Re: Test results on Unisys ES7000 64x 256gb using unstablec/s 16693 on 3.2.0 Release Candidate

[Bill Burns <bburns@redhat.com>]

Bill Burns wrote:
> Keir Fraser wrote:
>> On 31/1/08 18:12, "Bill Burns" <bburns@redhat.com> wrote:
>>
>>> I instrumented read_pmtimer_count and it does get called a couple
>>> of times during startup and it returns an increasing value. I made
>>> no attempt to determine if the rate was correct.
>>>
>>> I also tried the 3.1.3 and 3.2.0 Hypervisors and they exhibit
>>> the same problem on the es7000.
>>>
>>> It's not clear if is this a platform specific problem
>>> or not. So far the only reports of the problem are on the
>>> es7000. So for now I am running the attached patch to
>>> avoid the pmtimer on es7000 only.
>> Fair enough, but obviously this does need to be fixed: while not understood
>> it could point to any amount of other badness or corruption happening in the
>> background that we simply have not yet discovered.
>>
>>  -- Keir
>>
> 
> 
> I am hoping to get some feedback on a similar large
> system. Limiting dom0 memory seems to be the standard
> operating procedure on large memory systems so if it's
> a common problem then it's being masked.
> 

Got a report on a non-es7000 failure as well. They did not
indicate the actual failure, but said it failed to boot.
They induced the failure by both increasing the value of the
dom0_mem arg and by removing the arg entirely. They did not try
clocksource, but I have aske them too. So we can't be sure
yet that it's the same thing. But I think odds are it is.

 Bill


>  Bill
> 
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel