Re: [Xen-devel] [PATCH] SEDF: avoid gathering vCPU-s on pCPU0

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 02.03.13 at 04:44, Ian Campbell <ian.campbell@xxxxxxxxxx> wrote:
> On Fri, 2013-03-01 at 15:35 +0000, Jan Beulich wrote:
>> The introduction of vcpu_force_reschedule() in 14320:215b799fa181 was
>> incompatible with the SEDF scheduler: Any vCPU using
>> VCPUOP_stop_periodic_timer (e.g. any vCPU of half way modern PV Linux
>> guests) ends up on pCPU0 after that call. Obviously, running all PV
>> guests' (and namely Dom0's) vCPU-s on pCPU0 causes problems for those
>> guests rather sooner than later.
>> 
>> So the main thing that was clearly wrong (and bogus from the beginning)
>> was the use of cpumask_first() in sedf_pick_cpu(). It is being replaced
>> by a construct that prefers to put back the vCPU on the pCPU that it
>> got launched on.
>> 
> 
> Is this change at all related to the long standing failure to boot with
> sedf in the test harnesss?

Yes, very likely. It was looking at the logs (where all Dom0 vCPU-s
were similarly running on pCPU0) plus immediately seeing a hang
when trying it out that prompted me to finally look into the issue.

Jan


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