fix(ops): recover stale history error health

This commit is contained in:
lingniu
2026-07-16 06:48:47 +08:00
parent e99087f329
commit ec3071d59b
5 changed files with 72 additions and 6 deletions

View File

@@ -121,6 +121,7 @@ func main() {
flag.Float64Var(&thresholds.HistoryWriteRecentE2EP99MS, "history-write-recent-e2e-p99-ms", thresholds.HistoryWriteRecentE2EP99MS, "degrade when recent gateway received_at to history TDengine write p99 exceeds this many milliseconds; <=0 disables")
flag.Float64Var(&thresholds.HistoryWorkersMin, "history-workers-min", thresholds.HistoryWorkersMin, "degrade when history-writer runtime worker count is below this value; <=0 disables")
flag.Float64Var(&thresholds.HistoryLocationErrorMax, "history-location-error-max", thresholds.HistoryLocationErrorMax, "degrade when history-writer location derived write errors exceed this value; <0 disables")
flag.Float64Var(&thresholds.HistoryLocationErrorRecentSec, "history-location-error-recent-seconds", thresholds.HistoryLocationErrorRecentSec, "only degrade on history location write errors observed within this many seconds; <=0 evaluates the lifetime counter")
flag.Float64Var(&thresholds.HistoryLocationAccountingMaxRatio, "history-location-accounting-max-mismatch-ratio", thresholds.HistoryLocationAccountingMaxRatio, "degrade when location derived status counters do not account for successful history raw writes by more than this ratio; <=0 disables")
flag.Float64Var(&thresholds.HistoryFallbackErrorMax, "history-fallback-error-max", thresholds.HistoryFallbackErrorMax, "degrade when history-writer batch fallback single writes still fail; <0 disables")
flag.Float64Var(&thresholds.HistoryRetryMax, "history-retry-max", thresholds.HistoryRetryMax, "degrade when history-writer transient write retries exceed this value; <0 disables")