Add tool to help analyze binary size

tools/binary_size/run_binary_size_analysis.py

Index: tools/binary_size/run_binary_size_analysis.py
diff --git a/tools/binary_size/run_binary_size_analysis.py b/tools/binary_size/run_binary_size_analysis.py
new file mode 100755
index 0000000000000000000000000000000000000000..cd44225a1a90479faef8cbed6ca09b2817725bb5
--- /dev/null
+++ b/tools/binary_size/run_binary_size_analysis.py
@@ -0,0 +1,338 @@
+#!/usr/bin/python
+# Copyright 2014 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+"""Generate a spatial analysis against an arbitrary library.
+
+To use, build the 'binary_size_java' target. Then run this tool, passing
+in the location of the library to be analyzed along with any other options
+you desire.
+"""
+
+import fileinput
+import optparse
+import os
+import pprint
+import re
+import shutil
+import subprocess
+import sys
+import tempfile
+import json
+
+def format_bytes(bytes):
+    """Pretty-print a number of bytes."""
+    if bytes > 1e6:
+        bytes = bytes / 1.0e6
+        return '%.1fm' % bytes
+    if bytes > 1e3:
+        bytes = bytes / 1.0e3
+        return '%.1fk' % bytes
+    return str(bytes)
+
+
+def parse_nm(input):

[bulach, 2014/01/07 19:38:30]

not sure, is this needed?

[Andrew Hayden (chromium.org), 2014/01/08 00:56:45]

Yes, the bloat script parses nm to convert the strings to records for the
treemap. In the end (not now), we should probably have a little pylib for
parsing nm that we can share both with this code and the eventual pythonified
version of ParallelAddr2Line.

[bulach, 2014/01/08 15:04:00]

got it... there's some hidden irony in that whilst trying to reduce binary size,
there's this duplication of both python and java ;)
I'm looking forward to have all of this in one single language.

+    """Parse nm output.
+
+    Argument: an iterable over lines of nm output.
+
+    Yields: (symbol name, symbol type, symbol size, source file path).
+    Path may be None if nm couldn't figure out the source file.
+    """
+
+    # Match lines with size, symbol, optional location, optional discriminator
+    sym_re = re.compile(r'^[0-9a-f]{8} ([0-9a-f]{8}) (.) ([^\t]+)(?:\t(.*):[\d\?]+)?.*$')
+
+    # Match lines with addr but no size.
+    addr_re = re.compile(r'^[0-9a-f]{8} (.) ([^\t]+)(?:\t.*)?$')
+    # Match lines that don't have an address at all -- typically external symbols.
+    noaddr_re = re.compile(r'^ {8} (.) (.*)$')
+
+    for line in input:
+        line = line.rstrip()
+        match = sym_re.match(line)
+        if match:
+            size, type, sym = match.groups()[0:3]
+            size = int(size, 16)
+            type = type.lower()
+            if type == 'v':
+                type = 'w'  # just call them all weak
+            if type == 'b':
+                continue  # skip all BSS for now
+            path = match.group(4)
+            yield sym, type, size, path
+            continue
+        match = addr_re.match(line)
+        if match:
+            type, sym = match.groups()[0:2]
+            # No size == we don't care.
+            continue
+        match = noaddr_re.match(line)
+        if match:
+            type, sym = match.groups()
+            if type in ('U', 'w'):
+                # external or weak symbol
+                continue
+
+        print >>sys.stderr, 'unparsed:', repr(line)
+
+
+def treeify_syms(symbols):
+    dirs = {}
+    for sym, type, size, path in symbols:
+        if path:
+            path = os.path.normpath(path)
+            if path.startswith('/usr/include'):
+                path = path.replace('/usr/include', 'usrinclude')
+            elif path.startswith('/'):
+                path = path[1:]
+
+        parts = None
+        # TODO: make segmenting by namespace work.
+        if False and '::' in sym:
+            if sym.startswith('vtable for '):
+                sym = sym[len('vtable for '):]
+                parts = sym.split('::')
+                parts.append('[vtable]')
+            else:
+                parts = sym.split('::')
+            parts[0] = '::' + parts[0]
+        elif path and '/' in path:
+            parts = path.split('/')
+
+        if parts:
+            key = parts.pop()
+            tree = dirs
+            try:
+                for part in parts:
+                    assert part != '', path
+                    if part not in tree:
+                        tree[part] = {}
+                    tree = tree[part]
+                tree[key] = tree.get(key, 0) + size
+            except:
+                print >>sys.stderr, sym, parts, key
+                raise
+        else:
+            key = 'symbols without paths'
+            if key not in dirs:
+                dirs[key] = {}
+            tree = dirs[key]
+            subkey = 'misc'
+            if (sym.endswith('::__FUNCTION__') or
+                sym.endswith('::__PRETTY_FUNCTION__')):
+                subkey = '__FUNCTION__'
+            elif sym.startswith('CSWTCH.'):
+                subkey = 'CSWTCH'
+            elif '::' in sym:
+                subkey = sym[0:sym.find('::') + 2]
+            #else:
+            #    print >>sys.stderr, 'unbucketed (no path?):', sym, type, size, path
+            tree[subkey] = tree.get(subkey, 0) + size
+    return dirs
+
+
+def jsonify_tree(tree, name):
+    children = []
+    total = 0
+    files = 0
+
+    for key, val in tree.iteritems():
+        if isinstance(val, dict):
+            subtree = jsonify_tree(val, key)
+            total += subtree['data']['$area']
+            children.append(subtree)
+        else:
+            total += val
+            children.append({
+                    'name': key + ' ' + format_bytes(val),
+                    'data': { '$area': val }
+                    })
+
+    children.sort(key=lambda child: -child['data']['$area'])
+
+    return {
+        'name': name + ' ' + format_bytes(total),
+        'data': {
+            '$area': total,
+            },
+        'children': children,
+        }
+
+
+def dump_nm(infile, outfile):
+    dirs = treeify_syms(parse_nm(infile))
+    out = sys.stdout
+    if outfile is not None:
+        out = open(outfile, 'w')
+    out.write('var kTree = ' + json.dumps(jsonify_tree(dirs, '/'), indent=2))
+    out.flush()
+    if outfile is not None:
+        out.close()
+
+
+def run_pa2l(outfile, library, arch, threads, verbose=False):
+    """Run a parallel addr2line processing engine to dump and resolve symbols"""
+    out_dir = os.getenv('CHROMIUM_OUT_DIR', 'out')
+    buildtype = os.getenv('BUILDTYPE', 'Release')
+    classpath = out_dir + '/' + buildtype + '/lib.java/binary_size_java.jar'
+    cmd = ['java',
+           '-classpath', classpath,
+           'org.chromium.tools.binary_size.ParallelAddress2Line',
+           '--disambiguate',
+           '--outfile', outfile,
+           '--library', library,
+           '--threads', threads]
+    if verbose is True:
+        cmd.append('--verbose')
+    if arch == 'android-arm':
+        cmd.extend([
+                    '--nm', 'third_party/android_tools/ndk/toolchains/arm-linux-androideabi-4.7/prebuilt/linux-x86_64/bin/arm-linux-androideabi-nm',
+                    '--addr2line', 'third_party/android_tools/ndk/toolchains/arm-linux-androideabi-4.7/prebuilt/linux-x86_64/bin/arm-linux-androideabi-addr2line',
+        ])
+    elif arch == 'android-mips':
+        cmd.extend([
+                    '--nm', 'third_party/android_tools/ndk/toolchains/mipsel-linux-android-4.7/prebuilt/linux-x86_64/bin/mipsel-linux-android-nm',
+                    '--addr2line', 'third_party/android_tools/ndk/toolchains/mipsel-linux-android-4.7/prebuilt/linux-x86_64/bin/mipsel-linux-android-addr2line',
+        ])
+    elif arch == 'android-x86':
+        cmd.extend([
+                    '--nm', 'third_party/android_tools/ndk/toolchains/x86-4.7/prebuilt/linux-x86_64/bin/i686-linux-android-nm'
+                    '--addr2line', 'third_party/android_tools/ndk/toolchains/x86-4.7/prebuilt/linux-x86_64/bin/i686-linux-android-addr2line',
+        ])
+    # else, use whatever is in PATH (don't pass --nm or --addr2line)
+
+    if verbose:
+        print cmd
+
+    return_code = subprocess.call(cmd)
+    if return_code:
+        raise RuntimeError('Failed to run ParallelAddress2Line: returned ' + str(return_code))
+
+usage="""%prog [options]
+
+Runs a spatial analysis on a given library, looking up the source locations of
+its symbols and calculating how much space each directory, source file, and so
+on is taking. The result is a report that can be used to pinpoint sources of
+large portions of the binary, etceteras.
+
+Under normal circumstances, you only need to pass two arguments, thusly:
+
+  %prog --library /path/to/library --destdir /path/to/output
+
+In this mode, the program will dump the symbols from the specified library and
+map those symbols back to source locations, producing a web-based report in the
+specified output directory.
+
+Other options are available via '--help'.
+"""
+parser = optparse.OptionParser(usage=usage)
+parser.add_option('--nm-in', dest='nm_in', metavar='PATH',
+                  help='if specified, use nm input from <path> instead of '
+                  'generating it. Note that source locations should be present '
+                  'in the file; i.e., no addr2line symbol lookups will be '
+                  'performed when this option is specified. Mutually exclusive '
+                  'with --library.')
+parser.add_option('--destdir', metavar='PATH',
+                  help='write output to the specified directory. An HTML '
+                  'report is generated here along with supporting files; any '
+                  'existing report will be overwritten.')
+parser.add_option('--library', metavar='PATH',
+                  help='if specified, process symbols in the library at the '
+                  'specified path. Mutually exclusive with --nm-in.')
+parser.add_option('--arch',
+                  help='the architecture that the library is targeted to. '
+                  'Currently supports the following: '
+                  'host-native, android-arm, android-mips, android-x86.'
+                  'the default is host-native. This determines '
+                  'what nm/addr2line binaries are used. When host-native is '
+                  'chosen (the default), the program will use whichever '
+                  'nm/addr2line binaries are on the PATH. This is appropriate '
+                  'when you are analyzing a binary by and for your computer. '
+                  'This argument is only valid when using --library.')
+parser.add_option('--pa2l-threads', dest='threads',
+                  help='number of threads to use for the parallel addr2line '
+                  'processing pool; defaults to 1. More threads greatly '
+                  'improve throughput but eat RAM like popcorn, and take '
+                  'several gigabytes each. Start low and ramp this number up '
+                  'until your machine begins to struggle with RAM.'
+                  'This argument is only valid when using --library.')
+parser.add_option('-v', dest='verbose', action='store_true',
+                  help='be verbose, printing lots of status information.')
+parser.add_option('--nm-out', dest='nm_out',
+                  help='keep the nm output file, and store it at the specified '
+                  'path. This is useful if you want to see the fully processed '
+                  'nm output after the symbols have been mapped to source '
+                  'locations. By default, a tempfile is used and is deleted '
+                  'when the program terminates.'
+                  'This argument is only valid when using --library.')
+opts, args = parser.parse_args()
+
+if ((not opts.library) and (not opts.nm_in)) or (opts.library and opts.nm_in):
+    parser.error('exactly one of --library or --nm-in is required')
+if (opts.nm_in):
+    if opts.threads:
+        print >> sys.stderr, ('WARNING: --pa2l-threads has no effect '
+        'when used with --nm-in')
+    if opts.arch:
+        print >> sys.stderr, ('WARNING: --arch has no effect '
+        'when used with --nm-in')
+if not opts.destdir:
+    parser.error('--destdir is required argument')
+if not opts.threads:
+    opts.threads = 1
+if not opts.arch:
+    opts.arch = 'host-native'
+
+if opts.arch not in ['host-native', 'android-arm',
+                     'android-mips', 'android-x86']:
+    parser.error('arch must be one of '
+                 '[host-native,android-arm,android-mips,android-x86]')
+
+nm_in = opts.nm_in
+temp_file = None
+if nm_in is None:
+    if opts.nm_out is None:
+        temp_file = tempfile.NamedTemporaryFile(prefix='binary_size_nm', delete=False)
+        nm_in = temp_file.name
+    else:
+        nm_in = opts.nm_out
+
+    if opts.verbose:
+        print 'Running parallel addr2line, dumping symbols to ' + nm_in;
+    run_pa2l(outfile=nm_in,
+             library=opts.library,
+             arch=opts.arch,
+             threads=opts.threads,
+             verbose=(opts.verbose is True))
+elif opts.verbose:
+    print 'Using nm input from ' + nm_in
+
+if not os.path.exists(opts.destdir):
+    os.makedirs(opts.destdir, 0755)
+
+jspath = opts.destdir + '/treemap-dump.js'
+nmfile = open(nm_in, 'r')
+dump_nm(nmfile, jspath)
+if not os.path.exists(opts.destdir + '/webtreemap.js'):
+    url = 'https://github.com/martine/webtreemap/archive/gh-pages.zip'
+    tmpdir = tempfile.mkdtemp('binary_size')
+    try:
+        cmd = ['wget', '-O', tmpdir + '/webtreemap.zip', url]
+        return_code = subprocess.call(cmd)
+        if return_code:
+            raise RuntimeError('Failed to download: returned ' + str(return_code))
+        cmd = ['unzip', '-o', tmpdir + '/webtreemap.zip', '-d', tmpdir]
+        return_code = subprocess.call(cmd)
+        if return_code:
+            raise RuntimeError('Failed to unzip: returned ' + str(return_code))
+
+        shutil.move(tmpdir + '/webtreemap-gh-pages/COPYING', opts.destdir)
+        shutil.move(tmpdir + '/webtreemap-gh-pages/webtreemap.js', opts.destdir)
+        shutil.move(tmpdir + '/webtreemap-gh-pages/webtreemap.css', opts.destdir)
+    finally:
+        shutil.rmtree(tmpdir, ignore_errors=True)
+shutil.copy('tools/binary_size/template/index.html', opts.destdir)
+if opts.verbose:
+    print 'Report saved to ' + opts.destdir + '/index.html'