[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [xen-unstable test] 88047: regressions - FAIL



>>> On 01.04.16 at 16:56, <Ian.Jackson@xxxxxxxxxxxxx> wrote:
> Dario Faggioli writes ("Re: [Xen-devel] [xen-unstable test] 88047: 
> regressions - 
> FAIL"):
>> On Fri, 2016-04-01 at 07:44 -0600, Jan Beulich wrote:
>> > Might it be worth trying whether that's a deep C-state issue (by
>> > temporarily limiting their use of deep C states)?
> 
> I'm happy to try this.
> 
>> IIRC, it's the box(es) with the weird NUMA setup... something about
>> nodes without any memory:
> 
> Right.
> 
>> Not that I see how this could cause the long latencies / timeouts, though... 
> :-/
>> 
>> In any case, I think Jan's C states suggestion is worth a shot.
> 
> Forgive my ignorance, but how would I do that ?

As a first shot, disable them altogether by "max_cstate=1" on the
hypervisor command line. If that helps, we can bi-sect deeper
states as well as see whether there's a difference between the two
idle drivers.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.