From: "David S. Miller" <davem@redhat.com>
To: cfriesen@nortelnetworks.com
Cc: terje.eggestad@scali.com, linux-kernel@vger.kernel.org,
netdev@oss.sgi.com, linux-net@vger.kernel.org
Subject: Re: anyone ever done multicast AF_UNIX sockets?
Date: Mon, 03 Mar 2003 09:56:41 -0800 (PST) [thread overview]
Message-ID: <20030303.095641.87696857.davem@redhat.com> (raw)
In-Reply-To: <3E6399F1.10303@nortelnetworks.com>
From: Chris Friesen <cfriesen@nortelnetworks.com>
Date: Mon, 03 Mar 2003 13:07:45 -0500
Suppose I have a process that waits on UDP packets, the unified local
IPC that we're discussing, other unix sockets, and stdin. It's awfully
nice if the local IPC can be handled using the same select/poll
mechanism as all the other messaging.
So use UDP, you still haven't backed up your performance
claims. Experiment, set the SO_NO_CHECK socket option to
"1" and see if that makes a difference performance wise
for local clients.
But if performance is "so important", then you shouldn't really be
shying away from the shared memory suggestion and nothing is going to
top that (it eliminates all the copies, using flat out AF_UNIX over
UDP only truly eliminates some header processing, nothing more, the
copies are still there with AF_UNIX).
next prev parent reply other threads:[~2003-03-03 17:56 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-02-27 20:09 anyone ever done multicast AF_UNIX sockets? Chris Friesen
2003-02-27 22:21 ` Greg Daley
2003-02-28 13:33 ` jamal
2003-02-28 14:39 ` Chris Friesen
2003-03-01 3:18 ` jamal
2003-03-02 6:03 ` Chris Friesen
2003-03-02 14:11 ` jamal
2003-03-03 18:02 ` Chris Friesen
2003-03-03 12:51 ` Terje Eggestad
2003-03-03 12:35 ` David S. Miller
2003-03-03 17:09 ` Chris Friesen
2003-03-03 16:55 ` David S. Miller
2003-03-03 18:07 ` Chris Friesen
2003-03-03 17:56 ` David S. Miller [this message]
2003-03-03 19:11 ` Chris Friesen
2003-03-03 18:56 ` David S. Miller
2003-03-03 19:42 ` Terje Eggestad
2003-03-03 21:32 ` Chris Friesen
2003-03-03 23:38 ` Terje Eggestad
2003-03-03 19:39 ` Terje Eggestad
2003-03-03 22:29 ` Chris Friesen
2003-03-03 23:29 ` Terje Eggestad
2003-03-04 2:38 ` jamal
[not found] <3E5E7081.6020704@nortelnetworks.com.suse.lists.linux.kernel>
[not found] ` <20030228083009.Y53276@shell.cyberus.ca.suse.lists.linux.kernel>
[not found] ` <3E5F748E.2080605@nortelnetworks.com.suse.lists.linux.kernel>
[not found] ` <20030228212309.C57212@shell.cyberus.ca.suse.lists.linux.kernel>
[not found] ` <3E619E97.8010508@nortelnetworks.com.suse.lists.linux.kernel>
[not found] ` <20030302081916.S61365@shell.cyberus.ca.suse.lists.linux.kernel>
[not found] ` <3E6398C4.2020605@nortelnetworks.com.suse.lists.linux.kernel>
2003-03-03 18:18 ` Andi Kleen
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=20030303.095641.87696857.davem@redhat.com \
--to=davem@redhat.com \
--cc=cfriesen@nortelnetworks.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-net@vger.kernel.org \
--cc=netdev@oss.sgi.com \
--cc=terje.eggestad@scali.com \
/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).