summaryrefslogtreecommitdiff
path: root/tools/perf/scripts/python/flamegraph.py
blob: cf7ce8229a6cae61848c735fd0a38cb5748a7dd2 (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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
# flamegraph.py - create flame graphs from perf samples
# SPDX-License-Identifier: GPL-2.0
#
# Usage:
#
#     perf record -a -g -F 99 sleep 60
#     perf script report flamegraph
#
# Combined:
#
#     perf script flamegraph -a -F 99 sleep 60
#
# Written by Andreas Gerstmayr <agerstmayr@redhat.com>
# Flame Graphs invented by Brendan Gregg <bgregg@netflix.com>
# Works in tandem with d3-flame-graph by Martin Spier <mspier@netflix.com>
#
# pylint: disable=missing-module-docstring
# pylint: disable=missing-class-docstring
# pylint: disable=missing-function-docstring

from __future__ import print_function
import argparse
import hashlib
import io
import json
import os
import subprocess
import sys
import urllib.request

minimal_html = """<head>
  <link rel="stylesheet" type="text/css" href="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.css">
</head>
<body>
  <div id="chart"></div>
  <script type="text/javascript" src="https://d3js.org/d3.v7.js"></script>
  <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.min.js"></script>
  <script type="text/javascript">
  const stacks = [/** @flamegraph_json **/];
  // Note, options is unused.
  const options = [/** @options_json **/];

  var chart = flamegraph();
  d3.select("#chart")
        .datum(stacks[0])
        .call(chart);
  </script>
</body>
"""

# pylint: disable=too-few-public-methods
class Node:
    def __init__(self, name, libtype):
        self.name = name
        # "root" | "kernel" | ""
        # "" indicates user space
        self.libtype = libtype
        self.value = 0
        self.children = []

    def to_json(self):
        return {
            "n": self.name,
            "l": self.libtype,
            "v": self.value,
            "c": self.children
        }


class FlameGraphCLI:
    def __init__(self, args):
        self.args = args
        self.stack = Node("all", "root")

    @staticmethod
    def get_libtype_from_dso(dso):
        """
        when kernel-debuginfo is installed,
        dso points to /usr/lib/debug/lib/modules/*/vmlinux
        """
        if dso and (dso == "[kernel.kallsyms]" or dso.endswith("/vmlinux")):
            return "kernel"

        return ""

    @staticmethod
    def find_or_create_node(node, name, libtype):
        for child in node.children:
            if child.name == name:
                return child

        child = Node(name, libtype)
        node.children.append(child)
        return child

    def process_event(self, event):
        pid = event.get("sample", {}).get("pid", 0)
        # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
        # for user-space processes; let's use pid for kernel or user-space distinction
        if pid == 0:
            comm = event["comm"]
            libtype = "kernel"
        else:
            comm = "{} ({})".format(event["comm"], pid)
            libtype = ""
        node = self.find_or_create_node(self.stack, comm, libtype)

        if "callchain" in event:
            for entry in reversed(event["callchain"]):
                name = entry.get("sym", {}).get("name", "[unknown]")
                libtype = self.get_libtype_from_dso(entry.get("dso"))
                node = self.find_or_create_node(node, name, libtype)
        else:
            name = event.get("symbol", "[unknown]")
            libtype = self.get_libtype_from_dso(event.get("dso"))
            node = self.find_or_create_node(node, name, libtype)
        node.value += 1

    def get_report_header(self):
        if self.args.input == "-":
            # when this script is invoked with "perf script flamegraph",
            # no perf.data is created and we cannot read the header of it
            return ""

        try:
            output = subprocess.check_output(["perf", "report", "--header-only"])
            return output.decode("utf-8")
        except Exception as err:  # pylint: disable=broad-except
            print("Error reading report header: {}".format(err), file=sys.stderr)
            return ""

    def trace_end(self):
        stacks_json = json.dumps(self.stack, default=lambda x: x.to_json())

        if self.args.format == "html":
            report_header = self.get_report_header()
            options = {
                "colorscheme": self.args.colorscheme,
                "context": report_header
            }
            options_json = json.dumps(options)

            template_md5sum = None
            if self.args.format == "html":
                if os.path.isfile(self.args.template):
                    template = f"file://{self.args.template}"
                else:
                    if not self.args.allow_download:
                        print(f"""Warning: Flame Graph template '{self.args.template}'
does not exist. To avoid this please install a package such as the
js-d3-flame-graph or libjs-d3-flame-graph, specify an existing flame
graph template (--template PATH) or use another output format (--format
FORMAT).""",
                              file=sys.stderr)
                        if self.args.input == "-":
                            print("""Not attempting to download Flame Graph template as script command line
input is disabled due to using live mode. If you want to download the
template retry without live mode. For example, use 'perf record -a -g
-F 99 sleep 60' and 'perf script report flamegraph'. Alternatively,
download the template from:
https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/d3-flamegraph-base.html
and place it at:
/usr/share/d3-flame-graph/d3-flamegraph-base.html""",
                                  file=sys.stderr)
                            quit()
                        s = None
                        while s != "y" and s != "n":
                            s = input("Do you wish to download a template from cdn.jsdelivr.net? (this warning can be suppressed with --allow-download) [yn] ").lower()
                        if s == "n":
                            quit()
                    template = "https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/d3-flamegraph-base.html"
                    template_md5sum = "143e0d06ba69b8370b9848dcd6ae3f36"

            try:
                with urllib.request.urlopen(template) as template:
                    output_str = "".join([
                        l.decode("utf-8") for l in template.readlines()
                    ])
            except Exception as err:
                print(f"Error reading template {template}: {err}\n"
                      "a minimal flame graph will be generated", file=sys.stderr)
                output_str = minimal_html
                template_md5sum = None

            if template_md5sum:
                download_md5sum = hashlib.md5(output_str.encode("utf-8")).hexdigest()
                if download_md5sum != template_md5sum:
                    s = None
                    while s != "y" and s != "n":
                        s = input(f"""Unexpected template md5sum.
{download_md5sum} != {template_md5sum}, for:
{output_str}
continue?[yn] """).lower()
                    if s == "n":
                        quit()

            output_str = output_str.replace("/** @options_json **/", options_json)
            output_str = output_str.replace("/** @flamegraph_json **/", stacks_json)

            output_fn = self.args.output or "flamegraph.html"
        else:
            output_str = stacks_json
            output_fn = self.args.output or "stacks.json"

        if output_fn == "-":
            with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out:
                out.write(output_str)
        else:
            print("dumping data to {}".format(output_fn))
            try:
                with io.open(output_fn, "w", encoding="utf-8") as out:
                    out.write(output_str)
            except IOError as err:
                print("Error writing output file: {}".format(err), file=sys.stderr)
                sys.exit(1)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Create flame graphs.")
    parser.add_argument("-f", "--format",
                        default="html", choices=["json", "html"],
                        help="output file format")
    parser.add_argument("-o", "--output",
                        help="output file name")
    parser.add_argument("--template",
                        default="/usr/share/d3-flame-graph/d3-flamegraph-base.html",
                        help="path to flame graph HTML template")
    parser.add_argument("--colorscheme",
                        default="blue-green",
                        help="flame graph color scheme",
                        choices=["blue-green", "orange"])
    parser.add_argument("-i", "--input",
                        help=argparse.SUPPRESS)
    parser.add_argument("--allow-download",
                        default=False,
                        action="store_true",
                        help="allow unprompted downloading of HTML template")

    cli_args = parser.parse_args()
    cli = FlameGraphCLI(cli_args)

    process_event = cli.process_event
    trace_end = cli.trace_end
use. We could #ifdef CONFIG_PREEMPT the warning, but that is not good form. And there seems to be no suitable fix to in_atomic() when CONFIG_PREMPT is not on. As Ingo commented: > and we have no proper primitive to test for atomicity. (mainly > because we dont know about atomicity on a non-preempt kernel) So we drop the WARN_ON. Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2009-02-17x86, apic: remove duplicate asm/apic.h inclusionsIngo Molnar Impact: cleanup Signed-off-by: Ingo Molnar <mingo@elte.hu> 2009-02-17x86, apic: remove genapic.hIngo Molnar Impact: cleanup Remove genapic.h and remove all references to it. Signed-off-by: Ingo Molnar <mingo@elte.hu> 2009-02-09Merge branch 'x86/paravirt' into x86/apicIngo Molnar Conflicts: arch/x86/mach-voyager/voyager_smp.c 2009-01-31x86: UV fix uv_flush_send_and_wait()Cliff Wickman Impact: fix possible tlb mis-flushing on UV uv_flush_send_and_wait() should return a pointer if the broadcast remote tlb shootdown requests fail. That causes the conventional IPI method of shootdown to be used. Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Tejun Heo <tj@kernel.org> 2009-01-29x86: remove mach_apic.hIngo Molnar Spread mach_apic.h definitions into genapic.h. (with some knock-on effects on smp.h and apic.h.) Signed-off-by: Ingo Molnar <mingo@elte.hu> 2009-01-27Merge branch 'linus' into core/percpuIngo Molnar Conflicts: arch/x86/kernel/setup_percpu.c 2009-01-21x86: uv cleanupTejun Heo Impact: cleanup Make the following uv related cleanups. * collect visible uv related definitions and interfaces into uv/uv.h and use it. this cleans up the messy situation where on 64bit, uv is defined properly, on 32bit generic it's dummy and on the rest undefined. after this clean up, uv is defined on 64 and dummy on 32. * update uv_flush_tlb_others() such that it takes cpumask of to-be-flushed cpus as argument, instead of that minus self, and returns yet-to-be-flushed cpumask, instead of modifying the passed in parameter. this interface change will ease dummy implementation of uv_flush_tlb_others() and makes uv tlb flush related stuff defined in tlb_uv proper. Signed-off-by: Tejun Heo <tj@kernel.org> 2009-01-15x86, UV: cpu_relax in uv_wait_completionCliff Wickman The function uv_wait_completion() spins on reads of a memory-mapped register, waiting for completion of BAU hardware replies. It should call "cpu_relax()" between those reads to improve performance on hyperthreaded configurations. Signed-off-by: Cliff Wickman <cpw@sgi.com> Acked-by: Jack Steiner <steiner@sgi.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2009-01-11x86: change flush_tlb_others to take a const struct cpumaskRusty Russell Impact: reduce stack usage, use new cpumask API. This is made a little more tricky by uv_flush_tlb_others which actually alters its argument, for an IPI to be sent to the remaining cpus in the mask. I solve this by allocating a cpumask_var_t for this case and falling back to IPI should this fail. To eliminate temporaries in the caller, all flush_tlb_others implementations now do the this-cpu-elimination step themselves. Note also the curious "cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask)" which has been there since pre-git and yet f->flush_cpumask is always zero at this point. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com> 2009-01-02x86, UV: remove erroneous BAU initializationCliff Wickman Impact: fix crash on x86/UV UV is the SGI "UltraViolet" machine, which is x86_64 based. BAU is the "Broadcast Assist Unit", used for TLB shootdown in UV. This patch removes the allocation and initialization of an unused table. This table is left over from a development test mode. It is unused in the present code. And it was incorrectly initialized: 8 entries allocated but 17 initialized, causing slab corruption. This patch should go into 2.6.27 and 2.6.28 as well as the current tree. Diffed against 2.6.28 (linux-next, 12/30/08) Signed-off-by: Cliff Wickman <cpw@sgi.com> Cc: <stable@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-11-11x86, UV: fix redundant creation of sgi_uvCliff Wickman Impact: fix double entry creation in /proc There is a collision between two UV functions: both uv_ptc_init() and gru_proc_init() try to make /proc/sgi_uv So move it's creation to a single place: uv_system_init() Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-10-22x86/tlb_uv: remove strange mc146818rtc includeJeremy Fitzhardinge For some reason tlb_uv was including linux/mc146818rtc.h. It really just needs linux/seq_file.h Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citix.com> Cc: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-08-20x86, SGI UV: hardcode the TLB flush interrupt system vectorCliff Wickman The UV TLB shootdown mechanism needs a system interrupt vector. Its vector had been hardcoded as 200, but needs to moved to the reserved system vector range so that it does not collide with some device vector. This is still temporary until dynamic system IRQ allocation is provided. But it will be needed when real UV hardware becomes available and runs 2.6.27. Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08x86, SGI UV: uv_ptc_proc_write fixCliff Wickman Someone could write 0 bytes to /proc/sgi_uv/ptc_statistics, causing optstr[count - 1] = '\0'; to write to who-knows-where. (Andi Kleen noticed this need from a patch I sent for similar code in the ia64 world (sn2_ptc_proc_write()).) (count less than zero is not possible here, as count is unsigned) Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08x86, SGI UV: TLB shootdown using broadcast assist unit, v6Cliff Wickman v6: 6/19 close the security hole in uv_ptc_proc_write()) > Found a potential security hole while doing that: > static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, > size_t count, loff_t *data) > if (copy_from_user(optstr, user, count)) > return -EFAULT; > > is count guaranteed to never be larger than 64? is fixed below. It adds tlb_uv.o to the Makefile. Signed-off-by: Cliff Wickman <cpw@sgi.com> Cc: mingo@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08SGI UV: TLB shootdown using broadcast assist unit, fixIngo Molnar fix: arch/x86/kernel/tlb_uv.c: In function ‘uv_table_bases_init': arch/x86/kernel/tlb_uv.c:612: error: ‘bau_tabsp' undeclared (first use in this function) arch/x86/kernel/tlb_uv.c:612: error: (Each undeclared identifier is reported only once arch/x86/kernel/tlb_uv.c:612: error: for each function it appears in.) Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08SGI UV: clean up arch/x86/kernel/tlb_uv.cIngo Molnar Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08SGI UV: TLB shootdown using broadcast assist unitIngo Molnar TLB shootdown for SGI UV. v5: 6/12 corrections/improvements per Ingo's second review Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08SGI UV: TLB shootdown using broadcast assist unit, cleanupsCliff Wickman TLB shootdown for SGI UV. v1: 6/2 original v2: 6/3 corrections/improvements per Ingo's review v3: 6/4 split atomic operations off to a separate patch (Jeremy's review) v4: 6/12 include <mach_apic.h> rather than <asm/mach-bigsmp/mach_apic.h> (fixes a !SMP build problem that Ingo found) fix the index on uv_table_bases[blade] Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> 2008-07-08x86, SGI UV: TLB shootdown using broadcast assist unitCliff Wickman TLB shootdown for SGI UV. Depends on patch (in tip/x86/irq): x86-update-macros-used-by-uv-platform.patch Jack Steiner May 29 This patch provides the ability to flush TLB's in cpu's that are not on the local node. The hardware mechanism for distributing the flush messages is the UV's "broadcast assist unit". The hook to intercept TLB shootdown requests is a 2-line change to native_flush_tlb_others() (arch/x86/kernel/tlb_64.c). This code has been tested on a hardware simulator. The real hardware is not yet available. The shootdown statistics are provided through /proc/sgi_uv/ptc_statistics. The use of /sys was considered, but would have required the use of many /sys files. The debugfs was also considered, but these statistics should be available on an ongoing basis, not just for debugging. Issues to be fixed later: - The IRQ for the messaging interrupt is currently hardcoded as 200 (see UV_BAU_MESSAGE). It should be dynamically assigned in the future. - The use of appropriate udelay()'s is untested, as they are a problem in the simulator. Signed-off-by: Cliff Wickman <cpw@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>