2026-07-17 18:29:45 +00:00
1 changed files with 14 additions and 6 deletions
@@ -81,12 +81,17 @@ spec:
          # (the pre-2026-07 config) ingested every node/guest series 3x —
          # identical `id`, differing `instance` — a real TSDB cardinality
          # cost that dashboards had to paper over with max by (id).
-          # Trade-off: cluster metrics pause if .201 is down; node-local
-          # metrics below keep flowing from the surviving nodes.
+          #
+          # Target the pve Service (apps ns) rather than a hardcoded node IP:
+          # its EndpointSlice load-balances the PVE API across all three nodes,
+          # so cluster metrics keep flowing as long as ANY node is up, instead
+          # of pausing whenever .201 (jupiter) specifically is down. The
+          # exporter reaches the API on 8006 (verify_ssl:false, so the LB'd
+          # cert hostname mismatch is a non-issue).
          - job_name: pve
            static_configs:
              - targets:
-                  - "10.2.40.201"
+                  - "pve.apps.svc.cluster.local"
            metrics_path: /pve
            params:
              cluster: ["1"]
@@ -103,12 +108,15 @@ spec:
          # node-local and genuinely distinct per target, so every node is
          # scraped — this is the split recommended by prometheus-pve-exporter
          # upstream to avoid the cluster-collector duplication above.
+          # Targets are the node FQDNs, not raw IPs: the instance label then
+          # reads jupiter/neptune/saturn.renner.uno, and a renumbered node is
+          # picked up from DNS without editing this file.
          - job_name: pve-node
            static_configs:
              - targets:
-                  - "10.2.40.201"
-                  - "10.2.40.202"
-                  - "10.2.40.203"
+                  - "jupiter.renner.uno"
+                  - "neptune.renner.uno"
+                  - "saturn.renner.uno"
            metrics_path: /pve
            params:
              cluster: ["0"]