From bb23a73abd3bbbbf7897e91162c5db99b4be51ac Mon Sep 17 00:00:00 2001 From: Darren Burton Date: Thu, 18 Jun 2026 14:46:45 -0500 Subject: [PATCH] Fix: Increase startup probe timeout for influxdb3-enterprise 3.2+ - Increase startup probe initialDelaySeconds from 10s to 30s - Increase startup probe periodSeconds from 5s to 10s - Increase startup probe timeoutSeconds from 5s to 10s - Increase startup probe failureThreshold from 12 to 20 - Total startup window increased from 70s to 230s This change addresses startup failures in InfluxDB 3.2+ where initialization time increased to ~100 seconds due to: - Python Processing Engine initialization - WAL recovery operations - V2 compaction consumer preloading The new configuration provides a 2.3x safety buffer for typical 100s startups, compared to the previous 4-5x buffer for 15s startups. Fixes pod CrashLoopBackOff with exit code 137 (SIGKILL) on 3.2 deployments. Bump chart version to 0.1.1 --- charts/influxdb3-enterprise/Chart.yaml | 2 +- charts/influxdb3-enterprise/values.yaml | 11 ++++++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/charts/influxdb3-enterprise/Chart.yaml b/charts/influxdb3-enterprise/Chart.yaml index c6c967a75..f7641def9 100644 --- a/charts/influxdb3-enterprise/Chart.yaml +++ b/charts/influxdb3-enterprise/Chart.yaml @@ -2,7 +2,7 @@ apiVersion: v2 name: influxdb3-enterprise description: A Helm chart for deploying InfluxDB 3 Enterprise on Kubernetes type: application -version: 0.1.0 +version: 0.1.1 appVersion: "3.6.0" keywords: - influxdb diff --git a/charts/influxdb3-enterprise/values.yaml b/charts/influxdb3-enterprise/values.yaml index 1b6d0aef9..aaea04192 100644 --- a/charts/influxdb3-enterprise/values.yaml +++ b/charts/influxdb3-enterprise/values.yaml @@ -614,12 +614,13 @@ probes: # Startup probe settings # Protects container during initialization. Once successful, never runs again. - # For ~15s startup: 10s initial + (12 × 5s) = 70s total (4-5x safety buffer) + # For ~100s startup in 3.2: 30s initial + (20 × 10s) = 230s total (~2.3x safety buffer) + # Accounts for Python Processing Engine initialization, WAL recovery, and compaction preloading startup: - initialDelaySeconds: 10 # Wait ~50% of expected startup time - periodSeconds: 5 # Check every 5 seconds - timeoutSeconds: 5 - failureThreshold: 12 # 10s + (12 × 5s) = 70s total + initialDelaySeconds: 30 # Wait ~30% of expected startup time + periodSeconds: 10 # Check every 10 seconds (less aggressive) + timeoutSeconds: 10 # Increased timeout for slower environments + failureThreshold: 20 # 30s + (20 × 10s) = 230s total # Liveness probe settings # Only starts checking AFTER startup probe succeeds