[dm-devel] [Patch 1 of 2]: Cluster-aware log module - enabling cluster-aware mirrors

[Jonathan Brassow]

	brassow

The logging API needs an extra function to make cluster mirroring
possible.  This new function allows us to check whether a mirror
region is being recovered on another machine in the cluster.  This
helps us prevent simultaneous recovery I/O and process I/O to the
same locations on disk.

Cluster-aware log modules will implement this function.  Single
machine log modules will not.  So, there is no performance
penalty for single machine mirrors.

Signed-off-by: Jonathan Brassow <jbrassow at redhat.com>

Index: linux-2.6.26-rc8/drivers/md/dm-raid1.c
===================================================================
--- linux-2.6.26-rc8.orig/drivers/md/dm-raid1.c
+++ linux-2.6.26-rc8/drivers/md/dm-raid1.c
@@ -1157,6 +1157,9 @@ static void do_writes(struct mirror_set 
 	int state;
 	struct bio *bio;
 	struct bio_list sync, nosync, recover, *this_list = NULL;
+	struct bio_list requeue;
+	struct dm_dirty_log *log = ms->rh.log;
+	region_t region;
 
 	if (!writes->head)
 		return;
@@ -1167,9 +1170,18 @@ static void do_writes(struct mirror_set 
 	bio_list_init(&sync);
 	bio_list_init(&nosync);
 	bio_list_init(&recover);
+	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		state = rh_state(&ms->rh, bio_to_region(&ms->rh, bio), 1);
+		region = bio_to_region(&ms->rh, bio);
+
+		if (log->type->is_remote_recovering &&
+		    log->type->is_remote_recovering(log, region)) {
+			bio_list_add(&requeue, bio);
+			continue;
+		}
+
+		state = rh_state(&ms->rh, region, 1);
 		switch (state) {
 		case RH_CLEAN:
 		case RH_DIRTY:
@@ -1189,6 +1201,16 @@ static void do_writes(struct mirror_set 
 	}
 
 	/*
+	 * Add bios that are delayed due to remote recovery
+	 * back on to the write queue
+	 */
+	if (unlikely(requeue.head)) {
+		spin_lock_irq(&ms->lock);
+		bio_list_merge(&ms->writes, &requeue);
+		spin_unlock_irq(&ms->lock);
+	}
+
+	/*
 	 * Increment the pending counts for any regions that will
 	 * be written to (writes to recover regions are going to
 	 * be delayed).
Index: linux-2.6.26-rc8/include/linux/dm-dirty-log.h
===================================================================
--- linux-2.6.26-rc8.orig/include/linux/dm-dirty-log.h
+++ linux-2.6.26-rc8/include/linux/dm-dirty-log.h
@@ -113,6 +113,16 @@ struct dm_dirty_log_type {
 	 */
 	int (*status)(struct dm_dirty_log *log, status_type_t status_type,
 		      char *result, unsigned maxlen);
+
+	/*
+	 * is_remote_recovering is necessary for cluster mirroring. It provides
+	 * a way to detect recovery on another node, so we aren't writing
+	 * concurrently.  This function is likely to block (when a cluster log
+	 * is used).
+	 *
+	 * Returns: 0, 1
+	 */
+	int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region);
 };
 
 int dm_dirty_log_type_register(struct dm_dirty_log_type *type);