summaryrefslogtreecommitdiff
path: root/tools/perf/scripts/python/stackcollapse.py
blob: 1697b5e18c9622bdc82f7f9355745febb0a28705 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
# stackcollapse.py - format perf samples with one line per distinct call stack
# SPDX-License-Identifier: GPL-2.0
#
# This script's output has two space-separated fields.  The first is a semicolon
# separated stack including the program name (from the "comm" field) and the
# function names from the call stack.  The second is a count:
#
#  swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2
#
# The file is sorted according to the first field.
#
# Input may be created and processed using:
#
#  perf record -a -g -F 99 sleep 60
#  perf script report stackcollapse > out.stacks-folded
#
# (perf script record stackcollapse works too).
#
# Written by Paolo Bonzini <pbonzini@redhat.com>
# Based on Brendan Gregg's stackcollapse-perf.pl script.

import os
import sys
from collections import defaultdict
from optparse import OptionParser, make_option

sys.path.append(os.environ['PERF_EXEC_PATH'] + \
                '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')

from perf_trace_context import *
from Core import *
from EventClass import *

# command line parsing

option_list = [
    # formatting options for the bottom entry of the stack
    make_option("--include-tid", dest="include_tid",
                 action="store_true", default=False,
                 help="include thread id in stack"),
    make_option("--include-pid", dest="include_pid",
                 action="store_true", default=False,
                 help="include process id in stack"),
    make_option("--no-comm", dest="include_comm",
                 action="store_false", default=True,
                 help="do not separate stacks according to comm"),
    make_option("--tidy-java", dest="tidy_java",
                 action="store_true", default=False,
                 help="beautify Java signatures"),
    make_option("--kernel", dest="annotate_kernel",
                 action="store_true", default=False,
                 help="annotate kernel functions with _[k]")
]

parser = OptionParser(option_list=option_list)
(opts, args) = parser.parse_args()

if len(args) != 0:
    parser.error("unexpected command line argument")
if opts.include_tid and not opts.include_comm:
    parser.error("requesting tid but not comm is invalid")
if opts.include_pid and not opts.include_comm:
    parser.error("requesting pid but not comm is invalid")

# event handlers

lines = defaultdict(lambda: 0)

def process_event(param_dict):
    def tidy_function_name(sym, dso):
        if sym is None:
            sym = '[unknown]'

        sym = sym.replace(';', ':')
        if opts.tidy_java:
            # the original stackcollapse-perf.pl script gives the
            # example of converting this:
            #    Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V
            # to this:
            #    org/mozilla/javascript/MemberBox:.init
            sym = sym.replace('<', '')
            sym = sym.replace('>', '')
            if sym[0] == 'L' and sym.find('/'):
                sym = sym[1:]
            try:
                sym = sym[:sym.index('(')]
            except ValueError:
                pass

        if opts.annotate_kernel and dso == '[kernel.kallsyms]':
            return sym + '_[k]'
        else:
            return sym

    stack = list()
    if 'callchain' in param_dict:
        for entry in param_dict['callchain']:
            entry.setdefault('sym', dict())
            entry['sym'].setdefault('name', None)
            entry.setdefault('dso', None)
            stack.append(tidy_function_name(entry['sym']['name'],
                                            entry['dso']))
    else:
        param_dict.setdefault('symbol', None)
        param_dict.setdefault('dso', None)
        stack.append(tidy_function_name(param_dict['symbol'],
                                        param_dict['dso']))

    if opts.include_comm:
        comm = param_dict["comm"].replace(' ', '_')
        sep = "-"
        if opts.include_pid:
            comm = comm + sep + str(param_dict['sample']['pid'])
            sep = "/"
        if opts.include_tid:
            comm = comm + sep + str(param_dict['sample']['tid'])
        stack.append(comm)

    stack_string = ';'.join(reversed(stack))
    lines[stack_string] = lines[stack_string] + 1

def trace_end():
    list = lines.keys()
    list.sort()
    for stack in list:
        print "%s %d" % (stack, lines[stack])
/zstd_compress_test.c` [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. I benchmarked using `silesia.tar` [3], which is 211,988,480 B large. Run the following commands for the benchmark: sudo modprobe zstd_compress_test sudo mknod zstd_compress_test c 245 0 sudo cp silesia.tar zstd_compress_test The time is reported by the time of the userland `cp`. The MB/s is computed with 1,536,217,008 B / time(buffer size, hash) which includes the time to copy from userland. The Adjusted MB/s is computed with 1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)). The memory reported is the amount of memory the compressor requests. | Method | Size (B) | Time (s) | Ratio | MB/s | Adj MB/s | Mem (MB) | |----------|----------|----------|-------|---------|----------|----------| | none | 11988480 | 0.100 | 1 | 2119.88 | - | - | | zstd -1 | 73645762 | 1.044 | 2.878 | 203.05 | 224.56 | 1.23 | | zstd -3 | 66988878 | 1.761 | 3.165 | 120.38 | 127.63 | 2.47 | | zstd -5 | 65001259 | 2.563 | 3.261 | 82.71 | 86.07 | 2.86 | | zstd -10 | 60165346 | 13.242 | 3.523 | 16.01 | 16.13 | 13.22 | | zstd -15 | 58009756 | 47.601 | 3.654 | 4.45 | 4.46 | 21.61 | | zstd -19 | 54014593 | 102.835 | 3.925 | 2.06 | 2.06 | 60.15 | | zlib -1 | 77260026 | 2.895 | 2.744 | 73.23 | 75.85 | 0.27 | | zlib -3 | 72972206 | 4.116 | 2.905 | 51.50 | 52.79 | 0.27 | | zlib -6 | 68190360 | 9.633 | 3.109 | 22.01 | 22.24 | 0.27 | | zlib -9 | 67613382 | 22.554 | 3.135 | 9.40 | 9.44 | 0.27 | I benchmarked zstd decompression using the same method on the same machine. The benchmark file is located in the upstream zstd repo under `contrib/linux-kernel/zstd_decompress_test.c` [4]. The memory reported is the amount of memory required to decompress data compressed with the given compression level. If you know the maximum size of your input, you can reduce the memory usage of decompression irrespective of the compression level. | Method | Time (s) | MB/s | Adjusted MB/s | Memory (MB) | |----------|----------|---------|---------------|-------------| | none | 0.025 | 8479.54 | - | - | | zstd -1 | 0.358 | 592.15 | 636.60 | 0.84 | | zstd -3 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -5 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -10 | 0.374 | 566.81 | 607.42 | 2.51 | | zstd -15 | 0.379 | 559.34 | 598.84 | 4.61 | | zstd -19 | 0.412 | 514.54 | 547.77 | 8.80 | | zlib -1 | 0.940 | 225.52 | 231.68 | 0.04 | | zlib -3 | 0.883 | 240.08 | 247.07 | 0.04 | | zlib -6 | 0.844 | 251.17 | 258.84 | 0.04 | | zlib -9 | 0.837 | 253.27 | 287.64 | 0.04 | Tested in userland using the test-suite in the zstd repo under `contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under `contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8] with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the BtrFS and SquashFS patches coming next. [1] https://clang.llvm.org/docs/ClangFormat.html [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_compress_test.c [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_decompress_test.c [5] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/UserlandTest.cpp [6] http://llvm.org/docs/LibFuzzer.html [7] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/RoundTripCrash.c [8] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/DecompressCrash.c zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>