From: Andi Kleen <andi@firstfloor.org>
To: Waiman Long <Waiman.Long@hpe.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
Jan Kara <jack@suse.com>, Jeff Layton <jlayton@poochiereds.net>,
"J. Bruce Fields" <bfields@fieldses.org>,
Tejun Heo <tj@kernel.org>,
Christoph Lameter <cl@linux-foundation.org>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Andi Kleen <andi@firstfloor.org>,
Dave Chinner <dchinner@redhat.com>,
Boqun Feng <boqun.feng@gmail.com>,
Scott J Norton <scott.norton@hpe.com>,
Douglas Hatch <doug.hatch@hpe.com>
Subject: Re: [RESEND PATCH 1/5] lib/dlock-list: Distributed and lock-protected lists
Date: Tue, 7 Jun 2016 13:13:40 -0700 [thread overview]
Message-ID: <20160607201340.GL13997@two.firstfloor.org> (raw)
In-Reply-To: <1465328155-56754-2-git-send-email-Waiman.Long@hpe.com>
On Tue, Jun 07, 2016 at 03:35:51PM -0400, Waiman Long wrote:
> Linked list is used everywhere in the Linux kernel. However, if many
> threads are trying to add or delete entries into the same linked list,
> it can create a performance bottleneck.
>
> This patch introduces a new list APIs that provide a set of distributed
> lists (one per CPU), each of which is protected by its own spinlock.
One thing I don't like is that it is per CPU. One per CPU is almost
certainly overkill and not needed for true scalability, especially
on systems using SMT. Also it makes the case where everything has to
be walked more and more expensive, because all these locks have to
be taken. Even when not contended this will add up.
It would be better to do this per every Nth CPU. Now I don't have
a clear answer what the best N is, but I'm pretty sure it's > 1.
For example at least on SMT systems only per core instead of per
thread. Likely even more coarse grained, although per socket
may be not good enough.
-Andi
next prev parent reply other threads:[~2016-06-07 20:13 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-07 19:35 [RESEND PATCH 0/5] vfs: Use dlock list for SB's s_inodes list Waiman Long
2016-06-07 19:35 ` [RESEND PATCH 1/5] lib/dlock-list: Distributed and lock-protected lists Waiman Long
2016-06-07 20:13 ` Andi Kleen [this message]
2016-06-07 23:53 ` Waiman Long
2016-07-11 17:37 ` Waiman Long
2016-06-07 19:35 ` [RESEND PATCH 2/5] lib/dlock-list: Add __percpu modifier for parameters Waiman Long
2016-06-07 19:35 ` [RESEND PATCH 3/5] fsnotify: Simplify inode iteration on umount Waiman Long
2016-06-07 19:35 ` [RESEND PATCH 4/5] vfs: Remove unnecessary list_for_each_entry_safe() variants Waiman Long
2016-06-07 19:35 ` [RESEND PATCH 5/5] vfs: Use dlock list for superblock's inode list Waiman Long
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=20160607201340.GL13997@two.firstfloor.org \
--to=andi@firstfloor.org \
--cc=Waiman.Long@hpe.com \
--cc=bfields@fieldses.org \
--cc=boqun.feng@gmail.com \
--cc=cl@linux-foundation.org \
--cc=dchinner@redhat.com \
--cc=doug.hatch@hpe.com \
--cc=jack@suse.com \
--cc=jlayton@poochiereds.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=scott.norton@hpe.com \
--cc=tj@kernel.org \
--cc=viro@zeniv.linux.org.uk \
/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).