From a07259cd255769c61a9ed91ac85fdc07d9061f78 Mon Sep 17 00:00:00 2001 From: Sirius Devops Date: Mon, 25 May 2026 05:49:05 +0000 Subject: [PATCH 1/2] fix(trading-platform): increase startupProbe failureThreshold to 30 for data-service and dashboard Gives ~5min grace period for heavy lifespan init (Redis, DB, executors, model loading). Addresses 'up but not ready' state on data-service and dashboard (0/1 Ready). Live manifests in apps/base/customer1/... updated (source of truth). Helm templates can be synced later. See gke-hermes-infrastructure skill (trading-startup-probe-fix-2026-05-26.md). --- .../base/customer1/trading-platform/dashboard/deployment.yaml | 4 ++-- .../customer1/trading-platform/data-service/deployment.yaml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/apps/base/customer1/trading-platform/dashboard/deployment.yaml b/apps/base/customer1/trading-platform/dashboard/deployment.yaml index c2f3c1e..4a5b8b3 100644 --- a/apps/base/customer1/trading-platform/dashboard/deployment.yaml +++ b/apps/base/customer1/trading-platform/dashboard/deployment.yaml @@ -63,8 +63,8 @@ spec: path: /api/health port: 8000 initialDelaySeconds: 15 - periodSeconds: 5 - failureThreshold: 6 + periodSeconds: 10 + failureThreshold: 30 livenessProbe: httpGet: path: /api/health diff --git a/apps/base/customer1/trading-platform/data-service/deployment.yaml b/apps/base/customer1/trading-platform/data-service/deployment.yaml index be19da6..fa90442 100644 --- a/apps/base/customer1/trading-platform/data-service/deployment.yaml +++ b/apps/base/customer1/trading-platform/data-service/deployment.yaml @@ -65,8 +65,8 @@ spec: path: /health port: 8001 initialDelaySeconds: 15 - periodSeconds: 5 - failureThreshold: 6 + periodSeconds: 10 + failureThreshold: 30 livenessProbe: httpGet: path: /health From d002a7896b64bf2015e031b1534bad58dedb3f4f Mon Sep 17 00:00:00 2001 From: Sirius Devops Date: Mon, 25 May 2026 05:55:21 +0000 Subject: [PATCH 2/2] fix(dashboard): align port to 3000 and probes to root path - containerPort: 3000 (matches Next.js default + Dockerfile ENV PORT=3000) - All probes (startup/liveness/readiness): path (Next.js serves root when ready) - Service targetPort: 3000 Fixes 'not ready' and 'can't reach it' (previous mismatch with 8000 + /api/health which didn't exist). Live manifests updated (source of truth). --- .../trading-platform/dashboard/deployment.yaml | 18 +++++++++--------- .../trading-platform/dashboard/service.yaml | 2 +- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/apps/base/customer1/trading-platform/dashboard/deployment.yaml b/apps/base/customer1/trading-platform/dashboard/deployment.yaml index 4a5b8b3..26bb7b6 100644 --- a/apps/base/customer1/trading-platform/dashboard/deployment.yaml +++ b/apps/base/customer1/trading-platform/dashboard/deployment.yaml @@ -29,7 +29,7 @@ spec: image: ghcr.io/sirius0xdev/trading-dashboard:latest imagePullPolicy: Always ports: - - containerPort: 8000 + - containerPort: 3000 name: http resources: requests: @@ -60,20 +60,20 @@ spec: key: password startupProbe: httpGet: - path: /api/health - port: 8000 - initialDelaySeconds: 15 + path: / + port: 3000 + initialDelaySeconds: 5 periodSeconds: 10 failureThreshold: 30 livenessProbe: httpGet: - path: /api/health - port: 8000 - initialDelaySeconds: 30 + path: / + port: 3000 + initialDelaySeconds: 15 periodSeconds: 30 readinessProbe: httpGet: - path: /api/health - port: 8000 + path: / + port: 3000 initialDelaySeconds: 5 periodSeconds: 10 diff --git a/apps/base/customer1/trading-platform/dashboard/service.yaml b/apps/base/customer1/trading-platform/dashboard/service.yaml index 73bca2f..4600af4 100644 --- a/apps/base/customer1/trading-platform/dashboard/service.yaml +++ b/apps/base/customer1/trading-platform/dashboard/service.yaml @@ -13,6 +13,6 @@ spec: app: trading-dashboard ports: - port: 80 - targetPort: 8000 + targetPort: 3000 name: http type: ClusterIP