| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <tip-6745d8ea825966b0956c691cf7fccc13debedc39@git.kernel.org>
Date: Wed, 22 Jun 2016 00:44:14 -0700
From: tip-bot for Paolo Bonzini <tipbot@...or.com>
To: linux-tip-commits@...r.kernel.org
Cc: acme@...hat.com, linux-kernel@...r.kernel.org, pbonzini@...hat.com,
hpa@...or.com, jolsa@...nel.org, tglx@...utronix.de,
bgregg@...flix.com, mingo@...nel.org
Subject: [tip:perf/core] perf script: Add stackcollapse.py script
Commit-ID: 6745d8ea825966b0956c691cf7fccc13debedc39
Gitweb: http://git.kernel.org/tip/6745d8ea825966b0956c691cf7fccc13debedc39
Author: Paolo Bonzini <pbonzini@...hat.com>
AuthorDate: Tue, 12 Apr 2016 15:26:13 +0200
Committer: Arnaldo Carvalho de Melo <acme@...hat.com>
CommitDate: Tue, 21 Jun 2016 13:18:35 -0300
perf script: Add stackcollapse.py script
Add stackcollapse.py script as an example of parsing call chains, and
also of using optparse to access command line options.
The flame graph tools include a set of scripts that parse output from
various tools (including "perf script"), remove the offsets in the
function and collapse each stack to a single line. The website also
says "perf report could have a report style [...] that output folded
stacks directly, obviating the need for stackcollapse-perf.pl", so here
it is.
This script is a Python rewrite of stackcollapse-perf.pl, using the perf
scripting interface to access the perf data directly from Python.
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
Acked-by: Jiri Olsa <jolsa@...nel.org>
Cc: Brendan Gregg <bgregg@...flix.com>
Link: http://lkml.kernel.org/r/1460467573-22989-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
tools/perf/scripts/python/bin/stackcollapse-record | 8 ++
tools/perf/scripts/python/bin/stackcollapse-report | 3 +
tools/perf/scripts/python/stackcollapse.py | 127 +++++++++++++++++++++
3 files changed, 138 insertions(+)
diff --git a/tools/perf/scripts/python/bin/stackcollapse-record b/tools/perf/scripts/python/bin/stackcollapse-record
new file mode 100755
index 0000000..9d8f9f0
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-record
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+#
+# stackcollapse.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record "$@"
diff --git a/tools/perf/scripts/python/bin/stackcollapse-report b/tools/perf/scripts/python/bin/stackcollapse-report
new file mode 100755
index 0000000..356b965
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-report
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: produce callgraphs in short form for scripting use
+perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py -- "$@"
diff --git a/tools/perf/scripts/python/stackcollapse.py b/tools/perf/scripts/python/stackcollapse.py
new file mode 100755
index 0000000..a2dfcda
--- /dev/null
+++ b/tools/perf/scripts/python/stackcollapse.py
@@ -0,0 +1,127 @@
+#!/usr/bin/perl -w
+#
+# stackcollapse.py - format perf samples with one line per distinct call stack
+#
+# 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@...hat.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])
Powered by blists - more mailing lists