view contrib/catapipe.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload The search itself can take an extreme amount of time if there are a lot of revisions involved. I've got a local repo that took 6 minutes to push 1850 commits, and 60% of that time was spent here (there are ~70K files): \ 58.1% wrapper.py: extractpointers line 297: pointers = extractpointers(... | 57.7% wrapper.py: pointersfromctx line 352: for p in pointersfromctx(ct... | 57.4% wrapper.py: pointerfromctx line 397: p = pointerfromctx(ctx, f, ... \ 38.7% context.py: __contains__ line 368: if f not in ctx: | 38.7% util.py: __get__ line 82: return key in self._manifest | 38.7% context.py: _manifest line 1416: result = self.func(obj) | 38.7% manifest.py: read line 472: return self._manifestctx.re... \ 25.6% revlog.py: revision line 1562: text = rl.revision(self._node) \ 12.8% revlog.py: _chunks line 2217: bins = self._chunks(chain, ... | 12.0% revlog.py: decompressline 2112: ladd(decomp(buffer(data, ch... \ 7.8% revlog.py: checkhash line 2232: self.checkhash(text, node, ... | 7.8% revlog.py: hash line 2315: if node != self.hash(text, ... | 7.8% revlog.py: hash line 2242: return hash(text, p1, p2) \ 12.0% manifest.py: __init__ line 1565: self._data = manifestdict(t... \ 16.8% context.py: filenode line 378: if not _islfs(fctx.filelog(... | 15.7% util.py: __get__ line 706: return self._filelog | 14.8% context.py: _filelog line 1416: result = self.func(obj) | 14.8% localrepo.py: file line 629: return self._repo.file(self... | 14.8% filelog.py: __init__ line 1134: return filelog.filelog(self... | 14.5% revlog.py: __init__ line 24: censorable=True)
author Matt Harbison <matt_harbison@yahoo.com>
date Fri, 24 Aug 2018 17:45:46 -0400
parents 9a81f126f9fa
children e9706686451b
line wrap: on
line source

#!/usr/bin/env python3
#
# Copyright 2018 Google LLC.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Tool read primitive events from a pipe to produce a catapult trace.

For now the event stream supports

  START $SESSIONID ...

and

  END $SESSIONID ...

events. Everything after the SESSIONID (which must not contain spaces)
is used as a label for the event. Events are timestamped as of when
they arrive in this process and are then used to produce catapult
traces that can be loaded in Chrome's about:tracing utility. It's
important that the event stream *into* this process stay simple,
because we have to emit it from the shell scripts produced by
run-tests.py.

Typically you'll want to place the path to the named pipe in the
HGCATAPULTSERVERPIPE environment variable, which both run-tests and hg
understand.
"""
from __future__ import absolute_import, print_function

import argparse
import datetime
import json
import os

_TYPEMAP = {
    'START': 'B',
    'END': 'E',
}

_threadmap = {}

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('pipe', type=str, nargs=1,
                        help='Path of named pipe to create and listen on.')
    parser.add_argument('output', default='trace.json', type=str, nargs='?',
                        help='Path of named pipe to create and listen on.')
    parser.add_argument('--debug', default=False, action='store_true',
                        help='Print useful debug messages')
    args = parser.parse_args()
    fn = args.pipe[0]
    os.mkfifo(fn)
    try:
        with open(fn) as f, open(args.output, 'w') as out:
            out.write('[\n')
            start = datetime.datetime.now()
            while True:
                ev = f.readline().strip()
                if not ev:
                    continue
                now = datetime.datetime.now()
                if args.debug:
                    print(ev)
                verb, session, label = ev.split(' ', 2)
                if session not in _threadmap:
                    _threadmap[session] = len(_threadmap)
                pid = _threadmap[session]
                ts_micros = (now - start).total_seconds() * 1000000
                out.write(json.dumps(
                    {
                        "name": label,
                        "cat": "misc",
                        "ph": _TYPEMAP[verb],
                        "ts": ts_micros,
                        "pid": pid,
                        "tid": 1,
                        "args": {}
                    }))
                out.write(',\n')
    finally:
        os.unlink(fn)

if __name__ == '__main__':
    main()