From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org ([140.211.169.12]:36276 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752075AbdEQP5n (ORCPT ); Wed, 17 May 2017 11:57:43 -0400 Subject: Patch "jbd2: fix dbench4 performance regression for 'nobarrier' mounts" has been added to the 4.11-stable tree To: jack@suse.cz, gregkh@linuxfoundation.org, tytso@mit.edu Cc: , From: Date: Wed, 17 May 2017 17:56:03 +0200 Message-ID: <149503656311762@kroah.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ANSI_X3.4-1968 Content-Transfer-Encoding: 8bit Sender: stable-owner@vger.kernel.org List-ID: This is a note to let you know that I've just added the patch titled jbd2: fix dbench4 performance regression for 'nobarrier' mounts to the 4.11-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: jbd2-fix-dbench4-performance-regression-for-nobarrier-mounts.patch and it can be found in the queue-4.11 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let know about it. >>From 5052b069acf73866d00077d8bc49983c3ee903e5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sat, 29 Apr 2017 21:07:30 -0400 Subject: jbd2: fix dbench4 performance regression for 'nobarrier' mounts From: Jan Kara commit 5052b069acf73866d00077d8bc49983c3ee903e5 upstream. Commit b685d3d65ac7 "block: treat REQ_FUA and REQ_PREFLUSH as synchronous" removed REQ_SYNC flag from WRITE_FUA implementation. Since JBD2 strips REQ_FUA and REQ_FLUSH flags from submitted IO when the filesystem is mounted with nobarrier mount option, journal superblock writes ended up being async writes after this patch and that caused heavy performance regression for dbench4 benchmark with high number of processes. In my test setup with HP RAID array with non-volatile write cache and 32 GB ram, dbench4 runs with 8 processes regressed by ~25%. Fix the problem by making sure journal superblock writes are always treated as synchronous since they generally block progress of the journalling machinery and thus the whole filesystem. Fixes: b685d3d65ac791406e0dfd8779cc9b3707fea5a3 Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/journal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1348,7 +1348,7 @@ static int jbd2_write_superblock(journal jbd2_superblock_csum_set(journal, sb); get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(REQ_OP_WRITE, write_flags, bh); + ret = submit_bh(REQ_OP_WRITE, write_flags | REQ_SYNC, bh); wait_on_buffer(bh); if (buffer_write_io_error(bh)) { clear_buffer_write_io_error(bh); Patches currently in stable-queue which might be from jack@suse.cz are queue-4.11/fs-block_dev-always-invalidate-cleancache-in-invalidate_bdev.patch queue-4.11/jbd2-fix-dbench4-performance-regression-for-nobarrier-mounts.patch queue-4.11/fs-fix-data-invalidation-in-the-cleancache-during-direct-io.patch