Dear Kan, On Wed, Jan 3, 2018 at 9:20 PM, Liang, Kan <kan.li...@intel.com> wrote: > Hi Stephane and Andi, > > Could you please review the script? > > If it's OK for you, could you please Ack/Review this? > > Thanks, > Kan > >> >> From: Kan Liang <kan.li...@intel.com> >> >> 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 10 7.2% >> >> Signed-off-by: Kan Liang <kan.li...@intel.com> >> --- >> >> 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 >> >> tools/perf/scripts/python/bin/mem-phys-addr-record | 19 +++++ >> tools/perf/scripts/python/bin/mem-phys-addr-report | 3 + >> tools/perf/scripts/python/mem-phys-addr.py | 97 >> ++++++++++++++++++++++ >> .../util/scripting-engines/trace-event-python.c | 2 + >> 4 files changed, 121 insertions(+) >> create mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-record >> create mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-report >> create mode 100644 tools/perf/scripts/python/mem-phys-addr.py >> >> diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-record >> b/tools/perf/scripts/python/bin/mem-phys-addr-record >> new file mode 100644 >> index 0000000..5a87512 >> --- /dev/null >> +++ b/tools/perf/scripts/python/bin/mem-phys-addr-record >> @@ -0,0 +1,19 @@ >> +#!/bin/bash >> + >> +# >> +# Profiling physical memory by all retired load instructions/uops event >> +# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS >> +# >> + >> +load=`perf list | grep mem_inst_retired.all_loads` >> +if [ -z "$load" ]; then >> + load=`perf list | grep mem_uops_retired.all_loads` >> +fi >> +if [ -z "$load" ]; then >> + echo "There is no event to count all retired load instructions/uops." >> + exit 1 >> +fi >> + >> +arg=$(echo $load | tr -d ' ') >> +arg="$arg:P" >> +perf record --phys-data -e $arg $@ >> diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-report >> b/tools/perf/scripts/python/bin/mem-phys-addr-report >> new file mode 100644 >> index 0000000..3f2b847 >> --- /dev/null >> +++ b/tools/perf/scripts/python/bin/mem-phys-addr-report >> @@ -0,0 +1,3 @@ >> +#!/bin/bash >> +# description: resolve physical address samples >> +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py >> diff --git a/tools/perf/scripts/python/mem-phys-addr.py >> b/tools/perf/scripts/python/mem-phys-addr.py >> new file mode 100644 >> index 0000000..1d1f757 >> --- /dev/null >> +++ b/tools/perf/scripts/python/mem-phys-addr.py >> @@ -0,0 +1,97 @@ >> +# mem-phys-addr.py: Resolve physical address samples >> +# Copyright (c) 2017, Intel Corporation. >> +# >> +# This program is free software; you can redistribute it and/or modify it >> +# under the terms and conditions of the GNU General Public License, >> +# version 2, as published by the Free Software Foundation. >> +# >> +# This program is distributed in the hope it will be useful, but WITHOUT >> +# ANY WARRANTY; without even the implied warranty of >> MERCHANTABILITY or >> +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License >> for >> +# more details.
May be you could consider using an SPDX tag instead of this fine but long legalese? See Thomas doc patches [1] for details [1] https://lkml.org/lkml/2017/12/28/323 >> + >> +from __future__ import division >> +import os >> +import sys >> +import struct >> +import re >> +import bisect >> +import collections >> + >> +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ >> + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') >> + >> +system_ram = [] >> +pmem = [] >> +f = None >> +load_mem_type_cnt = collections.Counter() >> +event_name = None nit. may be it does not matter too much.... but using globals throughout as opposed to return values makes the script harder to read IMHO. >> + >> +def parse_iomem(): >> + global f >> + f = open('/proc/iomem', 'r') >> + for i, j in enumerate(f): >> + m = re.split('-|:',j,2) >> + if m[2].strip() == 'System RAM': >> + system_ram.append(long(m[0], 16)) >> + system_ram.append(long(m[1], 16)) >> + if m[2].strip() == 'Persistent Memory': >> + pmem.append(long(m[0], 16)) >> + pmem.append(long(m[1], 16)) >> + >> +def print_memory_type(): >> + print "Event: %s" % (event_name) >> + print "%-40s %10s %10s\n" % ("Memory type", "count", >> "percentage"), >> + print "%-40s %10s %10s\n" % >> ("----------------------------------------", \ >> + "-----------", "-----------"), >> + total = sum(load_mem_type_cnt.values()) >> + for mem_type, count in sorted(load_mem_type_cnt.most_common(), >> \ >> + key = lambda(k, v): (v, k), reverse = >> True): >> + print "%-40s %10d %10.1f%%\n" % (mem_type, count, 100 * >> count / total), >> + >> +def trace_begin(): >> + parse_iomem() >> + >> +def trace_end(): >> + print_memory_type() >> + f.close() >> + >> +def is_system_ram(phys_addr): >> + #/proc/iomem is sorted >> + position = bisect.bisect(system_ram, phys_addr) >> + if position % 2 == 0: >> + return False >> + return True >> + >> +def is_persistent_mem(phys_addr): >> + position = bisect.bisect(pmem, phys_addr) >> + if position % 2 == 0: >> + return False >> + return True >> + >> +def find_memory_type(phys_addr): >> + if phys_addr == 0: >> + return "N/A" >> + if is_system_ram(phys_addr): >> + return "System RAM" >> + >> + if is_persistent_mem(phys_addr): >> + return "Persistent Memory" >> + >> + #slow path, search all >> + f.seek(0, 0) >> + for j in f: >> + m = re.split('-|:',j,2) >> + if long(m[0], 16) <= phys_addr <= long(m[1], 16): >> + return m[2] >> + return "N/A" >> + >> +def process_event(param_dict): >> + name = param_dict["ev_name"] >> + sample = param_dict["sample"] >> + phys_addr = sample["phys_addr"] >> + >> + global event_name >> + if event_name == None: >> + event_name = name >> + load_mem_type_cnt[find_memory_type(phys_addr)] += 1 >> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c >> b/tools/perf/util/scripting-engines/trace-event-python.c >> index c7187f0..8cd6317 100644 >> --- a/tools/perf/util/scripting-engines/trace-event-python.c >> +++ b/tools/perf/util/scripting-engines/trace-event-python.c >> @@ -500,6 +500,8 @@ static PyObject *get_perf_sample_dict(struct >> perf_sample *sample, >> PyLong_FromUnsignedLongLong(sample->time)); >> pydict_set_item_string_decref(dict_sample, "period", >> PyLong_FromUnsignedLongLong(sample->period)); >> + pydict_set_item_string_decref(dict_sample, "phys_addr", >> + PyLong_FromUnsignedLongLong(sample- >> >phys_addr)); >> set_sample_read_in_dict(dict_sample, sample, evsel); >> pydict_set_item_string_decref(dict, "sample", dict_sample); >> >> -- >> 2.7.4 > -- Cordially Philippe Ombredanne
