From: Olaf Kirch <okir@suse.de>
To: Greg Banks <gnb@melbourne.sgi.com>
Cc: Neil Brown <neilb@suse.de>,
Linux NFS Mailing List <nfs@lists.sourceforge.net>
Subject: Re: [PATCH 000 of 11] knfsd: NUMAisation
Date: Wed, 26 Jul 2006 11:14:29 +0200 [thread overview]
Message-ID: <20060726091429.GB6979@suse.de> (raw)
In-Reply-To: <1153816400.21040.153.camel@hole.melbourne.sgi.com>
On Tue, Jul 25, 2006 at 06:33:20PM +1000, Greg Banks wrote:
> > /*
> > * Always select the oldest socket. It's not fair,
> > * but so is life
> > */
> > so I guess it is still correct ('oldest' is ambiguous). The new
> > situation is probably equally (un)fair - would you agree?
>
> Agreed. The algorithm makes no pretence at fairness, but at least
> we're no longer bouncing cachelines in global data structures to
> check for old sockets (a infrequent corner case) on every incoming
> packet (the main performance path).
I think picking the oldest is just as good as picking a random one. The
only bad choice is picking the youngest socket, as that will make active
connections thrash while leaving potentially idle ones untouched.
Olaf
--
Olaf Kirch | --- o --- Nous sommes du soleil we love when we play
okir@suse.de | / | \ sol.dhoop.naytheet.ah kin.ir.samse.qurax
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
NFS maillist - NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs
next prev parent reply other threads:[~2006-07-26 9:57 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-25 5:27 [PATCH 000 of 11] knfsd: NUMAisation Greg Banks
2006-07-25 7:13 ` Neil Brown
2006-07-25 8:02 ` Neil Brown
2006-07-25 9:03 ` Greg Banks
2006-07-25 8:33 ` Greg Banks
2006-07-26 9:14 ` Olaf Kirch [this message]
2006-07-31 1:02 ` Neil Brown
2006-07-31 10:33 ` Greg Banks
2006-07-25 14:05 ` Chuck Lever
2006-07-25 14:49 ` Paul Jimenez
2006-07-25 15:36 ` Chuck Lever
2006-07-26 6:25 ` Greg Banks
2006-07-26 18:26 ` Chuck Lever
2006-07-27 0:47 ` Greg Banks
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=20060726091429.GB6979@suse.de \
--to=okir@suse.de \
--cc=gnb@melbourne.sgi.com \
--cc=neilb@suse.de \
--cc=nfs@lists.sourceforge.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 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.