PLEASE TEST: IPI deadlock avoidance patch
Robert Watson
rwatson at freebsd.org
Thu Aug 26 08:52:46 PDT 2004
On Thu, 26 Aug 2004, Daniel Eriksson wrote:
> Craig Boston wrote:
>
> > Just a follow-up to my off-list message and another data point, with
> > this patch I no longer get deadlocks, however I now get random data
> > corruption.
>
> Me too!
>
> I've observed very strange data corruption on a filesystem exported via
> Samba from a dual P3/700 running with the IPI deadlock patch. About 10%
> is all files saved to the share while I had SMP enabled seems to be
> corrupt in one way or another.
Could you be more specific about "one way" or "another"? Specifically,
are you observing files that contain unexpected garbage, unexpected
regions of ASCII 0, unexpected contents of another file, etc? If it's
possible to narrow it down further, using hexdump, is it possible to
determine whether corruption begins and ends on page of file block
boundaries?
Also, is it possible for you to test whether you can trigger the
corruption solely through remote access via Samba, and not through the use
of other local programs and applications on the file system?
Robert N M Watson FreeBSD Core Team, TrustedBSD Projects
robert at fledge.watson.org Principal Research Scientist, McAfee Research
More information about the freebsd-current
mailing list