contrib/catapipe.py

dirstate-tree: Change status() results to not borrow DirstateMap

The `status` function takes a `&'tree mut DirstateMap<'on_disk>` parameter.
`'on_disk` borrows a read-only byte buffer with the contents of the
`.hg/dirstate` file. `DirstateMap` internally uses represents file paths as
`std::borrow::Cow<'on_disk, HgPath>`, which borrows the byte buffer when
possible and allocates an owned string if not, such as for files added to the
dirstate after it was loaded from disk.

Previously the return type of of `status` has a `'tree` lifetime, meaning it
could borrow all paths from the `DirstateMap`. With this changeset, that
lifetime is changed to `'on_disk` meaning that only paths from the byte buffer
can be borrowed, and paths allocated by `DirstateMap` must be copied.

Usually most paths are in the byte buffer, and most paths are not part of the
return value of `status`, so the number of extra copies should be small.

This change will enable `status` to mutate the `DirstateMap` after it has
finished constructing its return value. Previously such mutation would be
prevented by possible on-going borrows.

Differential Revision: https://phab.mercurial-scm.org/D10824

#!/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.

Usage:
    Terminal 1: $ catapipe.py /tmp/mypipe /tmp/trace.json
    Terminal 2: $ HGCATAPULTSERVERPIPE=/tmp/mypipe hg root
    <ctrl-c catapipe.py in Terminal 1>
    $ catapult/tracing/bin/trace2html /tmp/trace.json  # produce /tmp/trace.html
    <open trace.html in your browser of choice; the WASD keys are very useful>
    (catapult is located at https://github.com/catapult-project/catapult)

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. To trace *only* run-tests, use HGTESTCATAPULTSERVERPIPE instead.
"""
from __future__ import absolute_import, print_function

import argparse
import json
import os
import timeit

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

_threadmap = {}

# Timeit already contains the whole logic about which timer to use based on
# Python version and OS
timer = timeit.default_timer


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 json file to create where the traces ' 'will be stored.',
    )
    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 = timer()
            while True:
                ev = f.readline().strip()
                if not ev:
                    continue
                now = timer()
                if args.debug:
                    print(ev)
                verb, session, label = ev.split(' ', 2)
                if session not in _threadmap:
                    _threadmap[session] = len(_threadmap)
                if verb == 'COUNTER':
                    amount, label = label.split(' ', 1)
                    payload_args = {'value': int(amount)}
                else:
                    payload_args = {}
                pid = _threadmap[session]
                ts_micros = (now - start) * 1000000
                out.write(
                    json.dumps(
                        {
                            "name": label,
                            "cat": "misc",
                            "ph": _TYPEMAP[verb],
                            "ts": ts_micros,
                            "pid": pid,
                            "tid": 1,
                            "args": payload_args,
                        }
                    )
                )
                out.write(',\n')
    finally:
        os.unlink(fn)


if __name__ == '__main__':
    main()