arch/x86/events/rapl.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-)
This is v2 patch set for enabling per-core RAPL counters through energy-cores event on RAPL PMU. Added RFC tag because a new patch is added and this additional patch may need clarification from the community. While enabling this support with v1 patch [1], Stephane reported an issue where for the first reading of energy-cores event for every core was invalid [2]. This issue is addressed with patch 1 of this series. There is no change in patch 2. [1]: https://lore.kernel.org/lkml/20230217161354.129442-1-wyes.karny@amd.com/ [2]: https://lore.kernel.org/lkml/CABPqkBQ_bSTC-OEe_LrgUrpj2VsseX1ThvO-yLcEtF8vb4+AAw@mail.gmail.com/ Change log: v1 -> v2: - Added new patch to fix the issue reported by Stephane - Added RFC tag Wyes Karny (2): perf/x86/rapl: Fix energy-cores event perf/x86/rapl: Enable Core RAPL for AMD arch/x86/events/rapl.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) -- 2.34.1
Hello. On středa 1. března 2023 19:14:47 CET Wyes Karny wrote: > This is v2 patch set for enabling per-core RAPL counters through > energy-cores event on RAPL PMU. Added RFC tag because a new patch is > added and this additional patch may need clarification from the > community. > > While enabling this support with v1 patch [1], Stephane reported an > issue where for the first reading of energy-cores event for every core was > invalid [2]. This issue is addressed with patch 1 of this series. There > is no change in patch 2. > > [1]: https://lore.kernel.org/lkml/20230217161354.129442-1-wyes.karny@amd.com/ > [2]: https://lore.kernel.org/lkml/CABPqkBQ_bSTC-OEe_LrgUrpj2VsseX1ThvO-yLcEtF8vb4+AAw@mail.gmail.com/ > > Change log: > v1 -> v2: > - Added new patch to fix the issue reported by Stephane > - Added RFC tag > > Wyes Karny (2): > perf/x86/rapl: Fix energy-cores event > perf/x86/rapl: Enable Core RAPL for AMD > > arch/x86/events/rapl.c | 20 +++++++++++++++----- > 1 file changed, 15 insertions(+), 5 deletions(-) Since I was asked to re-test v2: ``` $ sudo perf stat -a --per-core -C 0-15 -e power/energy-cores/ -- dd if=/dev/zero of=/dev/null bs=1M count=1000000 1000000+0 records in 1000000+0 records out 1048576000000 bytes (1,0 TB, 977 GiB) copied, 17,0321 s, 61,6 GB/s Performance counter stats for 'system wide': S0-D0-C0 1 6,67 Joules power/energy-cores/ S0-D0-C1 1 197,93 Joules power/energy-cores/ S0-D0-C2 1 11,32 Joules power/energy-cores/ S0-D0-C3 1 13,88 Joules power/energy-cores/ S0-D0-C4 1 12,40 Joules power/energy-cores/ S0-D0-C5 1 5,10 Joules power/energy-cores/ S0-D0-C6 1 3,92 Joules power/energy-cores/ S0-D0-C7 1 5,65 Joules power/energy-cores/ S0-D0-C8 1 4,91 Joules power/energy-cores/ S0-D0-C9 1 57,18 Joules power/energy-cores/ S0-D0-C10 1 174,95 Joules power/energy-cores/ S0-D0-C11 1 3,58 Joules power/energy-cores/ S0-D0-C12 1 5,41 Joules power/energy-cores/ S0-D0-C13 1 5,33 Joules power/energy-cores/ S0-D0-C14 1 2,89 Joules power/energy-cores/ S0-D0-C15 1 5,61 Joules power/energy-cores/ 17,034519241 seconds time elapsed ``` Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> Thanks. -- Oleksandr Natalenko (post-factum)
© 2016 - 2025 Red Hat, Inc.