From: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
To: Pavel Machek <pavel@ucw.cz>
Cc: bert hubert <bert.hubert@netherlabs.nl>,
Andi Kleen <andi@firstfloor.org>,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: all syscalls initially taking 4usec on a P4? Re: nonblocking UDPv4 recvfrom() taking 4usec @ 3GHz?
Date: Sun, 25 Feb 2007 20:06:56 +0300 [thread overview]
Message-ID: <20070225170656.GA14698@2ka.mipt.ru> (raw)
In-Reply-To: <20070225104154.GA2045@elf.ucw.cz>
On Sun, Feb 25, 2007 at 11:41:54AM +0100, Pavel Machek (pavel@ucw.cz) wrote:
> > > I've done so, with some interesting results. Source on
> > > http://ds9a.nl/tmp/recvtimings.c - be careful to adjust the '3000' divider
> > > to your CPU frequency if you care about absolute numbers!
> > >
> > > These are two groups, each consisting of 10 consecutive nonblocking UDP
> > > recvfroms, with 10 packets preloaded. Reported is the number of microseconds
> > > per recvfrom call which yielded a packet:
> > >
> > > $ ./recvtimings
> > > 4.142333
> >
> > It can be recvfrom only problem - syscall overhead on my p4 (core duo,
> > debian testing) is bout 300 usec - to test I ran
>
> core duo is _not_ p4 class cpu; rsulets there will be very different.
Results nevertheless are the same.
Each syscall takes some time first (noticebly more than subsequent
calls), and that was a main problem for Bert.
Given the high load, recvfrom() can even take tens of microseconds
(although I can not provide a profile output yet, but I showed a data).
So, syscall overhead itself is very small no matter which type of the
CPU is used - athlon is about 300 nsec, via epia about 1.4 usec),
but the whole function can take quite a lot of time.
> Pavel
>
> --
> (english) http://www.livejournal.com/~pavelmachek
> (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
--
Evgeniy Polyakov
next prev parent reply other threads:[~2007-02-25 17:06 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-02-19 23:14 nonblocking UDPv4 recvfrom() taking 4usec @ 3GHz? bert hubert
2007-02-19 23:56 ` Stephen Hemminger
2007-02-20 8:04 ` bert hubert
2007-02-20 10:50 ` Andi Kleen
2007-02-20 16:27 ` all syscalls initially taking 4usec on a P4? " bert hubert
2007-02-20 16:41 ` Evgeniy Polyakov
2007-02-20 17:02 ` bert hubert
2007-02-20 17:11 ` Evgeniy Polyakov
2007-02-20 17:18 ` Evgeniy Polyakov
2007-02-21 11:06 ` Evgeniy Polyakov
2007-02-21 11:34 ` Andi Kleen
2007-02-20 18:42 ` Josef Sipek
2007-02-20 18:48 ` Evgeniy Polyakov
2007-02-20 19:33 ` bert hubert
2007-02-20 19:40 ` Benjamin LaHaise
2007-02-20 20:45 ` bert hubert
2007-02-20 21:02 ` Stephen Hemminger
2007-02-20 22:02 ` Rick Jones
2007-02-20 22:17 ` bert hubert
2007-02-20 22:22 ` Arjan van de Ven
2007-02-21 16:25 ` Chuck Ebbert
2007-02-20 22:46 ` Ian McDonald
2007-02-25 10:41 ` Pavel Machek
2007-02-25 17:06 ` Evgeniy Polyakov [this message]
2007-02-20 16:57 ` 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=20070225170656.GA14698@2ka.mipt.ru \
--to=johnpol@2ka.mipt.ru \
--cc=andi@firstfloor.org \
--cc=bert.hubert@netherlabs.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pavel@ucw.cz \
/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).