Messages in this thread | | | Date | Mon, 31 Mar 2008 16:02:44 +0200 | From | Pavel Machek <> | Subject | Re: MCE going wild, 14 megs of this in the logs |
| |
On Sun 2008-03-30 16:57:53, Gene Heskett wrote: > Greetings; > Mar 30 16:46:42 coyote kernel: [469249.031832] MCE: The hardware reports a non > fatal, correctable incident occurred on CPU 0. > Mar 30 16:46:42 coyote kernel: [469249.031838] Bank 1: d400400000000152 > Mar 30 16:46:42 coyote kernel: [469249.031841] MCE: The hardware reports a non > fatal, correctable incident occurred on CPU 0. > Mar 30 16:46:42 coyote kernel: [469249.031844] Bank 2: d40040000000017a > > Its always the same 2 addresses reported, and every 15 seconds. So I have the > non-fatal part of MCE now turned off, & 2.6.24.4 rebuilding. > > I saw this once before, and a nearly round the clock run of memtest86 gave my > memory a clean bill. Processor is an XP-2800, biostar mainboard with NForce2 > chipset. Is this possibly a known artifact of this hardware?
Thats expected. If ECC can correct the problem, memtest will pass.
I had similar problems, and was told by AMD that I had cpu with bad L2 cache.
-- (english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
| |