From 5500ab4ed3b8f0749ec584d8c5e2738bc01ea52e Mon Sep 17 00:00:00 2001 From: Gang He Date: Tue, 5 Mar 2019 15:41:45 -0800 Subject: ocfs2: fix the application IO timeout when fstrim is running The user reported this problem, the upper application IO was timeout when fstrim was running on this ocfs2 partition. the application monitoring resource agent considered that this application did not work, then this node was fenced by the cluster brain (e.g. pacemaker). The root cause is that fstrim thread always holds main_bm meta-file related locks until all the cluster groups are trimmed. This patch will make fstrim thread release main_bm meta-file related locks when each cluster group is trimmed, this will let the current application IO has a chance to claim the clusters from main_bm meta-file. Link: http://lkml.kernel.org/r/20190111090014.31645-1-ghe@suse.com Signed-off-by: Gang He Reviewed-by: Changwei Ge Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlmglue.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs/ocfs2/dlmglue.c') diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 7c835824247e..af405586c5b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; + /* Only one trimfs thread are allowed to work at the same time. */ + mutex_lock(&osb->obs_trim_fs_mutex); + ocfs2_lock_res_init_once(lockres); ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name); ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS, @@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb) ocfs2_simple_drop_lockres(osb, lockres); ocfs2_lock_res_free(lockres); + + mutex_unlock(&osb->obs_trim_fs_mutex); } static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res, -- cgit v1.2.3-58-ga151