On 3/9/15 21:25 , Ian Collins via smartos-discuss wrote:
> Ian Collins via smartos-discuss wrote:
>> Robert Mustacchi via smartos-discuss wrote:
>>> Hmm, so there are threads that are actively running inside the VM. What
>>> does kvmstat show here?
>> # kvmstat 30
>>      pid vcpu |  exits :  haltx   irqx  irqwx    iox  mmiox |   irqs
>> emul   eptv
>>    11445    0 |     51 :      7      1      1      9      1 | 8    
>> 31      0
>>    11445    1 |     50 :      6      1      0      8      1 | 7    
>> 33      0
>>    11583    0 |      5 :      1      0      0      0      0 | 1     
>> 4      0
>>    11583    1 |      8 :      1      0      0      0      0 | 1     
>> 6      0
>>    11583    2 |      5 :      1      0      0      0      0 | 1     
>> 4      0
>>    11583    3 |      6 :      1      0      0      0      0 | 1     
>> 4      0
>>    11583    4 |      5 :      1      0      0      0      0 | 1     
>> 4      0
>>    11583    5 |     12 :      2      0      0      0      0 | 2    
>> 10      0
>>    11583    6 |      6 :      1      0      0      0      0 | 1     
>> 4      0
>>    11583    7 |      7 :      1      0      0      0      0 | 1     
>> 5      0
>>    11606    0 |    143 :      0    123      0     20      0 | 0     
>> 0      0
>>    11606    1 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    2 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    3 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    4 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    5 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    6 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>    11606    7 |      0 :      0      0      0      0      0 | 0     
>> 0      0
>>
>> 11606 is the stuck guest.
>>
> 
> Robert, is there any more information you would like from me before I
> restart this guest?
> 

No, I don't have anything that I know of off hand that'd be good to see
here. Unfortunately, it seems like the guest has managed to get to a
state where only one CPU is running for some reason and from the
outside, it's not immediately obvious what got us here.

The fastest way to make forward progress here would probably be to try
to reproduce this with an illumos guest so we can inject an nmi via
vmadm and have that hopefully help us understand what the state of the
guest was, from which we can start backtracking to understand what might
be on the scene.

Robert


-------------------------------------------
smartos-discuss
Archives: https://www.listbox.com/member/archive/184463/=now
RSS Feed: https://www.listbox.com/member/archive/rss/184463/25769125-55cfbc00
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=25769125&id_secret=25769125-7688e9fb
Powered by Listbox: http://www.listbox.com

Reply via email to