From: Jonathan Brassow Subject: [PATCH] Log API addition for cluster-aware dirty log Date: Fri, 09 Jan 2009 12:14:25 -0600 Message-ID: <1231524865.24591.3.camel@hydrogen.msp.redhat.com> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Return-path: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: dm-devel@redhat.com List-Id: dm-devel.ids This patch is the same patch as posted in a previous e-mail. I am reposting so that it gets into Patchwork. The patch for "cluster-aware logging module" depends on this. 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 Index: linux-2.6/drivers/md/dm-raid1.c =================================================================== --- linux-2.6.orig/drivers/md/dm-raid1.c +++ linux-2.6/drivers/md/dm-raid1.c @@ -586,6 +586,9 @@ 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 = dm_rh_dirty_log(ms->rh); + region_t region; if (!writes->head) return; @@ -596,10 +599,18 @@ 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 = 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: @@ -619,6 +630,16 @@ 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/include/linux/dm-dirty-log.h =================================================================== --- linux-2.6.orig/include/linux/dm-dirty-log.h +++ linux-2.6/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);