Re: [RFC] [PATCH] Optimize TCP sendmsg in favour of fast devices?

[Rick Jones <rick.jones2@hp.com>]

Krishna Kumar2 wrote:
>>Herbert Xu <herbert@gondor.apana.org.au> wrote on 01/29/2010 02:36:25 PM:
>>
>>
>>>I ran 5 serial netperf's with 16K and another 5 serial netperfs
>>>with 64K I/O sizes, and the aggregate result is:
>>>
>>>0. Driver unsets F_SG but sets F_GSO:
>>>      Original code with 16K: 19471.65
>>>      New code with 16K:      19409.70
>>>      Original code with 64K: 21357.23
>>>      New code with 64K:      22050.42
>>
>>OK this is more in line with what I was expecting, namely that
>>enabling GSO is actually beneficial even without SG.
>>
>>It would be good to get the CPU utilisation figures so we can
>>see the complete picture.
> 
> 
> Same 5 runs of single netperf's:
> 
> 0. Driver unsets F_SG but sets F_GSO:
>         Org (16K):      BW: 18180.71    SD: 13.485
>         New (16K):      BW: 18113.15    SD: 13.551
>         Org (64K):      BW: 21980.28    SD: 10.306
>         New (64K):      BW: 21386.59    SD: 10.447
> 
> 1. Driver unsets F_SG, and with GSO off
>         Org (16K):      BW: 10894.62    SD: 26.591
>         New (16K):      BW: 7262.10     SD: 35.340
>         Org (64K):      BW: 12396.41    SD: 23.357
>         New (64K):      BW: 7853.02     SD: 32.405
> 
> 
> 2. Driver unsets F_SG and uses ethtool to set GSO:
>         Org (16K):      BW: 18094.11    SD: 13.603
>         New (16K):      BW: 17952.38    SD: 13.743
>         Org (64K):      BW: 21540.78    SD: 10.771
>         New (64K):      BW: 21818.35    SD: 10.598

Just a slight change in service demand there...  For those unfamiliar, 
service demand in netperf is the microseconds of non-idle CPU time per 
KB of data transferred.  Smaller is better.

happy benchmarking,

rick jones