From c43e63ddb3f6e24996f63e07873bac423f22a612 Mon Sep 17 00:00:00 2001
From: Joshua Long <44989821+jmclong@users.noreply.github.com>
Date: Mon, 26 Oct 2026 16:11:29 +0000
Subject: [PATCH] fix(helm): keep NVMe filesystems compatible with Ubuntu 22.04

Disable newer ext4 features for freshly formatted NVMe devices and RAID arrays while preserving existing filesystem labels and data.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 4e7adc4d-b2ae-4e92-9e76-2d857187198d
---
 helm/dacs-prereq/README.md             | 12 ++++++++++++
 helm/dacs-prereq/scripts/setup-raid.sh |  6 ++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/helm/dacs-prereq/README.md b/helm/dacs-prereq/README.md
index 6e26d00a..d3d19035 100644
--- a/helm/dacs-prereq/README.md
+++ b/helm/dacs-prereq/README.md
@@ -81,6 +81,11 @@ operations while retaining the image's tools. The script explicitly targets
 the host mount namespace and writes host configuration through `/proc/1/root`.
 Host `update-initramfs`, when available, runs in the host mount namespace.
 
+Both single-disk and RAID0 formatting explicitly disable `orphan_file` and
+`metadata_csum_seed`. This keeps the image-created ext4 filesystems compatible
+with Ubuntu 22.04's e2fsck 1.46.5. The host `fstab` entry uses fsck pass `2`, so
+the host can check the cache filesystem at boot.
+
 ### Reboot Behavior
 
 **Managed OS (persistent root filesystem):**
@@ -101,6 +106,13 @@ When the NVMe disks and their metadata are retained, the next setup run:
 Recovery depends on retention of the local disks and a successful setup run;
 this chart does not guarantee local-disk retention across node lifecycle events.
 
+### Upgrade Compatibility
+
+Existing cache filesystems are reused without changing their features.
+Upgrading the chart does not repair filesystems created with `orphan_file`
+enabled. On Ubuntu 22.04, those filesystems need separate remediation before
+the next node reboot to avoid a boot-time fsck failure.
+
 ### Filesystem Label
 
 The script labels all ext4 filesystems it creates with `dacs`.  This
diff --git a/helm/dacs-prereq/scripts/setup-raid.sh b/helm/dacs-prereq/scripts/setup-raid.sh
index d4dac85c..1e630ba6 100644
--- a/helm/dacs-prereq/scripts/setup-raid.sh
+++ b/helm/dacs-prereq/scripts/setup-raid.sh
@@ -20,6 +20,8 @@ set -euo pipefail
 
 readonly RAID_NAME="dacs"
 readonly FS_LABEL="dacs"
+# Keep image-created filesystems compatible with Ubuntu 22.04's e2fsck.
+readonly EXT4_FEATURES="^orphan_file,^metadata_csum_seed"
 readonly HOST_ROOT="/proc/1/root"
 MOUNT_POINT="${MOUNT_POINT:-/var/lib/ssd/cacheserver}"
 readonly NODE_HOSTNAME="${NODE_NAME:-$(uname -n 2>/dev/null || echo '<unknown>')}"
@@ -126,7 +128,7 @@ log "Found ${#UNUSED_DEVICES[@]} unused NVMe device(s): ${UNUSED_DEVICES[*]}"
 if [[ ${#UNUSED_DEVICES[@]} -eq 1 ]]; then
   DEVICE="${UNUSED_DEVICES[0]}"
   log "Formatting ${DEVICE} as ext4 (label '${FS_LABEL}')"
-  if ! mkfs.ext4 -F -L "${FS_LABEL}" "${DEVICE}"; then
+  if ! mkfs.ext4 -F -O "${EXT4_FEATURES}" -L "${FS_LABEL}" "${DEVICE}"; then
     log "ERROR: mkfs failed on ${DEVICE}."
     dump_diag
     exit 1
@@ -160,7 +162,7 @@ log "Waiting for RAID device..."
 sleep 5
 
 log "Formatting ${RAID_DEVICE} as ext4 (label '${FS_LABEL}')"
-if ! mkfs.ext4 -F -L "${FS_LABEL}" "${RAID_DEVICE}"; then
+if ! mkfs.ext4 -F -O "${EXT4_FEATURES}" -L "${FS_LABEL}" "${RAID_DEVICE}"; then
   log "ERROR: mkfs failed."
   dump_diag
   exit 1