On Mon, Dec 15, 2014 at 05:36:25PM -0700, Dann Frazier wrote:
> We've measured significant performance improvements for several
> benchmarks by using 64K pages (SPECint, sysbench mysql, and kernel
> compiling)[*]. I'd therefore like to discuss whether or not we should
> switch to 64K pages in vivid.
>
> There's the question of whether or not we would be penalizing the
> performance of other classes of workloads people want to run on arm64.
> If there are some representative tests we should be looking at, please
> let me know.
There are arm64 cell phones; I suspect the workload on a cellphone is
different enough from a server workload that it should be tested as well.
The end results may indicate 64k pages are a win everywhere or they
may indicate a need for two arm64 flavours when we eventually target
higher-end phones.
Sorry, I can't recommend any benchmarks that would simulate the cellphone
workload.
Thanks
