41013f0c09
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>
96 lines
2.3 KiB
Python
96 lines
2.3 KiB
Python
# mem-phys-addr.py: Resolve physical address samples
|
|
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# Copyright (c) 2018, Intel Corporation.
|
|
|
|
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')
|
|
|
|
#physical address ranges for System RAM
|
|
system_ram = []
|
|
#physical address ranges for Persistent Memory
|
|
pmem = []
|
|
#file object for proc iomem
|
|
f = None
|
|
#Count for each type of memory
|
|
load_mem_type_cnt = collections.Counter()
|
|
#perf event name
|
|
event_name = None
|
|
|
|
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
|