Add stale recovery to tracker mapping worker
The tracker-mapping worker clears mapping_requested_at at claim time, so a crash or hard failure between Process phases left the pattern dequeued, unmapped, and with nothing to re-trigger it. Only an incidental sibling remap could rescue it, so a lone pattern could stay stranded forever. Implement the worker.StaleRecoverer interface, mirroring the enrichment worker. ResetStaleMappings re-arms rows that were claimed but never assigned a catalog row (common_tracker_pattern_id IS NULL) once idle past a configurable window; a successful Process always assigns one via the unmatched fallback, so the predicate cleanly detects interrupted runs and self-heals after a single pass. ClearMappingRequestedAt now bumps updated_at so the stale clock starts at claim time and the sweep never recycles an in-flight claim. Plumb a StaleAfter knob (default 600s) through the config struct, builder env var, probod wiring, and Helm templates. Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
@@ -249,6 +249,7 @@ func (b *Builder) Build() (*probodconfig.FullConfig, error) {
|
||||
TrackerMappingWorker: probodconfig.TrackerMappingWorkerConfig{
|
||||
Interval: b.getEnvIntOrDefault("TRACKER_MAPPING_INTERVAL", 10),
|
||||
MaxConcurrency: b.getEnvIntOrDefault("TRACKER_MAPPING_MAX_CONCURRENCY", 3),
|
||||
StaleAfter: b.getEnvIntOrDefault("TRACKER_MAPPING_STALE_AFTER", 600),
|
||||
AgentTimeout: b.getEnvIntOrDefault("TRACKER_MAPPING_AGENT_TIMEOUT", 45),
|
||||
AgentMaxTurns: b.getEnvIntOrDefault("TRACKER_MAPPING_AGENT_MAX_TURNS", 4),
|
||||
},
|
||||
|
||||
@@ -223,6 +223,7 @@ func TestBuilder_Build_Defaults(t *testing.T) {
|
||||
// Tracker worker tuning — defaults
|
||||
assert.Equal(t, 10, cfg.Probod.TrackerMappingWorker.Interval)
|
||||
assert.Equal(t, 3, cfg.Probod.TrackerMappingWorker.MaxConcurrency)
|
||||
assert.Equal(t, 600, cfg.Probod.TrackerMappingWorker.StaleAfter)
|
||||
assert.Equal(t, 45, cfg.Probod.TrackerMappingWorker.AgentTimeout)
|
||||
assert.Equal(t, 4, cfg.Probod.TrackerMappingWorker.AgentMaxTurns)
|
||||
assert.Equal(t, 10, cfg.Probod.CommonPatternEnrichmentWorker.Interval)
|
||||
@@ -327,6 +328,7 @@ func TestBuilder_Build_CustomValues(t *testing.T) {
|
||||
// Tracker worker tuning override
|
||||
env["TRACKER_MAPPING_INTERVAL"] = "20"
|
||||
env["TRACKER_MAPPING_MAX_CONCURRENCY"] = "5"
|
||||
env["TRACKER_MAPPING_STALE_AFTER"] = "1200"
|
||||
env["TRACKER_MAPPING_AGENT_TIMEOUT"] = "30"
|
||||
env["TRACKER_MAPPING_AGENT_MAX_TURNS"] = "6"
|
||||
env["COMMON_PATTERN_ENRICHMENT_INTERVAL"] = "15"
|
||||
@@ -428,6 +430,7 @@ func TestBuilder_Build_CustomValues(t *testing.T) {
|
||||
// Tracker worker tuning — overrides
|
||||
assert.Equal(t, 20, cfg.Probod.TrackerMappingWorker.Interval)
|
||||
assert.Equal(t, 5, cfg.Probod.TrackerMappingWorker.MaxConcurrency)
|
||||
assert.Equal(t, 1200, cfg.Probod.TrackerMappingWorker.StaleAfter)
|
||||
assert.Equal(t, 30, cfg.Probod.TrackerMappingWorker.AgentTimeout)
|
||||
assert.Equal(t, 6, cfg.Probod.TrackerMappingWorker.AgentMaxTurns)
|
||||
assert.Equal(t, 15, cfg.Probod.CommonPatternEnrichmentWorker.Interval)
|
||||
|
||||
Reference in New Issue
Block a user