On 03/02/2016 07:20 PM, Steve Muckle wrote: > Why does the frequency value not help? It is true there may be issues of > a workload being memory bound and not responding quite linearly to > increasing frequency, but that would pose a problem for the current > algorithm also. Surely it's better to attempt a consistent policy which > doesn't vary based on a platform's fmin value?
FWIW I'm not trying to hold up this series - rather just discuss possibilities and differences with the now deprecated solution that may be able to be integrated here sometime in the near future.