Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Dario Faggioli
On Wed, 2016-05-18 at 12:03 -0600, Tony S wrote: > On Wed, May 18, 2016 at 11:59 AM, Tony S > wrote: > > On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky > > wrote: > > > Tony narrowed the problem down to update_curr() where vruntime is > > >

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Dario Faggioli
On Wed, 2016-05-18 at 12:03 -0600, Tony S wrote: > On Wed, May 18, 2016 at 11:59 AM, Tony S > wrote: > > On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky > > wrote: > > > Tony narrowed the problem down to update_curr() where vruntime is > > > calculated, based on runqueue's clock_task value.

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Tony S
On Wed, May 18, 2016 at 11:59 AM, Tony S wrote: > On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky > wrote: >> On 05/18/2016 12:10 PM, Dario Faggioli wrote: >>> On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: On 18/05/16 16:46,

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Tony S
On Wed, May 18, 2016 at 11:59 AM, Tony S wrote: > On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky > wrote: >> On 05/18/2016 12:10 PM, Dario Faggioli wrote: >>> On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: On 18/05/16 16:46, Boris Ostrovsky wrote: > > Won't we be

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Tony S
On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky wrote: > On 05/18/2016 12:10 PM, Dario Faggioli wrote: >> On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: >>> On 18/05/16 16:46, Boris Ostrovsky wrote: Won't we be accounting for stolen cycles twice

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Tony S
On Wed, May 18, 2016 at 11:20 AM, Boris Ostrovsky wrote: > On 05/18/2016 12:10 PM, Dario Faggioli wrote: >> On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: >>> On 18/05/16 16:46, Boris Ostrovsky wrote: Won't we be accounting for stolen cycles twice now --- once from

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Boris Ostrovsky
On 05/18/2016 12:10 PM, Dario Faggioli wrote: > On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: >> On 18/05/16 16:46, Boris Ostrovsky wrote: >>> >>> Won't we be accounting for stolen cycles twice now --- once from >>> steal_account_process_tick()->steal_clock() and second time from >>>

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Boris Ostrovsky
On 05/18/2016 12:10 PM, Dario Faggioli wrote: > On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: >> On 18/05/16 16:46, Boris Ostrovsky wrote: >>> >>> Won't we be accounting for stolen cycles twice now --- once from >>> steal_account_process_tick()->steal_clock() and second time from >>>

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Dario Faggioli
On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: > On 18/05/16 16:46, Boris Ostrovsky wrote: > >  > > Won't we be accounting for stolen cycles twice now --- once from > > steal_account_process_tick()->steal_clock() and second time from > > do_stolen_accounting()? > Uuh, yes. > > I guess I

Re: [Xen-devel] [PATCH] xen: add steal_clock support on x86

2016-05-18 Thread Dario Faggioli
On Wed, 2016-05-18 at 16:53 +0200, Juergen Gross wrote: > On 18/05/16 16:46, Boris Ostrovsky wrote: > >  > > Won't we be accounting for stolen cycles twice now --- once from > > steal_account_process_tick()->steal_clock() and second time from > > do_stolen_accounting()? > Uuh, yes. > > I guess I