feat(qemu-ga): failure-propagating fsfreeze dispatcher; enabled on nh3-svos (hooks were never run)

2026-10-05 19:25:14 -07:00
parent 36289f701a
commit 9175fbd539
2 changed files with 67 additions and 1 deletions
@@ -0,0 +1,66 @@
+#!/bin/bash
+# fsfreeze-dispatch: qemu-ga fsfreeze hook dispatcher that PROPAGATES failure (eshpfi configs/qemu-ga/, 2026-10-05).
+#
+# Debian's stock /etc/qemu/fsfreeze-hook logs a child hook's nonzero status but always exits 0, so a hook that
+# refuses to quiesce still lets the snapshot proceed (found by svos-dev on nh3-svos). This one does not:
+#   freeze: run hooks in name order; on the first failure, thaw the FAILING hook and then every hook that had
+#           completed, in reverse order (best effort), log any unwind failure, and exit 1.
+#   thaw:   run every hook in reverse name order, exit 1 if any failed (never stop early).
+# Wired in by /etc/qemu/qemu-ga.conf `fsfreeze-hook=/usr/local/sbin/fsfreeze-dispatch`. The packaged
+# /etc/qemu/fsfreeze-hook (a dpkg conffile) is left untouched. Same hook dir and log file as the stock hook.
+set -u
+HOOKDIR=/etc/qemu/fsfreeze-hook.d
+LOGFILE=/var/log/qga-fsfreeze-hook.log
+action=${1:-}
+
+log() { printf '%s: %s\n' "$(date)" "$1" >>"$LOGFILE" 2>/dev/null || logger -t qemu-ga-freeze-hook "$1"; }
+
+ignored() {
+    case "$1" in
+        *~ | *.bak | *.orig | *.rpmnew | *.rpmorig | *.rpmsave | *.sample | *.dpkg-old | *.dpkg-new | *.dpkg-tmp | \
+        *.dpkg-dist | *.dpkg-bak | *.dpkg-backup | *.dpkg-remove) return 0 ;;
+    esac
+    return 1
+}
+
+hooks=()
+if [ -d "$HOOKDIR" ]; then
+    while IFS= read -r -d '' f; do
+        ignored "$f" && continue
+        [ -f "$f" ] && [ -x "$f" ] && hooks+=("$f")
+    done < <(find "$HOOKDIR" -mindepth 1 -maxdepth 1 -print0 | LC_ALL=C sort -z)
+fi
+
+run() { # $1 hook, $2 action
+    log "Executing $1 $2"
+    "$1" "$2" >>"$LOGFILE" 2>&1
+    local st=$?
+    [ "$st" -ne 0 ] && log "Error: $1 $2 finished with status=$st"
+    return "$st"
+}
+
+case "$action" in
+    freeze)
+        completed=()
+        for h in "${hooks[@]}"; do
+            if run "$h" freeze; then
+                completed+=("$h")
+            else
+                log "freeze FAILED at $h: unwinding (thaw $h, then ${#completed[@]} completed hook(s) in reverse)"
+                unwind_failed=0
+                run "$h" thaw || unwind_failed=1
+                for ((i = ${#completed[@]} - 1; i >= 0; i--)); do run "${completed[$i]}" thaw || unwind_failed=1; done
+                [ "$unwind_failed" -ne 0 ] && log "UNWIND FAILURE: at least one thaw during the freeze unwind failed"
+                exit 1
+            fi
+        done
+        exit 0 ;;
+    thaw)
+        rc=0
+        for ((i = ${#hooks[@]} - 1; i >= 0; i--)); do run "${hooks[$i]}" thaw || rc=1; done
+        [ "$rc" -ne 0 ] && log "thaw: at least one hook failed"
+        exit "$rc" ;;
+    *)
+        log "fsfreeze-dispatch: unknown action '$action'"
+        exit 1 ;;
+esac