Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 30 Sep 2006 14:39:06 -0400
From:      Kris Kennaway <kris@obsecurity.org>
To:        Paul Allen <pallen@ugcs.caltech.edu>
Cc:        freebsd-stable@freebsd.org, Craig Boston <craig@feniz.gank.org>, Kris Kennaway <kris@obsecurity.org>
Subject:   Re: CALL FOR TESTERS! [Re: 6.2 SHOWSTOPPER - em completely unusable on 6.2]
Message-ID:  <20060930183906.GA76658@xor.obsecurity.org>
In-Reply-To: <20060930060535.GA3467@riyal.ugcs.caltech.edu>
References:  <451AEB02.2090806@samsco.org> <002201c6e290$45ece980$b3db87d4@multiplay.co.uk> <451BD89F.8080203@samsco.org> <451C1F6D.2020302@mail.uni-mainz.de> <7.0.1.0.0.20060928152807.17bbe448@sentex.net> <451C271A.9040904@samsco.org> <20060930011904.GA62626@nowhere> <20060930013439.GB62626@nowhere> <20060930014242.GB42433@xor.obsecurity.org> <20060930060535.GA3467@riyal.ugcs.caltech.edu>

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

--gKMricLos+KVdGMg
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Fri, Sep 29, 2006 at 11:05:35PM -0700, Paul Allen wrote:
> >From Kris Kennaway <kris@obsecurity.org>, Fri, Sep 29, 2006 at 09:42:42P=
M -0400:
> > On Fri, Sep 29, 2006 at 08:34:39PM -0500, Craig Boston wrote:
> > > On Fri, Sep 29, 2006 at 08:19:04PM -0500, Craig Boston wrote:
> > > > On Thu, Sep 28, 2006 at 01:48:42PM -0600, Scott Long wrote:
> > > > > http://people.freebsd.org/~scottl/usb_fastintr_RELENG_6.diff
> > > >=20
> > > > At first glance it appeared to work, but I'm about to do some more
> > > > testing since I just discovered that I have to kldload something
> > > > (anything) first in order to reproduce the problem.  Weird.
> > >=20
> > > I can confirm that despite the other side effect I already mentioned,
> > > this patch does fix or at least mask the problem I'm seing with em (a=
nd
> > > probably usb).
> >=20
> > Which is odd since the hypothesis Scott was working on should have
> > shown up clearly in the mutex trace, but did not.
>=20
> But it is consistent with there being a beat-frequency problem with=20
> respect to the scheduler.  I think the number you really need is not
> how long giant was held but how long was spent waiting for it.

It also seemed to show that nothing was really waiting for it (the
cnt_* entries).

Kris

--gKMricLos+KVdGMg
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.5 (FreeBSD)

iD8DBQFFHrnJWry0BWjoQKURAqDhAKCfmFLkp/RP8zGIw+LK6U0ctNUB+QCbB/4x
1RhJiOxF1g0CwzF1Tf/Ab5w=
=uFXF
-----END PGP SIGNATURE-----

--gKMricLos+KVdGMg--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060930183906.GA76658>