From 7513c2a761d69d2a93f17146b3563527d3618ba0 Mon Sep 17 00:00:00 2001
From: Jonathan Brassow <jbrassow@redhat.com>
Date: Thu, 2 Apr 2009 19:55:30 +0100
Subject: dm raid1: add is_remote_recovering hook for clusters

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@redhat.com>
Acked-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 62d5948..536ef0b 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -588,6 +588,9 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	int state;
 	struct bio *bio;
 	struct bio_list sync, nosync, recover, *this_list = NULL;
+	struct bio_list requeue;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
+	region_t region;
 
 	if (!writes->head)
 		return;
@@ -598,10 +601,18 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&sync);
 	bio_list_init(&nosync);
 	bio_list_init(&recover);
+	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		state = dm_rh_get_state(ms->rh,
-					dm_rh_bio_to_region(ms->rh, bio), 1);
+		region = dm_rh_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 = dm_rh_get_state(ms->rh, region, 1);
 		switch (state) {
 		case DM_RH_CLEAN:
 		case DM_RH_DIRTY:
@@ -621,6 +632,16 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	}
 
 	/*
+	 * 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).
diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h
index 727602b..5e8b11d 100644
--- a/include/linux/dm-dirty-log.h
+++ b/include/linux/dm-dirty-log.h
@@ -116,6 +116,16 @@ 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);
-- 
cgit v0.10.2