From mboxrd@z Thu Jan  1 00:00:00 1970
From: Eric Dumazet <dada1-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
Subject: Re: [Bug #11308] tbench regression on each kernel release from	2.6.22
 -&gt; 2.6.28
Date: Fri, 21 Nov 2008 09:51:32 +0100
Message-ID: <49267694.1030506@cosmosbay.com>
References: <1ScKicKnTUE.A.VxH.DIHIJB@chimera> <NjF0-fuClJC.A.73B.cLHIJB@chimera> <20081117090648.GG28786@elte.hu> <Pine.LNX.4.64.0811191341570.23502@quilx.com> <Pine.LNX.4.64.0811201727070.9089@quilx.com> <20081121083044.GL16242@elte.hu>
Mime-Version: 1.0
Content-Transfer-Encoding: QUOTED-PRINTABLE
Return-path: <kernel-testers-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
In-Reply-To: <20081121083044.GL16242-X9Un+BFzKDI@public.gmane.org>
Sender: kernel-testers-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
List-ID: <kernel-testers.vger.kernel.org>
Content-Type: text/plain; charset="iso-8859-1"; format="flowed"
To: Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>
Cc: Christoph Lameter <cl-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>, "Rafael J. Wysocki" <rjw-KKrjLPT3xs0@public.gmane.org>, Linux Kernel Mailing List <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>, Kernel Testers List <kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>, Mike Galbraith <efault-Mmb7MZpHnFY@public.gmane.org>, Peter Zijlstra <a.p.zijlstra-/NLkJaSkS4VmR6Xm/wNWPw@public.gmane.org>, "David S. Miller" <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>

Ingo Molnar a =E9crit :
> * Christoph Lameter <cl-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org> wrote:
>=20
>> hmmm... Well we are almost there.
>>
>> 2.6.22:
>>
>> Throughput 2526.15 MB/sec 8 procs
>>
>> 2.6.28-rc5:
>>
>> Throughput 2486.2 MB/sec 8 procs
>>
>> 8p Dell 1950 and the number of processors specified on the tbench=20
>> command line.
>=20
> And with net-next we might even be able to get past that magic limit?=
=20
> net-next is linus-latest plus the latest and greatest networking bits=
:
>=20
>  $ cat .git/config
>=20
>  [remote "net-next"]
> 	url =3D git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next=
-2.6.git
> 	fetch =3D +refs/heads/*:refs/remotes/net-next/*
>=20
> ... so might be worth a test. Just to satisfy our curiosity and to=20
> possibly close the entry :-)
>=20

Well, bits in net-next are new stuff for 2.6.29, not really regression =
fixes,
but yes, they should give nice tbench speedups.


Now, I wish sockets and pipes not going through dcache, not tbench affa=
ir
of course but real workloads...

running 8 processes on a 8 way machine doing a=20

for (;;)
	close(socket(AF_INET, SOCK_STREAM, 0));

is slow as hell, we hit so many contended cache lines ...

ticket spin locks are slower in this case (dcache_lock for example
is taken twice when we allocate a socket(), once in d_alloc(), another =
one
in d_instantiate())