From: Andi Kleen <andi@firstfloor.org>
To: Andreas Dilger <adilger@dilger.ca>
Cc: Phillip Susi <psusi@ubuntu.com>,
Matthew Wilcox <willy@linux.intel.com>, "Zuckerman\,
Boris" <borisz@hp.com>,
"linux-fsdevel\@vger.kernel.org" <linux-fsdevel@vger.kernel.org>
Subject: Re: Tracking actual disk write sources instead of flush thread
Date: Sun, 27 Apr 2014 20:27:56 -0700 [thread overview]
Message-ID: <87y4yqku9v.fsf@tassilo.jf.intel.com> (raw)
In-Reply-To: <68A83B3D-D029-4863-B9D9-2BD9894FDFDC@dilger.ca> (Andreas Dilger's message of "Wed, 23 Apr 2014 17:19:25 -0600")
Andreas Dilger <adilger@dilger.ca> writes:
> I think that adding a pointer or integer per page would meet resistance,
> but I think it is pretty reasonable to track this on a per-inode
> basis.
That's a really bad hot cache line in the making.
> It is fairly uncommon to have multiple threads writing to the same file,
> and I would guess it is vanishingly rare that different applications are
> writing to the same file at one time.
Sounds like a bad assumption to me.
Likely would be a scalability disaster.
-Andi
--
ak@linux.intel.com -- Speaking for myself only
next prev parent reply other threads:[~2014-04-28 3:27 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-16 2:01 Tracking actual disk write sources instead of flush thread Phillip Susi
2014-04-16 14:01 ` Matthew Wilcox
2014-04-16 15:15 ` Phillip Susi
2014-04-16 16:42 ` Andreas Dilger
2014-04-16 17:44 ` Zuckerman, Boris
2014-04-16 18:18 ` Phillip Susi
2014-04-16 18:28 ` Zuckerman, Boris
2014-04-16 19:27 ` Phillip Susi
2014-04-23 13:48 ` Matthew Wilcox
2014-04-23 19:39 ` Phillip Susi
2014-04-23 23:00 ` Theodore Ts'o
2014-04-24 1:20 ` Phillip Susi
2014-04-23 23:19 ` Andreas Dilger
2014-04-24 1:39 ` Phillip Susi
2014-04-28 3:27 ` Andi Kleen [this message]
2014-04-16 19:33 ` Andi Kleen
2014-04-24 19:33 ` Jan Kara
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=87y4yqku9v.fsf@tassilo.jf.intel.com \
--to=andi@firstfloor.org \
--cc=adilger@dilger.ca \
--cc=borisz@hp.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=psusi@ubuntu.com \
--cc=willy@linux.intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.