From: Theodore Ts'o <tytso@mit.edu>
To: Ext4 Developers List <linux-ext4@vger.kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Subject: [PATCH 2/6] jbd2: calculate statistics without holding j_state_lock and j_list_lock
Date: Sun, 9 Mar 2014 01:05:37 -0500 [thread overview]
Message-ID: <1394345141-3471-2-git-send-email-tytso@mit.edu> (raw)
In-Reply-To: <1394345141-3471-1-git-send-email-tytso@mit.edu>
The two hottest locks, and thus the biggest scalability bottlenecks,
in the jbd2 layer, are the j_list_lock and j_state_lock. This has
inspired some people to do some truly unnatural things[1].
[1] https://www.usenix.org/system/files/conference/fast14/fast14-paper_kang.pdf
We don't need to be holding both j_state_lock and j_list_lock while
calculating the journal statistics, so move those calculations to the
very end of jbd2_journal_commit_transaction.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
fs/jbd2/commit.c | 36 ++++++++++++++++++------------------
1 file changed, 18 insertions(+), 18 deletions(-)
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 765b31d..af36252 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -1083,24 +1083,7 @@ restart_loop:
atomic_read(&commit_transaction->t_handle_count);
trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
commit_transaction->t_tid, &stats.run);
-
- /*
- * Calculate overall stats
- */
- spin_lock(&journal->j_history_lock);
- journal->j_stats.ts_tid++;
- if (commit_transaction->t_requested)
- journal->j_stats.ts_requested++;
- journal->j_stats.run.rs_wait += stats.run.rs_wait;
- journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
- journal->j_stats.run.rs_running += stats.run.rs_running;
- journal->j_stats.run.rs_locked += stats.run.rs_locked;
- journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
- journal->j_stats.run.rs_logging += stats.run.rs_logging;
- journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
- journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
- journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
- spin_unlock(&journal->j_history_lock);
+ stats.ts_requested = (commit_transaction->t_requested) ? 1 : 0;
commit_transaction->t_state = T_COMMIT_CALLBACK;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
@@ -1157,4 +1140,21 @@ restart_loop:
spin_unlock(&journal->j_list_lock);
write_unlock(&journal->j_state_lock);
wake_up(&journal->j_wait_done_commit);
+
+ /*
+ * Calculate overall stats
+ */
+ spin_lock(&journal->j_history_lock);
+ journal->j_stats.ts_tid++;
+ journal->j_stats.ts_requested += stats.ts_requested;
+ journal->j_stats.run.rs_wait += stats.run.rs_wait;
+ journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
+ journal->j_stats.run.rs_running += stats.run.rs_running;
+ journal->j_stats.run.rs_locked += stats.run.rs_locked;
+ journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+ journal->j_stats.run.rs_logging += stats.run.rs_logging;
+ journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+ journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+ journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
+ spin_unlock(&journal->j_history_lock);
}
--
1.9.0
next prev parent reply other threads:[~2014-03-09 6:05 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-09 6:05 [PATCH 1/6] jbd2: don't hold j_state_lock while calling wake_up() Theodore Ts'o
2014-03-09 6:05 ` Theodore Ts'o [this message]
2014-03-09 6:05 ` [PATCH 3/6] jbd2: add transaction to checkpoint list earlier Theodore Ts'o
2014-03-09 6:05 ` [PATCH 4/6] jbd2: check jh->b_transaction without taking j_list_lock Theodore Ts'o
2014-03-09 6:05 ` [PATCH 5/6] jbd2: minimize region locked by j_list_lock in journal_get_create_access() Theodore Ts'o
2014-03-09 6:05 ` [PATCH 6/6] jbd2: minimize region locked by j_list_lock in jbd2_journal_forget() Theodore Ts'o
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1394345141-3471-2-git-send-email-tytso@mit.edu \
--to=tytso@mit.edu \
--cc=linux-ext4@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).