From 9f281c48517d89495109f36c29635e039e20bd07 Mon Sep 17 00:00:00 2001 From: James Peru Mmbono Date: Tue, 7 Jul 2026 14:04:50 +0300 Subject: [PATCH] NAS backup: resume paused VM on backup failure and fix missing exit (#12822) * NAS backup: resume paused VM on backup failure and fix missing exit When a NAS backup job fails (e.g. due to backup storage being full or I/O errors), the VM may remain indefinitely paused because: 1. The cleanup() function never checks or resumes the VM's paused state that was set by virsh backup-begin during the push backup operation. 2. The 'Failed' case in the backup job monitoring loop calls cleanup() but lacks an 'exit' statement, causing an infinite loop where the script repeatedly detects the failed job and calls cleanup(). 3. Similarly, backup_stopped_vm() calls cleanup() on qemu-img convert failure but does not exit, allowing the loop to continue with subsequent disks despite the failure. This fix: - Adds VM state detection and resume to cleanup(), ensuring the VM is always resumed if found in a paused state during error handling - Adds missing 'exit 1' after cleanup() in the Failed backup job case to prevent the infinite monitoring loop - Adds missing 'exit 1' after cleanup() in backup_stopped_vm() on qemu-img convert failure Co-Authored-By: Claude Opus 4.6 * ci: retrigger workflow (flaky/stale shards) * nasbackup.sh: keep cleanup() best-effort if domstate fails With set -eo pipefail, a non-zero virsh domstate (libvirt unavailable or the domain gone) in the vm_state assignment would abort cleanup() before the rm/umount/rmdir. Append '|| true' so cleanup always runs to completion. Addresses the review suggestion (Copilot, endorsed by @abh1sar and @weizhouapache). Signed-off-by: James Peru --------- Signed-off-by: James Peru Co-authored-by: Claude Opus 4.6 Co-authored-by: jmsperu --- scripts/vm/hypervisor/kvm/nasbackup.sh | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/scripts/vm/hypervisor/kvm/nasbackup.sh b/scripts/vm/hypervisor/kvm/nasbackup.sh index 441312f35e8..e7ad3657cf0 100755 --- a/scripts/vm/hypervisor/kvm/nasbackup.sh +++ b/scripts/vm/hypervisor/kvm/nasbackup.sh @@ -167,7 +167,8 @@ backup_running_vm() { break ;; Failed) echo "Virsh backup job failed" - cleanup ;; + cleanup + exit 1 ;; esac sleep 5 done @@ -221,6 +222,7 @@ backup_stopped_vm() { if ! qemu-img convert -O qcow2 "$disk" "$output" > "$logFile" 2> >(cat >&2); then echo "qemu-img convert failed for $disk $output" cleanup + exit 1 fi name="datadisk" done @@ -265,6 +267,19 @@ mount_operation() { cleanup() { local status=0 + # Resume the VM if it was paused during backup to prevent it from + # remaining indefinitely paused when the backup job fails (e.g. due + # to storage full or I/O errors on the backup target) + local vm_state + vm_state=$(virsh -c qemu:///system domstate "$VM" 2>/dev/null || true) + if [[ "$vm_state" == "paused" ]]; then + log -ne "Resuming paused VM $VM during backup cleanup" + if ! virsh -c qemu:///system resume "$VM" > /dev/null 2>&1; then + echo "Failed to resume VM $VM" + status=1 + fi + fi + rm -rf "$dest" || { echo "Failed to delete $dest"; status=1; } umount "$mount_point" || { echo "Failed to unmount $mount_point"; status=1; } rmdir "$mount_point" || { echo "Failed to remove mount point $mount_point"; status=1; }