kubernetes/infrastructure/rook-ceph-cluster/cephcluster.yaml

@@ -24,6 +24,27 @@ spec:
   # gives headroom for parallel restores during cluster rebuild too
   # (paperless + audiobookshelf + immich + ... all clone at once).
   cephConfig:
+    mon:
+      # Ceph's 30% default assumes the mon has a filesystem to itself, where
+      # 30% free is a meaningful reserve. Here the mons live on
+      # dataDirHostPath /var/lib/rook — the node's /var, shared with ~29 GB
+      # of containerd image and snapshot storage — and the mon DB itself is
+      # ~106 MB. So the default measures container churn, not Ceph: k8s-2
+      # trips MON_DISK_LOW whenever the image cache fills, and image GC does
+      # not clear it (most of /var/lib/containerd is overlayfs snapshots held
+      # by running containers, which GC cannot reclaim — see #434).
+      # 20% of a 60 GB /var still leaves ~12 GB against a 106 MB database.
+      # mon_data_avail_crit stays at the 5% default, and CephMonDiskLow in
+      # monitoring-rules watches /var directly for the real risk, which is the
+      # node filling rather than the mon growing.
+      #
+      # BARE-METAL MIGRATION: revisit this. Give the mons their own volume and
+      # the default 30% becomes meaningful again, at which point this override
+      # should be dropped rather than carried over. It cannot be done on the
+      # current cluster — every StorageClass is Ceph-backed, so a mon PVC
+      # would be circular, and Rook only applies mon.volumeClaimTemplate to
+      # newly created mons, never migrating existing ones.
+      mon_data_avail_warn: "20"
     mgr:
       mgr/volumes/max_concurrent_clones: "16"
     # QLC tune for the Crucial P2 NVMe per host. Baseline 2026-05-05: