Skip to content

Query Metrics

Query metrics overview⚓︎

Prometheus in Hydrolix⚓︎

The Hydrolix stack includes Prometheus, an open-source metrics database. Hydrolix continuously updates its Prometheus instance with metrics information.

You can query, view, and actively monitor this information using a stack's Grafana instance, or you can access it with your own monitoring platform. See Prometheus Integration for more information about setting up Prometheus with an external server.

Use multiple components with a metric⚓︎

If more than one component uses a given metric, querying it will return results from all relevant components. You can restrict results to a specific component by adding a service keyword to your query.

For example, process_open_fds{service="stream-peer"}.

Query metrics⚓︎

These metrics track activity specific to querying.

Metric Type Components Purpose
net_connect_attempts_total Histogram Head/Query peer Histogram of TCP connection attempts to the storage service.
net_connect_seconds Histogram Head/Query peer Histogram of time to connect over TCP to the storage service, in seconds.
net_dns_resolve_seconds Histogram Head/Query peer Histogram of DNS resolution time for the storage service, in seconds.
net_http_response_time Histogram Head/Query peer Histogram of HTTP response times from the storage service, in seconds.
net_http_response_bytes Histogram Head/Query peer Histogram of HTTP bytes downloaded from the storage service.
net_http_attempts_total Histogram Head/Query peer Histogram of HTTP connection attempts to the storage service.
net_http_status_code Histogram Head/Query peer Histogram of HTTP status codes from the storage service.
vfs_cache_hitmiss_total Histogram Head/Query peer Histogram of cache status (bucket=0 cache miss, bucket=1 cache hit).
vfs_cache_read_bytes Histogram Head/Query peer Histogram of bytes read from the cache.
vfs_net_read_bytes Histogram Head/Query peer Histogram of bytes read from the network.
vfs_cache_lru_file_eviction_total Histogram Head/Query peer Histogram of file evictions from the cache.
epoll_cpu_seconds Histogram Head/Query peer Histogram of CPU usage in seconds.
epoll_io_seconds Histogram Head/Query peer Histogram of I/O times in seconds.
epoll_poll_seconds Histogram Head/Query peer Histogram of wait times for file descriptors, in seconds.
hdx_storage_r_catalog_partitions_total Histogram Head/Query peer Histogram of per-query catalog partition count.
hdx_storage_r_partitions_read_total Histogram Head/Query peer Histogram of per-query partition read count.
hdx_storage_r_partitions_per_core_total Histogram Head/Query peer Histogram of per-core partition usage count.
hdx_storage_r_peers_used_total Histogram Query peer Histogram of storage used total.
hdx_storage_r_cores_used_total Histogram Query peer Histogram of cores used total.
hdx_storage_r_catalog_timerange Histogram Head/Query peer Histogram of query time-range distribution.
hdx_partition_columns_read_total Histogram Head/Query peer Histogram of columns read.
hdx_partition_block_decode_seconds Histogram Head/Query peer Histogram of time spent decoding HDX blocks, in seconds.
hdx_partition_open_seconds Histogram Head/Query peer Histogram of time spent opening HDX partitions, in seconds.
hdx_partition_read_seconds Histogram Head/Query peer Histogram of time spent reading HDX partitions, in seconds.
hdx_partition_skipped_total Histogram Head/Query peer Histogram of partitions skipped due to no matching columns.
hdx_partition_blocks_read_total Histogram Head/Query peer Histogram of partition-block read counts.
hdx_partition_blocks_avail_total Histogram Head/Query peer Histogram of partition blocks available.
hdx_partition_index_decision Histogram Head/Query peer Histogram of partition decisions (bucket=0 full scan, 1 partial scan, 2 no match).
hdx_partition_index_lookup_seconds Histogram Head/Query peer Histogram of index lookup times, in seconds.
hdx_partition_index_blocks_skipped_percent Histogram Head/Query peer Histogram of skipped index blocks, in percentage.
hdx_partition_index_blocks_skipped_total Histogram Head/Query peer Histogram of total skipped index blocks.
hdx_partition_rd_w_err_total Histogram Head/Query peer Histogram of read/write errors (bucket=0 read error, 1 write error, 3 error).
query_iowait_seconds Histogram Head/Query peer Histogram of query I/O wait times, in seconds.
query_cpuwait_seconds Histogram Head/Query peer Histogram of query CPU wait times, in seconds.
query_hdx_ch_conv_seconds Histogram Head/Query peer Histogram of time spent converting HDX blocks to ClickHouse, in seconds.
query_health Histogram Head/Query peer Histogram of query health (bucket=0 initiated error, 1 succeeded, 2 error).
query_peer_availability Histogram Head/Query peer Histogram of peer availability (bucket=0 primary_peer_available, 1 secondary_peer_available, 2 no_reachable_peers).
query_attempts_total Histogram Head/Query peer Histogram of total query attempts.
query_response_seconds Histogram Head/Query peer Histogram of total query response times, in seconds.
query_rows_read_total Histogram Head/Query peer Histogram of total query rows read.
query_read_bytes Histogram Head/Query peer Histogram of total query read bytes.
query_rows_written_total Histogram Head/Query peer Histogram of total query rows written.

For a complete list of the metrics used by Hydrolix, including Prometheus, RabbitMQ, and others, see All Metrics.