Linux Perf PMU Events does not have UNCORE_CXL events in Sapphire Rapids
I’m using Linux 6.5.0 on Xeon 6438, and I noticed that there is a uncore_cxl.json file under tools/perf/pmu-events/arch/x86/sapphirerapids/
, which defines many cxl related events, but I can’t find them by `perf list’, so how to access these events?
Why does perf record –branch-any affect the CPU usage of the process?
The bounty expires in 6 days. Answers to this question are eligible for a +50 reputation bounty. zcfh wants to draw more attention to this question. The background is that I want to collect lbr events on the machine for pgo. But when I execute perf, I find that the CPU utilization of the processes […]