[Scst-devel] [ofa-general] SRP/mlx4 interrupts throttling performance
Cameron Harr
cameron at harr.org
Fri Feb 27 11:56:31 PST 2009
Vladislav Bolkhovitin wrote:
>>
>> This is with 634. It's pretty bad:
>> 338316.44
>> 329698.04
>> 307972.7133
>> 345682.4733
>> 344165.08
>
> Definitely, you suffer from the system "tiring" effect. So, to get
> comparable results you should do measurements in a predefined state of
> the system, for instance just after boot, and in a row, i.e. one
> immediately after one.
I think you're right, that the system is getting "tired." I think I am
going to rest with the benchmarking for now though and just stick with
the latest code in trunk, noting that my "Test 4" reliably produces the
best results.
Cameron
More information about the general
mailing list