view mercurial/lsprofcalltree.py @ 23497:5817f71c2336

obsstore: disable garbage collection during initialization (issue4456)

Python garbage collection is triggered by container creation. So code that
creates a lot of tuples tends to trigger GC a lot. We disable the gc during
obsolescence marker parsing and associated initialization. This provides an
interesting speedup (25%).

Load marker function on my 58758 markers repo:
before: 0.468247 seconds
after:  0.344362 seconds

The benefit is a bit less visible overall. With python2.6 on my system I see:
after:  0.60
before: 0.53

The difference is probably explained by the delaying of a costly GC. (but there
is still a win). Marking involved tuples, lists and dicts as ignorable by the
garbage collector should give us more benefit. But this is another adventure.

Thanks goes to Siddharth Agarwal for the lead.

"""
lsprofcalltree.py - lsprof output which is readable by kcachegrind

Authors:
    * David Allouche <david <at> allouche.net>
    * Jp Calderone & Itamar Shtull-Trauring
    * Johan Dahlin

This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""

def label(code):
    if isinstance(code, str):
        return '~' + code    # built-in functions ('~' sorts at the end)
    else:
        return '%s %s:%d' % (code.co_name,
                             code.co_filename,
                             code.co_firstlineno)

class KCacheGrind(object):
    def __init__(self, profiler):
        self.data = profiler.getstats()
        self.out_file = None

    def output(self, out_file):
        self.out_file = out_file
        print >> out_file, 'events: Ticks'
        self._print_summary()
        for entry in self.data:
            self._entry(entry)

    def _print_summary(self):
        max_cost = 0
        for entry in self.data:
            totaltime = int(entry.totaltime * 1000)
            max_cost = max(max_cost, totaltime)
        print >> self.out_file, 'summary: %d' % (max_cost,)

    def _entry(self, entry):
        out_file = self.out_file

        code = entry.code
        #print >> out_file, 'ob=%s' % (code.co_filename,)
        if isinstance(code, str):
            print >> out_file, 'fi=~'
        else:
            print >> out_file, 'fi=%s' % (code.co_filename,)
        print >> out_file, 'fn=%s' % (label(code),)

        inlinetime = int(entry.inlinetime * 1000)
        if isinstance(code, str):
            print >> out_file, '0 ', inlinetime
        else:
            print >> out_file, '%d %d' % (code.co_firstlineno, inlinetime)

        # recursive calls are counted in entry.calls
        if entry.calls:
            calls = entry.calls
        else:
            calls = []

        if isinstance(code, str):
            lineno = 0
        else:
            lineno = code.co_firstlineno

        for subentry in calls:
            self._subentry(lineno, subentry)
        print >> out_file

    def _subentry(self, lineno, subentry):
        out_file = self.out_file
        code = subentry.code
        #print >> out_file, 'cob=%s' % (code.co_filename,)
        print >> out_file, 'cfn=%s' % (label(code),)
        if isinstance(code, str):
            print >> out_file, 'cfi=~'
            print >> out_file, 'calls=%d 0' % (subentry.callcount,)
        else:
            print >> out_file, 'cfi=%s' % (code.co_filename,)
            print >> out_file, 'calls=%d %d' % (
                subentry.callcount, code.co_firstlineno)

        totaltime = int(subentry.totaltime * 1000)
        print >> out_file, '%d %d' % (lineno, totaltime)