mirrors/pikasTech-unidesk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add hwlab workbench projection observability config

Browse Source
This commit is contained in:
Codex
2026-06-19 03:08:40 +00:00
parent 6f4bf0ac86
commit 08c3cf60d7
2 changed files with 97 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/hwlab-node-lanes.yaml
+79
View File
@@ -172,12 +172,26 @@ lanes:
lowSampleThreshold: 5
metricPrefixes:
- hwlab_workbench_
- hwlab_agentrun_
- hwlab_webui_
- hwlab_http_
requiredSeries:
- hwlab_workbench_journey_total
- hwlab_workbench_event_phase_duration_seconds_count
- hwlab_workbench_backend_event_visible_latency_seconds_count
- hwlab_workbench_projection_lag_events_bucket
- hwlab_workbench_projection_lag_seconds_bucket
- hwlab_workbench_projection_stuck_traces
- hwlab_workbench_projection_cursor_advance_total
- hwlab_workbench_turn_get_duration_seconds_bucket
- hwlab_workbench_turn_get_response_bytes_bucket
- hwlab_agentrun_result_duration_seconds_bucket
- hwlab_agentrun_result_pages_scanned_bucket
- hwlab_agentrun_result_events_scanned_bucket
- hwlab_workbench_projector_batch_duration_seconds_bucket
- hwlab_workbench_projector_candidates_total
- hwlab_workbench_projector_events_processed_total
- hwlab_workbench_projector_last_success_unixtime
backendLabelDenylist:
- unknown
maxUnknownEventLines: 0
@@ -216,6 +230,41 @@ lanes:
groupBy: [namespace, gitops_target, journey, route, cache, auth_state, outcome]
matchLabels:
journey: workbench_open_first_visible|workbench_open_full_load
- id: workbench_projection_lag_p95
metric: hwlab:workbench_projection_lag:p95_seconds
sourceMetric: hwlab_workbench_projection_lag_seconds
quantile: 0.95
window: 5m
minSamples: 1
groupBy: [namespace, gitops_target, node, lane, projection_status, source, status, reason]
- id: workbench_terminal_projection_delay_p95
metric: hwlab:workbench_terminal_projection_delay:p95_seconds
sourceMetric: hwlab_workbench_terminal_projection_delay_seconds
quantile: 0.95
window: 5m
minSamples: 1
groupBy: [namespace, gitops_target, node, lane, projection_status, source, status, reason]
- id: workbench_turn_get_p95
metric: hwlab:workbench_turn_get:p95_seconds
sourceMetric: hwlab_workbench_turn_get_duration_seconds
quantile: 0.95
window: 5m
minSamples: 1
groupBy: [namespace, gitops_target, node, lane, route, status, degraded_reason]
- id: agentrun_result_p95
metric: hwlab:agentrun_result:p95_seconds
sourceMetric: hwlab_agentrun_result_duration_seconds
quantile: 0.95
window: 5m
minSamples: 1
groupBy: [namespace, gitops_target, node, lane, event_count_bucket, status]
- id: workbench_projector_batch_p95
metric: hwlab:workbench_projector_batch:p95_seconds
sourceMetric: hwlab_workbench_projector_batch_duration_seconds
quantile: 0.95
window: 5m
minSamples: 1
groupBy: [namespace, gitops_target, node, lane, phase, status]
warningAlerts:
- id: HWLABWorkbenchSubmitFirstVisibleSlow
ruleId: workbench_submit_first_visible_p95
@@ -243,6 +292,36 @@ lanes:
thresholdSeconds: 13
minSamples: 5
for: 10m
- id: WorkbenchProjectionStuck
ruleId: workbench_projection_lag_p95
severity: warning
thresholdSeconds: 60
minSamples: 1
for: 10m
- id: WorkbenchTerminalProjectionMissing
ruleId: workbench_terminal_projection_delay_p95
severity: warning
thresholdSeconds: 60
minSamples: 1
for: 10m
- id: WorkbenchTurnReadSlow
ruleId: workbench_turn_get_p95
severity: warning
thresholdSeconds: 5
minSamples: 1
for: 10m
- id: AgentRunResultSlowLongTrace
ruleId: agentrun_result_p95
severity: warning
thresholdSeconds: 2.5
minSamples: 1
for: 10m
- id: WorkbenchProjectorNoProgress
ruleId: workbench_projector_batch_p95
severity: warning
thresholdSeconds: 10
minSamples: 1
for: 10m
runtimeImageRewrites:
- source: fatedier/frpc:v0.68.1
target: 127.0.0.1:5000/hwlab/frpc:v0.68.1