Hi Marcelo, On Tue, Feb 15, 2011 at 18:16, Marcelo Tosatti <mtosatti@xxxxxxxxxx> wrote: > On Sun, Feb 13, 2011 at 03:03:40PM +0200, Avi Kivity wrote: >> On 02/13/2011 04:07 AM, Ruben Kerkhof wrote: >> >And tonight we had another one of those errors we had a few weeks ago: >> > >> >2011-02-13T02:56:28.694496+01:00 phy005 kernel: EPT: Misconfiguration. >> >2011-02-13T02:56:28.694908+01:00 phy005 kernel: EPT: GPA: 0x2edff000 >> >> This GPA indexes into the 511th entry of the spte. ÂMarcelo, does >> this remind you of https://bugzilla.kernel.org/show_bug.cgi?id=27052 >> by any chance? > > This and the others reported. So yes, it looks something is corrupting > memory. Ruben, you can try to boot with slub_debug=ZFPU kernel option. Sure, but not for a while, I'm first moving all my customers of this machine. We've had to reboot it like 5 or 6 times in the last couple of weeks. As soon as that's done I'm going to test the hell out of it. Now that we moved a few of the vm's we don't see any oopses, so it could either be that it only triggers under load, or there's a specific guest which is triggering it. > Is there any reason for not upgrading to FC14? I haven't had a reason to upgrade yet, all our other machines are running fine, using the same kernel. Plus I'm still finding lots of issues unrelated to kvm on F14, broken ssh in combination with openldap, ipmi bugs, selinux policy etc. Next to that it takes a lot of time to test all our images etc. I'll probably skip the F14 kernel and go straight to 2.638, since that should bring significant improvements like THP, async pagefaults etc. Kind regards, Ruben -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
