From 2c97cf138527a0f0283fcca9acf4a06216bec7da Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 2 May 2016 11:33:09 -0400 Subject: [PATCH] md-cluser: make resync_finish only called after pers->sync_request It is not reasonable that cluster raid to release resync lock before the last pers->sync_request has finished. As the metadata will be changed when node performs resync, we need to inform other nodes to update metadata, so the MD_CHANGE_PENDING flag is set before finish resync. Then metadata_update_finish is move ahead to ensure that METADATA_UPDATED msg is sent before finish resync, and metadata_update_start need to be run after "repeat:" label accordingly. Reviewed-by: NeilBrown Signed-off-by: Guoqing Jiang Signed-off-by: Shaohua Li --- drivers/md/md.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4fd7d7757f2d..dd83a50d892c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2291,6 +2291,7 @@ void md_update_sb(struct mddev *mddev, int force_change) return; } +repeat: if (mddev_is_clustered(mddev)) { if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags)) force_change = 1; @@ -2303,7 +2304,7 @@ void md_update_sb(struct mddev *mddev, int force_change) return; } } -repeat: + /* First make sure individual recovery_offsets are correct */ rdev_for_each(rdev, mddev) { if (rdev->raid_disk >= 0 && @@ -2430,6 +2431,9 @@ repeat: md_super_wait(mddev); /* if there was a failure, MD_CHANGE_DEVS was set, and we re-write super */ + if (mddev_is_clustered(mddev) && ret == 0) + md_cluster_ops->metadata_update_finish(mddev); + spin_lock(&mddev->lock); if (mddev->in_sync != sync_req || test_bit(MD_CHANGE_DEVS, &mddev->flags)) { @@ -2452,9 +2456,6 @@ repeat: clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); } - - if (mddev_is_clustered(mddev) && ret == 0) - md_cluster_ops->metadata_update_finish(mddev); } EXPORT_SYMBOL(md_update_sb); @@ -7785,7 +7786,6 @@ void md_do_sync(struct md_thread *thread) struct md_rdev *rdev; char *desc, *action = NULL; struct blk_plug plug; - bool cluster_resync_finished = false; int ret; /* just incase thread restarts... */ @@ -8103,11 +8103,6 @@ void md_do_sync(struct md_thread *thread) mddev->curr_resync_completed = mddev->curr_resync; sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } - /* tell personality and other nodes that we are finished */ - if (mddev_is_clustered(mddev)) { - md_cluster_ops->resync_finish(mddev); - cluster_resync_finished = true; - } mddev->pers->sync_request(mddev, max_sectors, &skipped); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && @@ -8147,9 +8142,15 @@ void md_do_sync(struct md_thread *thread) set_bit(MD_CHANGE_DEVS, &mddev->flags); if (mddev_is_clustered(mddev) && - test_bit(MD_RECOVERY_INTR, &mddev->recovery) && - !cluster_resync_finished) + ret == 0) { + /* set CHANGE_PENDING here since maybe another + * update is needed, so other nodes are informed */ + set_bit(MD_CHANGE_PENDING, &mddev->flags); + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, + !test_bit(MD_CHANGE_PENDING, &mddev->flags)); md_cluster_ops->resync_finish(mddev); + } spin_lock(&mddev->lock); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {