perf script python: Add script to profile and resolve physical mem type
authorKan Liang <Kan.liang@intel.com>
Thu, 4 Jan 2018 20:59:55 +0000 (12:59 -0800)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Fri, 12 Jan 2018 14:06:57 +0000 (11:06 -0300)
commit41013f0c095980775e0746272873891ca7c28fb1
treeb9bf612e5b54740e7ac40d5beeb088c8e7c26f1e
parentdd8bd53ab86133327412e74bf5ba31a8ec2826d4
perf script python: Add script to profile and resolve physical mem type

There could be different types of memory in the system. E.g normal
System Memory, Persistent Memory. To understand how the workload maps to
those memories, it's important to know the I/O statistics of them.  Perf
can collect physical addresses, but those are raw data.  It still needs
extra work to resolve the physical addresses.  Provide a script to
facilitate the physical addresses resolving and I/O statistics.

Profile with MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS
event if any of them is available.

Look up the /proc/iomem and resolve the physical address.  Provide
memory type summary.

Here is an example output:

  # perf script report mem-phys-addr
  Event: mem_inst_retired.all_loads:P
  Memory type                                    count   percentage
  ----------------------------------------  -----------  -----------
  System RAM                                        74        53.2%
  Persistent Memory                                 55        39.6%
  N/A

  ---

Changes since V2:
 - Apply the new license rules.
 - Add comments for globals

Changes since V1:
 - Do not mix DLA and Load Latency. Do not compare the loads and stores.
   Only profile the loads.
 - Use event name to replace the RAW event

Signed-off-by: Kan Liang <Kan.liang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lkml.kernel.org/r/1515099595-34770-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/scripts/python/bin/mem-phys-addr-record [new file with mode: 0644]
tools/perf/scripts/python/bin/mem-phys-addr-report [new file with mode: 0644]
tools/perf/scripts/python/mem-phys-addr.py [new file with mode: 0644]
tools/perf/util/scripting-engines/trace-event-python.c