From ea32ba9ae3461e10b11f78341a8f0e62c7299b36 Mon Sep 17 00:00:00 2001 From: Ryan Ding Date: Mon, 21 Dec 2015 11:01:12 +0800 Subject: [PATCH] ocfs2: call ocfs2_abort when journal abort orabug: 22293201 journal can not recover from abort state, so we should take following action to prevent file system from corruption: 1. change to readonly filesystem when local mount. We can not afford further write, so change to RO state is reasonable. 2. panic when cluster mount. Because we can not release lock resource in this state, other node will hung when it require a lock owned by this node. So panic and remaster is a reasonable choise. ocfs2_abort() will do all the above work. Signed-off-by: Ryan Ding --- fs/ocfs2/journal.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index ff531928269e..afa750cfb7fd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -30,7 +30,6 @@ #include #include #include -#include #include @@ -2241,7 +2240,7 @@ static int __ocfs2_wait_on_mount(struct ocfs2_super *osb, int quota) static int ocfs2_commit_thread(void *arg) { - int status; + int status = 0; struct ocfs2_super *osb = arg; struct ocfs2_journal *journal = osb->journal; @@ -2255,21 +2254,25 @@ static int ocfs2_commit_thread(void *arg) wait_event_interruptible(osb->checkpoint_event, atomic_read(&journal->j_num_trans) || kthread_should_stop()); + if (status < 0) { + /* As we can not terminate by ourself, just enter an + * empty loop to wait for stop. + */ + continue; + } status = ocfs2_commit_cache(osb); if (status < 0) { - static unsigned long abort_warn_time; - - /* Warn about this once per minute */ - if (printk_timed_ratelimit(&abort_warn_time, 60*HZ)) - mlog(ML_ERROR, "status = %d, journal is " - "already aborted.\n", status); /* - * After ocfs2_commit_cache() fails, j_num_trans has a - * non-zero value. Sleep here to avoid a busy-wait - * loop. + * journal can not recover from abort state, there is + * no need to keep commit cache. So we should either + * change to readonly(local mount) or just panic + * (cluster mount). + * We should also clear j_num_trans to prevent further + * commit. */ - msleep_interruptible(1000); + atomic_set(&journal->j_num_trans, 0); + ocfs2_abort(osb->sb, "Detected aborted journal"); } if (kthread_should_stop() && atomic_read(&journal->j_num_trans)){ -- 2.50.1