Adding pinned uuid for rootfs

docs/TODO.md

@@ -113,6 +113,23 @@ boot LAN.
   writable → multi-user.
 - This validation **gates** item #1 (network-manager port) and item #3
   (errata → design v3).
+- **Bench findings (boot debug, 2026-06-14):**
+  - Initramfs has no resolver (dracut writes `resolv.conf` only via its own
+    DHCP path, not a manual `dhclient`), so the NVMe discovery address must be
+    an **IP**, not a DNS name — build with `-var nvmet_traddr=192.168.50.10`.
+    Old UKIs carrying `nvme.fleet.lab` can't connect early in boot.
+  - NVMe controller indices are **not stable**: a transient discovery
+    controller can take `nvme0`, pushing the I/O controller to `nvme1`. The
+    hardcoded `/dev/nvme0n1` in the cmdline was a latent brick. **Fixed:**
+    namespace UUID pinned on the target (`spdk-setup.sh` `add_ns -u
+    f1ee7000-0000-4000-8000-000000000001`) and the cmdline now references
+    `/dev/disk/by-id/nvme-uuid.<uuid>` (`extract-artifacts.sh`). The two
+    constants MUST stay in sync; make them version-specific for #6.
+  - `nvme_tcp`/`nvme_fabrics` must be loaded before `/dev/nvme-fabrics` exists
+    (dracut's `nvmf` module does this in a normal boot; at `rd.break` modprobe
+    manually).
+  - SPDK: add the listener to the discovery subsystem explicitly
+    (`nqn.2014-08.org.nvmexpress.discovery`) to silence the deprecation warning.
 
 ## [ ] 6. Rolling fleet updates (multi-version serve → cohort reboots)
 

scripts/extract-artifacts.sh

@@ -23,6 +23,14 @@ DISABLE_DOT1X=${3:-false}
 # environments. Defaults to the literal placeholder so build-oci.sh's warning
 # fires if it was never set.
 NVMET_TRADDR=${NVMET_TRADDR:-NVMET_TRADDR}
+# Stable root-namespace UUID. The root device is referenced by-id
+# (/dev/disk/by-id/nvme-uuid.$ROOT_NS_UUID) rather than /dev/nvmeNn1 because
+# NVMe controller indices are NOT stable: a transient discovery controller can
+# take nvme0, pushing the I/O controller to nvme1, so a hardcoded node is a
+# latent brick in an immutable signed cmdline. MUST match ROOT_NS_UUID in
+# serving/spdk-setup.sh (which assigns it on the target via add_ns -u).
+ROOT_NS_UUID=${ROOT_NS_UUID:-f1ee7000-0000-4000-8000-000000000001}
+ROOT_DEV="/dev/disk/by-id/nvme-uuid.${ROOT_NS_UUID}"
 
 for bin in virt-copy-out virt-tar-out virt-ls mkfs.erofs veritysetup jq; do
     command -v "$bin" >/dev/null || { echo "ERROR: $bin not found on build host" >&2; exit 1; }
@@ -96,8 +104,8 @@ printf '%s' \
   "rd.nvmf.discover=tcp,${NVMET_TRADDR},4420 " \
   "root=/dev/mapper/root rootfstype=erofs rootflags=ro " \
   "systemd.verity=yes roothash=${ROOT_HASH} " \
-  "systemd.verity_root_data=/dev/nvme0n1 " \
-  "systemd.verity_root_hash=/dev/nvme0n1 " \
+  "systemd.verity_root_data=${ROOT_DEV} " \
+  "systemd.verity_root_hash=${ROOT_DEV} " \
   "systemd.verity_root_options=hash-offset=${HASH_OFFSET}" \
   > "$OUT/cmdline.txt"
 

serving/spdk-setup.sh

@@ -10,6 +10,15 @@ set -euo pipefail
 
 ROOTFS="/artifacts/rootfs.erofs"
 SUBNQN="${SUBNQN:-nqn.2026-06.org.example.fleet:rootfs}"
+# Fixed, fleet-generic namespace UUID. The host references the root device as
+# /dev/disk/by-id/nvme-uuid.$ROOT_NS_UUID on the kernel cmdline, which is stable
+# regardless of NVMe controller enumeration order (the I/O controller can land
+# on nvme0/nvme1/... depending on whether a transient discovery controller took
+# a slot first — so a hardcoded /dev/nvme0n1 is unsafe). MUST match
+# ROOT_NS_UUID in scripts/extract-artifacts.sh, which bakes it into the UKI
+# cmdline. NOTE: for multi-version serving (TODO #6) make this version-specific
+# alongside the per-version NQN, so a host can't connect the wrong rootfs.
+ROOT_NS_UUID="${ROOT_NS_UUID:-f1ee7000-0000-4000-8000-000000000001}"
 TADDR="${TARGET_ADDR:-0.0.0.0}"
 TPORT="${TARGET_PORT:-4420}"
 CPUMASK="${SPDK_CPUMASK:-0x1}"
@@ -58,14 +67,27 @@ echo "==> exposing $ROOTFS as bdev 'rootfs' (4 KiB blocks)"
 echo "==> creating subsystem $SUBNQN (allow any host — lab/no-auth)"
 "$RPC" nvmf_create_subsystem "$SUBNQN" -a -s SPDKLAB0000000001 -d FleetRootfs
 
-echo "==> adding namespace 1"
+echo "==> adding namespace 1 (uuid $ROOT_NS_UUID)"
 # Read-only is enforced by the bdev_aio '-r' open above (this SPDK's add_ns has
 # no --read-only flag), plus the :ro image-volume mount and the client's erofs
 # ro + dm-verity.
-"$RPC" nvmf_subsystem_add_ns "$SUBNQN" rootfs
+# -u pins the namespace UUID so the host can reference it as
+# /dev/disk/by-id/nvme-uuid.$ROOT_NS_UUID (stable across controller indices).
+"$RPC" nvmf_subsystem_add_ns "$SUBNQN" rootfs -u "$ROOT_NS_UUID"
 
-echo "==> adding TCP listener ${TADDR}:${TPORT} (also serves discovery)"
+echo "==> adding TCP listener ${TADDR}:${TPORT} to $SUBNQN"
 "$RPC" nvmf_subsystem_add_listener "$SUBNQN" -t tcp -a "$TADDR" -s "$TPORT"
 
+# Also add the listener to the well-known discovery subsystem. Without this,
+# SPDK still answers discovery on this listener but logs a deprecation warning
+# ("listener was not added to the discovery subsystem") and the implicit
+# behaviour is slated for removal. Explicitly registering it is the supported
+# way and future-proofs `nvme discover` against an SPDK bump. Best-effort:
+# tolerate older SPDK builds where the discovery NQN can't take a listener.
+echo "==> adding TCP listener ${TADDR}:${TPORT} to the discovery subsystem"
+"$RPC" nvmf_subsystem_add_listener nqn.2014-08.org.nvmexpress.discovery \
+    -t tcp -a "$TADDR" -s "$TPORT" \
+    || echo "WARNING: could not add listener to discovery subsystem (older SPDK?) — discovery still works via the deprecated implicit path." >&2
+
 echo "==> SPDK serving $SUBNQN over tcp/${TPORT}; rd.nvmf.discover=tcp,${TADDR},${TPORT}"
 wait "$TGT_PID"