From: Rusty Russell <rusty@rustcorp.com.au>
To: Ian Kent <raven@themaw.net>
Cc: ia6432@inbox.ru, linux-kernel@vger.kernel.org,
autofs@linux.kernel.org, nfs@lists.sourceforge.net
Subject: Re: [NFS] nfs or autofs related hangs
Date: Tue, 17 Feb 2004 18:37:49 +1100 [thread overview]
Message-ID: <20040217183749.490777c5.rusty@rustcorp.com.au> (raw)
In-Reply-To: <Pine.LNX.4.58.0402160910300.28358@wombat.indigo.net.au>
On Mon, 16 Feb 2004 09:13:55 +0800 (WST)
Ian Kent <raven@themaw.net> wrote:
> On Sun, 15 Feb 2004, Rusty Russell wrote:
> > Is this __cacheline_aligned_in_smp really required?
>
> I must admit I put this together without much thought with a "cut and
> paste".
>
> But, please tell me. I'm not entirely clear on what conditions I
> should be concerned about blowing the cache.
You should usually try to declare the spinlock near the things it protects, in
the hope that they'll be in the same cacheline. If we blow 128 bytes for
every spinlock, things will get slower, not faster.
ie. like any optimization, the default should be not to do it unless there's
a reason[1]
Cheers,
Rusty.
[1] An optimization being defined here as something with tradeoffs.
Doing the obviously superior thing is not an optimization, it's simply
being a decent coder.
--
there are those who do and those who hang on and you don't see too
many doers quoting their contemporaries. -- Larry McVoy
next prev parent reply other threads:[~2004-02-18 0:15 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <E1AoQvL-0002NP-00.ia6432-inbox-ru@f21.mail.ru>
2004-02-08 15:32 ` Ian Kent
2004-02-09 14:32 ` Re[2]: " "Peter Lojkin"
2004-02-09 15:21 ` Ian Kent
2004-02-09 15:43 ` Re[3]: " "Peter Lojkin"
2004-02-09 16:13 ` raven
2004-02-15 8:53 ` Rusty Russell
2004-02-16 1:13 ` Ian Kent
2004-02-17 7:37 ` Rusty Russell [this message]
2004-02-18 1:02 ` Ian Kent
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=20040217183749.490777c5.rusty@rustcorp.com.au \
--to=rusty@rustcorp.com.au \
--cc=autofs@linux.kernel.org \
--cc=ia6432@inbox.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=nfs@lists.sourceforge.net \
--cc=raven@themaw.net \
/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®