Previously system RAM and persistent memory were hard code matched, change so that the label of the memory region is just read from /proc/iomem. This avoids frequent N/A samples. Change the /proc/iomem reading, event processing and output so that nested entries appear and their counts count toward their parent. As labels may be repeated, include the memory ranges in the output to make it clear why, for example, "System RAM" appears twice. Before: Event: mem_inst_retired.all_loads:P Memory type count percentage ---------------------------------------- ---------- ---------- System RAM 9460 96.5% N/A 998 3.5% After: Event: mem_inst_retired.all_loads:P Memory type count percentage ---------------------------------------- ---------- ---------- 100000000-105f7fffff : System RAM 36741 96.5 841400000-8416599ff : Kernel data 89 0.2 840800000-8412a6fff : Kernel rodata 60 0.2 841ebe000-8423fffff : Kernel bss 34 0.1 0-fff : Reserved 1345 3.5 100000-89dd9fff : System RAM 2 0.0 Before: Event: mem_inst_retired.any:P Memory type count percentage ---------------------------------------- ----------- ----------- System RAM 9460 90.5% N/A 998 9.5% After: Event: mem_inst_retired.any:P Memory type count percentage ---------------------------------------- ---------- ---------- 100000000-105f7fffff : System RAM 9460 90.5 841400000-8416599ff : Kernel data 45 0.4 840800000-8412a6fff : Kernel rodata 19 0.2 841ebe000-8423fffff : Kernel bss 12 0.1 0-fff : Reserved 998 9.5 The code has been updated to python 3 with type hints and resolving issues reported by mypy and pylint. Tabs are swapped to spaces as preferred in PEP8, because most lines of code were modified (of this small file) and this makes pylint significantly less noisy. Committer testing: root@number:/tmp# grep -m1 "model name" /proc/cpuinfo model name : Intel(R) Core(TM) i7-14700K root@number:/tmp# root@number:/tmp# perf script mem-phys-addr -a find / /bin /lib /lib64 /sbin Warning: 744 out of order events recorded. Event: cpu_core/mem_inst_retired.all_loads/P Memory type count percentage ---------------------------------------- ---------- ---------- 100000000-8bfbfffff : System RAM 364561 76.5 621400000-6223a6fff : Kernel rodata 10474 2.2 622400000-62283d4bf : Kernel data 4828 1.0 623304000-6237fffff : Kernel bss 1063 0.2 620000000-6213fffff : Kernel code 98 0.0 0-fff : Reserved 111480 23.4 100000-2b0ca017 : System RAM 337 0.1 2fbad000-30d92fff : System RAM 44 0.0 2c79d000-2fbabfff : System RAM 30 0.0 30d94000-316d5fff : System RAM 16 0.0 2b131a58-2c71dfff : System RAM 7 0.0 root@number:/tmp# Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Kan Liang <kan.liang@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20241119180130.19160-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
127 lines
4.1 KiB
Python
127 lines
4.1 KiB
Python
# mem-phys-addr.py: Resolve physical address samples
|
|
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# Copyright (c) 2018, Intel Corporation.
|
|
|
|
import os
|
|
import sys
|
|
import re
|
|
import bisect
|
|
import collections
|
|
from dataclasses import dataclass
|
|
from typing import (Dict, Optional)
|
|
|
|
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
|
|
'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
|
|
|
|
@dataclass(frozen=True)
|
|
class IomemEntry:
|
|
"""Read from a line in /proc/iomem"""
|
|
begin: int
|
|
end: int
|
|
indent: int
|
|
label: str
|
|
|
|
# Physical memory layout from /proc/iomem. Key is the indent and then
|
|
# a list of ranges.
|
|
iomem: Dict[int, list[IomemEntry]] = collections.defaultdict(list)
|
|
# Child nodes from the iomem parent.
|
|
children: Dict[IomemEntry, set[IomemEntry]] = collections.defaultdict(set)
|
|
# Maximum indent seen before an entry in the iomem file.
|
|
max_indent: int = 0
|
|
# Count for each range of memory.
|
|
load_mem_type_cnt: Dict[IomemEntry, int] = collections.Counter()
|
|
# Perf event name set from the first sample in the data.
|
|
event_name: Optional[str] = None
|
|
|
|
def parse_iomem():
|
|
"""Populate iomem from /proc/iomem file"""
|
|
global iomem
|
|
global max_indent
|
|
global children
|
|
with open('/proc/iomem', 'r', encoding='ascii') as f:
|
|
for line in f:
|
|
indent = 0
|
|
while line[indent] == ' ':
|
|
indent += 1
|
|
if indent > max_indent:
|
|
max_indent = indent
|
|
m = re.split('-|:', line, 2)
|
|
begin = int(m[0], 16)
|
|
end = int(m[1], 16)
|
|
label = m[2].strip()
|
|
entry = IomemEntry(begin, end, indent, label)
|
|
# Before adding entry, search for a parent node using its begin.
|
|
if indent > 0:
|
|
parent = find_memory_type(begin)
|
|
assert parent, f"Given indent expected a parent for {label}"
|
|
children[parent].add(entry)
|
|
iomem[indent].append(entry)
|
|
|
|
def find_memory_type(phys_addr) -> Optional[IomemEntry]:
|
|
"""Search iomem for the range containing phys_addr with the maximum indent"""
|
|
for i in range(max_indent, -1, -1):
|
|
if i not in iomem:
|
|
continue
|
|
position = bisect.bisect_right(iomem[i], phys_addr,
|
|
key=lambda entry: entry.begin)
|
|
if position is None:
|
|
continue
|
|
iomem_entry = iomem[i][position-1]
|
|
if iomem_entry.begin <= phys_addr <= iomem_entry.end:
|
|
return iomem_entry
|
|
print(f"Didn't find {phys_addr}")
|
|
return None
|
|
|
|
def print_memory_type():
|
|
print(f"Event: {event_name}")
|
|
print(f"{'Memory type':<40} {'count':>10} {'percentage':>10}")
|
|
print(f"{'-' * 40:<40} {'-' * 10:>10} {'-' * 10:>10}")
|
|
total = sum(load_mem_type_cnt.values())
|
|
# Add count from children into the parent.
|
|
for i in range(max_indent, -1, -1):
|
|
if i not in iomem:
|
|
continue
|
|
for entry in iomem[i]:
|
|
global children
|
|
for child in children[entry]:
|
|
if load_mem_type_cnt[child] > 0:
|
|
load_mem_type_cnt[entry] += load_mem_type_cnt[child]
|
|
|
|
def print_entries(entries):
|
|
"""Print counts from parents down to their children"""
|
|
global children
|
|
for entry in sorted(entries,
|
|
key = lambda entry: load_mem_type_cnt[entry],
|
|
reverse = True):
|
|
count = load_mem_type_cnt[entry]
|
|
if count > 0:
|
|
mem_type = ' ' * entry.indent + f"{entry.begin:x}-{entry.end:x} : {entry.label}"
|
|
percent = 100 * count / total
|
|
print(f"{mem_type:<40} {count:>10} {percent:>10.1f}")
|
|
print_entries(children[entry])
|
|
|
|
print_entries(iomem[0])
|
|
|
|
def trace_begin():
|
|
parse_iomem()
|
|
|
|
def trace_end():
|
|
print_memory_type()
|
|
|
|
def process_event(param_dict):
|
|
if "sample" not in param_dict:
|
|
return
|
|
|
|
sample = param_dict["sample"]
|
|
if "phys_addr" not in sample:
|
|
return
|
|
|
|
phys_addr = sample["phys_addr"]
|
|
entry = find_memory_type(phys_addr)
|
|
if entry:
|
|
load_mem_type_cnt[entry] += 1
|
|
|
|
global event_name
|
|
if event_name is None:
|
|
event_name = param_dict["ev_name"]
|