>> I did a comparison test on 2.4.17, 2.5.25 stock kernels and on 2.5.25
>> with NAPI enabled e1000 driver using netperf3, tcp_stream 1 adapter
>> test using UNI kernels. The test setup/results can be found at:
>>
http://www-124.ibm.com/developerworks/opensource/linuxperf/netperf/results/july_02/netperf2.5.25results.htm
>On which machine(s) do you actually test the kernels? Source machine?
>Destination machine? Or both?
I am just catching up with my mail. Sorry about that. I don't think
I understand your question completely. Let me answer, if I don't make
it clear ask me again.
The client and the server systems have the same level kernels. The CPU
utilization collected at server end is used to derive the throughput
scaled to CPU. The throughput for tcp_stream reflects the rate of
transmits at the client and the rate of receives at the server.
Regards,
Mala
Mala Anand
IBM Linux Technology Center - Kernel Performance
E-mail:manand@us.ibm.com
http://www-124.ibm.com/developerworks/opensource/linuxperf
http://www-124.ibm.com/developerworks/projects/linuxperf
Phone:838-8088; Tie-line:678-8088
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Sep 15 2002 - 22:00:28 EST