On Thu, 30 Jun 2011, Glauber Costa wrote: > On 06/30/2011 09:59 AM, Eric B Munson wrote: > >On Thu, 30 Jun 2011, Avi Kivity wrote: > > > >>On 06/30/2011 12:56 AM, Eric B Munson wrote: > >>>My mail provider seems to have dropped patch 1 of the series so I can't reply > >>>directly to it, please add my Tested-by there as well. > >> > >>How did you test it then? > >> > > > >I built host and guest kernels with the patches and pinned a while(1) and the > >CPU thread from qemu to CPU 2 on the host. I then started the same while(1) > >process in guest and verified that I see ~50% steal time reported. > > > >I then built 2.6.39 (just the code I had present) on the guest and time it > >while it was competing with the while(1) on the host for CPU time. Next I > >built the guest kernel with STEAL_TIME=N and reran the kernel compile to make > >sure that there weren't any huge variations in performace. > > > >Eric > I think what Avi means is, it won't even compile without PATCH 1/9. > If you don't have it, how could you test it ? > It made it to several lkml archives.
Attachment:
signature.asc
Description: Digital signature
