RE: [Xen-ia64-devel] [PATCH] [Resend]Enable hash vtlb

["Magenheimer, Dan (HP Labs Fort Collins)" <dan.magenheimer@xxxxxx>]

> I wonder if the time command is appropriate for measuring
> performance in a domU?  Are we sure the "real" component
> is measuring elapsed wall clock time?  If not, perhaps
> "time" is not accounting for time spent in the hypervisor
> and time spent in dom0 (e.g. backend drivers).
> 
> In all my past measurements, I've used "date +%s" before
> and after and subtracted the difference.

FYI, I did a preliminary test and found that "time" and
"date +%s" are yielding essentially the same result for dom0,
even with dom0 also doing Linux builds.  So ignore that
question.

However, I did see widely varying time results for domU,
varying in some cases by more than 10% (yes, I ignored
the builds that ended with "gcc segmentation fault" and
the first build). Are others seeing a wide variance also?

Dan

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel