author | Augie Fackler <raf@durin42.com> |
Sun, 10 Feb 2013 04:04:22 -0600 | |
changeset 18641 | 6204e4d4dd6d |
parent 18638 | 047110c0e2a8 |
child 18707 | d1a2b086d058 |
permissions | -rw-r--r-- |
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 |
|
18636
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
8 |
from i18n import _ |
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
9 |
import os, signal, sys, util |
18635
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
10 |
|
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
11 |
def countcpus(): |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
12 |
'''try to count the number of CPUs on the system''' |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
13 |
|
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
14 |
# posix |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
15 |
try: |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
16 |
n = int(os.sysconf('SC_NPROCESSORS_ONLN')) |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
17 |
if n > 0: |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
18 |
return n |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
19 |
except (AttributeError, ValueError): |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
20 |
pass |
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 |
# windows |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
23 |
try: |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
24 |
n = int(os.environ['NUMBER_OF_PROCESSORS']) |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
25 |
if n > 0: |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
26 |
return n |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
27 |
except (KeyError, ValueError): |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
28 |
pass |
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
29 |
|
fed06dd07665
worker: count the number of CPUs
Bryan O'Sullivan <bryano@fb.com>
parents:
diff
changeset
|
30 |
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
|
31 |
|
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
32 |
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
|
33 |
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
|
34 |
if s: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
35 |
try: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
36 |
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
|
37 |
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
|
38 |
return n |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
39 |
except ValueError: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
40 |
raise util.Abort(_('number of cpus must be an integer')) |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
41 |
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
|
42 |
|
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
43 |
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
|
44 |
_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
|
45 |
else: |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
46 |
_startupcost = 1e30 |
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
47 |
|
dcb27c153a40
worker: estimate whether it's worth running a task in parallel
Bryan O'Sullivan <bryano@fb.com>
parents:
18635
diff
changeset
|
48 |
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
|
49 |
'''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
|
50 |
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
|
51 |
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
|
52 |
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
|
53 |
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
|
54 |
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
|
55 |
|
18638
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
56 |
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
|
57 |
'''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
|
58 |
processes. |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
59 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
60 |
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
|
61 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
62 |
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
|
63 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
64 |
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
|
65 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
66 |
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
|
67 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
68 |
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
|
69 |
workers |
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 |
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
|
72 |
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
|
73 |
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
|
74 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
75 |
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
|
76 |
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
|
77 |
workers = _numworkers(ui) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
78 |
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
|
79 |
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
|
80 |
if pid == 0: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
81 |
try: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
82 |
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
|
83 |
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
|
84 |
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
|
85 |
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
|
86 |
except KeyboardInterrupt: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
87 |
os._exit(255) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
88 |
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
|
89 |
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
|
90 |
oldhandler = signal.getsignal(signal.SIGINT) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
91 |
signal.signal(signal.SIGINT, signal.SIG_IGN) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
92 |
def cleanup(): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
93 |
# python 2.4 is too dumb for try/yield/finally |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
94 |
signal.signal(signal.SIGINT, oldhandler) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
95 |
problems = 0 |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
96 |
for i in xrange(workers): |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
97 |
problems |= os.wait()[1] |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
98 |
if problems: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
99 |
sys.exit(1) |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
100 |
try: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
101 |
for line in fp: |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
102 |
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
|
103 |
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
|
104 |
except: # re-raises |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
105 |
cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
106 |
raise |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
107 |
cleanup() |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
108 |
|
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
109 |
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
|
110 |
_platformworker = _posixworker |
047110c0e2a8
worker: allow a function to be run in multiple worker processes
Bryan O'Sullivan <bryano@fb.com>
parents:
18637
diff
changeset
|
111 |
|
18637
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
112 |
def partition(lst, nslices): |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
113 |
'''partition a list into N slices of equal size''' |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
114 |
n = len(lst) |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
115 |
chunk, slop = n / nslices, n % nslices |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
116 |
end = 0 |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
117 |
for i in xrange(nslices): |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
118 |
start = end |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
119 |
end = start + chunk |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
120 |
if slop: |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
121 |
end += 1 |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
122 |
slop -= 1 |
ac4dbceeb14a
worker: partition a list (of tasks) into equal-sized chunks
Bryan O'Sullivan <bryano@fb.com>
parents:
18636
diff
changeset
|
123 |
yield lst[start:end] |