view mercurial/lsprof.py @ 26379:39d643252b9f

revlog: use existing file handle when reading during _addrevision _addrevision() may need to read from revlogs as part of computing deltas. Previously, we would flush existing file handles and open a new, short-lived file handle to perform the reading. If we have an existing file handle, it seems logical to reuse it for reading instead of opening a new file handle. This patch makes that the new behavior. After this patch, revlog files are only reopened when adding revisions if the revlog is switched from inline to non-inline. On Linux when unbundling a bundle of the mozilla-central repo, this patch has the following impact on system call counts: Call Before After Delta write 827,639 673,390 -154,249 open 700,103 684,089 -16,014 read 74,489 74,489 0 fstat 493,924 461,896 -32,028 close 249,131 233,117 -16,014 stat 242,001 242,001 0 lstat 18,676 18,676 0 lseek 20,268 20,268 0 ioctl 14,652 13,173 -1,479 TOTAL 3,180,758 2,930,679 -250,079 It's worth noting that many of the open() calls fail due to missing files. That's why there are many more open() calls than close(). Despite the significant system call reduction, this change does not seem to have a significant performance impact on Linux. On Windows 10 (not a VM, on a SSD), this patch appears to reduce unbundle time for mozilla-central from ~960s to ~920s. This isn't as significant as I was hoping. But a decrease it is nonetheless. Still, Windows unbundle performance is still >2x slower than Linux. Despite the lack of significant gains, fewer system calls is fewer system calls. If nothing else, this will narrow the focus of potential areas to optimize in the future.
author Gregory Szorc <gregory.szorc@gmail.com>
date Sun, 27 Sep 2015 16:08:18 -0700
parents a40d608e2a7b
children 9c75daf89450
line wrap: on
line source

import sys
from _lsprof import Profiler, profiler_entry

__all__ = ['profile', 'Stats']

def profile(f, *args, **kwds):
    """XXX docstring"""
    p = Profiler()
    p.enable(subcalls=True, builtins=True)
    try:
        f(*args, **kwds)
    finally:
        p.disable()
    return Stats(p.getstats())


class Stats(object):
    """XXX docstring"""

    def __init__(self, data):
        self.data = data

    def sort(self, crit="inlinetime"):
        """XXX docstring"""
        if crit not in profiler_entry.__dict__:
            raise ValueError("Can't sort by %s" % crit)
        self.data.sort(key=lambda x: getattr(x, crit), reverse=True)
        for e in self.data:
            if e.calls:
                e.calls.sort(key=lambda x: getattr(x, crit), reverse=True)

    def pprint(self, top=None, file=None, limit=None, climit=None):
        """XXX docstring"""
        if file is None:
            file = sys.stdout
        d = self.data
        if top is not None:
            d = d[:top]
        cols = "% 12s %12s %11.4f %11.4f   %s\n"
        hcols = "% 12s %12s %12s %12s %s\n"
        file.write(hcols % ("CallCount", "Recursive", "Total(s)",
                            "Inline(s)", "module:lineno(function)"))
        count = 0
        for e in d:
            file.write(cols % (e.callcount, e.reccallcount, e.totaltime,
                               e.inlinetime, label(e.code)))
            count += 1
            if limit is not None and count == limit:
                return
            ccount = 0
            if climit and e.calls:
                for se in e.calls:
                    file.write(cols % (se.callcount, se.reccallcount,
                                       se.totaltime, se.inlinetime,
                                       "    %s" % label(se.code)))
                    count += 1
                    ccount += 1
                    if limit is not None and count == limit:
                        return
                    if climit is not None and ccount == climit:
                        break

    def freeze(self):
        """Replace all references to code objects with string
        descriptions; this makes it possible to pickle the instance."""

        # this code is probably rather ickier than it needs to be!
        for i in range(len(self.data)):
            e = self.data[i]
            if not isinstance(e.code, str):
                self.data[i] = type(e)((label(e.code),) + e[1:])
            if e.calls:
                for j in range(len(e.calls)):
                    se = e.calls[j]
                    if not isinstance(se.code, str):
                        e.calls[j] = type(se)((label(se.code),) + se[1:])

_fn2mod = {}

def label(code):
    if isinstance(code, str):
        return code
    try:
        mname = _fn2mod[code.co_filename]
    except KeyError:
        for k, v in list(sys.modules.iteritems()):
            if v is None:
                continue
            if not isinstance(getattr(v, '__file__', None), str):
                continue
            if v.__file__.startswith(code.co_filename):
                mname = _fn2mod[code.co_filename] = k
                break
        else:
            mname = _fn2mod[code.co_filename] = '<%s>' % code.co_filename

    return '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)


if __name__ == '__main__':
    import os
    sys.argv = sys.argv[1:]
    if not sys.argv:
        print >> sys.stderr, "usage: lsprof.py <script> <arguments...>"
        sys.exit(2)
    sys.path.insert(0, os.path.abspath(os.path.dirname(sys.argv[0])))
    stats = profile(execfile, sys.argv[0], globals(), locals())
    stats.sort()
    stats.pprint()