AFAIK there is no support to adjust the number of cores used or the
cores frequency in runtime.
Not sure if there is full support to dynamically switch between polling
and interrupt mode, but I believe most of the infra is already there
(read below thread).
https://lists.fd.io/pipermail/vpp-dev/2017-January/003868.html
Thanks,
Sergio
On 30/08/2017 12:59, Tobias Sundqvist wrote:
Hi I guess the silence tells that there are no way of dynamically
scale the number of cores used by VPP when VPP already has started.
If anyone has any idea if it is dynamically possible to change the way
the cores is used just send me an email. Perhaps it could be possible
to assign a certain core to not poll the interface or something
similar, then the core would still be in use of VPP but the CPU load
would go down.
BR /Tobias
On 24 August 2017 at 10:36, Tobias Sundqvist
<tobias.sundqv...@tieto.com <mailto:tobias.sundqv...@tieto.com>> wrote:
Hi we are building an application that uses vpp and when I have
some questions that concerns multi core usage.
In the run that we are doing now we are using 4 cores and we use
some DPDK polling of an interface which makes the cpu load go 100%
on all cores. We are interested in energy consumption in the
application we are creating and would like to be able to scale up
and down the cpu usage during runtime.
Is it possible to dynamically change the number of cores used by
VPP or specify somehow which cores that are used for polling of an
certain interface during runtime?
During low and high traffic we would like to scale up and down the
amount of cores that is used.
If the polling is causing the cpu to go to 100% would it help
using Turboboost and Speedstep, would it actually lower the
frequency when the traffic is low?
BR /Tobias
_______________________________________________
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
_______________________________________________
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
