Date: Wed, 9 Jan 2013 17:38:39 -0800 (PST) From: Barney Cordoba <barney_cordoba@yahoo.com> To: freebsd-net@freebsd.org Subject: Re: To SMP or not to SMP Message-ID: <1357781919.7451.YahooMailClassic@web121602.mail.ne1.yahoo.com> In-Reply-To: <1357754924.51744.YahooMailClassic@web121601.mail.ne1.yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--- On Wed, 1/9/13, Barney Cordoba <barney_cordoba@yahoo.com> wrote:
> From: Barney Cordoba <barney_cordoba@yahoo.com>
> Subject: Re: To SMP or not to SMP
> To: "Mark Atkinson" <atkin901@gmail.com>
> Cc: freebsd-net@freebsd.org
> Date: Wednesday, January 9, 2013, 1:08 PM
>=20
>=20
> --- On Tue, 1/8/13, Mark Atkinson <atkin901@gmail.com>
> wrote:
>=20
> > From: Mark Atkinson <atkin901@gmail.com>
> > Subject: Re: To SMP or not to SMP
> > To: freebsd-net@freebsd.org
> > Date: Tuesday, January 8, 2013, 11:29 AM
> > -----BEGIN PGP SIGNED MESSAGE-----
> > Hash: SHA1
> >=20
> > On 01/07/2013 18:25, Barney Cordoba wrote:
> > > I have a situation where I have to run 9.1 on an
> old
> > single core
> > > box. Does anyone have a handle on whether it's
> better
> > to build a
> > > non SMP kernel or to just use a standard SMP build
> with
> > just the
> > > one core? Thanks.
> >=20
> > You can build a SMP kernel, but you'll get better
> > performance (in my
> > experience) with SCHED_4BSD on single cpu than with
> ULE.
> >=20
>=20
> I've tested the 2 schedulers on an SMP kernel with 1 core. I
> don't have
> a 1 core system to test with so I'm using an E5520
> with=A0 1 core enabled.
>=20
> Bridging a controlled test (curl-loader doing a web-load
> test with 100=20
> users that consistently generates 870Mb/s and 77Kpps, I see
> the following:
>=20
> top -SH
>=20
> ULE:
>=20
> idle: 74.85%
> kernel {em1 que} 17.68%
> kernel {em0 que} 5.86%
> httpd: .49%=A0=20
>=20
> 4BSD:
>=20
> idle: 70.95%
> kernel {em1 que} 18.07%
> kernel {em0 que} 4.44%
> httpd: .93%
>=20
> Note that the https is a monitor I'm running.
>=20
> so it appears that theres 7% of usage missing (all other
> apps show 0%
> usage).=20
>=20
> If i had to guess just looking at the numbers, it seems that
> 4BSD might=20
> do better with the interrupt level stuff, and not as good
> with user=20
> level context switching. I think they're close enough to
> stick with ULE
> so I can just use a stock kernel.
>=20
> One thing that bothers me is the idle sits at 100% when
> other tasks are=20
> registering values under light loads, so it's certainly not
> all that=20
> accurate.
>=20
> BC
Ok, thanks to J Baldwin's tip I got a NON-SMP kernel running with some
interesting results. Here's all 4 tests:
I've tested the 2 schedulers on an SMP kernel with 1 core. I don't have
a 1 core system to test with so I'm using an E5520 with 1 core enabled.
Bridging a controlled test (curl-loader doing a web-load test with 100=20
users that consistently generates 870Mb/s and 77Kpps, I see the following:
top -SH
ULE (SMP):
idle: 74.85%
kernel {em1 que} 17.68%
kernel {em0 que} 5.86%
httpd: .49% =20
4BSD (SMP):
idle: 70.95%
kernel {em1 que} 18.07%
kernel {em0 que} 4.44%
httpd: .93%
4BSD (NON-SMP):
idle: 72.95%
kernel {em1 que} 15.04%
kernel {em0 que} 6.10%
httpd: 1.17%
ULE (NON-SMP):
idle: 76.17%
kernel {em1 que} 16.99%
kernel {em0 que} 5.18%
httpd: 1.66%
A kernel with SMP off seems to be a bit more efficient. A better test would
be to have more stuff running, but Im about out of time on this project.
BC
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1357781919.7451.YahooMailClassic>