Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 24 Apr 2005 23:14:59 -0700
From:      Kris Kennaway <kris@obsecurity.org>
To:        Julian Elischer <julian@elischer.org>
Cc:        Kris Kennaway <kris@obsecurity.org>
Subject:   Re: FreeBSD 6 is coming too fast
Message-ID:  <20050425061459.GA33247@xor.obsecurity.org>
In-Reply-To: <426C6B1D.3040704@elischer.org>
References:  <20050424175543.71041.qmail@web51805.mail.yahoo.com> <20050424151517.O68772@lexi.siliconlandmark.com> <3822.216.177.243.38.1114385370.localmail@webmail.dnswatch.com> <20050425000459.GA28667@xor.obsecurity.org> <6.2.1.2.0.20050424204611.072105a0@64.7.153.2> <20050425010242.GA44110@xor.obsecurity.org> <6.2.1.2.0.20050424210422.03d22990@64.7.153.2> <20050425014453.GA59981@xor.obsecurity.org> <426C6B1D.3040704@elischer.org>

next in thread | previous in thread | raw e-mail | index | archive | help

--2oS5YaxWCcQjTEyO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Sun, Apr 24, 2005 at 08:59:25PM -0700, Julian Elischer wrote:
> Kris Kennaway wrote:
>=20
> >Measuring disk device performance (i.e. running a benchmark against
> >the bare device) and filesystem performance (writing to a filesystem
> >on the device) are very different things.
>=20
> I wish people would stop trying to deny that we have serious work in fron=
t=20
> of us to get the VFS and disk IO figures back to where they were before.
>=20
> there ARE slowdowns and I have seen it both with tests on teh basic=20
> hardware and throug the filesystems.  I don't know why this surproses=20
> people because we have still a lot of work to do in teh interrupt latency=
=20
> field for example, and I doubt that even PHK would say that there is no=
=20
> work left to do in geom.
> Where we are now is closing in on "feature complete". Now we need to=20
> profile and optimise.

OK, but note that I didn't deny anything, I only questioned whether
the OP was observing a real problem (he didn't mention disk I/O, or in
fact any specific claim) or whether it was a coloured perception based
on the (incorrect) assumption that gcc compilation speed was measuring
a performance loss in FreeBSD.

Kris

--2oS5YaxWCcQjTEyO
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (FreeBSD)

iD8DBQFCbIrjWry0BWjoQKURAixoAKDz6DJfBTaaJLHHjbM4b91epqu1JQCggy+w
c1zDPPELT9ZZUHZGrLq5wwo=
=1XB2
-----END PGP SIGNATURE-----

--2oS5YaxWCcQjTEyO--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050425061459.GA33247>