unsigned long start;
int error, neg = 0;
- log_debug(ls, "recover %llx", rv->seq);
+ log_debug(ls, "recover %llx", (unsigned long long)rv->seq);
mutex_lock(&ls->ls_recoverd_active);
error = dlm_recover_members(ls, rv, &neg);
if (error) {
- log_error(ls, "recover_members failed %d", error);
+ log_debug(ls, "recover_members failed %d", error);
goto fail;
}
start = jiffies;
error = dlm_recover_directory(ls);
if (error) {
- log_error(ls, "recover_directory failed %d", error);
+ log_debug(ls, "recover_directory failed %d", error);
goto fail;
}
- /*
- * Purge directory-related requests that are saved in requestqueue.
- * All dir requests from before recovery are invalid now due to the dir
- * rebuild and will be resent by the requesting nodes.
- */
-
- dlm_purge_requestqueue(ls);
-
/*
* Wait for all nodes to complete directory rebuild.
*/
error = dlm_recover_directory_wait(ls);
if (error) {
- log_error(ls, "recover_directory_wait failed %d", error);
+ log_debug(ls, "recover_directory_wait failed %d", error);
goto fail;
}
error = dlm_recover_masters(ls);
if (error) {
- log_error(ls, "recover_masters failed %d", error);
+ log_debug(ls, "recover_masters failed %d", error);
goto fail;
}
error = dlm_recover_locks(ls);
if (error) {
- log_error(ls, "recover_locks failed %d", error);
+ log_debug(ls, "recover_locks failed %d", error);
goto fail;
}
error = dlm_recover_locks_wait(ls);
if (error) {
- log_error(ls, "recover_locks_wait failed %d", error);
+ log_debug(ls, "recover_locks_wait failed %d", error);
goto fail;
}
*/
dlm_recover_rsbs(ls);
+ } else {
+ /*
+ * Other lockspace members may be going through the "neg" steps
+ * while also adding us to the lockspace, in which case they'll
+ * be doing the recover_locks (RS_LOCKS) barrier.
+ */
+ dlm_set_recover_status(ls, DLM_RS_LOCKS);
+
+ error = dlm_recover_locks_wait(ls);
+ if (error) {
+ log_debug(ls, "recover_locks_wait failed %d", error);
+ goto fail;
+ }
}
dlm_release_root_list(ls);
+ /*
+ * Purge directory-related requests that are saved in requestqueue.
+ * All dir requests from before recovery are invalid now due to the dir
+ * rebuild and will be resent by the requesting nodes.
+ */
+
+ dlm_purge_requestqueue(ls);
+
dlm_set_recover_status(ls, DLM_RS_DONE);
error = dlm_recover_done_wait(ls);
if (error) {
- log_error(ls, "recover_done_wait failed %d", error);
+ log_debug(ls, "recover_done_wait failed %d", error);
goto fail;
}
error = enable_locking(ls, rv->seq);
if (error) {
- log_error(ls, "enable_locking failed %d", error);
+ log_debug(ls, "enable_locking failed %d", error);
goto fail;
}
error = dlm_process_requestqueue(ls);
if (error) {
- log_error(ls, "process_requestqueue failed %d", error);
+ log_debug(ls, "process_requestqueue failed %d", error);
goto fail;
}
error = dlm_recover_waiters_post(ls);
if (error) {
- log_error(ls, "recover_waiters_post failed %d", error);
+ log_debug(ls, "recover_waiters_post failed %d", error);
goto fail;
}
dlm_astd_wake();
- log_debug(ls, "recover %llx done: %u ms", rv->seq,
+ log_debug(ls, "recover %llx done: %u ms",
+ (unsigned long long)rv->seq,
jiffies_to_msecs(jiffies - start));
mutex_unlock(&ls->ls_recoverd_active);
fail:
dlm_release_root_list(ls);
- log_debug(ls, "recover %llx error %d", rv->seq, error);
+ log_debug(ls, "recover %llx error %d",
+ (unsigned long long)rv->seq, error);
mutex_unlock(&ls->ls_recoverd_active);
return error;
}
+/* The dlm_ls_start() that created the rv we take here may already have been
+ stopped via dlm_ls_stop(); in that case we need to leave the RECOVERY_STOP
+ flag set. */
+
static void do_ls_recovery(struct dlm_ls *ls)
{
struct dlm_recover *rv = NULL;
spin_lock(&ls->ls_recover_lock);
rv = ls->ls_recover_args;
ls->ls_recover_args = NULL;
- clear_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+ if (rv && ls->ls_recover_seq == rv->seq)
+ clear_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
spin_unlock(&ls->ls_recover_lock);
if (rv) {
struct dlm_ls *ls;
ls = dlm_find_lockspace_local(arg);
+ if (!ls) {
+ log_print("dlm_recoverd: no lockspace %p", arg);
+ return -1;
+ }
while (!kthread_should_stop()) {
set_current_state(TASK_INTERRUPTIBLE);
void dlm_recoverd_suspend(struct dlm_ls *ls)
{
+ wake_up(&ls->ls_wait_general);
mutex_lock(&ls->ls_recoverd_active);
}