Commit-ID: 6fa7aa50b2c48400bbd045daf3a2498882eb0596 Gitweb: http://git.kernel.org/tip/6fa7aa50b2c48400bbd045daf3a2498882eb0596 Author: Tejun Heo <[email protected]> AuthorDate: Fri, 28 Oct 2016 12:58:12 -0400 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 14 Jan 2017 11:30:06 +0100
fs/jbd2, locking/mutex, sched/wait: Use mutex_lock_io() for journal->j_checkpoint_mutex When an ext4 fs is bogged down by a lot of metadata IOs (in the reported case, it was deletion of millions of files, but any massive amount of journal writes would do), after the journal is filled up, tasks which try to access the filesystem and aren't currently performing the journal writes end up waiting in __jbd2_log_wait_for_space() for journal->j_checkpoint_mutex. Because those mutex sleeps aren't marked as iowait, this condition can lead to misleadingly low iowait and /proc/stat:procs_blocked. While iowait propagation is far from strict, this condition can be triggered fairly easily and annotating these sleeps correctly helps initial diagnosis quite a bit. Use the new mutex_lock_io() for journal->j_checkpoint_mutex so that these sleeps are properly marked as iowait. Reported-by: Mingbo Wan <[email protected]> Signed-off-by: Tejun Heo <[email protected]> Signed-off-by: Peter Zijlstra (Intel) <[email protected]> Cc: Andreas Dilger <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Jan Kara <[email protected]> Cc: Jens Axboe <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Mike Galbraith <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Theodore Ts'o <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: [email protected] Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Ingo Molnar <[email protected]> --- fs/jbd2/commit.c | 2 +- fs/jbd2/journal.c | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 8c51436..b6b194e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -393,7 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { jbd_debug(3, "super block updated\n"); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); /* * We hold j_checkpoint_mutex so tail cannot change under us. * We don't need any special data guarantees for writing sb diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index a097048..d8a5d0a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -944,7 +944,7 @@ out: */ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); if (tid_gt(tid, journal->j_tail_sequence)) __jbd2_update_log_tail(journal, tid, block); mutex_unlock(&journal->j_checkpoint_mutex); @@ -1304,7 +1304,7 @@ static int journal_reset(journal_t *journal) journal->j_flags |= JBD2_FLUSHED; } else { /* Lock here to make assertions happy... */ - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); /* * Update log tail information. We use REQ_FUA since new * transaction will start reusing journal space and so we @@ -1691,7 +1691,7 @@ int jbd2_journal_destroy(journal_t *journal) spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); /* @@ -1713,7 +1713,7 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); journal->j_tail_sequence = @@ -1955,7 +1955,7 @@ int jbd2_journal_flush(journal_t *journal) spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); @@ -1965,7 +1965,7 @@ int jbd2_journal_flush(journal_t *journal) if (is_journal_aborted(journal)) return -EIO; - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); if (!err) { err = jbd2_cleanup_journal_tail(journal); if (err < 0) {
