├── .gitignore ├── LICENSE ├── Makefile ├── README.rst ├── setup.py ├── src └── taskmaster │ ├── __init__.py │ ├── cli │ ├── __init__.py │ ├── master.py │ ├── run.py │ ├── slave.py │ └── spawn.py │ ├── client.py │ ├── constants.py │ ├── example.py │ ├── progressbar.py │ ├── server.py │ └── util.py └── tests ├── __init__.py └── taskmaster ├── __init__.py └── cli ├── __init__.py ├── master ├── __init__.py └── tests.py └── slave ├── __init__.py └── tests.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[co] 2 | 3 | # Packages 4 | *.egg 5 | *.egg-info 6 | dist 7 | build 8 | eggs 9 | parts 10 | bin 11 | var 12 | sdist 13 | develop-eggs 14 | .installed.cfg 15 | 16 | # Installer logs 17 | pip-log.txt 18 | 19 | # Unit test / coverage reports 20 | .coverage 21 | .tox 22 | 23 | # Translations 24 | *.mo 25 | 26 | # Mr Developer 27 | .mr.developer.cfg 28 | 29 | # Taskmaster 30 | *.state 31 | *.tmp -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright 2010 DISQUS 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | test: 2 | python setup.py test -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | Taskmaster 2 | ---------- 3 | 4 | Taskmaster is a simple distributed queue designed for handling large numbers of one-off tasks. 5 | 6 | We built this at DISQUS to handle frequent, but uncommon tasks like "migrate this data to a new schema". 7 | 8 | Why? 9 | ---- 10 | 11 | You might ask, "Why not use Celery?". Well the answer is simply that normal queueing requires (not literally, 12 | but it'd be painful without) you to buffer all tasks into a central location. This becomes a problem when you 13 | have a large amount of tasks, especially when they contain a large amount of data. 14 | 15 | Imagine you have 1 billion tasks, each weighing in at 5k. Thats, uncompressed, at minimum 4 terabytes of storage 16 | required just to keep that around, and gains you very little. 17 | 18 | Taskmaster on the other hand is designed to take a resumable iterator, and only pull in a maximum number of 19 | jobs at a time (using standard Python Queue's). This ensures a consistent memory pattern that can scale linearly. 20 | 21 | Requirements 22 | ------------ 23 | 24 | Requirements **should** be handled by setuptools, but if they are not, you will need the following Python packages: 25 | 26 | * progressbar 27 | * pyzmq (zeromq) 28 | * gevent 29 | * gevent_zeromq 30 | 31 | 32 | A note on Gevent 33 | ---------------- 34 | 35 | Being that Taskmaster uses gevent for both its iterator task (master) and its consumers, your application will need 36 | to correctly implement non-blocking gevent compatible callers. In most cases this won't be a problem, but if you're 37 | using the network you'll need to look for a compatible library for your adapter. For example, there is an alternative 38 | version of ``psycopg2`` designed for gevent called ``gevent-psycopg2``. 39 | 40 | Usage 41 | ----- 42 | 43 | Create an iterator, and callback:: 44 | 45 | # taskmaster/example.py 46 | def get_jobs(last=0): 47 | # last would be sent if state was resumed 48 | # from a previous run 49 | for i in xrange(last, 100000000): 50 | # jobs yielded must be serializeable with pickle 51 | yield i 52 | 53 | def handle_job(i): 54 | # this **must** be idempotent, as resuming the process may execute a job 55 | # that had already been run 56 | print "Got %r!" % i 57 | 58 | 59 | Spawn a master:: 60 | 61 | $ tm-master taskmaster.example 62 | 63 | You can also pass keyword arguments for the master:: 64 | 65 | $ tm-master taskmaster.example argument=value 66 | 67 | Spawn a slave:: 68 | 69 | $ tm-slave taskmaster.example 70 | 71 | Or spawn 8 slaves (each containing a threadpool):: 72 | 73 | $ tm-spawn taskmaster.example 8 74 | 75 | Dont like the magical function discover for master/slave? Specify your own targets:: 76 | 77 | $ tm-master taskmaster.example:get_jobs 78 | $ tm-slave taskmaster.example:handle_job 79 | 80 | Maybe you simply need to run things on the same server? 81 | 82 | :: 83 | 84 | $ tm-run taskmaster/example.py 8 85 | 86 | .. note:: All arguments are optional, and the address will default to ``tcp://0.0.0.0:3050``. -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python 2 | 3 | from setuptools import setup, find_packages 4 | 5 | setup( 6 | name="taskmaster", 7 | license='Apache License 2.0', 8 | version="0.8.2", 9 | description=("A simple distributed queue designed for " 10 | "handling one-off tasks with large sets of tasks"), 11 | author="David Cramer", 12 | author_email="dcramer@gmail.com", 13 | url="https://github.com/dcramer/taskmaster", 14 | packages=find_packages("src"), 15 | package_dir={'': 'src'}, 16 | entry_points={ 17 | 'console_scripts': [ 18 | 'tm-master = taskmaster.cli.master:main', 19 | 'tm-slave = taskmaster.cli.slave:main', 20 | 'tm-spawn = taskmaster.cli.spawn:main', 21 | 'tm-run = taskmaster.cli.run:main', 22 | ], 23 | }, 24 | install_requires=[ 25 | 'progressbar', 26 | 'gevent', 27 | 'gevent_zeromq', 28 | # 'pyzmq-static', 29 | ], 30 | tests_require=[ 31 | 'unittest2', 32 | 'Nose>=1.0', 33 | ], 34 | classifiers=[ 35 | "Environment :: Console", 36 | "Intended Audience :: Developers", 37 | "Programming Language :: Python", 38 | "Topic :: Software Development", 39 | "Topic :: Utilities", 40 | ]) 41 | -------------------------------------------------------------------------------- /src/taskmaster/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | taskmaster 3 | ~~~~~~~~~~ 4 | 5 | :copyright: (c) 2010 DISQUS. 6 | :license: Apache License 2.0, see LICENSE for more details. 7 | """ 8 | -------------------------------------------------------------------------------- /src/taskmaster/cli/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | taskmaster.cli 3 | ~~~~~~~~~~~~~~ 4 | 5 | :copyright: (c) 2010 DISQUS. 6 | :license: Apache License 2.0, see LICENSE for more details. 7 | """ 8 | -------------------------------------------------------------------------------- /src/taskmaster/cli/master.py: -------------------------------------------------------------------------------- 1 | """ 2 | taskmaster.cli.master 3 | ~~~~~~~~~~~~~~~~~~~~~ 4 | 5 | :copyright: (c) 2010 DISQUS. 6 | :license: Apache License 2.0, see LICENSE for more details. 7 | """ 8 | 9 | from taskmaster.util import parse_options 10 | from taskmaster.constants import (DEFAULT_LOG_LEVEL, 11 | DEFAULT_ADDRESS, DEFAULT_BUFFER_SIZE) 12 | 13 | 14 | def run(target, kwargs=None, reset=False, size=DEFAULT_BUFFER_SIZE, 15 | address=DEFAULT_ADDRESS, log_level=DEFAULT_LOG_LEVEL): 16 | from taskmaster.server import Server, Controller 17 | 18 | server = Server(address, size=size, log_level=log_level) 19 | 20 | controller = Controller(server, target, kwargs=kwargs, log_level=log_level) 21 | if reset: 22 | controller.reset() 23 | controller.start() 24 | 25 | 26 | def main(): 27 | import optparse 28 | import sys 29 | parser = optparse.OptionParser() 30 | parser.add_option("--address", dest="address", default=DEFAULT_ADDRESS) 31 | parser.add_option("--size", dest="size", default=DEFAULT_BUFFER_SIZE, type=int) 32 | parser.add_option("--reset", dest="reset", default=False, action='store_true') 33 | parser.add_option("--log-level", dest="log_level", default=DEFAULT_LOG_LEVEL) 34 | (options, args) = parser.parse_args() 35 | if len(args) < 1: 36 | print 'Usage: tm-master [key=value, key2=value2]' 37 | sys.exit(1) 38 | sys.exit(run(args[0], parse_options(args[1:]), **options.__dict__)) 39 | 40 | if __name__ == '__main__': 41 | main() 42 | -------------------------------------------------------------------------------- /src/taskmaster/cli/run.py: -------------------------------------------------------------------------------- 1 | """ 2 | taskmaster.cli.run 3 | ~~~~~~~~~~~~~~~~~~ 4 | 5 | :copyright: (c) 2010 DISQUS. 6 | :license: Apache License 2.0, see LICENSE for more details. 7 | """ 8 | 9 | from multiprocessing import Process 10 | from taskmaster.cli.spawn import run as run_spawn 11 | from taskmaster.cli.master import run as run_master 12 | from taskmaster.constants import (DEFAULT_LOG_LEVEL, DEFAULT_ADDRESS, 13 | DEFAULT_ITERATOR_TARGET, 14 | DEFAULT_CALLBACK_TARGET, 15 | DEFAULT_BUFFER_SIZE, DEFAULT_RETRIES, 16 | DEFAULT_TIMEOUT) 17 | from taskmaster.util import parse_options 18 | 19 | 20 | def run(get_jobs_target, handle_job_target, procs, 21 | kwargs=None, log_level=DEFAULT_LOG_LEVEL, 22 | address=DEFAULT_ADDRESS, reset=False, size=DEFAULT_BUFFER_SIZE, 23 | retries=DEFAULT_RETRIES, timeout=DEFAULT_TIMEOUT): 24 | pool = [ 25 | Process(target=run_master, args=[get_jobs_target], kwargs={ 26 | 'log_level': log_level, 27 | 'address': address, 28 | 'size': size, 29 | 'reset': reset, 30 | 'kwargs': kwargs, 31 | }), 32 | Process(target=run_spawn, args=[handle_job_target, procs], kwargs={ 33 | 'log_level': log_level, 34 | 'address': address, 35 | 'progressbar': False, 36 | 'retries': retries, 37 | 'timeout': timeout, 38 | }), 39 | ] 40 | 41 | for p in pool: 42 | p.start() 43 | 44 | for p in (p for p in pool if p.is_alive()): 45 | p.join(0) 46 | 47 | 48 | def main(): 49 | import optparse 50 | import sys 51 | parser = optparse.OptionParser() 52 | parser.add_option("--address", dest="address", default=DEFAULT_ADDRESS) 53 | parser.add_option("--size", dest="size", default='10000', type=int) 54 | parser.add_option("--retries", dest="retries", default=DEFAULT_RETRIES, type=int) 55 | parser.add_option("--timeout", dest="timeout", default=DEFAULT_TIMEOUT, type=int) 56 | parser.add_option("--reset", dest="reset", default=False, action='store_true') 57 | parser.add_option("--log-level", dest="log_level", default=DEFAULT_LOG_LEVEL) 58 | parser.add_option("--get-jobs-callback", dest="get_jobs_target", default=DEFAULT_ITERATOR_TARGET) 59 | parser.add_option("--handle-job-callback", dest="handle_job_target", default=DEFAULT_CALLBACK_TARGET) 60 | (options, args) = parser.parse_args() 61 | if len(args) < 2: 62 | print 'Usage: tm-run