scripts/bloat-o-meter

#!/usr/bin/python
#
# Copyright 2004 Matt Mackall <mpm@selenic.com>
#
# inspired by perl Bloat-O-Meter (c) 1997 by Andi Kleen
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

import sys, os, re

def usage():
    sys.stderr.write("usage: %s file1 file2\n" % sys.argv[0])
    sys.exit(-1)

if len(sys.argv) < 3:
    usage()

for f in sys.argv[1:3]:
    if not os.path.exists(f):
        sys.stderr.write("Error: file '%s' does not exist\n" % f)
        usage()

sym_args = " ".join(sys.argv[3:])
def getsizes(file):
    sym, alias = {}, {}
    dynsym_filter = re.compile("^\s+\d+:\s+[\dA-Fa-f]+\s+\d+\s+\w+\s+\w+\s+\w+\s+\w+\s+\w+\n$")
    for l in os.popen("readelf -W -s %s %s" % (sym_args, file)).readlines():
        if not dynsym_filter.match(l): continue
        num, value, size, typ, bind, vis, ndx, name = l.strip().split()
        if ndx == "UND": continue # skip undefined
        if typ in ["SECTION", "FILES"]: continue # skip sections and files
        if "." in name: name = "static." + name.split(".")[0]
        value = int(value, 16)
        size = int(size)
        if bind != "GLOBAL": # see if it is an alias
            alias[name] = {"addr" : value, "size":  size}
        else:
            sym[name] = {"addr" : value, "size":  size}
    for a_nam, a_dat in alias.iteritems():
        impl = [k for k, v in sym.iteritems() if v.get("addr") == a_dat["addr"]]
        # If the non-GLOBAL sym has an implementation elsewhere then
        # it's an alias, disregard it.
        if not impl:
            # If this non-GLOBAL sym does not have an implementation at
            # another address, then treat it as a normal symbol.
            sym[a_nam] = a_dat
    for l in os.popen("readelf -W -S " + file).readlines():
        x = l.split()
        if len(x)<6: continue
        # Should take these into account too!
        #if x[1] not in [".text", ".rodata", ".symtab", ".strtab"]: continue
        if x[1] not in [".rodata"]: continue
        sym[x[1]] = {"addr" : int(x[3], 16), "size" : int(x[5], 16)}
    return sym

old = getsizes(sys.argv[1])
new = getsizes(sys.argv[2])
grow, shrink, add, remove, up, down = 0, 0, 0, 0, 0, 0
delta, common = [], []

for a in old.iterkeys():
    if a in new:
        common.append(a)

for name in old:
    if name not in common:
        remove += 1
        sz = old[name].get("size", 0)
        down += sz
        delta.append((-sz, name))

for name in new:
    if name not in common:
        add += 1
        sz = new[name].get("size", 0)
        up += sz
        delta.append((sz, name))

for name in common:
        d = new[name].get("size", 0) - old[name].get("size", 0)
        if d>0: grow, up = grow+1, up+d
        elif d<0: shrink, down = shrink+1, down-d
        else:
            continue
        delta.append((d, name))

delta.sort()
delta.reverse()

print "%-48s %7s %7s %+7s" % ("function", "old", "new", "delta")
for d, n in delta:
    if d:
        old_sz = old.get(n, {}).get("size", "-")
        new_sz = new.get(n, {}).get("size", "-")
        print "%-48s %7s %7s %+7d" % (n, old_sz, new_sz, d)
print "-"*78
total="(add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s)%%sTotal: %s bytes"\
    % (add, remove, grow, shrink, up, -down, up-down)
print total % (" "*(80-len(total)))