From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: Andi Kleen <ak@suse.de>
Cc: davem@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: Fire Engine??
Date: Wed, 26 Nov 2003 18:23:17 -0500 [thread overview]
Message-ID: <16325.13797.417933.122067@charged.uio.no> (raw)
In-Reply-To: <20031127000145.61187530.ak@suse.de>
>>>>> " " == Andi Kleen <ak@suse.de> writes:
> Current sunrpc does two recvmsgs for each record to first get
> the record length and then the payload.
> This means you take all the locks and other overhead twice per
> packet.
> Having a special function that peeks directly at the TCP
> receive queue would be much faster (and falls back to normal
> recvmsg when there is no data waiting)
Oh, right... That would be the server code you are thinking of, then.
The client already does something like this. I've added a function
tcp_read_sock() that is called directly from tcp_data_ready() and
hence fills the page cache directly from within the softirq.
There are a still few inefficiencies with this approach, though. Most
notable is the fact that you need to call kmap_atomic() several times
per page since the socket lower layers will usually be feeding you 1
skb at a time. I thought you might be referring to those (and that you
might have a good solution to propose ;-))
Cheers,
Trond
next prev parent reply other threads:[~2003-11-26 23:23 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <BAY1-DAV15JU71pROHD000040e2@hotmail.com.suse.lists.linux.kernel>
[not found] ` <20031125183035.1c17185a.davem@redhat.com.suse.lists.linux.kernel>
2003-11-26 9:53 ` Fire Engine?? Andi Kleen
2003-11-26 11:35 ` John Bradford
2003-11-26 18:50 ` Mike Fedyk
2003-11-26 19:19 ` Diego Calleja García
2003-11-26 19:59 ` Mike Fedyk
2003-11-27 3:54 ` Bill Huey
2003-11-26 15:00 ` Trond Myklebust
2003-11-26 23:01 ` Andi Kleen
2003-11-26 23:23 ` Trond Myklebust [this message]
2003-11-26 23:38 ` Andi Kleen
2003-11-26 19:30 ` David S. Miller
2003-11-26 19:58 ` Paul Menage
2003-11-26 20:03 ` David S. Miller
2003-11-26 22:29 ` Andi Kleen
2003-11-26 22:36 ` David S. Miller
2003-11-26 22:56 ` Andi Kleen
2003-11-26 23:13 ` David S. Miller
2003-11-26 23:29 ` Andi Kleen
2003-11-26 23:41 ` Ben Greear
2003-11-27 0:01 ` Fast timestamps David S. Miller
2003-11-27 0:30 ` Mitchell Blank Jr
2003-11-27 1:57 ` Ben Greear
2003-11-26 20:01 ` Fire Engine?? Jamie Lokier
2003-11-26 20:04 ` David S. Miller
2003-11-26 21:54 ` Pekka Pietikainen
2003-11-26 20:22 ` Theodore Ts'o
2003-11-26 21:02 ` David S. Miller
2003-11-26 21:24 ` Jamie Lokier
2003-11-26 21:38 ` David S. Miller
2003-11-26 23:43 ` Jamie Lokier
2003-11-26 21:34 ` Arjan van de Ven
2003-11-26 22:58 ` Andi Kleen
2003-11-27 12:16 ` Ingo Oeser
2003-11-26 22:39 ` Andi Kleen
2003-11-26 22:46 ` David S. Miller
2003-11-26 0:15 Mr. BOFH
2003-11-26 2:30 ` David S. Miller
2003-11-26 5:41 ` Valdis.Kletnieks
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=16325.13797.417933.122067@charged.uio.no \
--to=trond.myklebust@fys.uio.no \
--cc=ak@suse.de \
--cc=davem@redhat.com \
--cc=linux-kernel@vger.kernel.org \
/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).