fix(ha/cluster-init): detect StandAlone DRBD state in sync wait loop
Check NixOS configurations / eval-hosts (push) Successful in 10m21s

If the DRBD peer connection drops during the initial sync wait (cs:StandAlone),
the loop would spin forever printing "waiting for sync progress" with no
indication of what's wrong. Now parses cs: from /proc/drbd each tick and
dies with a clear error if StandAlone is detected. Also shows the cs: field
in the non-syncing message so the actual connection state is always visible.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-07-29 01:29:04 +10:00
co-authored by Claude Sonnet 4.6
parent 367158548e
commit c7268ade8e
+8 -2
View File
@@ -250,17 +250,23 @@ while true; do
log "DRBD initial sync complete (dstate: $_dstate)"
break
fi
# Parse connection state from /proc/drbd (cs:SyncSource, cs:Connected, cs:StandAlone …)
_cs=$(grep -oE 'cs:[A-Za-z]+' /proc/drbd 2>/dev/null | head -1 | sed 's/cs://' || echo "unknown")
# /proc/drbd uses variable whitespace: "sync'ed: 5.2%" (two spaces).
_pct=$(grep -oE "sync'ed:[[:space:]]+[0-9.]+" /proc/drbd 2>/dev/null | grep -oE "[0-9.]+" | head -1 || echo "")
_eta=$(grep -oE "finish:[[:space:]]+[0-9:]+" /proc/drbd 2>/dev/null | grep -oE "[0-9:]+$" | head -1 || echo "")
_spd=$(grep -oE "speed:[[:space:]]+[0-9,]+" /proc/drbd 2>/dev/null | grep -oE "[0-9,]+$" | head -1 || echo "")
_sync_iter=$(( _sync_iter + 1 ))
_sc="${_sync_chars[$_sync_iter % 4]}"
if [[ -n "$_pct" ]]; then
if [[ "$_cs" == "StandAlone" ]]; then
printf "\r%-80s\r" ""
die "DRBD is StandAlone — peer connection lost (dstate: $_dstate). " \
"Check corosync/network and re-run cluster-init."
elif [[ -n "$_pct" ]]; then
printf "\r [%s] syncing: %s%% done — ETA %s @ %s K/s " \
"$_sc" "$_pct" "${_eta:-??:??:??}" "${_spd:-?}"
else
printf "\r [%s] dstate: %s — waiting for sync progress " "$_sc" "$_dstate"
printf "\r [%s] cs:%s dstate:%s — waiting for sync to start " "$_sc" "$_cs" "$_dstate"
fi
sleep 3
done