[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Z9P8EDcGv0m__WiN@gmail.com>
Date: Fri, 14 Mar 2025 10:51:12 +0100
From: Ingo Molnar <mingo@...nel.org>
To: kan.liang@...ux.intel.com
Cc: peterz@...radead.org, acme@...nel.org, namhyung@...nel.org,
irogers@...gle.com, adrian.hunter@...el.com, ak@...ux.intel.com,
linux-kernel@...r.kernel.org, eranian@...gle.com,
thomas.falcon@...el.com
Subject: Re: [PATCH V2 0/3] Support auto counter reload
* kan.liang@...ux.intel.com <kan.liang@...ux.intel.com> wrote:
> From: Kan Liang <kan.liang@...ux.intel.com>
>
> Changes since V1:
> - Add a check to the reload value which cannot exceeds the max period
> - Avoid invoking intel_pmu_enable_acr() for the perf metrics event.
> - Update comments explain to case which the event->attr.config2 exceeds
> the group size
> The 2498 samples are all from the branch-misses events for the Loop 2.
>
> The number of samples and overhead is significantly reduced without
> losing any information.
Ok, that looks like a pretty sweet PMU feature.
What is the hardware support range of this auto count reload feature,
how recent CPU does one have to have?
The series has aged a bit though, while a variant of patch #1 has been
merged already under:
47a973fd7563 perf/x86/intel: Fix ARCH_PERFMON_NUM_COUNTER_LEAF
... but #2 and #3 don't apply cleanly anymore.
Mind sending a refreshed series perhaps?
Thanks,
Ingo
Powered by blists - more mailing lists