Messages in this thread Patch in this message | | | From | Stephane Eranian <> | Subject | [PATCH 7/8] perf record: add option to sample physical load/store addresses | Date | Fri, 21 Jun 2013 16:20:47 +0200 |
| |
This patch adds the --phys-addr option to perf record. This is used with memory access sampling to capture physical addresses. The option may be used in conjunction with -d, thereby providing virtual and physical addresses for a memory access. This is useful to disambiguate shared memory accesses between processes.
Signed-off-by: Stephane Eranian <eranian@google.com> --- tools/perf/Documentation/perf-record.txt | 4 ++++ tools/perf/builtin-record.c | 2 ++ 2 files changed, 6 insertions(+)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index d4da111..ebf98c5 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -188,6 +188,10 @@ Enable weightened sampling. An additional weight is recorded per sample and can displayed with the weight and local_weight sort keys. This currently works for TSX abort events and some memory events in precise mode on modern Intel CPUs. +--phys_addr:: +Samples physical address for memory loads and stores. May be used in conjunction with +the -d option when using memory access sampling (via perf mem). + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fff985c..40bcede 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -932,6 +932,8 @@ const struct option record_options[] = { "per thread counts"), OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Sample addresses"), + OPT_BOOLEAN(0, "phys-addr", &record.opts.sample_phys_address, + "Sample physical addresses"), OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"), OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, -- 1.8.1.2
| |