Index: alertserver/alerts.cfg |
diff --git a/alertserver/alerts.cfg b/alertserver/alerts.cfg |
index cd4dccee681111ba301618f4a3a4a3d0df2ce97a..fded1f4017d9fde8ca45e094c1b86d65512107f3 100644 |
--- a/alertserver/alerts.cfg |
+++ b/alertserver/alerts.cfg |
@@ -17,7 +17,7 @@ nag = "24h" |
[[rule]] |
name = "Gold Alert (GM)" |
message = "At least one untriaged GM has been found. Please visit https://gold.skia.org/ to triage." |
-query = "select value from /skiacorrectness.skia-gold-prod.status.untriaged.by_corpus.gm.value/ limit 1" |
+query = "select value from /^skiacorrectness.skia-gold-prod.status.untriaged.by_corpus.gm.value$/ limit 1" |
category = "Gold" |
condition = "x > 0" |
actions = ["Email(alerts@skia.org)"] |
@@ -26,8 +26,8 @@ nag = "24h" |
[[rule]] |
name = "Expired Ingores (Gold)" |
-message = "At least one expired ignore rule has been found. Please visit https://gold.skia.org/2/ignores to delete or extend." |
-query = "select value from /skiacorrectness.skia-gold-prod.num-expired-ignore-rules.value/ limit 1" |
+message = "At least one expired ignore rule has been found. Please visit https://gold.skia.org/ignores to delete or extend." |
+query = "select value from /^skiacorrectness.skia-gold-prod.num-expired-ignore-rules.value$/ limit 1" |
category = "Gold" |
condition = "x > 0" |
actions = ["Email(alerts@skia.org)"] |
@@ -67,13 +67,23 @@ nag = "1h" |
[[rule]] |
name = "Ingore Monitoring Failure (Gold)" |
message = "At least two rounds of monitoring for expired ignore rules have failed back to back." |
-query = "select mean(value) from /skiacorrectness.skia-gold-prod.expired-ignore-rules-monitoring.time-since-last-successful-update.value/ where time > now() - 10m" |
+query = "select mean(value) from /^skiacorrectness.skia-gold-prod.expired-ignore-rules-monitoring.time-since-last-successful-update.value$/ where time > now() - 10m" |
category = "infra" |
condition = "x >= 200" |
actions = ["Email(infra-alerts@skia.org)"] |
auto-dismiss = true |
nag = "1h" |
+[[rule]] |
+name = "Gold Hash Prober" |
+message = "The list of currently considered image digests is not accessible at https://gold.skia.org/_/hashes" |
+query = "select mean(value) from /^prober.skiagold_hashes.failure.value$/ where time > now() - 10m;" |
+category = "infra" |
+condition = "x >= 1" |
+actions = ["Email(infra-alerts@skia.org)"] |
+auto-dismiss = false |
+nag = "1h" |
+ |
# |
# SkFiddle |
# |