Re: MPI benchmark performance gap between native linux anddomU

[xuehai zhang <hai@cs.uchicago.edu>]

Jose,

Thank you so much for your valueable information.

>   I guess I overlooked the rates you reported in your post.
>   Looking now at your rates carefully I got somewhat confused. When you
> say MB/sec do you mean Megabyte/sec or Migabit/sec? 

It is Megabyte/sec (2^20 bytes)

> In any case these
> are much lower rates than in our case (we were using a gigabit network).
> Now, I am starting to think that your problem might be different than
> ours, but it does not hurt to try changing the advertised window, just
> in case.

I will try your suggestion and sent out update tomorrow morning.

>   Also, the numbers your report are inconsistent. You mention that your
> network is 10 MB/s, and that native linux achieve 14.9 MB/s. How is it
> possible to achieve a throughput higher than the network bandwidth?
> Could you please clarify?

Yes, it is a little confusing. It is due to the caculation of SendRecv's throughput. If you take a 
look at the PMB user manual (following the link in my previous email), the throughput is defined as 
2X/1.048567/time (time is latency). So, it is a weighted throughput and could go beyond 10MB/s, 
which is the max bandwidth of the network.

Thanks.

Xuehai