increase grafana healthcheck start_period and reduce error logs #55
@@ -9,7 +9,7 @@ export LOKI_YML_VERSION=v3
|
||||
export PROMETHEUS_YML_VERSION=v2
|
||||
export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
|
||||
export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
|
||||
export GF_ALERTS_NODE_VERSION=v4
|
||||
export GF_ALERTS_NODE_VERSION=v5
|
||||
export CONFIG_ALLOY_VERSION=v3
|
||||
|
||||
# migrates secrets from old names to new names by reading values from the
|
||||
|
||||
@@ -71,8 +71,7 @@ groups:
|
||||
description: ""
|
||||
runbook_url: ""
|
||||
summary: Less than {{ env "ALERT_NODE_DISK_SPACE_LEFT" }}% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
|
||||
labels:
|
||||
"": ""
|
||||
labels: {}
|
||||
isPaused: false
|
||||
{{ end }}
|
||||
{{ if (env "ALERT_NODE_MEMORY_USAGE") }}
|
||||
|
||||
+1
-1
@@ -48,7 +48,7 @@ services:
|
||||
interval: 5s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 10s
|
||||
start_period: 300s
|
||||
|
|
||||
|
||||
configs:
|
||||
gf_custom_ini:
|
||||
|
||||
Reference in New Issue
Block a user
Do we really need 300s?
a new deployment took 5 retries, with 10s timeout, 3 retries, and 5s intervals, I felt like 5 minutes are a fair enough grace for a new container
reminder that the healthceck passes early if the container was ready and doesn't wait the full 300s, it's more like a timeout for the first healthceck to pass