ctdb-scripts: Fetch recovery lock option from config file in 01.reclock

[metze/samba/wip.git] / ctdb / config / events.d / 01.reclock

diff --git a/ctdb/config/events.d/01.reclock b/ctdb/config/events.d/01.reclock
index ec50989743f57e41ed4d3c27b18106a7cac282a7..e14d8c22f488576b300f7f22ce91f17241687cc2 100755 (executable)
--- a/ctdb/config/events.d/01.reclock
+++ b/ctdb/config/events.d/01.reclock
@@ -2,44 +2,72 @@
 # script to check accessibility to the reclock file on a node
 
 [ -n "$CTDB_BASE" ] || \
-    export CTDB_BASE=$(cd -P $(dirname "$0") ; dirname "$PWD")
+    CTDB_BASE=$(d=$(dirname "$0") ; cd -P "$d" ; dirname "$PWD")
 
-. $CTDB_BASE/functions
-loadconfig
+. "${CTDB_BASE}/functions"
 
-case "$1" in 
-    init)
+load_script_options
+
+ctdb_setup_state_dir "service" "reclock"
+
+ctdb_get_reclock_option ()
+{
+       _reclock_opt_file="${CTDB_SCRIPT_VARDIR}/recovery_lock.cache"
+
+       if [ -f "$_reclock_opt_file" ] ; then
+               . "$_reclock_opt_file"
+               return
+       fi
+
+       ctdb_translate_option "cluster" \
+                             "recovery lock" \
+                             "CTDB_RECOVERY_LOCK" >"$_reclock_opt_file"
+
+       . "$_reclock_opt_file"
+}
+
+ctdb_get_reclock_option
+
+# If CTDB_RECOVERY_LOCK specifies a helper then exit because this
+# script can't do anything useful.
+case "$CTDB_RECOVERY_LOCK" in
+!*) exit 0 ;;
+esac
+
+case "$1" in
+init)
        ctdb_counter_init
+
+       if [ -n "$CTDB_RECOVERY_LOCK" ] ; then
+           d=$(dirname "$CTDB_RECOVERY_LOCK")
+           mkdir -vp "$d"
+       fi
        ;;
-    
-    monitor)
-       RECLOCKFILE=$(ctdb -Y getreclock)
 
+monitor)
        # Early exit if not using a reclock file
-       [ -n "$RECLOCKFILE" ] || exit 0
+       [ -n "$CTDB_RECOVERY_LOCK" ] || exit 0
 
        # Try to stat the reclock file as a background process so that
        # we don't block in case the cluster filesystem is unavailable
        (
-           if stat $RECLOCKFILE ; then
+           if stat "$CTDB_RECOVERY_LOCK" ; then
                # We could stat the file, reset the counter
                ctdb_counter_init
            fi
        ) >/dev/null 2>&1 &
 
        ctdb_counter_incr
-       if ! ctdb_check_counter "quiet" -ge 200 ; then
-           echo "Reclock file \"$RECLOCKFILE\" can not be accessed. Shutting down."
+       num_fails=$(ctdb_counter_get)
+       if [ "$num_fails" -ge 200 ] ; then
+           echo "Reclock file \"$CTDB_RECOVERY_LOCK\" can not be accessed. Shutting down."
            df
            sleep 1
-           ctdb shutdown
+           $CTDB shutdown
+           exit 1
+       elif [ "$num_fails" -ge 4 ] ; then
+               die "ERROR: ${num_fails} consecutive failures checking reclock"
        fi
-
-       ctdb_check_counter "error" -gt 3
-       ;;
-
-    *)
-       ctdb_standard_event_handler "$@"
        ;;
 esac