From 795cef5a85e9621885b764b86804039d849cf911 Mon Sep 17 00:00:00 2001
From: rock <locartrock@gmail.com>
Date: Tue, 15 Sep 2026 08:16:01 +0900
Subject: [PATCH] feat(prometheus): scale up storage to 100Gi and move to
 worker-1

- Increase PVC from 20Gi to 100Gi (talos-cp-1 disk full)
- Move from az-a (talos-cp-1) to worker-1 (648GB available)
- Increase retention from 15d to 30d (95GB limit)
- Fixes Prometheus pod restarts due to disk pressure
---
 k8s/infra/monitoring/prometheus-values.yaml | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/k8s/infra/monitoring/prometheus-values.yaml b/k8s/infra/monitoring/prometheus-values.yaml
index a7360e6..0796c63 100644
--- a/k8s/infra/monitoring/prometheus-values.yaml
+++ b/k8s/infra/monitoring/prometheus-values.yaml
@@ -54,8 +54,8 @@ alertmanager:
 # ── Prometheus ────────────────────────────────────────────────────────────────
 prometheus:
   prometheusSpec:
-    retention: 15d
-    retentionSize: "18GB"
+    retention: 30d
+    retentionSize: "95GB"
 
     # scrapeTimeout MUST be <= scrapeInterval or the operator refuses to generate
     # the Prometheus config ("scrapeTimeout greater than scrapeInterval") and no
@@ -64,10 +64,9 @@ prometheus:
     scrapeTimeout: 60s
     evaluationInterval: 30s
 
-    # Pin to az-a (talos-cp-1) — sole Longhorn node; else the RWO PVC can't
-    # attach on cp-2/cp-3 (CSINode lacks driver.longhorn.io).
+    # Pin to worker-1 for more storage capacity
     nodeSelector:
-      topology.kubernetes.io/zone: az-a
+      kubernetes.io/hostname: worker-1
 
     # Persistent storage — metrics survive node reboots and pod restarts.
     # Uses the default `longhorn` StorageClass; nodeSelector above already pins
@@ -79,7 +78,7 @@ prometheus:
           accessModes: ["ReadWriteOnce"]
           resources:
             requests:
-              storage: 20Gi
+              storage: 100Gi
 
     resources:
       requests: