Date: Mon, 21 Feb 2005 11:47:51 -0800 From: Kris Kennaway <kris@obsecurity.org> To: Kris Kennaway <kris@obsecurity.org> Cc: sparc64@FreeBSD.org Subject: Re: System clock died on e420r Message-ID: <20050221194750.GA49363@xor.obsecurity.org> In-Reply-To: <20050214230635.GA86332@xor.obsecurity.org> References: <20050214203742.GA46345@xor.obsecurity.org> <37395.1108419291@critter.freebsd.dk> <20050214230635.GA86332@xor.obsecurity.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--M9NhX3UHpAaciwkO Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Feb 14, 2005 at 03:06:35PM -0800, Kris Kennaway wrote: > On Mon, Feb 14, 2005 at 11:14:51PM +0100, Poul-Henning Kamp wrote: > >=20 > > If hardclock dies, timecounters (like much else) suffers. >=20 > Surely, so why is it happening and how can it be fixed? :) >=20 > jhb suspected there might be unserialized access to the time counter > on sparc64. This doesn't explain the i386 problems, but they could be > related to other recent commits. Note that the only problems I've > seen so far are on SMP machines. It happened again on a quad-cpu e450 machine after updating it from RELENG_5 from December to top of RELENG_5. What sparc64-related changes have recently been merged that could cause this? Kris --M9NhX3UHpAaciwkO Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (FreeBSD) iD8DBQFCGjrmWry0BWjoQKURAkLNAKCDhASOmZWh5JK7/CKGUdhT31tXYwCgzI6Q Nd6dpBv+MWoGolR4CTmiG2U= =IXXQ -----END PGP SIGNATURE----- --M9NhX3UHpAaciwkO--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050221194750.GA49363>