From f37c6aacb71d88759de157da96d5cf6bee5cba7a Mon Sep 17 00:00:00 2001 From: Ethan Dickson Date: Thu, 26 Sep 2024 13:49:20 +0000 Subject: [PATCH] fix(docs): add `coderd_workspace_latest_build_status` prometheus metric --- docs/admin/prometheus.md | 157 +++++++++++++++++----------------- scripts/metricsdocgen/metrics | 3 + 2 files changed, 82 insertions(+), 78 deletions(-) diff --git a/docs/admin/prometheus.md b/docs/admin/prometheus.md index 005770b5c10e9..0917b26b0c637 100644 --- a/docs/admin/prometheus.md +++ b/docs/admin/prometheus.md @@ -103,83 +103,84 @@ deployment. They will always be available from the agent. -| Name | Type | Description | Labels | -| ------------------------------------------------------------- | --------- | -------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | -| `agent_scripts_executed_total` | counter | Total number of scripts executed by the Coder agent. Includes cron scheduled scripts. | `agent_name` `success` `template_name` `username` `workspace_name` | -| `coderd_agents_apps` | gauge | Agent applications with statuses. | `agent_name` `app_name` `health` `username` `workspace_name` | -| `coderd_agents_connection_latencies_seconds` | gauge | Agent connection latencies in seconds. | `agent_name` `derp_region` `preferred` `username` `workspace_name` | -| `coderd_agents_connections` | gauge | Agent connections with statuses. | `agent_name` `lifecycle_state` `status` `tailnet_node` `username` `workspace_name` | -| `coderd_agents_up` | gauge | The number of active agents per workspace. | `template_name` `username` `workspace_name` | -| `coderd_agentstats_connection_count` | gauge | The number of established connections by agent | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_connection_median_latency_seconds` | gauge | The median agent connection latency | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_currently_reachable_peers` | gauge | The number of peers (e.g. clients) that are currently reachable over the encrypted network. | `agent_name` `connection_type` `template_name` `username` `workspace_name` | -| `coderd_agentstats_rx_bytes` | gauge | Agent Rx bytes | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_session_count_jetbrains` | gauge | The number of session established by JetBrains | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_session_count_reconnecting_pty` | gauge | The number of session established by reconnecting PTY | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_session_count_ssh` | gauge | The number of session established by SSH | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_session_count_vscode` | gauge | The number of session established by VSCode | `agent_name` `username` `workspace_name` | -| `coderd_agentstats_startup_script_seconds` | gauge | The number of seconds the startup script took to execute. | `agent_name` `success` `template_name` `username` `workspace_name` | -| `coderd_agentstats_tx_bytes` | gauge | Agent Tx bytes | `agent_name` `username` `workspace_name` | -| `coderd_api_active_users_duration_hour` | gauge | The number of users that have been active within the last hour. | | -| `coderd_api_concurrent_requests` | gauge | The number of concurrent API requests. | | -| `coderd_api_concurrent_websockets` | gauge | The total number of concurrent API websockets. | | -| `coderd_api_request_latencies_seconds` | histogram | Latency distribution of requests in seconds. | `method` `path` | -| `coderd_api_requests_processed_total` | counter | The total number of processed API requests | `code` `method` `path` | -| `coderd_api_websocket_durations_seconds` | histogram | Websocket duration distribution of requests in seconds. | `path` | -| `coderd_api_workspace_latest_build` | gauge | The latest workspace builds with a status. | `status` | -| `coderd_api_workspace_latest_build_total` | gauge | DEPRECATED: use coderd_api_workspace_latest_build instead | `status` | -| `coderd_insights_applications_usage_seconds` | gauge | The application usage per template. | `application_name` `slug` `template_name` | -| `coderd_insights_parameters` | gauge | The parameter usage per template. | `parameter_name` `parameter_type` `parameter_value` `template_name` | -| `coderd_insights_templates_active_users` | gauge | The number of active users of the template. | `template_name` | -| `coderd_license_active_users` | gauge | The number of active users. | | -| `coderd_license_limit_users` | gauge | The user seats limit based on the active Coder license. | | -| `coderd_license_user_limit_enabled` | gauge | Returns 1 if the current license enforces the user limit. | | -| `coderd_metrics_collector_agents_execution_seconds` | histogram | Histogram for duration of agents metrics collection in seconds. | | -| `coderd_oauth2_external_requests_rate_limit` | gauge | The total number of allowed requests per interval. | `name` `resource` | -| `coderd_oauth2_external_requests_rate_limit_next_reset_unix` | gauge | Unix timestamp of the next interval | `name` `resource` | -| `coderd_oauth2_external_requests_rate_limit_remaining` | gauge | The remaining number of allowed requests in this interval. | `name` `resource` | -| `coderd_oauth2_external_requests_rate_limit_reset_in_seconds` | gauge | Seconds until the next interval | `name` `resource` | -| `coderd_oauth2_external_requests_rate_limit_total` | gauge | DEPRECATED: use coderd_oauth2_external_requests_rate_limit instead | `name` `resource` | -| `coderd_oauth2_external_requests_rate_limit_used` | gauge | The number of requests made in this interval. | `name` `resource` | -| `coderd_oauth2_external_requests_total` | counter | The total number of api calls made to external oauth2 providers. 'status_code' will be 0 if the request failed with no response. | `name` `source` `status_code` | -| `coderd_provisionerd_job_timings_seconds` | histogram | The provisioner job time duration in seconds. | `provisioner` `status` | -| `coderd_provisionerd_jobs_current` | gauge | The number of currently running provisioner jobs. | `provisioner` | -| `coderd_workspace_builds_total` | counter | The number of workspaces started, updated, or deleted. | `action` `owner_email` `status` `template_name` `template_version` `workspace_name` | -| `go_gc_duration_seconds` | summary | A summary of the pause duration of garbage collection cycles. | | -| `go_goroutines` | gauge | Number of goroutines that currently exist. | | -| `go_info` | gauge | Information about the Go environment. | `version` | -| `go_memstats_alloc_bytes` | gauge | Number of bytes allocated and still in use. | | -| `go_memstats_alloc_bytes_total` | counter | Total number of bytes allocated, even if freed. | | -| `go_memstats_buck_hash_sys_bytes` | gauge | Number of bytes used by the profiling bucket hash table. | | -| `go_memstats_frees_total` | counter | Total number of frees. | | -| `go_memstats_gc_sys_bytes` | gauge | Number of bytes used for garbage collection system metadata. | | -| `go_memstats_heap_alloc_bytes` | gauge | Number of heap bytes allocated and still in use. | | -| `go_memstats_heap_idle_bytes` | gauge | Number of heap bytes waiting to be used. | | -| `go_memstats_heap_inuse_bytes` | gauge | Number of heap bytes that are in use. | | -| `go_memstats_heap_objects` | gauge | Number of allocated objects. | | -| `go_memstats_heap_released_bytes` | gauge | Number of heap bytes released to OS. | | -| `go_memstats_heap_sys_bytes` | gauge | Number of heap bytes obtained from system. | | -| `go_memstats_last_gc_time_seconds` | gauge | Number of seconds since 1970 of last garbage collection. | | -| `go_memstats_lookups_total` | counter | Total number of pointer lookups. | | -| `go_memstats_mallocs_total` | counter | Total number of mallocs. | | -| `go_memstats_mcache_inuse_bytes` | gauge | Number of bytes in use by mcache structures. | | -| `go_memstats_mcache_sys_bytes` | gauge | Number of bytes used for mcache structures obtained from system. | | -| `go_memstats_mspan_inuse_bytes` | gauge | Number of bytes in use by mspan structures. | | -| `go_memstats_mspan_sys_bytes` | gauge | Number of bytes used for mspan structures obtained from system. | | -| `go_memstats_next_gc_bytes` | gauge | Number of heap bytes when next garbage collection will take place. | | -| `go_memstats_other_sys_bytes` | gauge | Number of bytes used for other system allocations. | | -| `go_memstats_stack_inuse_bytes` | gauge | Number of bytes in use by the stack allocator. | | -| `go_memstats_stack_sys_bytes` | gauge | Number of bytes obtained from system for stack allocator. | | -| `go_memstats_sys_bytes` | gauge | Number of bytes obtained from system. | | -| `go_threads` | gauge | Number of OS threads created. | | -| `process_cpu_seconds_total` | counter | Total user and system CPU time spent in seconds. | | -| `process_max_fds` | gauge | Maximum number of open file descriptors. | | -| `process_open_fds` | gauge | Number of open file descriptors. | | -| `process_resident_memory_bytes` | gauge | Resident memory size in bytes. | | -| `process_start_time_seconds` | gauge | Start time of the process since unix epoch in seconds. | | -| `process_virtual_memory_bytes` | gauge | Virtual memory size in bytes. | | -| `process_virtual_memory_max_bytes` | gauge | Maximum amount of virtual memory available in bytes. | | -| `promhttp_metric_handler_requests_in_flight` | gauge | Current number of scrapes being served. | | -| `promhttp_metric_handler_requests_total` | counter | Total number of scrapes by HTTP status code. | `code` | +| Name | Type | Description | Labels | +| ------------------------------------------------------------- | --------- | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | +| `agent_scripts_executed_total` | counter | Total number of scripts executed by the Coder agent. Includes cron scheduled scripts. | `agent_name` `success` `template_name` `username` `workspace_name` | +| `coderd_agents_apps` | gauge | Agent applications with statuses. | `agent_name` `app_name` `health` `username` `workspace_name` | +| `coderd_agents_connection_latencies_seconds` | gauge | Agent connection latencies in seconds. | `agent_name` `derp_region` `preferred` `username` `workspace_name` | +| `coderd_agents_connections` | gauge | Agent connections with statuses. | `agent_name` `lifecycle_state` `status` `tailnet_node` `username` `workspace_name` | +| `coderd_agents_up` | gauge | The number of active agents per workspace. | `template_name` `username` `workspace_name` | +| `coderd_agentstats_connection_count` | gauge | The number of established connections by agent | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_connection_median_latency_seconds` | gauge | The median agent connection latency | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_currently_reachable_peers` | gauge | The number of peers (e.g. clients) that are currently reachable over the encrypted network. | `agent_name` `connection_type` `template_name` `username` `workspace_name` | +| `coderd_agentstats_rx_bytes` | gauge | Agent Rx bytes | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_session_count_jetbrains` | gauge | The number of session established by JetBrains | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_session_count_reconnecting_pty` | gauge | The number of session established by reconnecting PTY | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_session_count_ssh` | gauge | The number of session established by SSH | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_session_count_vscode` | gauge | The number of session established by VSCode | `agent_name` `username` `workspace_name` | +| `coderd_agentstats_startup_script_seconds` | gauge | The number of seconds the startup script took to execute. | `agent_name` `success` `template_name` `username` `workspace_name` | +| `coderd_agentstats_tx_bytes` | gauge | Agent Tx bytes | `agent_name` `username` `workspace_name` | +| `coderd_api_active_users_duration_hour` | gauge | The number of users that have been active within the last hour. | | +| `coderd_api_concurrent_requests` | gauge | The number of concurrent API requests. | | +| `coderd_api_concurrent_websockets` | gauge | The total number of concurrent API websockets. | | +| `coderd_api_request_latencies_seconds` | histogram | Latency distribution of requests in seconds. | `method` `path` | +| `coderd_api_requests_processed_total` | counter | The total number of processed API requests | `code` `method` `path` | +| `coderd_api_websocket_durations_seconds` | histogram | Websocket duration distribution of requests in seconds. | `path` | +| `coderd_api_workspace_latest_build` | gauge | The latest workspace builds with a status. | `status` | +| `coderd_api_workspace_latest_build_total` | gauge | DEPRECATED: use coderd_api_workspace_latest_build instead | `status` | +| `coderd_insights_applications_usage_seconds` | gauge | The application usage per template. | `application_name` `slug` `template_name` | +| `coderd_insights_parameters` | gauge | The parameter usage per template. | `parameter_name` `parameter_type` `parameter_value` `template_name` | +| `coderd_insights_templates_active_users` | gauge | The number of active users of the template. | `template_name` | +| `coderd_license_active_users` | gauge | The number of active users. | | +| `coderd_license_limit_users` | gauge | The user seats limit based on the active Coder license. | | +| `coderd_license_user_limit_enabled` | gauge | Returns 1 if the current license enforces the user limit. | | +| `coderd_metrics_collector_agents_execution_seconds` | histogram | Histogram for duration of agents metrics collection in seconds. | | +| `coderd_oauth2_external_requests_rate_limit` | gauge | The total number of allowed requests per interval. | `name` `resource` | +| `coderd_oauth2_external_requests_rate_limit_next_reset_unix` | gauge | Unix timestamp of the next interval | `name` `resource` | +| `coderd_oauth2_external_requests_rate_limit_remaining` | gauge | The remaining number of allowed requests in this interval. | `name` `resource` | +| `coderd_oauth2_external_requests_rate_limit_reset_in_seconds` | gauge | Seconds until the next interval | `name` `resource` | +| `coderd_oauth2_external_requests_rate_limit_total` | gauge | DEPRECATED: use coderd_oauth2_external_requests_rate_limit instead | `name` `resource` | +| `coderd_oauth2_external_requests_rate_limit_used` | gauge | The number of requests made in this interval. | `name` `resource` | +| `coderd_oauth2_external_requests_total` | counter | The total number of api calls made to external oauth2 providers. 'status_code' will be 0 if the request failed with no response. | `name` `source` `status_code` | +| `coderd_provisionerd_job_timings_seconds` | histogram | The provisioner job time duration in seconds. | `provisioner` `status` | +| `coderd_provisionerd_jobs_current` | gauge | The number of currently running provisioner jobs. | `provisioner` | +| `coderd_workspace_builds_total` | counter | The number of workspaces started, updated, or deleted. | `action` `owner_email` `status` `template_name` `template_version` `workspace_name` | +| `coderd_workspace_latest_build_status` | gauge | The current workspace statuses by template, transition, and owner. | `status` `template_name` `template_version` `workspace_owner` `workspace_transition` | +| `go_gc_duration_seconds` | summary | A summary of the pause duration of garbage collection cycles. | | +| `go_goroutines` | gauge | Number of goroutines that currently exist. | | +| `go_info` | gauge | Information about the Go environment. | `version` | +| `go_memstats_alloc_bytes` | gauge | Number of bytes allocated and still in use. | | +| `go_memstats_alloc_bytes_total` | counter | Total number of bytes allocated, even if freed. | | +| `go_memstats_buck_hash_sys_bytes` | gauge | Number of bytes used by the profiling bucket hash table. | | +| `go_memstats_frees_total` | counter | Total number of frees. | | +| `go_memstats_gc_sys_bytes` | gauge | Number of bytes used for garbage collection system metadata. | | +| `go_memstats_heap_alloc_bytes` | gauge | Number of heap bytes allocated and still in use. | | +| `go_memstats_heap_idle_bytes` | gauge | Number of heap bytes waiting to be used. | | +| `go_memstats_heap_inuse_bytes` | gauge | Number of heap bytes that are in use. | | +| `go_memstats_heap_objects` | gauge | Number of allocated objects. | | +| `go_memstats_heap_released_bytes` | gauge | Number of heap bytes released to OS. | | +| `go_memstats_heap_sys_bytes` | gauge | Number of heap bytes obtained from system. | | +| `go_memstats_last_gc_time_seconds` | gauge | Number of seconds since 1970 of last garbage collection. | | +| `go_memstats_lookups_total` | counter | Total number of pointer lookups. | | +| `go_memstats_mallocs_total` | counter | Total number of mallocs. | | +| `go_memstats_mcache_inuse_bytes` | gauge | Number of bytes in use by mcache structures. | | +| `go_memstats_mcache_sys_bytes` | gauge | Number of bytes used for mcache structures obtained from system. | | +| `go_memstats_mspan_inuse_bytes` | gauge | Number of bytes in use by mspan structures. | | +| `go_memstats_mspan_sys_bytes` | gauge | Number of bytes used for mspan structures obtained from system. | | +| `go_memstats_next_gc_bytes` | gauge | Number of heap bytes when next garbage collection will take place. | | +| `go_memstats_other_sys_bytes` | gauge | Number of bytes used for other system allocations. | | +| `go_memstats_stack_inuse_bytes` | gauge | Number of bytes in use by the stack allocator. | | +| `go_memstats_stack_sys_bytes` | gauge | Number of bytes obtained from system for stack allocator. | | +| `go_memstats_sys_bytes` | gauge | Number of bytes obtained from system. | | +| `go_threads` | gauge | Number of OS threads created. | | +| `process_cpu_seconds_total` | counter | Total user and system CPU time spent in seconds. | | +| `process_max_fds` | gauge | Maximum number of open file descriptors. | | +| `process_open_fds` | gauge | Number of open file descriptors. | | +| `process_resident_memory_bytes` | gauge | Resident memory size in bytes. | | +| `process_start_time_seconds` | gauge | Start time of the process since unix epoch in seconds. | | +| `process_virtual_memory_bytes` | gauge | Virtual memory size in bytes. | | +| `process_virtual_memory_max_bytes` | gauge | Maximum amount of virtual memory available in bytes. | | +| `promhttp_metric_handler_requests_in_flight` | gauge | Current number of scrapes being served. | | +| `promhttp_metric_handler_requests_total` | counter | Total number of scrapes by HTTP status code. | `code` | diff --git a/scripts/metricsdocgen/metrics b/scripts/metricsdocgen/metrics index 414605de1cd70..35110a9834efb 100644 --- a/scripts/metricsdocgen/metrics +++ b/scripts/metricsdocgen/metrics @@ -707,6 +707,9 @@ coderd_provisionerd_job_timings_seconds_count{provisioner="terraform",status="su # HELP coderd_provisionerd_jobs_current The number of currently running provisioner jobs. # TYPE coderd_provisionerd_jobs_current gauge coderd_provisionerd_jobs_current{provisioner="terraform"} 0 +# HELP coderd_workspace_latest_build_status The current workspace statuses by template, transition, and owner. +# TYPE coderd_workspace_latest_build_status gauge +coderd_workspace_latest_build_status{status="failed",template_name="docker",template_version="sweet_gould9",workspace_owner="admin",workspace_transition="stop"} 1 # HELP coderd_workspace_builds_total The number of workspaces started, updated, or deleted. # TYPE coderd_workspace_builds_total counter coderd_workspace_builds_total{action="START",owner_email="admin@coder.com",status="failed",template_name="docker",template_version="gallant_wright0",workspace_name="test1"} 1