From: "Theodore Y. Ts'o" <tytso@mit.edu>
To: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>, Joseph Qi <jiangqi903@gmail.com>,
Dave Chinner <david@fromorbit.com>,
Andreas Dilger <adilger@dilger.ca>,
Ext4 Developers List <linux-ext4@vger.kernel.org>,
Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>,
Liu Bo <bo.liu@linux.alibaba.com>
Subject: Re: [RFC] performance regression with "ext4: Allow parallel DIO reads"
Date: Tue, 20 Aug 2019 12:08:05 -0400 [thread overview]
Message-ID: <20190820160805.GB10232@mit.edu> (raw)
In-Reply-To: <a8ddec64-d87c-ae7a-9b02-2f24da2396e9@linux.alibaba.com>
On Tue, Aug 20, 2019 at 11:00:39AM +0800, Joseph Qi wrote:
>
> I've tested parallel dio reads with dioread_nolock, it doesn't have
> significant performance improvement and still poor compared with reverting
> parallel dio reads. IMO, this is because with parallel dio reads, it take
> inode shared lock at the very beginning in ext4_direct_IO_read().
Why is that a problem? It's a shared lock, so parallel threads should
be able to issue reads without getting serialized?
Are you using sufficiently fast storage devices that you're worried
about cache line bouncing of the shared lock? Or do you have some
other concern, such as some other thread taking an exclusive lock?
- Ted
next prev parent reply other threads:[~2019-08-20 16:08 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-19 9:22 [RFC] performance regression with "ext4: Allow parallel DIO reads" Joseph Qi
2019-07-23 11:17 ` Joseph Qi
2019-07-25 21:20 ` Andreas Dilger
2019-07-26 1:12 ` Joseph Qi
2019-07-27 1:57 ` Andreas Dilger
2019-07-27 2:16 ` Joseph Qi
2019-07-28 22:51 ` Dave Chinner
2019-07-30 1:34 ` Joseph Qi
2019-08-15 15:13 ` Jan Kara
2019-08-16 13:23 ` Joseph Qi
2019-08-16 14:57 ` Jan Kara
2019-08-20 3:00 ` Joseph Qi
2019-08-20 16:08 ` Theodore Y. Ts'o [this message]
2019-08-21 1:04 ` Joseph Qi
2019-08-21 3:34 ` Theodore Y. Ts'o
2019-08-22 6:45 ` Joseph Qi
2019-08-22 5:40 ` Dave Chinner
2019-08-23 7:57 ` Joseph Qi
2019-08-23 8:07 ` Joseph Qi
2019-08-23 10:16 ` Dave Chinner
2019-08-23 13:08 ` Joseph Qi
2019-08-24 2:18 ` Dave Chinner
2019-08-26 8:39 ` Jan Kara
2019-08-26 19:10 ` Andreas Dilger
2019-08-27 1:00 ` Joseph Qi
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=20190820160805.GB10232@mit.edu \
--to=tytso@mit.edu \
--cc=adilger@dilger.ca \
--cc=bo.liu@linux.alibaba.com \
--cc=david@fromorbit.com \
--cc=jack@suse.cz \
--cc=jiangqi903@gmail.com \
--cc=joseph.qi@linux.alibaba.com \
--cc=linux-ext4@vger.kernel.org \
--cc=xiaoguang.wang@linux.alibaba.com \
/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).