PLEASE TEST: IPI deadlock avoidance patch
Doug White
dwhite at gumbysoft.com
Thu Aug 26 11:20:28 PDT 2004
On Thu, 26 Aug 2004, Garance A Drosihn wrote:
> >Signal 6 is SIGABRT, which is usually intentional. You'd have to
> >check the output for a specific process that abended. I'd also
> >have to scan the make code for any abort() calls.
>
> I have not pinned this down yet, but I have determined that it is
> not related to the USE_KQUEUE `make'. It is only happening if I do
> several -j buildworlds in a row, and (at least so far) only if I
> also have the folding-at-home client running as a background task.
I guess I'll go run that client and beat up my testbox a bit :)
I'm suspecting the data corruption issue isn't directly caused by the IPI
fix, but rather it just unmasked an existing issue.
--
Doug White | FreeBSD: The Power to Serve
dwhite at gumbysoft.com | www.FreeBSD.org
More information about the freebsd-current
mailing list