Mercurial > public > mercurial-scm > hg-stable
annotate mercurial/worker.py @ 30421:47de34f79f93
worker: wait worker pid explicitly
Before this patch, waitforworkers uses os.wait() to collect child workers, and
only wait len(pids) processes. This can have serious issues if other code
spawns new processes and does not reap them: 1. worker.py may get wrong exit
code and kill innocent workers. 2. worker.py may continue without waiting for
all workers to complete.
This patch fixes the issue by using waitpid to wait worker pid explicitly.
However, this patch introduces a new issue: worker failure may not be handled
immediately. The issue will be addressed in next patches.
author | Jun Wu <quark@fb.com> |
---|---|
date | Thu, 28 Jul 2016 20:51:20 +0100 |
parents | 7a5d6e2fd2d5 |
children | 7bc25549e084 |
rev | line source |
---|---|
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
1 # worker.py - master-slave parallelism support |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
2 # |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
3 # Copyright 2013 Facebook, Inc. |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
4 # |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
5 # This software may be used and distributed according to the terms of the |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
6 # GNU General Public License version 2 or any later version. |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
7 |
25992
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
8 from __future__ import absolute_import |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
9 |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
10 import errno |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
11 import os |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
12 import signal |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
13 import sys |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
14 import threading |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
15 |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
16 from .i18n import _ |
30406 | 17 from . import ( |
18 error, | |
19 util, | |
20 ) | |
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
21 |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
22 def countcpus(): |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
23 '''try to count the number of CPUs on the system''' |
26568
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
24 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
25 # posix |
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
26 try: |
26568
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
27 n = int(os.sysconf('SC_NPROCESSORS_ONLN')) |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
28 if n > 0: |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
29 return n |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
30 except (AttributeError, ValueError): |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
31 pass |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
32 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
33 # windows |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
34 try: |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
35 n = int(os.environ['NUMBER_OF_PROCESSORS']) |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
36 if n > 0: |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
37 return n |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
38 except (KeyError, ValueError): |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
39 pass |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
40 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
41 return 1 |
18636
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
42 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
43 def _numworkers(ui): |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
44 s = ui.config('worker', 'numcpus') |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
45 if s: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
46 try: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
47 n = int(s) |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
48 if n >= 1: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
49 return n |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
50 except ValueError: |
26587
56b2bcea2529
error: get Abort from 'error' instead of 'util'
Pierre-Yves David <pierre-yves.david@fb.com>
parents:
26568
diff
changeset
|
51 raise error.Abort(_('number of cpus must be an integer')) |
18636
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
52 return min(max(countcpus(), 4), 32) |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
53 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
54 if os.name == 'posix': |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
55 _startupcost = 0.01 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
56 else: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
57 _startupcost = 1e30 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
58 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
59 def worthwhile(ui, costperop, nops): |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
60 '''try to determine whether the benefit of multiple processes can |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
61 outweigh the cost of starting them''' |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
62 linear = costperop * nops |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
63 workers = _numworkers(ui) |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
64 benefit = linear - (_startupcost * workers + linear / workers) |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
65 return benefit >= 0.15 |
18637
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
66 |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
67 def worker(ui, costperarg, func, staticargs, args): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
68 '''run a function, possibly in parallel in multiple worker |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
69 processes. |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
70 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
71 returns a progress iterator |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
72 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
73 costperarg - cost of a single task |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
74 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
75 func - function to run |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
76 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
77 staticargs - arguments to pass to every invocation of the function |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
78 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
79 args - arguments to split into chunks, to pass to individual |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
80 workers |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
81 ''' |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
82 if worthwhile(ui, costperarg, len(args)): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
83 return _platformworker(ui, func, staticargs, args) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
84 return func(*staticargs + (args,)) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
85 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
86 def _posixworker(ui, func, staticargs, args): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
87 rfd, wfd = os.pipe() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
88 workers = _numworkers(ui) |
18708
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
89 oldhandler = signal.getsignal(signal.SIGINT) |
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
90 signal.signal(signal.SIGINT, signal.SIG_IGN) |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
91 pids, problem = [], [0] |
30420
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
92 def killworkers(): |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
93 # if one worker bails, there's no good reason to wait for the rest |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
94 for p in pids: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
95 try: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
96 os.kill(p, signal.SIGTERM) |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
97 except OSError as err: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
98 if err.errno != errno.ESRCH: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
99 raise |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
100 def waitforworkers(): |
30421 | 101 for pid in pids: |
102 st = _exitstatus(os.waitpid(pid, 0)[1]) | |
30420
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
103 if st and not problem[0]: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
104 problem[0] = st |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
105 killworkers() |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
106 for pargs in partition(args, workers): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
107 pid = os.fork() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
108 if pid == 0: |
18708
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
109 signal.signal(signal.SIGINT, oldhandler) |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
110 try: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
111 os.close(rfd) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
112 for i, item in func(*(staticargs + (pargs,))): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
113 os.write(wfd, '%d %s\n' % (i, item)) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
114 os._exit(0) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
115 except KeyboardInterrupt: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
116 os._exit(255) |
19408
c7ec39c1a381
worker: properly report errors from worker processes (issue3982)
Matt Mackall <mpm@selenic.com>
parents:
19406
diff
changeset
|
117 # other exceptions are allowed to propagate, we rely |
c7ec39c1a381
worker: properly report errors from worker processes (issue3982)
Matt Mackall <mpm@selenic.com>
parents:
19406
diff
changeset
|
118 # on lock.py's pid checks to avoid release callbacks |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
119 pids.append(pid) |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
120 pids.reverse() |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
121 os.close(wfd) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
122 fp = os.fdopen(rfd, 'rb', 0) |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
123 t = threading.Thread(target=waitforworkers) |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
124 t.start() |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
125 def cleanup(): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
126 signal.signal(signal.SIGINT, oldhandler) |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
127 t.join() |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
128 status = problem[0] |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
129 if status: |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
130 if status < 0: |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
131 os.kill(os.getpid(), -status) |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
132 sys.exit(status) |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
133 try: |
30406 | 134 for line in util.iterfile(fp): |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
135 l = line.split(' ', 1) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
136 yield int(l[0]), l[1][:-1] |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
137 except: # re-raises |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
138 killworkers() |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
139 cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
140 raise |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
141 cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
142 |
18707
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
143 def _posixexitstatus(code): |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
144 '''convert a posix exit status into the same form returned by |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
145 os.spawnv |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
146 |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
147 returns None if the process was stopped instead of exiting''' |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
148 if os.WIFEXITED(code): |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
149 return os.WEXITSTATUS(code) |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
150 elif os.WIFSIGNALED(code): |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
151 return -os.WTERMSIG(code) |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
152 |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
153 if os.name != 'nt': |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
154 _platformworker = _posixworker |
18707
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
155 _exitstatus = _posixexitstatus |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
156 |
18637
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
157 def partition(lst, nslices): |
28181
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
158 '''partition a list into N slices of roughly equal size |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
159 |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
160 The current strategy takes every Nth element from the input. If |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
161 we ever write workers that need to preserve grouping in input |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
162 we should consider allowing callers to specify a partition strategy. |
28292
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
163 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
164 mpm is not a fan of this partitioning strategy when files are involved. |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
165 In his words: |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
166 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
167 Single-threaded Mercurial makes a point of creating and visiting |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
168 files in a fixed order (alphabetical). When creating files in order, |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
169 a typical filesystem is likely to allocate them on nearby regions on |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
170 disk. Thus, when revisiting in the same order, locality is maximized |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
171 and various forms of OS and disk-level caching and read-ahead get a |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
172 chance to work. |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
173 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
174 This effect can be quite significant on spinning disks. I discovered it |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
175 circa Mercurial v0.4 when revlogs were named by hashes of filenames. |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
176 Tarring a repo and copying it to another disk effectively randomized |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
177 the revlog ordering on disk by sorting the revlogs by hash and suddenly |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
178 performance of my kernel checkout benchmark dropped by ~10x because the |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
179 "working set" of sectors visited no longer fit in the drive's cache and |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
180 the workload switched from streaming to random I/O. |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
181 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
182 What we should really be doing is have workers read filenames from a |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
183 ordered queue. This preserves locality and also keeps any worker from |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
184 getting more than one file out of balance. |
28181
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
185 ''' |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
186 for i in range(nslices): |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
187 yield lst[i::nslices] |