Re: [PATCH v6 00/40] arm_mpam: Add KVM/arm64 and resctrl glue code

[Jesse Chick]

Hi Ben,


> Thanks for all the reviewing and testing so far. Just a bit more to get this
> over the line.


I tested this patch series, specifically L3 CPOR, on an Ampere
implementation with common benchmarking tools (lmbench, multichase).


> Generally the resctrl glue code works by picking what MPAM features it can expose
> from the MPAM drive, then configuring the structs that back the resctrl helpers.
> If your platform is sufficiently Xeon shaped, you should be able to get L2/L3 CPOR
> bitmaps exposed via resctrl. CSU counters work if they are on/after the L3. MBWU
> counters are considerably more hairy, and depend on hueristics around the topology,
> and a bunch of stuff trying to emulate ABMC.


The observed latency in increasingly large R/W operations scaled as
expected across various numbers of competing processes and cache
portions. The distinct jumps in latency as successive cache level
capacities were exceeded indicates that (a) L3 CPOR is configurable from
user space via the resctrl interface as described in this series and (b)
that the feature itself is working correctly.

For the series:

Tested-by: Jesse Chick <jessechick@xxxxxxxxxxxxxxxxxxxxxx>

Thanks,
Jesse