From 7363e20b65e2dcd178d8dcbece796f13be5822fb Mon Sep 17 00:00:00 2001
From: Joao Marcal <jmarcal@redhat.com>
Date: Tue, 14 Mar 2023 16:39:30 +0100
Subject: [PATCH] Adds startupProbe to prometheus-adapter (#2029)
Issue: https://issues.redhat.com/browse/OCPBUGS-7694
Problem: in clusters with a large nb of CRDs deployed prom-adapter takes too long to discover all of them which makes it fail the livenessProbe
Solution: introduce a startupProbe that gives 3 minutes for prom-adapter to initialize
Signed-off-by: JoaoBraveCoding <jmarcal@redhat.com>
---
.../components/prometheus-adapter.libsonnet | 11 +++++++++--
manifests/prometheusAdapter-deployment.yaml | 9 +++++++--
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/jsonnet/kube-prometheus/components/prometheus-adapter.libsonnet b/jsonnet/kube-prometheus/components/prometheus-adapter.libsonnet
index f83601cf..bf620fc6 100644
--- a/jsonnet/kube-prometheus/components/prometheus-adapter.libsonnet
+++ b/jsonnet/kube-prometheus/components/prometheus-adapter.libsonnet
@@ -236,13 +236,21 @@ function(params) {
'--tls-cipher-suites=' + std.join(',', pa._config.tlsCipherSuites),
],
resources: pa._config.resources,
+ startupProbe: {
+ httpGet: {
+ path: '/livez',
+ port: 'https',
+ scheme: 'HTTPS',
+ },
+ periodSeconds: 10,
+ failureThreshold: 18,
+ },
readinessProbe: {
httpGet: {
path: '/readyz',
port: 'https',
scheme: 'HTTPS',
},
- initialDelaySeconds: 30,
periodSeconds: 5,
failureThreshold: 5,
},
@@ -252,7 +260,6 @@ function(params) {
port: 'https',
scheme: 'HTTPS',
},
- initialDelaySeconds: 30,
periodSeconds: 5,
failureThreshold: 5,
},
diff --git a/manifests/prometheusAdapter-deployment.yaml b/manifests/prometheusAdapter-deployment.yaml
index fcfdf356..ac196193 100644
--- a/manifests/prometheusAdapter-deployment.yaml
+++ b/manifests/prometheusAdapter-deployment.yaml
@@ -44,7 +44,6 @@ spec:
path: /livez
port: https
scheme: HTTPS
- initialDelaySeconds: 30
periodSeconds: 5
name: prometheus-adapter
ports:
@@ -56,7 +55,6 @@ spec:
path: /readyz
port: https
scheme: HTTPS
- initialDelaySeconds: 30
periodSeconds: 5
resources:
limits:
@@ -71,6 +69,13 @@ spec:
drop:
- ALL
readOnlyRootFilesystem: true
+ startupProbe:
+ failureThreshold: 18
+ httpGet:
+ path: /livez
+ port: https
+ scheme: HTTPS
+ periodSeconds: 10
volumeMounts:
- mountPath: /tmp
name: tmpfs
--
GitLab