From: Andrea Righi <righi.andrea@gmail.com>
To: Paul Menage <menage@google.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>,
Gui Jianfeng <guijianfeng@cn.fujitsu.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
agk@sourceware.org, akpm@linux-foundation.org, axboe@kernel.dk,
baramsori72@gmail.com, Carl Henrik Lunde <chlunde@ping.uio.no>,
dave@linux.vnet.ibm.com, Divyesh Shah <dpshah@google.com>,
eric.rannaud@gmail.com, fernando@oss.ntt.co.jp,
Hirokazu Takahashi <taka@valinux.co.jp>,
Li Zefan <lizf@cn.fujitsu.com>,
matt@bluehost.com, dradford@bluehost.com, ngupta@google.com,
randy.dunlap@oracle.com, roberto@unbit.it,
Ryo Tsuruta <ryov@valinux.co.jp>,
Satoshi UCHIDA <s-uchida@ap.jp.nec.com>,
subrata@linux.vnet.ibm.com, yoshikawa.takuya@oss.ntt.co.jp,
containers@lists.linux-foundation.org,
linux-kernel@vger.kernel.org,
Andrea Righi <righi.andrea@gmail.com>
Subject: [PATCH 9/9] ext3: do not throttle metadata and journal IO
Date: Tue, 14 Apr 2009 22:21:20 +0200 [thread overview]
Message-ID: <1239740480-28125-10-git-send-email-righi.andrea@gmail.com> (raw)
In-Reply-To: <1239740480-28125-1-git-send-email-righi.andrea@gmail.com>
Delaying journal IO can unnecessarily delay other independent IO
operations from different cgroups.
Add BIO_RW_META flag to the ext3 journal IO that informs the io-throttle
subsystem to account but not delay journal IO and avoid potential
priority inversion problems.
Signed-off-by: Andrea Righi <righi.andrea@gmail.com>
---
fs/jbd/commit.c | 4 ++--
fs/jbd2/commit.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index a8e8513..2e444af 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -318,7 +318,7 @@ void journal_commit_transaction(journal_t *journal)
int first_tag = 0;
int tag_flag;
int i;
- int write_op = WRITE;
+ int write_op = WRITE | (1 << BIO_RW_META);
/*
* First job: lock down the current transaction and wait for
@@ -357,7 +357,7 @@ void journal_commit_transaction(journal_t *journal)
* instead we rely on sync_buffer() doing the unplug for us.
*/
if (commit_transaction->t_synchronous_commit)
- write_op = WRITE_SYNC_PLUG;
+ write_op = WRITE_SYNC_PLUG | (1 << BIO_RW_META);
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
DEFINE_WAIT(wait);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 073c8c3..61484d0 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -367,7 +367,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
int tag_bytes = journal_tag_bytes(journal);
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
- int write_op = WRITE;
+ int write_op = WRITE | (1 << BIO_RW_META);
/*
* First job: lock down the current transaction and wait for
@@ -408,7 +408,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
* instead we rely on sync_buffer() doing the unplug for us.
*/
if (commit_transaction->t_synchronous_commit)
- write_op = WRITE_SYNC_PLUG;
+ write_op = WRITE_SYNC_PLUG | (1 << BIO_RW_META);
stats.u.run.rs_wait = commit_transaction->t_max_wait;
stats.u.run.rs_locked = jiffies;
stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
--
1.5.6.3
next prev parent reply other threads:[~2009-04-14 20:24 UTC|newest]
Thread overview: 104+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-14 20:21 [PATCH 0/9] cgroup: io-throttle controller (v13) Andrea Righi
2009-04-14 20:21 ` [PATCH 1/9] io-throttle documentation Andrea Righi
2009-04-17 1:24 ` KAMEZAWA Hiroyuki
2009-04-17 1:56 ` Li Zefan
2009-04-17 10:25 ` Andrea Righi
2009-04-17 10:41 ` Andrea Righi
2009-04-17 11:35 ` Fernando Luis Vázquez Cao
2009-04-20 9:38 ` Ryo Tsuruta
2009-04-20 15:00 ` Andrea Righi
2009-04-27 10:45 ` Ryo Tsuruta
2009-04-27 12:15 ` Ryo Tsuruta
2009-04-27 21:56 ` Andrea Righi
2009-04-17 7:34 ` Gui Jianfeng
2009-04-17 7:43 ` KAMEZAWA Hiroyuki
2009-04-17 9:29 ` Gui Jianfeng
2009-04-17 9:55 ` Andrea Righi
2009-04-17 17:39 ` Vivek Goyal
2009-04-17 23:12 ` Andrea Righi
2009-04-19 13:42 ` Vivek Goyal
2009-04-19 15:47 ` Andrea Righi
2009-04-20 21:28 ` Vivek Goyal
2009-04-20 22:05 ` Andrea Righi
2009-04-21 1:08 ` Vivek Goyal
2009-04-21 8:37 ` Andrea Righi
2009-04-21 14:23 ` Vivek Goyal
2009-04-21 18:29 ` Vivek Goyal
2009-04-21 21:36 ` Andrea Righi
2009-04-21 21:28 ` Andrea Righi
2009-04-19 13:54 ` Vivek Goyal
2009-04-14 20:21 ` [PATCH 2/9] res_counter: introduce ratelimiting attributes Andrea Righi
2009-04-14 20:21 ` [PATCH 3/9] bio-cgroup controller Andrea Righi
2009-04-15 2:15 ` KAMEZAWA Hiroyuki
2009-04-15 9:37 ` Andrea Righi
2009-04-15 12:38 ` Ryo Tsuruta
2009-04-15 13:23 ` Andrea Righi
2009-04-15 23:58 ` KAMEZAWA Hiroyuki
2009-04-16 10:42 ` Andrea Righi
2009-04-16 12:00 ` Ryo Tsuruta
2009-04-17 0:04 ` KAMEZAWA Hiroyuki
2009-04-17 9:44 ` Andrea Righi
2009-04-15 13:07 ` Andrea Righi
2009-04-16 22:29 ` Andrew Morton
2009-04-17 0:20 ` KAMEZAWA Hiroyuki
2009-04-17 0:44 ` Andrew Morton
2009-04-17 1:44 ` Ryo Tsuruta
2009-04-17 4:15 ` Andrew Morton
2009-04-17 7:48 ` Ryo Tsuruta
2009-04-17 1:50 ` Balbir Singh
2009-04-17 9:40 ` Andrea Righi
2009-04-17 1:49 ` Takuya Yoshikawa
2009-04-17 2:24 ` KAMEZAWA Hiroyuki
2009-04-17 7:22 ` Ryo Tsuruta
2009-04-17 8:00 ` KAMEZAWA Hiroyuki
2009-04-17 8:48 ` KAMEZAWA Hiroyuki
2009-04-17 8:51 ` KAMEZAWA Hiroyuki
2009-04-17 11:27 ` Block I/O tracking (was Re: [PATCH 3/9] bio-cgroup controller) Fernando Luis Vázquez Cao
2009-04-17 22:09 ` Andrea Righi
2009-04-17 7:32 ` [PATCH 3/9] bio-cgroup controller Ryo Tsuruta
2009-04-17 10:22 ` Balbir Singh
2009-04-20 11:35 ` Ryo Tsuruta
2009-04-20 14:56 ` Andrea Righi
2009-04-21 11:39 ` Ryo Tsuruta
2009-04-21 15:31 ` Balbir Singh
2009-04-14 20:21 ` [PATCH 4/9] support checking of cgroup subsystem dependencies Andrea Righi
2009-04-14 20:21 ` [PATCH 5/9] io-throttle controller infrastructure Andrea Righi
2009-04-14 20:21 ` [PATCH 6/9] kiothrottled: throttle buffered (writeback) IO Andrea Righi
2009-04-14 20:21 ` [PATCH 7/9] io-throttle instrumentation Andrea Righi
2009-04-14 20:21 ` [PATCH 8/9] export per-task io-throttle statistics to userspace Andrea Righi
2009-04-14 20:21 ` Andrea Righi [this message]
2009-04-17 12:38 ` [PATCH 9/9] ext3: do not throttle metadata and journal IO Theodore Tso
2009-04-17 12:50 ` Jens Axboe
2009-04-17 14:39 ` Andrea Righi
2009-04-21 0:18 ` Theodore Tso
2009-04-21 8:30 ` Andrea Righi
2009-04-21 14:06 ` Theodore Tso
2009-04-21 14:31 ` Andrea Righi
2009-04-21 16:35 ` Theodore Tso
2009-04-21 17:23 ` Balbir Singh
2009-04-21 17:46 ` Theodore Tso
2009-04-21 18:14 ` Balbir Singh
2009-04-21 19:14 ` Theodore Tso
2009-04-21 20:49 ` Andrea Righi
2009-04-22 0:33 ` KAMEZAWA Hiroyuki
2009-04-22 1:21 ` KAMEZAWA Hiroyuki
2009-04-22 10:22 ` Andrea Righi
2009-04-23 0:05 ` KAMEZAWA Hiroyuki
2009-04-23 1:22 ` Theodore Tso
2009-04-23 2:54 ` KAMEZAWA Hiroyuki
2009-04-23 4:35 ` Theodore Tso
2009-04-23 4:58 ` Andrew Morton
2009-04-23 5:37 ` KAMEZAWA Hiroyuki
2009-04-23 9:44 ` Andrea Righi
2009-04-23 12:17 ` Theodore Tso
2009-04-23 12:27 ` Theodore Tso
2009-04-23 21:13 ` Andrea Righi
2009-04-24 0:26 ` KAMEZAWA Hiroyuki
2009-04-24 5:14 ` Balbir Singh
2009-04-23 10:03 ` Andrea Righi
2009-04-22 3:30 ` Balbir Singh
2009-04-24 15:10 ` Balbir Singh
2009-04-16 22:24 ` [PATCH 0/9] cgroup: io-throttle controller (v13) Andrew Morton
2009-04-17 9:37 ` Andrea Righi
2009-04-30 13:20 ` Alan D. Brunelle
2009-05-01 11:11 ` Andrea Righi
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=1239740480-28125-10-git-send-email-righi.andrea@gmail.com \
--to=righi.andrea@gmail.com \
--cc=agk@sourceware.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=balbir@linux.vnet.ibm.com \
--cc=baramsori72@gmail.com \
--cc=chlunde@ping.uio.no \
--cc=containers@lists.linux-foundation.org \
--cc=dave@linux.vnet.ibm.com \
--cc=dpshah@google.com \
--cc=dradford@bluehost.com \
--cc=eric.rannaud@gmail.com \
--cc=fernando@oss.ntt.co.jp \
--cc=guijianfeng@cn.fujitsu.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizf@cn.fujitsu.com \
--cc=matt@bluehost.com \
--cc=menage@google.com \
--cc=ngupta@google.com \
--cc=randy.dunlap@oracle.com \
--cc=roberto@unbit.it \
--cc=ryov@valinux.co.jp \
--cc=s-uchida@ap.jp.nec.com \
--cc=subrata@linux.vnet.ibm.com \
--cc=taka@valinux.co.jp \
--cc=yoshikawa.takuya@oss.ntt.co.jp \
/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
all inboxes | Powered by JetHome®