ThreadPoolingMixIn

[pavel.uvarov at gmail.com]

On Jun 2, 7:15 pm, Michael Ströder <mich... at stroeder.com> wrote:
> pavel.uva... at gmail.com wrote:
> > To benchmark this I used a simple tcp server which writes a small
> > (16k)
> > string to the client and closes the connection.
>
> Just a general note: When benchmarking such a network service it would
> be valuable to see benchmark results for several data sizes. I'd expect
> better numbers for a ThreadPoolingMixIn when there are more requests
> with smaller data size.
>
> Ciao, Michael.

Here are benchmarks for FreeBSD 6.2, amd64

packet_size         x         y
          0    499.57   1114.54
       1024    499.29   1130.02
       3072    500.09   1119.14
       7168    498.20   1111.76
      15360    499.29   1086.73
      31744    500.04   1036.46
      64512    499.43    939.60
     130048    499.28    737.44
     261120    498.04    499.03
     523264    307.54    312.04
    1047552    173.57    185.32
    2096128     93.61     94.39

x = ThreadingMixIn replies/s
y = ThreadPoolingMixIn replies/s