Hi Ilya,

>> Tuning the per EMC insertion probability per port based on detailed
>knowledge about the nature of traffic patterns seems a micro-optimization to
>me, which might be helpful in very controlled setups e.g. in synthetic
>benchmarks, but very hard to apply in more general use cases, such as
>vSwitch in OpenStack, where the entity (Nova compute) configuring the
>vhostuser VM ports has no knowledge at all about traffic characteristics.
>>
>> The nice property of the probabilistic EMC insertion is that flows with more
>traffic have a higher chance of ending up in the EMC than flows with lower
>traffic. In your case the few big encapsulated flows from the VM should have
>a higher chance to make it into the EMC than the many smaller individual
>flows into the VM and thus automatically get the bulk of EMC hits.
>>
>> Do you have empirical data that shows that this effect is not sufficient and
>performance can be significantly improved by per-port probabilities?
>>
>> In any case I would request to keep the global configuration option and only
>add the per-port option to override the global probability if wanted.
>>
>
>+1 for backwards compatibility by keeping the global config.

Thanks for this patch. 
I proposed a similar approach as incremental addition when the EMC probabilistic
insertion patch was upstreamed. My concern then was as it's a global config all 
the
PMD threads and ports would be affected. This was also discussed in one of the 
community calls then.

The general feedback was, though it sounds helpful in lab scenarios where the 
user has
pre knowledge of traffic, number of VMs, Phy and vhostuser ports , it may be 
not be the 
case in OpenStack deployments. The OpenStack folks mentioned that this kind of 
optimizations
can't be easily used in their deployments.

Regards,
Bhanuprakash. 
_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to