From 5f50c1125d1bb8417a74363e9baaa97d8ae53d7b Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Sat, 25 May 2024 22:04:08 -0700 Subject: [PATCH] docs(alerting.md): add region-based outage alerting to docs --- docs/my-website/docs/proxy/alerting.md | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/my-website/docs/proxy/alerting.md b/docs/my-website/docs/proxy/alerting.md index 533235ac9ce..3c70b6a33ac 100644 --- a/docs/my-website/docs/proxy/alerting.md +++ b/docs/my-website/docs/proxy/alerting.md @@ -199,4 +199,28 @@ curl -X GET --location 'http://0.0.0.0:4000/health/services?service=webhook' \ * "team": The event is related to a team. * "proxy": The event is related to a proxy. -- `event_message` *str*: A human-readable description of the event. \ No newline at end of file +- `event_message` *str*: A human-readable description of the event. + +## Advanced - Region-outage alerting (✨ Enterprise feature) + +Setup alerts if a provider region is having an outage. + +```yaml +general_settings: + alerting: ["slack"] + alert_types: ["region_outage_alerts"] +``` + +By default this will trigger if multiple models in a region fail 5+ requests in 1 minute. '400' status code errors are not counted (i.e. BadRequestErrors). + +Control thresholds with: + +```yaml +general_settings: + alerting: ["slack"] + alert_types: ["region_outage_alerts"] + alerting_args: + region_outage_alert_ttl: 60 # time-window in seconds + minor_outage_alert_threshold: 5 # number of errors to trigger a minor alert + major_outage_alert_threshold: 10 # number of errors to trigger a major alert +``` \ No newline at end of file