From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gerry Reno Subject: Re: Cannot load latest 2.6.32.10 kernel on AMD quad-core Date: Thu, 29 Apr 2010 12:50:58 -0400 Message-ID: <4BD9B8F2.2000409@verizon.net> References: <4BD461A2.8040502@verizon.net> <4BD4BF06.7040905@verizon.net>, <4BD4F608.5000808@verizon.net> <4BD5129D.2020105@verizon.net>, <20100426200412.GK17817@reaktio.net> <4BD6051E.2000208@verizon.net>, <20100426215221.GP17817@reaktio.net> <4BD6237F.8090809@verizon.net>, <4BD62910.3070602@verizon.net> <4BD6508C.3070500@verizon.net>, <20100427091528.GV17817@reaktio.net> <4BD72059.2090503@verizon.net>, <4BD98F7F.2060809@verizon.net> , <4BD99BDB.4090906@verizon.net> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1365363729==" Return-path: In-reply-to: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org This is a multi-part message in MIME format. --===============1365363729== Content-type: multipart/alternative; boundary=------------020603060301030807070307 This is a multi-part message in MIME format. --------------020603060301030807070307 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit On 04/29/2010 11:11 AM, Mike Viau wrote: > Thu, 29 Apr 2010 10:46:51 -0400 wrote: > > >> I've been changing various settings trying to figure out what > is the > >> problem and today after a very long wait (> 5 min) I was able > to see a > >> login prompt. But things are not well. During the boot I now see: > >> XENBUS: Unable to read cpu state. > >> XENBUS: Unable to read cpu state. > >> XENBUS: Unable to read cpu state. > >> XENBUS: Unable to read cpu state. > >> > > > I get these message on boot too (note there is not long delay to > get these messages but they do appear closer to the end of my boot > up sequence). FYI, it has not affected XEN for as far as I could see. > > Mike, what processor are you running on? > > > > A fairly recent Intel(R) Core(TM) i7 CPU 860 @ 2.80GHz > > processor : 0 > vendor_id : GenuineIntel > cpu family : 6 > model : 30 > model name : Intel(R) Core(TM) i7 CPU 860 @ 2.80GHz > stepping : 5 > cpu MHz : 2800.132 > cache size : 8192 KB > fpu : yes > fpu_exception : yes > cpuid level : 11 > wp : yes > flags : fpu de tsc msr pae cx8 apic sep mtrr cmov pat > clflush acpi mmx fxsr sse sse2 ss ht syscall nx lm constant_tsc > rep_good nonstop_tsc aperfmperf pni est ssse3 cx16 sse4_1 sse4_2 > popcnt hypervisor lahf_lm ida > bogomips : 5600.26 > clflush size : 64 > cache_alignment : 64 > address sizes : 36 bits physical, 48 bits virtual > power management: > > > Intel processors do not seem to have the same problem for some reason. I did see though a large number of "soft lockup" bugs reported for Lucid Lynx recently (2.6.32-21). The problem I'm seeing is just with the latest pv_ops dom0 kernel on AMD hardware. Before I tore down the previous Xen installation in order to load 4.0.0-rc8 I was running 2.6.31.6 and xen 3.4.1 which worked with the exception of the checksumming problem which turned out to be a blocker. But now something has changed between 2.6.31.6 and 2.6.32.10 that seriously affected AMD processor hardware with a "soft lockup" problem. -Gerry --------------020603060301030807070307 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit On 04/29/2010 11:11 AM, Mike Viau wrote:
Thu, 29 Apr 2010 10:46:51 -0400 <greno@verizon.net> wrote:

>> I've been changing various settings trying to figure out what is the
>> problem and today after a very long wait (> 5 min) I was able to see a
>> login prompt. But things are not well. During the boot I now see:
>> XENBUS: Unable to read cpu state.
>> XENBUS: Unable to read cpu state.
>> XENBUS: Unable to read cpu state.
>> XENBUS: Unable to read cpu state.
>>

> I get these message on boot too (note there is not long delay to get these messages but they do appear closer to the end of my boot up sequence). FYI, it has not affected XEN for as far as I could see.

Mike, what processor are you running on?



A fairly recent Intel(R) Core(TM) i7 CPU         860  @ 2.80GHz

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 30
model name      : Intel(R) Core(TM) i7 CPU         860  @ 2.80GHz
stepping        : 5
cpu MHz         : 2800.132
cache size      : 8192 KB
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
flags           : fpu de tsc msr pae cx8 apic sep mtrr cmov pat clflush acpi mmx fxsr sse sse2 ss ht syscall nx lm constant_tsc rep_good nonstop_tsc aperfmperf pni est ssse3 cx16 sse4_1 sse4_2 popcnt hypervisor lahf_lm ida
bogomips        : 5600.26
clflush size    : 64
cache_alignment : 64
address sizes   : 36 bits physical, 48 bits virtual
power management:



Intel processors do not seem to have the same problem for some reason.  I did see though a large number of "soft lockup" bugs reported for Lucid Lynx recently (2.6.32-21).

The problem I'm seeing is just with the latest pv_ops dom0 kernel on AMD hardware.  Before I tore down the previous Xen installation in order to load 4.0.0-rc8 I was running 2.6.31.6 and xen 3.4.1 which worked with the exception of the checksumming problem which turned out to be a blocker.  But now something has changed between 2.6.31.6 and 2.6.32.10 that seriously affected AMD processor hardware with a "soft lockup" problem.

-Gerry


--------------020603060301030807070307-- --===============1365363729== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel --===============1365363729==--