From: Eric Dumazet <dada1@cosmosbay.com>
To: Kyle Moffett <mrmacman_g4@mac.com>
Cc: "Michael K. Edwards" <medwards.linux@gmail.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Anton Blanchard <anton@samba.org>,
Davide Libenzi <davidel@xmailserver.org>,
Avi Kivity <avi@argo.co.il>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Al Viro <viro@zeniv.linux.org.uk>
Subject: Re: [patch] epoll use a single inode ...
Date: Thu, 08 Mar 2007 08:24:04 +0100 [thread overview]
Message-ID: <45EFBA14.9090307@cosmosbay.com> (raw)
In-Reply-To: <6E1C86DF-D512-418C-B270-BC5C4316BC0A@mac.com>
Kyle Moffett a écrit :
>
> Prefetching is also fairly critical on a Power4 or G5 PowerPC system as
> they have a long memory latency; an L2-cache miss can cost 200+ cycles.
> On such systems the "dcbt" prefetch instruction brings in a single
> 128-byte cacheline and has no serializing effects whatsoever, making it
> ideal for use in a linked-list-traversal inner loop.
OK, 200 cycles...
But what is the cost of the conditional branch you added in prefetch(x) ?
if (!x) return;
(correctly predicted or not, but do powerPC have a BTB ?)
About the NULL 'potential problem', maybe we could use a dummy nil (but
mapped) object, and use its address in lists, ie compare for &nil instead of
NULL. This would avoid :
- The conditional test in some prefetch() implementations
- The potential TLB problem with the NULL value.
next prev parent reply other threads:[~2007-03-08 7:24 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <45ED1A3C.6030707@argo.co.il>
2007-03-07 0:37 ` [patch] epoll use a single inode Davide Libenzi
2007-03-07 0:51 ` Linus Torvalds
2007-03-07 1:01 ` Davide Libenzi
2007-03-07 1:27 ` Linus Torvalds
2007-03-07 1:47 ` Davide Libenzi
2007-03-07 6:52 ` Eric Dumazet
2007-03-07 7:15 ` Davide Libenzi
2007-03-07 7:16 ` Eric Dumazet
2007-03-07 8:56 ` Christoph Hellwig
2007-03-07 17:21 ` Linus Torvalds
2007-03-07 17:02 ` Linus Torvalds
2007-03-07 17:31 ` Eric Dumazet
2007-03-07 17:36 ` Eric Dumazet
2007-03-07 17:45 ` Linus Torvalds
2007-03-07 18:06 ` Eric Dumazet
2007-03-07 18:30 ` Linus Torvalds
2007-03-07 18:52 ` Eric Dumazet
2007-03-07 19:07 ` Linus Torvalds
2007-03-07 22:14 ` Anton Blanchard
2007-03-07 22:57 ` Linus Torvalds
2007-03-08 1:25 ` Michael K. Edwards
2007-03-08 2:48 ` Kyle Moffett
2007-03-08 7:24 ` Eric Dumazet [this message]
2007-03-08 16:57 ` Valdis.Kletnieks
2007-03-09 1:34 ` Kyle Moffett
2007-03-09 2:52 ` Anton Blanchard
2007-03-09 2:51 ` Anton Blanchard
2007-03-08 3:20 ` Linus Torvalds
2007-03-08 8:37 ` Michael K. Edwards
2007-03-09 2:46 ` Anton Blanchard
2007-03-08 8:56 ` Christoph Hellwig
2007-03-08 9:42 ` Eric Dumazet
2007-03-08 10:21 ` Christoph Hellwig
2007-03-08 11:11 ` Eric Dumazet
2007-03-08 11:18 ` Christoph Hellwig
2007-03-08 15:52 ` Linus Torvalds
2007-03-08 16:58 ` [PATCH] VFS : Delay the dentry name generation on sockets and pipes Eric Dumazet
2007-03-08 18:29 ` Eric Dumazet
2007-03-09 10:18 ` [PATCH, take2] " Eric Dumazet
2007-03-09 18:22 ` Linus Torvalds
2007-03-10 1:21 ` [PATCH, take3] " Eric Dumazet
2007-03-08 20:00 ` [patch] epoll use a single inode Bob Copeland
[not found] <45ED046A.5010508@argo.co.il>
2007-03-06 7:27 ` Davide Libenzi
2007-03-05 21:25 Davide Libenzi
2007-03-05 21:52 ` Eric Dumazet
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=45EFBA14.9090307@cosmosbay.com \
--to=dada1@cosmosbay.com \
--cc=akpm@linux-foundation.org \
--cc=anton@samba.org \
--cc=avi@argo.co.il \
--cc=davidel@xmailserver.org \
--cc=linux-kernel@vger.kernel.org \
--cc=medwards.linux@gmail.com \
--cc=mrmacman_g4@mac.com \
--cc=torvalds@linux-foundation.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 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.