FreeBSD Crashes with AMD
bakul at BitBlocks.com
Wed Jan 7 01:21:38 PST 2004
> > for example,
> > http://www.anime.net/~goemon/linux-ecc/
> > Though, not all are built well enough.
> Hmm, well I am very suprised to see the Via VT400 in there - I can't see
> anything on the spec page for it that says it supports ECC, and the manual
> for the KT400 board doesn't say explicitly that ECC is supported.
I haven't checked the veracity of information on that page.
Also see tomsHardware site. My point was ECC systems are
available and not too expensive anymore. But you'd have to
check a vendor's claim before buying.
> It would be nice, but there are patches out there, grab them, clean them up
> and submit them :)
If anyone else gets there before me I wouldn't be upset! But
seriously, while I understand someone has to sign up for it,
a server class OS needs to have ecc support. You can hand
out such jobs the next time someone new asks how they can
help. But you'd have to clearly specify the task (a man page
is usually sufficient).
> I just thought my idea was pretty cute, it would also be nice to say to people
> with mystery SIGSEGV's that the break into the loader type 'memtest' and see
> if they get errors :)
It was creative alright!
My experience has been that memtest like tests do not help
with nasty, marginal power/timing related errors that only up
on a heavily loaded multiuser os. Start a few compiles,
finds, pure number crunching programs, throw in a few crashme
kind of tests and see how well things stand up. Then run the
same load at highest/lowest rated temperatures and for 24
hours or more.
More information about the freebsd-current