Mercurial > public > mercurial-scm > hg-stable
annotate mercurial/worker.py @ 30640:a150173da1c1
py3: replace os.environ with encoding.environ (part 2 of 5)
author | Pulkit Goyal <7895pulkit@gmail.com> |
---|---|
date | Sun, 18 Dec 2016 01:46:39 +0530 |
parents | 86cd09bc13ba |
children | d524c88511a7 |
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 |
2d76f8a2d831
worker: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
25660
diff
changeset
|
15 from .i18n import _ |
30406 | 16 from . import ( |
30640
a150173da1c1
py3: replace os.environ with encoding.environ (part 2 of 5)
Pulkit Goyal <7895pulkit@gmail.com>
parents:
30530
diff
changeset
|
17 encoding, |
30406 | 18 error, |
30530
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
19 scmutil, |
30406 | 20 util, |
21 ) | |
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
22 |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
23 def countcpus(): |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
24 '''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
|
25 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
26 # posix |
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
27 try: |
26568
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
28 n = int(os.sysconf('SC_NPROCESSORS_ONLN')) |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
29 if n > 0: |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
30 return n |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
31 except (AttributeError, ValueError): |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
32 pass |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
33 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
34 # windows |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
35 try: |
30640
a150173da1c1
py3: replace os.environ with encoding.environ (part 2 of 5)
Pulkit Goyal <7895pulkit@gmail.com>
parents:
30530
diff
changeset
|
36 n = int(encoding.environ['NUMBER_OF_PROCESSORS']) |
26568
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
37 if n > 0: |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
38 return n |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
39 except (KeyError, ValueError): |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
40 pass |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
41 |
c0501c26b05c
worker: restore old countcpus code (issue4869)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26063
diff
changeset
|
42 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
|
43 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
44 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
|
45 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
|
46 if s: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
47 try: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
48 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
|
49 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
|
50 return n |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
51 except ValueError: |
26587
56b2bcea2529
error: get Abort from 'error' instead of 'util'
Pierre-Yves David <pierre-yves.david@fb.com>
parents:
26568
diff
changeset
|
52 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
|
53 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
|
54 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
55 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
|
56 _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
|
57 else: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
58 _startupcost = 1e30 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
59 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
60 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
|
61 '''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
|
62 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
|
63 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
|
64 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
|
65 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
|
66 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
|
67 |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
68 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
|
69 '''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
|
70 processes. |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
71 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
72 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
|
73 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
74 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
|
75 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
76 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
|
77 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
78 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
|
79 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
80 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
|
81 workers |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
82 ''' |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
83 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
|
84 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
|
85 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
|
86 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
87 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
|
88 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
|
89 workers = _numworkers(ui) |
18708
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
90 oldhandler = signal.getsignal(signal.SIGINT) |
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
91 signal.signal(signal.SIGINT, signal.SIG_IGN) |
30423 | 92 pids, problem = set(), [0] |
30420
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
93 def killworkers(): |
30432
237b2883cbd8
worker: make sure killworkers() never be interrupted by another SIGCHLD
Yuya Nishihara <yuya@tcha.org>
parents:
30431
diff
changeset
|
94 # unregister SIGCHLD handler as all children will be killed. This |
237b2883cbd8
worker: make sure killworkers() never be interrupted by another SIGCHLD
Yuya Nishihara <yuya@tcha.org>
parents:
30431
diff
changeset
|
95 # function shouldn't be interrupted by another SIGCHLD; otherwise pids |
237b2883cbd8
worker: make sure killworkers() never be interrupted by another SIGCHLD
Yuya Nishihara <yuya@tcha.org>
parents:
30431
diff
changeset
|
96 # could be updated while iterating, which would cause inconsistency. |
237b2883cbd8
worker: make sure killworkers() never be interrupted by another SIGCHLD
Yuya Nishihara <yuya@tcha.org>
parents:
30431
diff
changeset
|
97 signal.signal(signal.SIGCHLD, oldchldhandler) |
30420
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
98 # 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
|
99 for p in pids: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
100 try: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
101 os.kill(p, signal.SIGTERM) |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
102 except OSError as err: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
103 if err.errno != errno.ESRCH: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
104 raise |
30422
7bc25549e084
worker: allow waitforworkers to be non-blocking
Jun Wu <quark@fb.com>
parents:
30421
diff
changeset
|
105 def waitforworkers(blocking=True): |
30424
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
106 for pid in pids.copy(): |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
107 p = st = 0 |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
108 while True: |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
109 try: |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
110 p, st = os.waitpid(pid, (0 if blocking else os.WNOHANG)) |
30431
0e6ce6313e47
worker: fix missed break on successful waitpid()
Yuya Nishihara <yuya@tcha.org>
parents:
30426
diff
changeset
|
111 break |
30424
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
112 except OSError as e: |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
113 if e.errno == errno.EINTR: |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
114 continue |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
115 elif e.errno == errno.ECHILD: |
30434
03f7aa2bd0e3
worker: discard waited pid by anyone who noticed it first
Yuya Nishihara <yuya@tcha.org>
parents:
30433
diff
changeset
|
116 # child would already be reaped, but pids yet been |
03f7aa2bd0e3
worker: discard waited pid by anyone who noticed it first
Yuya Nishihara <yuya@tcha.org>
parents:
30433
diff
changeset
|
117 # updated (maybe interrupted just after waitpid) |
03f7aa2bd0e3
worker: discard waited pid by anyone who noticed it first
Yuya Nishihara <yuya@tcha.org>
parents:
30433
diff
changeset
|
118 pids.discard(pid) |
03f7aa2bd0e3
worker: discard waited pid by anyone who noticed it first
Yuya Nishihara <yuya@tcha.org>
parents:
30433
diff
changeset
|
119 break |
30424
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
120 else: |
5069a8a40b1b
worker: make waitforworkers reentrant
Jun Wu <quark@fb.com>
parents:
30423
diff
changeset
|
121 raise |
30422
7bc25549e084
worker: allow waitforworkers to be non-blocking
Jun Wu <quark@fb.com>
parents:
30421
diff
changeset
|
122 if p: |
30434
03f7aa2bd0e3
worker: discard waited pid by anyone who noticed it first
Yuya Nishihara <yuya@tcha.org>
parents:
30433
diff
changeset
|
123 pids.discard(p) |
30422
7bc25549e084
worker: allow waitforworkers to be non-blocking
Jun Wu <quark@fb.com>
parents:
30421
diff
changeset
|
124 st = _exitstatus(st) |
30420
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
125 if st and not problem[0]: |
7a5d6e2fd2d5
worker: move killworkers and waitforworkers up
Jun Wu <quark@fb.com>
parents:
30406
diff
changeset
|
126 problem[0] = st |
30425
e8fb03cfbbde
worker: add a SIGCHLD handler to collect worker immediately
Jun Wu <quark@fb.com>
parents:
30424
diff
changeset
|
127 def sigchldhandler(signum, frame): |
e8fb03cfbbde
worker: add a SIGCHLD handler to collect worker immediately
Jun Wu <quark@fb.com>
parents:
30424
diff
changeset
|
128 waitforworkers(blocking=False) |
30433
f2d13eb85198
worker: kill workers after all zombie processes are reaped
Yuya Nishihara <yuya@tcha.org>
parents:
30432
diff
changeset
|
129 if problem[0]: |
f2d13eb85198
worker: kill workers after all zombie processes are reaped
Yuya Nishihara <yuya@tcha.org>
parents:
30432
diff
changeset
|
130 killworkers() |
30425
e8fb03cfbbde
worker: add a SIGCHLD handler to collect worker immediately
Jun Wu <quark@fb.com>
parents:
30424
diff
changeset
|
131 oldchldhandler = signal.signal(signal.SIGCHLD, sigchldhandler) |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
132 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
|
133 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
|
134 if pid == 0: |
18708
86524a70c0f6
worker: fix a race in SIGINT handling
Bryan O'Sullivan <bryano@fb.com>
parents:
18707
diff
changeset
|
135 signal.signal(signal.SIGINT, oldhandler) |
30425
e8fb03cfbbde
worker: add a SIGCHLD handler to collect worker immediately
Jun Wu <quark@fb.com>
parents:
30424
diff
changeset
|
136 signal.signal(signal.SIGCHLD, oldchldhandler) |
30530
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
137 |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
138 def workerfunc(): |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
139 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
|
140 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
|
141 os.write(wfd, '%d %s\n' % (i, item)) |
30530
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
142 |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
143 # make sure we use os._exit in all code paths. otherwise the worker |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
144 # may do some clean-ups which could cause surprises like deadlock. |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
145 # see sshpeer.cleanup for example. |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
146 try: |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
147 scmutil.callcatch(ui, workerfunc) |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
148 except KeyboardInterrupt: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
149 os._exit(255) |
30530
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
150 except: # never return, therefore no re-raises |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
151 try: |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
152 ui.traceback() |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
153 finally: |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
154 os._exit(255) |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
155 else: |
86cd09bc13ba
worker: use os._exit for posix worker in all cases
Jun Wu <quark@fb.com>
parents:
30434
diff
changeset
|
156 os._exit(0) |
30423 | 157 pids.add(pid) |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
158 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
|
159 fp = os.fdopen(rfd, 'rb', 0) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
160 def cleanup(): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
161 signal.signal(signal.SIGINT, oldhandler) |
30426
c27614f2dec1
worker: stop using a separate thread waiting for children
Jun Wu <quark@fb.com>
parents:
30425
diff
changeset
|
162 waitforworkers() |
30425
e8fb03cfbbde
worker: add a SIGCHLD handler to collect worker immediately
Jun Wu <quark@fb.com>
parents:
30424
diff
changeset
|
163 signal.signal(signal.SIGCHLD, oldchldhandler) |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
164 status = problem[0] |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
165 if status: |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
166 if status < 0: |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
167 os.kill(os.getpid(), -status) |
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
168 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
|
169 try: |
30406 | 170 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
|
171 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
|
172 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
|
173 except: # re-raises |
18709
9955fc5ee24b
worker: handle worker failures more aggressively
Bryan O'Sullivan <bryano@fb.com>
parents:
18708
diff
changeset
|
174 killworkers() |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
175 cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
176 raise |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
177 cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
178 |
18707
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
179 def _posixexitstatus(code): |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
180 '''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
|
181 os.spawnv |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
182 |
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
183 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
|
184 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
|
185 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
|
186 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
|
187 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
|
188 |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
189 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
|
190 _platformworker = _posixworker |
18707
d1a2b086d058
worker: on error, exit similarly to the first failing worker
Bryan O'Sullivan <bryano@fb.com>
parents:
18638
diff
changeset
|
191 _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
|
192 |
18637
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
193 def partition(lst, nslices): |
28181
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
194 '''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
|
195 |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
196 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
|
197 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
|
198 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
|
199 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
200 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
|
201 In his words: |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
202 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
203 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
|
204 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
|
205 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
|
206 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
|
207 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
|
208 chance to work. |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
209 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
210 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
|
211 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
|
212 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
|
213 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
|
214 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
|
215 "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
|
216 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
|
217 |
3eb7faf6d958
worker: document poor partitioning scheme impact
Gregory Szorc <gregory.szorc@gmail.com>
parents:
28181
diff
changeset
|
218 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
|
219 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
|
220 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
|
221 ''' |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
222 for i in range(nslices): |
f8efc8a3a991
worker: change partition strategy to every Nth element
Gregory Szorc <gregory.szorc@gmail.com>
parents:
26587
diff
changeset
|
223 yield lst[i::nslices] |