dm raid1: keep issuing IO after leg failure

Currently if there is a leg failure, the bio will be put into the hold
list until userspace does a remove/replace on the leg.  Doing so in a
cluster config (clvmd) is problematic because there may be a temporary
path failure that results in cluster raid1 remove/replace.  Such
recovery takes a long time due to a full resync.

Update dm-raid1 to optionally ignore these failures so bios continue
being issued without interrupton.  To enable this feature userspace
must pass "keep_log" when creating the dm-raid1 device.

Signed-off-by: Lidong Zhong <lzhong@suse.com>
Tested-by: Liuhua Wang <lwang@suse.com>
Acked-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

drivers/md/dm-raid1.c

@@ -24,7 +24,9 @@
 #define MAX_RECOVERY 1	/* Maximum number of regions recovered in parallel. */
 
 #define DM_RAID1_HANDLE_ERRORS	0x01
+#define DM_RAID1_KEEP_LOG	0x02
 #define errors_handled(p)	((p)->features & DM_RAID1_HANDLE_ERRORS)
+#define keep_log(p)		((p)->features & DM_RAID1_KEEP_LOG)
 
 static DECLARE_WAIT_QUEUE_HEAD(_kmirrord_recovery_stopped);
 
@@ -229,7 +231,7 @@ static void fail_mirror(struct mirror *m, enum dm_raid1_error error_type)
 	if (m != get_default_mirror(ms))
 		goto out;
 
-	if (!ms->in_sync) {
+	if (!ms->in_sync && !keep_log(ms)) {
 		/*
 		 * Better to issue requests to same failing device
 		 * than to risk returning corrupt data.
@@ -370,6 +372,17 @@ static int recover(struct mirror_set *ms, struct dm_region *reg)
 	return r;
 }
 
+static void reset_ms_flags(struct mirror_set *ms)
+{
+	unsigned int m;
+
+	ms->leg_failure = 0;
+	for (m = 0; m < ms->nr_mirrors; m++) {
+		atomic_set(&(ms->mirror[m].error_count), 0);
+		ms->mirror[m].error_type = 0;
+	}
+}
+
 static void do_recovery(struct mirror_set *ms)
 {
 	struct dm_region *reg;
@@ -398,6 +411,7 @@ static void do_recovery(struct mirror_set *ms)
 		/* the sync is complete */
 		dm_table_event(ms->ti->table);
 		ms->in_sync = 1;
+		reset_ms_flags(ms);
 	}
 }
 
@@ -759,7 +773,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 		dm_rh_delay(ms->rh, bio);
 
 	while ((bio = bio_list_pop(&nosync))) {
-		if (unlikely(ms->leg_failure) && errors_handled(ms)) {
+		if (unlikely(ms->leg_failure) && errors_handled(ms) && !keep_log(ms)) {
 			spin_lock_irq(&ms->lock);
 			bio_list_add(&ms->failures, bio);
 			spin_unlock_irq(&ms->lock);
@@ -803,15 +817,21 @@ static void do_failures(struct mirror_set *ms, struct bio_list *failures)
 
 		/*
 		 * If all the legs are dead, fail the I/O.
-		 * If we have been told to handle errors, hold the bio
-		 * and wait for userspace to deal with the problem.
+		 * If the device has failed and keep_log is enabled,
+		 * fail the I/O.
+		 *
+		 * If we have been told to handle errors, and keep_log
+		 * isn't enabled, hold the bio and wait for userspace to
+		 * deal with the problem.
+		 *
 		 * Otherwise pretend that the I/O succeeded. (This would
 		 * be wrong if the failed leg returned after reboot and
 		 * got replicated back to the good legs.)
 		 */
-		if (!get_valid_mirror(ms))
+
+		if (unlikely(!get_valid_mirror(ms) || (keep_log(ms) && ms->log_failure)))
 			bio_endio(bio, -EIO);
-		else if (errors_handled(ms))
+		else if (errors_handled(ms) && !keep_log(ms))
 			hold_bio(ms, bio);
 		else
 			bio_endio(bio, 0);
@@ -987,6 +1007,7 @@ static int parse_features(struct mirror_set *ms, unsigned argc, char **argv,
 	unsigned num_features;
 	struct dm_target *ti = ms->ti;
 	char dummy;
+	int i;
 
 	*args_used = 0;
 
@@ -1007,14 +1028,24 @@ static int parse_features(struct mirror_set *ms, unsigned argc, char **argv,
 		return -EINVAL;
 	}
 
+	for (i = 0; i < num_features; i++) {
 		if (!strcmp("handle_errors", argv[0]))
 			ms->features |= DM_RAID1_HANDLE_ERRORS;
+		else if (!strcmp("keep_log", argv[0]))
+			ms->features |= DM_RAID1_KEEP_LOG;
 		else {
 			ti->error = "Unrecognised feature requested";
 			return -EINVAL;
 		}
 
+		argc--;
+		argv++;
 		(*args_used)++;
+	}
+	if (!errors_handled(ms) && keep_log(ms)) {
+		ti->error = "keep_log feature requires the handle_errors feature";
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1029,7 +1060,7 @@ static int parse_features(struct mirror_set *ms, unsigned argc, char **argv,
  * log_type is "core" or "disk"
  * #log_params is between 1 and 3
  *
- * If present, features must be "handle_errors".
+ * If present, supported features are "handle_errors" and "keep_log".
  */
 static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
@@ -1363,6 +1394,7 @@ static void mirror_status(struct dm_target *ti, status_type_t type,
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
 	unsigned int m, sz = 0;
+	int num_feature_args = 0;
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
 	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 	char buffer[ms->nr_mirrors + 1];
@@ -1392,8 +1424,17 @@ static void mirror_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" %s %llu", ms->mirror[m].dev->name,
 			       (unsigned long long)ms->mirror[m].offset);
 
-		if (ms->features & DM_RAID1_HANDLE_ERRORS)
-			DMEMIT(" 1 handle_errors");
+		num_feature_args += !!errors_handled(ms);
+		num_feature_args += !!keep_log(ms);
+		if (num_feature_args) {
+			DMEMIT(" %d", num_feature_args);
+			if (errors_handled(ms))
+				DMEMIT(" handle_errors");
+			if (keep_log(ms))
+				DMEMIT(" keep_log");
+		}
+
+		break;
 	}
 }
 
@@ -1413,7 +1454,7 @@ static int mirror_iterate_devices(struct dm_target *ti,
 
 static struct target_type mirror_target = {
 	.name	 = "mirror",
-	.version = {1, 13, 2},
+	.version = {1, 14, 0},
 	.module	 = THIS_MODULE,
 	.ctr	 = mirror_ctr,
 	.dtr	 = mirror_dtr,