Re: [Xen-devel] [PATCH 00/19] Assorted fixes and improvements to Credit2

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 20.06.16 at 13:43, <dario.faggioli@xxxxxxxxxx> wrote:
> On Mon, 2016-06-20 at 01:43 -0600, Jan Beulich wrote:
>> > 
>> > > 
>> > > > 
>> > > > On 17.06.16 at 19:32, <dario.faggioli@xxxxxxxxxx> wrote:
>> > > -------------------------------------|---------------------------------|
>> > > Xen build, high VM load, with noise | Iperf, high VM load, with noise |
>> > > -------------------------------------|---------------------------------|
>> > >            runq=core   runq=socket  |           runq=core runq=socket |
>> > > baseline     41.466       30.630    | baseline    20.333     20.633   |
>> > > patched      36.840       29.080    | patched     19.967     21.000   |
>> > > =======================================================================|
>> > Which, summarizing, means:
>> >  * as far as Credit2 is concerned,  applying this series and using
>> > runq=socket
>> >    is what _ALWAYS_ provides the best results.
>> Always? What about the increase on far the right side of the above
>> table fragment? It's not a big change, but anyway.
>> 
> Not sure I follow. By 'far the right side' you mean the results of
> "Iperf, high VM load, with noise"?
> 
> If yes, the 'patched' and 'runq=socket' element shows the highest
> value, which in this case is a good thing, because this is Iperf and
> the number is the total throughput in Gbps, and the higher it is, the
> better.

Oh, I see. You certainly said so somewhere in the description;
it's not the first time finding lower-is-better numbers right next
to higher-is-better managed to confuse me.

Jan


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