Re: [ovs-dev] [PATCH net-next v1 1/1] net: openvswitch: ovs_packet_cmd_execute put sw_flow mainbody in stack

[Eddy Tao]

More explanation to the meaning of performance data

>>Mode Iterations   Variance    Average

Iterations: the number of executions of the same test case (each 
iteration get a performance value of perf[n] )

Average:  sum of all execution and then divided by 'n_iterations'. Below 
is the pseudo code

               for (sum=0,i=0;i<iterations;i++) sum+= perf[i];

               average = sum/iterations

Variance: A percentage value describing the overall deviation of 
performance results from average. Below is the pseudo code

               for (deviation=0,i=0;i<iterations;i++) deviation+= 
square(perf[i] - average);

               variance = ((square_root(deviation/iterations)) * 
100)/average


On 2023/2/20 11:04, Eddy Tao wrote:
> Hi， Simon:
>
>     To have better visibility of the effect of the patch, i did 
> another test below
>
> Disabling data-path flow installation to steer traffic to slow path 
> only, thus I can observe the performance on slow path, where 
> ovs_packet_cmd_execute is extensively used
>
>
> Testing topology
>
>             |-----|
>       nic1--|     |--nic1
>       nic2--|     |--nic2
> VM1(16cpus) | ovs |   VM2(16 cpus)
>       nic3--|     |--nic3
>       nic4--|     |--nic4
>             |-----|
> 2 netperf client threads on each vnic
>
> netperf -H $peer -p $((port+$i)) -t TCP_STREAM  -l 60
> netperf -H $peer -p $((port+$i)) -t TCP_RR  -l 60 -- -R 1 -r 120,240
> netperf -H $peer -p $((port+$i)) -t TCP_CRR -l 60 -- -R 1 -r 120,240
>
>   Mode Iterations   Variance    Average
>
> TCP_STREAM     10      %3.83       1433 ==> before the change
> TCP_STREAM     10      %3.39       1504 ==> after  the change
>
> TCP_RR         10      %2.35      45145 ==> before the change
> TCP_RR         10      %1.06      47250 ==> after  the change
>
> TCP_CRR        10      %0.54      11310 ==> before the change
> TCP_CRR        10      %2.64      12741 ==> after  the change
>
>
> Considering the size and simplicity of the patch, i would say the 
> performance benefit is decent.
>
> Thanks
>
> eddy
>
>
> _______________________________________________
> dev mailing list
> dev@xxxxxxxxxxxxxxx
> https://mail.openvswitch.org/mailman/listinfo/ovs-dev