From: Andi Kleen <andi@firstfloor.org>
To: Mike Waychison <mikew@google.com>
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v1 0/8] Deferred dput() and iput() -- reducing lock contention
Date: Wed, 21 Jan 2009 06:52:16 +0100 [thread overview]
Message-ID: <877i4pdx4f.fsf@basil.nowhere.org> (raw)
In-Reply-To: <20090117022936.20425.43248.stgit@crlf.corp.google.com> (Mike Waychison's message of "Fri, 16 Jan 2009 18:29:36 -0800")
Mike Waychison <mikew@google.com> writes:
> livelock on dcache_lock/inode_lock (specifically in atomic_dec_and_lock())
I'm not sure how something can livelock in atomic_dec_and_lock which
doesn't take a spinlock itself? Are you saying you run into NUMA memory
unfairness here? Or did I misparse you?
> This patchset is an attempt to try and reduce the locking overheads associated
> with final dput() and final iput(). This is done by batching dentries and
> inodes into per-process queues and processing them in 'parallel' to consolidate
> some of the locking.
I was wondering what this does to the latencies when dput/iput
is only done for very objects. Does it increase costs then
significantly?
As a high level comment it seems like a lot of work to work
around global locks, like the inode_lock, where it might be better to
just split the lock up? Mind you I don't have a clear proposal
how to do that, but surely it's doable somehow.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2009-01-21 5:53 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-01-17 2:29 [PATCH v1 0/8] Deferred dput() and iput() -- reducing lock contention Mike Waychison
2009-01-17 2:29 ` [PATCH v1 1/8] Deferred batching of dput() Mike Waychison
2009-01-17 10:15 ` Evgeniy Polyakov
2009-01-20 20:07 ` Mike Waychison
2009-01-17 2:29 ` [PATCH v1 2/8] Parallel dput() Mike Waychison
2009-01-17 2:29 ` [PATCH v1 3/8] Deferred batching of iput() Mike Waychison
2009-01-17 10:18 ` Evgeniy Polyakov
2009-01-20 20:07 ` Mike Waychison
2009-01-17 2:29 ` [PATCH v1 4/8] Fixing iput() called from put_super path Mike Waychison
2009-01-17 2:30 ` [PATCH v1 5/8] Parallelize iput() Mike Waychison
2009-01-17 2:30 ` [PATCH v1 6/8] hugetlbfs drop_inode update Mike Waychison
2009-01-17 2:30 ` [PATCH v1 7/8] Make drop_caches flush pending dput()s and iput()s Mike Waychison
2009-01-17 2:30 ` [PATCH v1 8/8] Make the sync path drain dentries and inodes Mike Waychison
2009-01-17 7:04 ` [PATCH v1 0/8] Deferred dput() and iput() -- reducing lock contention Eric Dumazet
2009-01-20 20:00 ` Mike Waychison
2009-01-20 20:00 ` Mike Waychison
2009-01-17 8:12 ` Dave Chinner
2009-01-20 19:01 ` Mike Waychison
2009-01-29 2:09 ` Mike Waychison
2009-01-21 5:52 ` Andi Kleen [this message]
2009-01-21 6:22 ` Mike Waychison
2009-01-21 8:48 ` Andi Kleen
2009-01-21 17:28 ` Mike Waychison
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=877i4pdx4f.fsf@basil.nowhere.org \
--to=andi@firstfloor.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mikew@google.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.