports the memory consumed by internal RPC request processing. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_corrupted_headers)vectorized_internal_rpc_corrupted_headers Counts the number of internal RPC requests with corrupted headers. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_dispatch_handler_latency)vectorized_internal_rpc_dispatch_handler_latency Provides a histogram of the latency experienced in internal RPC dispatch handlers. **Type**: histogram * * * ## [](#vectorized_internal_rpc_latency)vectorized_internal_rpc_latency Reports the overall latency for internal RPC service requests. **Type**: histogram * * * ## [](#vectorized_internal_rpc_max_service_mem_bytes)vectorized_internal_rpc_max_service_mem_bytes Reports the maximum memory allocated for internal RPC services. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_method_not_found_errors)vectorized_internal_rpc_method_not_found_errors Counts the number of internal RPC requests that referenced a non-existent method. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_received_bytes)vectorized_internal_rpc_received_bytes Counts the total number of bytes received from internal RPC clients. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_requests_blocked_memory)vectorized_internal_rpc_requests_blocked_memory Counts the number of internal RPC requests blocked due to memory backpressure. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_requests_completed)vectorized_internal_rpc_requests_completed Counts the total number of successfully completed internal RPC requests. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_requests_pending)vectorized_internal_rpc_requests_pending Reports the number of internal RPC requests currently pending. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_sent_bytes)vectorized_internal_rpc_sent_bytes Counts the total number of bytes sent in internal RPC responses. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_internal_rpc_service_errors)vectorized_internal_rpc_service_errors Counts the total number of service errors encountered by the internal RPC layer. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_io_queue_activations)vectorized_io_queue_activations Counts the number of times the IO queue was activated from an idle state. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` - `stream` * * * ## [](#vectorized_io_queue_adjusted_consumption)vectorized_io_queue_adjusted_consumption Reports the disk capacity units consumed by a class, adjusted for class shares and idling preemption. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` - `stream` * * * ## [](#vectorized_io_queue_consumption)vectorized_io_queue_consumption Indicates the total disk capacity units consumed by a class. A per-second increment suggests full utilization. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` - `stream` * * * ## [](#vectorized_io_queue_delay)vectorized_io_queue_delay Measures the random delay time experienced in the IO queue. **Type**: gauge **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_disk_queue_length)vectorized_io_queue_disk_queue_length Reports the current number of requests waiting in the disk queue. **Type**: gauge **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_flow_ratio)vectorized_io_queue_flow_ratio Indicates the ratio of the dispatch rate to the completion rate in the IO queue. Values greater than 1.0 may indicate stalls or disk issues. **Type**: gauge **Labels**: - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_queue_length)vectorized_io_queue_queue_length Reports the current number of requests in the general IO queue. **Type**: gauge **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_shares)vectorized_io_queue_shares Indicates the current share allocation for the IO queue. **Type**: gauge **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_starvation_time_sec)vectorized_io_queue_starvation_time_sec Reports the total time (in seconds) the IO queue has experienced starvation. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_bytes)vectorized_io_queue_total_bytes Reports the total number of bytes processed by the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_delay_sec)vectorized_io_queue_total_delay_sec Counts the total delay time (in seconds) experienced within the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_exec_sec)vectorized_io_queue_total_exec_sec Reports the total time (in seconds) spent executing IO operations. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_operations)vectorized_io_queue_total_operations Counts the total number of operations that have passed through the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_read_bytes)vectorized_io_queue_total_read_bytes Reports the total number of bytes read through the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_read_ops)vectorized_io_queue_total_read_ops Counts the total number of read operations processed by the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_split_bytes)vectorized_io_queue_total_split_bytes Reports the total number of bytes that have been split by IO operations. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_split_ops)vectorized_io_queue_total_split_ops Counts the total number of IO requests that were split. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_write_bytes)vectorized_io_queue_total_write_bytes Reports the total number of bytes written through the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_io_queue_total_write_ops)vectorized_io_queue_total_write_ops Counts the total number of write operations processed by the IO queue. **Type**: counter **Labels**: - `class` - `iogroup` - `mountpoint` - `shard` * * * ## [](#vectorized_kafka_batch_size)vectorized_kafka_batch_size Provides a histogram of the batch sizes across all topics at the Kafka layer. **Type**: histogram * * * ## [](#vectorized_kafka_fetch_pid_delay_seconds_total)vectorized_kafka_fetch_pid_delay_seconds_total Reports the cumulative fetch delay (in seconds) set by the PID controller. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_fetch_pid_error_total)vectorized_kafka_fetch_pid_error_total Reports the cumulative error in the fetch PID controller. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_fetch_read_distribution)vectorized_kafka_fetch_read_distribution Provides a histogram distribution of read path timings at the Kafka layer. **Type**: histogram * * * ## [](#vectorized_kafka_fetch_sessions_cache_mem_usage_bytes)vectorized_kafka_fetch_sessions_cache_mem_usage_bytes Reports the memory usage (in bytes) of the Kafka fetch sessions cache. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_kafka_fetch_sessions_cache_sessions_count)vectorized_kafka_fetch_sessions_cache_sessions_count Indicates the total number of active Kafka fetch sessions. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_kafka_group_offset)vectorized_kafka_group_offset Displays the offset for a given group, partition, and topic. **Type**: gauge **Labels**: - `group` - `partition` - `shard` - `topic` * * * ## [](#vectorized_kafka_handler_latency_microseconds)vectorized_kafka_handler_latency_microseconds Provides a histogram of Kafka request latencies (in microseconds). **Type**: histogram * * * ## [](#vectorized_kafka_handler_received_bytes_total)vectorized_kafka_handler_received_bytes_total Counts the total number of bytes received by the Kafka request handler. **Type**: counter **Labels**: - `handler` - `shard` * * * ## [](#vectorized_kafka_handler_requests_completed_total)vectorized_kafka_handler_requests_completed_total Counts the total number of successfully completed Kafka requests. **Type**: counter **Labels**: - `handler` - `shard` * * * ## [](#vectorized_kafka_handler_requests_errored_total)vectorized_kafka_handler_requests_errored_total Counts the total number of Kafka requests that resulted in an error. **Type**: counter **Labels**: - `handler` - `shard` * * * ## [](#vectorized_kafka_handler_requests_in_progress_total)vectorized_kafka_handler_requests_in_progress_total Reports the current number of Kafka requests in progress. **Type**: counter **Labels**: - `handler` - `shard` * * * ## [](#vectorized_kafka_handler_sent_bytes_total)vectorized_kafka_handler_sent_bytes_total Counts the total number of bytes sent in Kafka responses. **Type**: counter **Labels**: - `handler` - `shard` * * * ## [](#vectorized_kafka_latency_fetch_latency_us)vectorized_kafka_latency_fetch_latency_us Provides a histogram of fetch latencies (in microseconds) at the Kafka layer. **Type**: histogram * * * ## [](#vectorized_kafka_latency_produce_latency_us)vectorized_kafka_latency_produce_latency_us Provides a histogram of produce latencies (in microseconds) at the Kafka layer. **Type**: histogram * * * ## [](#vectorized_kafka_produced_bytes)vectorized_kafka_produced_bytes Counts the total number of bytes produced, segmented by compression type. **Type**: counter **Labels**: - `compression_type` - `shard` * * * ## [](#vectorized_kafka_quotas_client_quota_throttle_time)vectorized_kafka_quotas_client_quota_throttle_time Provides a histogram of client quota throttling delays (in seconds) per rule and quota type based on [client throughput limits](https://docs.redpanda.com/streaming/25.2/manage/cluster-maintenance/manage-throughput/#client-throughput-limits). **Type**: histogram * * * ## [](#vectorized_kafka_quotas_client_quota_throughput)vectorized_kafka_quotas_client_quota_throughput Provides a histogram of client quota throughput per rule and quota type. **Type**: histogram * * * ## [](#vectorized_kafka_quotas_quota_effective)vectorized_kafka_quotas_quota_effective Reports the currently effective quota in bytes per second. **Type**: counter **Labels**: - `direction` - `shard` * * * ## [](#vectorized_kafka_quotas_throttle_time)vectorized_kafka_quotas_throttle_time Provides a histogram of throttling times (in seconds) based on [broker-wide throughput limits](https://docs.redpanda.com/streaming/25.2/manage/cluster-maintenance/manage-throughput/#broker-wide-throughput-limits) across the Kafka layer. **Type**: histogram * * * ## [](#vectorized_kafka_quotas_traffic_egress)vectorized_kafka_quotas_traffic_egress Counts the total amount of Kafka traffic (in bytes) sent to clients. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_quotas_traffic_intake)vectorized_kafka_quotas_traffic_intake Counts the total amount of Kafka traffic (in bytes) received from clients. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_active_connections)vectorized_kafka_rpc_active_connections Reports the number of active Kafka RPC connections. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_connection_close_errors)vectorized_kafka_rpc_connection_close_errors Counts the number of errors encountered while closing Kafka RPC connections. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_connections_rejected)vectorized_kafka_rpc_connections_rejected Counts the number of Kafka RPC connection attempts rejected due to connection limits. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_connections_rejected_rate_limit)vectorized_kafka_rpc_connections_rejected_rate_limit Counts the number of Kafka RPC connection attempts rejected due to rate limits. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_connections_wait_rate)vectorized_kafka_rpc_connections_wait_rate Counts the number of Kafka RPC connections delayed due to rate limiting. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_connects)vectorized_kafka_rpc_connects Counts the total number of accepted Kafka RPC connections. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_consumed_mem_bytes)vectorized_kafka_rpc_consumed_mem_bytes Reports the memory (in bytes) consumed by Kafka RPC request processing. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_corrupted_headers)vectorized_kafka_rpc_corrupted_headers Counts the number of Kafka RPC requests with corrupted headers. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_dispatch_handler_latency)vectorized_kafka_rpc_dispatch_handler_latency Provides a histogram of latencies (in seconds) in Kafka RPC dispatch handlers. **Type**: histogram * * * ## [](#vectorized_kafka_rpc_fetch_avail_mem_bytes)vectorized_kafka_rpc_fetch_avail_mem_bytes Reports the available memory for processing Kafka RPC fetch requests. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_max_service_mem_bytes)vectorized_kafka_rpc_max_service_mem_bytes Reports the maximum memory allocated for Kafka RPC services. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_method_not_found_errors)vectorized_kafka_rpc_method_not_found_errors Counts the number of Kafka RPC requests for methods that do not exist. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_produce_bad_create_time)vectorized_kafka_rpc_produce_bad_create_time An incrementing counter for the number of times a producer created a message with a timestamp skewed from the broker’s date and time. This metric is related to the following properties: - [`log_message_timestamp_alert_before_ms`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#log_message_timestamp_alert_before_ms): Increment this gauge when the create\_timestamp on a message is too far in the past as compared to the broker’s time. - [`log_message_timestamp_alert_after_ms`](https://docs.redpanda.com/streaming/25.2/reference/properties/cluster-properties/#log_message_timestamp_alert_after_ms): Increment this gauge when the create\_timestamp on a message is too far in the future as compared to the broker’s time. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_received_bytes)vectorized_kafka_rpc_received_bytes Counts the total number of bytes received by the Kafka RPC layer. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_requests_blocked_memory)vectorized_kafka_rpc_requests_blocked_memory Counts the number of Kafka RPC requests blocked due to insufficient memory. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_requests_completed)vectorized_kafka_rpc_requests_completed Counts the total number of successfully completed Kafka RPC requests. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_requests_pending)vectorized_kafka_rpc_requests_pending Reports the number of Kafka RPC requests that are currently pending. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_sasl_session_expiration_total)vectorized_kafka_rpc_sasl_session_expiration_total Counts the total number of SASL session expirations in Kafka RPC. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_sasl_session_reauth_attempts_total)vectorized_kafka_rpc_sasl_session_reauth_attempts_total Counts the total number of SASL reauthentication attempts in Kafka RPC. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_sasl_session_revoked_total)vectorized_kafka_rpc_sasl_session_revoked_total Counts the total number of revoked SASL sessions in Kafka RPC. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_sent_bytes)vectorized_kafka_rpc_sent_bytes Counts the total number of bytes sent by the Kafka RPC layer. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_rpc_service_errors)vectorized_kafka_rpc_service_errors Counts the total number of service errors encountered in Kafka RPC. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_schema_id_cache_batches_decompressed)vectorized_kafka_schema_id_cache_batches_decompressed Counts the number of batches decompressed for server-side schema ID validation. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_schema_id_cache_hits)vectorized_kafka_schema_id_cache_hits Counts the number of cache hits in the server-side schema ID validation cache. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_kafka_schema_id_cache_misses)vectorized_kafka_schema_id_cache_misses Counts the number of cache misses in the server-side schema ID validation cache. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_leader_balancer_leader_transfer_error)vectorized_leader_balancer_leader_transfer_error Counts the number of errors encountered during leader transfer attempts. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_leader_balancer_leader_transfer_no_improvement)vectorized_leader_balancer_leader_transfer_no_improvement Counts the number of leader transfer attempts that did not result in improved balance. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_leader_balancer_leader_transfer_succeeded)vectorized_leader_balancer_leader_transfer_succeeded Counts the total number of successful leader transfers. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_leader_balancer_leader_transfer_timeout)vectorized_leader_balancer_leader_transfer_timeout Counts the number of leader transfer attempts that timed out. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_allocated_memory)vectorized_memory_allocated_memory Reports the total amount of memory allocated (in bytes) by the process. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_memory_available_memory)vectorized_memory_available_memory Reports the total amount of potentially available memory (free plus reclaimable) per shard. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_memory_available_memory_low_water_mark)vectorized_memory_available_memory_low_water_mark Reports the low-water mark for available memory since process start. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_memory_cross_cpu_free_operations)vectorized_memory_cross_cpu_free_operations Counts the number of cross-CPU free operations executed. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_free_memory)vectorized_memory_free_memory Reports the current free memory (in bytes) per shard. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_memory_free_operations)vectorized_memory_free_operations Counts the total number of free operations performed. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_malloc_failed)vectorized_memory_malloc_failed Counts the total number of failed memory allocation attempts. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_malloc_live_objects)vectorized_memory_malloc_live_objects Reports the current number of live objects allocated via malloc. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_memory_malloc_operations)vectorized_memory_malloc_operations Counts the total number of malloc operations performed. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_reclaims_operations)vectorized_memory_reclaims_operations Counts the total number of memory reclaim operations performed. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_memory_total_memory)vectorized_memory_total_memory Reports the total memory size (in bytes) available per shard. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_network_bytes_received)vectorized_network_bytes_received Counts the total number of bytes received over network sockets. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_network_bytes_sent)vectorized_network_bytes_sent Counts the total number of bytes sent over network sockets. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_node_status_rpcs_received)vectorized_node_status_rpcs_received Reports the number of broker status RPCs received by this broker. **Type**: gauge * * * ## [](#vectorized_node_status_rpcs_sent)vectorized_node_status_rpcs_sent Reports the number of broker status RPCs sent by this broker. **Type**: gauge * * * ## [](#vectorized_node_status_rpcs_timed_out)vectorized_node_status_rpcs_timed_out Reports the number of broker status RPCs that have timed out. **Type**: gauge * * * ## [](#vectorized_ntp_archiver_compacted_replaced_bytes)vectorized_ntp_archiver_compacted_replaced_bytes Number of bytes removed from object storage by compaction operations. This is tracked on a per-topic and per-partition basis. This metric resets every time partition leadership changes. It tracks whether or not compaction is performing operations on object storage. The `namespace` label supports the following options for this metric: - `kafka` - User topics - `kafka_internal` - Internal Kafka topic, such as consumer groups - `redpanda` - Redpanda-only internal data **Type**: gauge **Labels**: - `namespace=("kafka" | "kafka_internal" | "redpanda")` - `topic` - `partition` * * * ### [](#vectorized_ntp_archiver_missing)vectorized_ntp_archiver_missing Counts the number of missing offsets due to gaps. This metric is tracked on a per-topic and per-partition basis. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_ntp_archiver_pending)vectorized_ntp_archiver_pending Reports the difference between the last committed offset and the last offset uploaded to Tiered Storage for each partition. A value of zero for this metric indicates that all data for a partition is uploaded to Tiered Storage. This metric is impacted by the [`cloud_storage_segment_max_upload_interval_sec`](https://docs.redpanda.com/streaming/25.2/reference/properties/object-storage-properties/#cloud_storage_segment_max_upload_interval_sec) property. If this interval is set to 5 minutes, the archiver uploads committed segments to Tiered Storage every 5 minutes or less. If this metric continues growing for longer than the configured interval, it can indicate a potential network issue with the upload path for that partition. The `namespace` label supports the following options for this metric: - `kafka` - User topics - `kafka_internal` - Internal Kafka topic, such as consumer groups - `redpanda` - Redpanda-only internal data **Type**: gauge **Labels**: - `namespace=("kafka" | "kafka_internal" | "redpanda")` - `topic` - `partition` * * * ### [](#vectorized_ntp_archiver_uploaded)vectorized_ntp_archiver_uploaded Counts the number of offsets uploaded to object storage. This metric is tracked on a per-topic and per-partition basis. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ### [](#vectorized_ntp_archiver_uploaded_bytes)vectorized_ntp_archiver_uploaded_bytes Counts the number of bytes uploaded to object storage. This metric is tracked on a per-topic and per-partition basis. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_pandaproxy_request_errors_total)vectorized_pandaproxy_request_errors_total Counts the total number of REST proxy server errors, segmented by operation and status. **Type**: counter **Labels**: - `operation` - `shard` - `status` * * * ## [](#vectorized_pandaproxy_request_latency)vectorized_pandaproxy_request_latency Provides a histogram of REST proxy request latencies. **Type**: histogram * * * ## [](#vectorized_raft_append_entries_buffer_flushes)vectorized_raft_append_entries_buffer_flushes Counts the number of flushes performed on the append entries buffer. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_buffered_protocol_buffered_bytes)vectorized_raft_buffered_protocol_buffered_bytes Reports the total size (in bytes) of append entries requests currently buffered. **Type**: gauge **Labels**: - `shard` - `target_node_id` * * * ## [](#vectorized_raft_buffered_protocol_buffered_requests)vectorized_raft_buffered_protocol_buffered_requests Counts the number of append entries requests currently buffered. **Type**: gauge **Labels**: - `shard` - `target_node_id` * * * ## [](#vectorized_raft_buffered_protocol_inflight_requests)vectorized_raft_buffered_protocol_inflight_requests Counts the number of append entries requests sent to a target broker that are awaiting responses. **Type**: gauge **Labels**: - `shard` - `target_node_id` * * * ## [](#vectorized_raft_configuration_change_in_progress)vectorized_raft_configuration_change_in_progress Indicates if the current raft group configuration is in a joint state (i.e. undergoing change). **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_done_replicate_requests)vectorized_raft_done_replicate_requests Counts the total number of replicate requests that have completed. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_full_heartbeat_requests)vectorized_raft_full_heartbeat_requests Counts the number of full heartbeat messages sent by the raft leader. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_group_configuration_updates)vectorized_raft_group_configuration_updates Counts the total number of raft group configuration updates. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_group_count)vectorized_raft_group_count Reports the total number of raft groups present. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_heartbeat_requests_errors)vectorized_raft_heartbeat_requests_errors Counts the number of failed heartbeat requests within a raft group. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_leader_for)vectorized_raft_leader_for Indicates the number of raft groups for which this broker is the leader. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_leadership_changes)vectorized_raft_leadership_changes Counts the number of leader elections won by this broker. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_learners_gap_bytes)vectorized_raft_learners_gap_bytes Reports the total number of bytes that must be sent to learners to catch up. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_lightweight_heartbeat_requests)vectorized_raft_lightweight_heartbeat_requests Counts the number of lightweight heartbeat messages sent by the raft leader. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_log_flushes)vectorized_raft_log_flushes Counts the number of log flush operations performed. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_log_truncations)vectorized_raft_log_truncations Counts the number of log truncations performed. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_offset_translator_inconsistency_errors)vectorized_raft_offset_translator_inconsistency_errors Counts the number of append entries requests that failed the offset translator consistency check. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_received_append_requests)vectorized_raft_received_append_requests Counts the total number of append requests received. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_received_vote_requests)vectorized_raft_received_vote_requests Counts the total number of vote requests received. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_recovery_offsets_pending)vectorized_raft_recovery_offsets_pending Reports the sum of offsets that need recovery on this broker. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_recovery_partition_movement_assigned_bandwidth)vectorized_raft_recovery_partition_movement_assigned_bandwidth Reports the bandwidth (bytes/sec) assigned for partition movement in the last tick. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_recovery_partition_movement_available_bandwidth)vectorized_raft_recovery_partition_movement_available_bandwidth Reports the available bandwidth (bytes/sec) for partition movement. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_recovery_partitions_active)vectorized_raft_recovery_partitions_active Counts the number of partition replicas currently in recovery on this broker. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_recovery_partitions_to_recover)vectorized_raft_recovery_partitions_to_recover Counts the number of partition replicas that still require recovery on this broker. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_raft_recovery_requests)vectorized_raft_recovery_requests Counts the total number of recovery requests issued. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_recovery_requests_errors)vectorized_raft_recovery_requests_errors Counts the total number of failed recovery requests. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_ack_all_requests)vectorized_raft_replicate_ack_all_requests Counts replicate requests that required quorum acknowledgments with an explicit flush. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_ack_all_requests_no_flush)vectorized_raft_replicate_ack_all_requests_no_flush Counts replicate requests that required quorum acknowledgments but did not use an explicit flush. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_ack_leader_requests)vectorized_raft_replicate_ack_leader_requests Counts replicate requests that acknowledged only the leader. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_ack_none_requests)vectorized_raft_replicate_ack_none_requests Counts replicate requests that did not require any acknowledgment. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_batch_flush_requests)vectorized_raft_replicate_batch_flush_requests Counts the number of batch flush operations in replicate requests. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_replicate_request_errors)vectorized_raft_replicate_request_errors Counts the number of failed replicate requests. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_raft_sent_vote_requests)vectorized_raft_sent_vote_requests Counts the total number of vote requests sent. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_reactor_abandoned_failed_futures)vectorized_reactor_abandoned_failed_futures Counts the total number of futures that were abandoned while still containing an exception. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_bytes_read)vectorized_reactor_aio_bytes_read Counts the total number of bytes read via asynchronous IO. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_bytes_write)vectorized_reactor_aio_bytes_write Counts the total number of bytes written via asynchronous IO. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_errors)vectorized_reactor_aio_errors Counts the total number of asynchronous IO errors. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_outsizes)vectorized_reactor_aio_outsizes Counts the total number of AIO operations that exceeded configured IO limits. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_reads)vectorized_reactor_aio_reads Counts the total number of AIO read operations. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_aio_writes)vectorized_reactor_aio_writes Counts the total number of AIO write operations. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_awake_time_ms_total)vectorized_reactor_awake_time_ms_total Reports the total wall-clock time (in milliseconds) the reactor was awake. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_cpp_exceptions)vectorized_reactor_cpp_exceptions Counts the total number of C++ exceptions thrown by the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_cpu_busy_ms)vectorized_reactor_cpu_busy_ms Reports the total CPU busy time (in milliseconds) for the reactor thread. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_cpu_steal_time_ms)vectorized_reactor_cpu_steal_time_ms Reports the total amount of time (in milliseconds) the reactor was runnable but was not scheduled (steal time). **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_cpu_used_time_ms)vectorized_reactor_cpu_used_time_ms Reports the total CPU time used by the reactor thread (from CLOCK\_THREAD\_CPUTIME). **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_read_bytes)vectorized_reactor_fstream_read_bytes Counts the total number of bytes read from disk file streams. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_read_bytes_blocked)vectorized_reactor_fstream_read_bytes_blocked Counts the number of bytes read from disk that had to block due to insufficient read-ahead buffers. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_reads)vectorized_reactor_fstream_reads Counts the total number of read operations from disk file streams. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_reads_ahead_bytes_discarded)vectorized_reactor_fstream_reads_ahead_bytes_discarded Counts the number of buffered bytes that were discarded after being read ahead but not used. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_reads_aheads_discarded)vectorized_reactor_fstream_reads_aheads_discarded Counts the number of times that pre-read buffers were discarded due to being unnecessary. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fstream_reads_blocked)vectorized_reactor_fstream_reads_blocked Counts the number of times a disk read had to block because pre-read buffers were insufficient. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_fsyncs)vectorized_reactor_fsyncs Counts the total number of fsync operations performed by the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_io_threaded_fallbacks)vectorized_reactor_io_threaded_fallbacks Counts the number of times the reactor fell back to an IO-threaded path. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_logging_failures)vectorized_reactor_logging_failures Counts the total number of logging failures encountered by the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_polls)vectorized_reactor_polls Counts the total number of poll cycles executed by the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_sleep_time_ms_total)vectorized_reactor_sleep_time_ms_total Reports the total wall-clock sleep time (in milliseconds) of the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_stalls)vectorized_reactor_stalls Provides a histogram of durations for which the reactor experienced stalls. **Type**: histogram * * * ## [](#vectorized_reactor_tasks_pending)vectorized_reactor_tasks_pending Reports the current number of pending tasks in the reactor’s task queue. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_reactor_tasks_processed)vectorized_reactor_tasks_processed Counts the total number of tasks processed by the reactor. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_reactor_timers_pending)vectorized_reactor_timers_pending Reports the current number of pending timer tasks in the reactor. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_reactor_utilization)vectorized_reactor_utilization Indicates the CPU utilization of the reactor thread. Shows the true utilization of the CPU by a Redpanda process. This metric has per-broker and per-shard granularity. If a shard (CPU core) is at 100% utilization for a continuous period of real-time processing, for example more than a few seconds, you will likely observe high latency for partitions assigned to that shard. Use topic-aware [intra-broker partition balancing](https://docs.redpanda.com/streaming/25.2/manage/cluster-maintenance/cluster-balancing/#intra-broker-partition-balancing) to balance partition assignments and alleviate load on individual shards. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_rest_proxy_inflight_requests_memory_usage_ratio)vectorized_rest_proxy_inflight_requests_memory_usage_ratio Reports the memory usage ratio for in-flight REST proxy requests. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_rest_proxy_inflight_requests_usage_ratio)vectorized_rest_proxy_inflight_requests_usage_ratio Reports the overall usage ratio of in-flight REST proxy requests. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_rest_proxy_queued_requests_memory_blocked)vectorized_rest_proxy_queued_requests_memory_blocked Reports the number of REST proxy requests that are queued due to memory limitations. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_rpc_client_active_connections)vectorized_rpc_client_active_connections Indicates the number of currently active RPC client connections. **Type**: gauge **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_client_correlation_errors)vectorized_rpc_client_client_correlation_errors Counts errors in client correlation IDs within RPC responses. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_connection_errors)vectorized_rpc_client_connection_errors Counts the number of connection errors encountered by the RPC client. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_connects)vectorized_rpc_client_connects Counts the total number of RPC client connection attempts. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_corrupted_headers)vectorized_rpc_client_corrupted_headers Counts the number of RPC responses received with corrupted headers. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_in_bytes)vectorized_rpc_client_in_bytes Reports the total number of bytes received by the RPC client. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_out_bytes)vectorized_rpc_client_out_bytes Reports the total number of bytes sent (including headers) by the RPC client. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_read_dispatch_errors)vectorized_rpc_client_read_dispatch_errors Counts the number of errors encountered while dispatching RPC responses. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_request_errors)vectorized_rpc_client_request_errors Counts the total number of request errors encountered by the RPC client. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_request_timeouts)vectorized_rpc_client_request_timeouts Counts the number of RPC client request timeouts. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_requests)vectorized_rpc_client_requests Counts the total number of RPC client requests made. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_requests_blocked_memory)vectorized_rpc_client_requests_blocked_memory Counts the number of RPC client requests that were blocked due to insufficient memory. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_requests_pending)vectorized_rpc_client_requests_pending Reports the current number of pending RPC client requests. **Type**: gauge **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_rpc_client_server_correlation_errors)vectorized_rpc_client_server_correlation_errors Counts the number of RPC responses with mismatched server correlation IDs. **Type**: counter **Labels**: - `connection_cache_label` - `shard` - `target` * * * ## [](#vectorized_scheduler_queue_length)vectorized_scheduler_queue_length Reports the current size of the scheduler queue (in tasks), indicating backlog. **Type**: gauge **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_runtime_ms)vectorized_scheduler_runtime_ms Reports the accumulated runtime (in milliseconds) of a scheduler queue. A rate of 1000ms per second suggests full utilization. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_shares)vectorized_scheduler_shares Indicates the share allocation for a scheduler queue. **Type**: gauge **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_starvetime_ms)vectorized_scheduler_starvetime_ms Reports the accumulated starvation time (in milliseconds) for a scheduler queue. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_tasks_processed)vectorized_scheduler_tasks_processed Counts the total number of tasks processed by the scheduler. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_time_spent_on_task_quota_violations_ms)vectorized_scheduler_time_spent_on_task_quota_violations_ms Reports the total time (in milliseconds) that the scheduler has violated task quotas. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_scheduler_waittime_ms)vectorized_scheduler_waittime_ms Reports the accumulated wait time (in milliseconds) for a scheduler queue. **Type**: counter **Labels**: - `group` - `shard` * * * ## [](#vectorized_schema_registry_cache_schema_count)vectorized_schema_registry_cache_schema_count Reports the total number of schemas stored in the schema registry cache. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_schema_registry_cache_schema_memory_bytes)vectorized_schema_registry_cache_schema_memory_bytes Reports the memory usage (in bytes) of schemas stored in the registry. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_schema_registry_cache_subject_count)vectorized_schema_registry_cache_subject_count Reports the total number of subjects in the schema registry. **Type**: gauge **Labels**: - `deleted` - `shard` * * * ## [](#vectorized_schema_registry_cache_subject_version_count)vectorized_schema_registry_cache_subject_version_count Reports the number of versions for a given subject in the schema registry. **Type**: gauge **Labels**: - `deleted` - `shard` - `subject` * * * ## [](#vectorized_schema_registry_inflight_requests_memory_usage_ratio)vectorized_schema_registry_inflight_requests_memory_usage_ratio Reports the memory usage ratio for in-flight schema registry requests. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_schema_registry_inflight_requests_usage_ratio)vectorized_schema_registry_inflight_requests_usage_ratio Reports the usage ratio for in-flight schema registry requests. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_schema_registry_queued_requests_memory_blocked)vectorized_schema_registry_queued_requests_memory_blocked Reports the number of schema registry requests queued due to memory constraints. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_security_audit_buffer_usage_ratio)vectorized_security_audit_buffer_usage_ratio Reports the usage ratio of the audit event buffer. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_security_audit_client_buffer_usage_ratio)vectorized_security_audit_client_buffer_usage_ratio Reports the usage ratio of the audit client’s send buffer. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_security_audit_errors_total)vectorized_security_audit_errors_total Counts the total number of errors encountered while creating or publishing audit log entries. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_security_audit_last_event_timestamp_seconds)vectorized_security_audit_last_event_timestamp_seconds Reports the timestamp (in seconds since the epoch) of the last successful audit log event. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_space_management_available_reclaimable_bytes)vectorized_space_management_available_reclaimable_bytes Reports the total amount of reclaimable data available under space management. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_disk_usage_bytes)vectorized_space_management_disk_usage_bytes Reports the total disk usage (in bytes) managed by space management. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_local_retention_reclaimable_bytes)vectorized_space_management_local_retention_reclaimable_bytes Reports the amount of data above the local retention target that is reclaimable. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_reclaim_active_segment_bytes)vectorized_space_management_reclaim_active_segment_bytes Estimates the amount of data above the active segment that can be reclaimed. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_reclaim_estimate_bytes)vectorized_space_management_reclaim_estimate_bytes Provides an estimate of the data (in bytes) to be reclaimed in the last space management schedule. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_reclaim_local_bytes)vectorized_space_management_reclaim_local_bytes Estimates the amount of data above local retention that will be reclaimed. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_reclaim_low_hinted_bytes)vectorized_space_management_reclaim_low_hinted_bytes Estimates the amount of data above the low-space threshold (with hints) to be reclaimed. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_reclaim_low_non_hinted_bytes)vectorized_space_management_reclaim_low_non_hinted_bytes Estimates the amount of data above the low-space threshold (without hints) to be reclaimed. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_retention_reclaimable_bytes)vectorized_space_management_retention_reclaimable_bytes Reports the total reclaimable data as per the standard retention policy. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_target_disk_size_bytes)vectorized_space_management_target_disk_size_bytes Specifies the target maximum disk usage (in bytes) for space management. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_space_management_target_excess_bytes)vectorized_space_management_target_excess_bytes Reports the amount of disk usage exceeding the target threshold. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_stall_detector_reported)vectorized_stall_detector_reported Counts the total number of stalls reported (see detailed traces for context). **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_compaction_backlog_controller_backlog_size)vectorized_storage_compaction_backlog_controller_backlog_size Reports the current backlog size for the storage compaction controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_storage_compaction_backlog_controller_error)vectorized_storage_compaction_backlog_controller_error Reports the error (difference between target and current backlog) in the compaction controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_storage_compaction_backlog_controller_shares)vectorized_storage_compaction_backlog_controller_shares Reports the number of shares output by the storage compaction controller. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_cached_bytes)vectorized_storage_kvstore_cached_bytes Reports the size (in bytes) of the in-memory key-value store cache. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_entries_fetched)vectorized_storage_kvstore_entries_fetched Counts the number of key-value entries fetched from the store. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_entries_removed)vectorized_storage_kvstore_entries_removed Counts the number of key-value entries removed from the store. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_entries_written)vectorized_storage_kvstore_entries_written Counts the number of key-value entries written to the store. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_key_count)vectorized_storage_kvstore_key_count Reports the total number of keys currently stored in the key-value store. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_kvstore_segments_rolled)vectorized_storage_kvstore_segments_rolled Counts the number of segments that have been rolled in the key-value store. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_log_batch_parse_errors)vectorized_storage_log_batch_parse_errors Counts the number of errors encountered while parsing log batches. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_batch_write_errors)vectorized_storage_log_batch_write_errors Counts the number of errors encountered while writing log batches. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_batches_read)vectorized_storage_log_batches_read Counts the total number of log batches read. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_batches_written)vectorized_storage_log_batches_written Counts the total number of log batches written. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_bytes_prefix_truncated)vectorized_storage_log_bytes_prefix_truncated Counts the number of bytes removed due to prefix truncation of log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_cache_hits)vectorized_storage_log_cache_hits Counts the number of cache hits in the log reader cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_cache_misses)vectorized_storage_log_cache_misses Counts the number of cache misses in the log reader cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_cached_batches_read)vectorized_storage_log_cached_batches_read Counts the total number of log batches read from cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_cached_read_bytes)vectorized_storage_log_cached_read_bytes Counts the total number of bytes read from the log cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_chunked_compaction_runs)vectorized_storage_log_chunked_compaction_runs Counts the number of times chunked compaction has been executed, which can also indicate failures in building key–offset maps. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_cleanly_compacted_segment)vectorized_storage_log_cleanly_compacted_segment Counts the number of segments that were successfully compacted with proper deduplication. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_closed_segment_bytes)vectorized_storage_log_closed_segment_bytes Reports the total number of bytes contained in closed log segments. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_compacted_segment)vectorized_storage_log_compacted_segment Counts the total number of compacted log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_compaction_ratio)vectorized_storage_log_compaction_ratio Reports the average compaction ratio for log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `topic` * * * ## [](#vectorized_storage_log_compaction_removed_bytes)vectorized_storage_log_compaction_removed_bytes Counts the total number of bytes removed from local storage by compaction operations. This is tracked on a per-topic and per-partition basis. It tracks whether compaction is performing operations on local storage. The namespace label supports the following options for this metric: - `kafka`: User topics - `kafka_internal`: Internal Kafka topic, such as consumer groups - `redpanda`: Redpanda-only internal data **Type**: counter **Labels**: - `namespace=("kafka" | "kafka_internal" | "redpanda")` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_complete_sliding_window_rounds)vectorized_storage_log_complete_sliding_window_rounds Counts the number of complete rounds executed in sliding window compaction. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_corrupted_compaction_indices)vectorized_storage_log_corrupted_compaction_indices Counts the number of times the compaction index had to be reconstructed due to corruption. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_dirty_segment_bytes)vectorized_storage_log_dirty_segment_bytes Reports the total number of bytes contained in dirty (non-compacted) log segments. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_log_segments_active)vectorized_storage_log_log_segments_active Counts the current number of active local log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_log_segments_created)vectorized_storage_log_log_segments_created Counts the total number of local log segments created since broker startup. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_log_segments_removed)vectorized_storage_log_log_segments_removed Counts the total number of local log segments removed since broker startup. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_partition_size)vectorized_storage_log_partition_size Reports the current size (in bytes) of a partition’s log. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_read_bytes)vectorized_storage_log_read_bytes Counts the total number of bytes read from log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_readers_added)vectorized_storage_log_readers_added Counts the total number of log readers that have been added to the cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_readers_evicted)vectorized_storage_log_readers_evicted Counts the total number of log readers evicted from the cache. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_segments_marked_tombstone_free)vectorized_storage_log_segments_marked_tombstone_free Counts the number of log segments verified to be free of tombstones via compaction. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_tombstones_removed)vectorized_storage_log_tombstones_removed Counts the number of tombstone records removed during compaction (per retention policy). **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_log_written_bytes)vectorized_storage_log_written_bytes Counts the total number of bytes written to log segments. **Type**: counter **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_storage_manager_housekeeping_log_processed)vectorized_storage_manager_housekeeping_log_processed Counts the number of logs processed by the storage housekeeping routine. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_storage_manager_logs)vectorized_storage_manager_logs Reports the number of logs currently managed by the storage manager. **Type**: gauge **Labels**: - `shard` * * * ## [](#vectorized_storage_manager_urgent_gc_runs)vectorized_storage_manager_urgent_gc_runs Counts the number of urgent garbage collection runs executed by the storage manager. **Type**: counter **Labels**: - `shard` * * * ## [](#vectorized_tx_partition_idempotency_pid_cache_size)vectorized_tx_partition_idempotency_pid_cache_size Reports the number of active producer ID–sequence pairs used for idempotency in transactions. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic` * * * ## [](#vectorized_tx_partition_tx_num_inflight_requests)vectorized_tx_partition_tx_num_inflight_requests Reports the number of ongoing transactional requests for a partition. **Type**: gauge **Labels**: - `namespace` - `partition` - `shard` - `topic`