├── LICENSE ├── NOTICE ├── README.md ├── redis.aurora └── redis_elector.py /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 [yyyy] [name of copyright owner] 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. 203 | 204 | -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- 1 | aurora-redis 2 | Copyright (C) 2015 Gutefrage.net GmbH 3 | 4 | This software was originally developed at Gutefrage.net GmbH 5 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | Aurora Redis lets you set up a redis cluster that consists of one master and several slaves. 2 | If the master goes down, another nodes get elected as master, and the other slaves are pointed to the new master. 3 | Every time Redis does a database dump, this dump gets copied to HDFS. Also, if there's no available Master / you're bootstrapping the Cluster, the dump is copied over from HDFS and the cluster is started from that. 4 | For writing clients can fetch the current redis master via zookeeper. For reading you could either use the normal serverset that's done by aurora, or you could use a proxy (e.g. HAProxy) that get's populated by the serverset. 5 | 6 | ## What it does 7 | - The Job consists of 4 processes: copy,run,backup,election 8 | - Copy is run first, it fetches the redis binary and the python helper script to the sandbox 9 | - Run, Backup & Election are run in parallel after that 10 | - Election: is trying to get the current state of the cluster. If it has a state, the flag file "running" is created. If the current instance is going to be the Master one, also the flag file "isMaster" is created 11 | - Run: is waiting for the flag file "running" before it starts the redis server. If the flag file "isMaster" is found, it tried to fetch the latest redis dump from HDFS before starting the server 12 | - Backup: this is only active when the flag file "isMaster" is found, it then watches if there's a new "dump.rdb". If there is one, copy it to HDFS 13 | 14 | 15 | ## Before you start 16 | - There are a lot of hardcoded "hdfs://hdfscluster/path/to/redis" values in the .aurora file, you should change them before you use it 17 | - You need to copy a redis-server binary to the HDFS path mentioned above 18 | - You need to define the zookeeper cluster you're going to use. You can either edit it in the redis_electory.py file, or you can set the "zk_hosts" ENV in the .aurora file 19 | 20 | ## ToDo 21 | - It's rather crude right now, a lot of hardcoded values and usage of flag files seem to be bad as well 22 | - Right now the zookeeper entry is in the form of "ip:port", it probably makes sense to switch to the serverset format that aurora is already using 23 | - The local ip address is fetched via $(ifconfig bond0 | grep "inet addr" | awk -F: '{print $2}' | awk '{print $1}') ... there has to be a better way :) 24 | -------------------------------------------------------------------------------- /redis.aurora: -------------------------------------------------------------------------------- 1 | #################### 2 | ## 3 | ## Aurora Config for HA redis 4 | ## 5 | ################### 6 | # 7 | copy = Process( 8 | name = 'CopyFromHDFS', 9 | cmdline = """ 10 | /usr/bin/hadoop fs -copyToLocal hdfs://hdfscluster/path/to/redis/redis-server . && chmod a+x redis-server 11 | /usr/bin/hadoop fs -copyToLocal hdfs://hdfscluster/path/to/redis/redis_elector.py . && chmod a+x redis_elector.py 12 | """ 13 | ) 14 | 15 | run = Process( 16 | name = 'RunRedis', 17 | cmdline = """ 18 | while [ ! -e "running" ]; do sleep 1; done 19 | if [ -e "isMaster" ] 20 | then 21 | /usr/bin/hadoop fs -copyToLocal hdfs://hdfscluster/path/to/redis/dump.rdb . 22 | fi 23 | touch redisRunning 24 | ./redis-server --port {{thermos.ports[redis]}} 25 | """ 26 | ) 27 | 28 | election = Process( 29 | name = "Election", 30 | cmdline = """ 31 | export redis_host=$(ifconfig bond0 | grep "inet addr" | awk -F: '{print $2}' | awk '{print $1}') 32 | export redis_port={{thermos.ports[redis]}} 33 | ./redis_elector.py 34 | """ 35 | ) 36 | 37 | backup = Process( 38 | name = 'Backup', 39 | cmdline = """ 40 | lastBackup=$(date +%s) 41 | while true 42 | do 43 | if [ -e "isMaster" ] && [ -e "dump.rdb" ] 44 | then 45 | filemtime=$(stat -c %Y dump.rdb) 46 | if [ "$filemtime" -gt "$lastBackup" ] 47 | then 48 | /usr/bin/hadoop fs -put -f dump.rdb hdfs://hdfscluster/path/to/redis/ 49 | lastBackup=$filemtime 50 | echo "Saved Backup" 51 | fi 52 | fi 53 | sleep 10; 54 | done 55 | """ 56 | ) 57 | 58 | 59 | task = Task( 60 | processes = [copy,run,backup,election], 61 | constraints = [Constraint(order = [copy.name(), run.name()]), Constraint(order = [copy.name(), backup.name()]), Constraint(order = [copy.name(), election.name()])], 62 | resources = Resources(cpu = 0.005, ram = 1024*MB, disk = 512*MB)) 63 | 64 | updateconfig = UpdateConfig(batch_size=3) 65 | 66 | announce = Announcer(primary_port='redis') 67 | 68 | jobs = [ 69 | Service(announce = announce, task = task, update_config=updateconfig, cluster = 'prodcluster', role = 'tools', environment = 'prod' , name = "redis", instances = 5, constraints = { }), 70 | ] 71 | 72 | -------------------------------------------------------------------------------- /redis_elector.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """ 3 | redis_elector 4 | - uses Kazoo Election method to find a Redis master and configures the slaves to replicate from it. 5 | """ 6 | 7 | 8 | from time import sleep 9 | import os 10 | import sys 11 | import signal 12 | import datetime 13 | 14 | import redis 15 | from kazoo.client import KazooClient 16 | from kazoo.client import KazooState 17 | 18 | 19 | reconnect_time = 10 20 | reconnected = True 21 | master = False 22 | 23 | redis_host = os.getenv('redis_host', "127.0.0.1") 24 | redis_port = os.getenv('redis_port', "6639") 25 | redis_address = redis_host + ":" + redis_port 26 | 27 | zk_base = os.getenv('zk_base', "/redis") 28 | zk_hosts = os.getenv('zk_hosts', "zookeeper:2181") 29 | zk_path_to_master = zk_base + "/master" 30 | 31 | def logger(msg): 32 | print datetime.datetime.now() + ": " + msg 33 | sys.stdout.flush() 34 | 35 | def signal_handler(signal, frame): 36 | global zk_connection 37 | print('Processing signal. Shutting down...') 38 | # Let's try to close the zk connection so that our ephemeral node gets freed faster 39 | zk_connection.remove_listener(zookeeper_listener) 40 | zk_connection.stop() 41 | sys.exit(0) 42 | 43 | def zookeeper_listener(state): 44 | global reconnected 45 | 46 | if state == KazooState.LOST or state == KazooState.SUSPENDED: 47 | # Register somewhere that the session was lost or being disconnected from Zookeeper 48 | logger("Connection lost, retrying in %d seconds" % reconnect_time) 49 | sleep(reconnect_time) 50 | 51 | else: 52 | # Handle being connected/reconnected to Zookeeper 53 | logger("Reconnected to Zookeeper!") 54 | reconnected = True 55 | 56 | 57 | def zookeeper_watcher(zk_connection): 58 | @zk_connection.DataWatch(zk_path_to_master) 59 | def watcher(data, stat, event): 60 | if data != None and (event == None or event.type == "CHANGED"): 61 | if data == redis_address: 62 | # Create Master flag file before running flag file 63 | touch("isMaster") 64 | # At this point make sure that the flag file really exists 65 | touch("running") 66 | 67 | logger("Unsetting possible slave config") 68 | set_redis_slave(None, None) 69 | 70 | else: 71 | touch("running") 72 | redis_address_parts = data.split(':') 73 | 74 | if os.path.exists("isMaster"): 75 | logger("Master flag file found, deleting...") 76 | os.remove("isMaster") 77 | 78 | logger("Set Master to %s on port %s " % (redis_address_parts[0], redis_address_parts[1])) 79 | set_redis_slave(redis_address_parts[0], redis_address_parts[1]) 80 | 81 | 82 | 83 | def start_election_and_take_position(): 84 | global reconnected 85 | while True: 86 | if reconnected: 87 | reconnected = False 88 | 89 | zookeeper_watcher(zk_connection) 90 | 91 | election = zk_connection.Election(zk_base + "/lockpath") 92 | 93 | # Slaves stop at this point, idling the zk connection, waiting for zk.DataWatch. 94 | # Master continues... 95 | election.run(set_redis_master) 96 | 97 | sleep(10) 98 | 99 | 100 | def set_redis_master(): 101 | global master 102 | master = True 103 | 104 | logger("I am taking the crown! (Elected master...) ") 105 | zk_connection.ensure_path(zk_base) 106 | 107 | # Should never be necessary, just to be sure. 108 | if zk_connection.exists(zk_path_to_master): 109 | zk_connection.delete(zk_path_to_master) 110 | 111 | zk_connection.create(zk_path_to_master, ephemeral=True) 112 | zk_connection.set(zk_path_to_master, redis_address) 113 | 114 | # Sleeping forever, idling the zk connection, waiting for zk.DataWatch 115 | while True: 116 | if reconnected: 117 | return 118 | 119 | sleep(10) 120 | 121 | 122 | def set_redis_slave(tHost, tPort): 123 | success = False 124 | timeout = 120 125 | retry_time = 5 126 | 127 | while success != True: 128 | try: 129 | redis_connection.slaveof(host=tHost, port=tPort) 130 | success = True 131 | except redis.ConnectionError: 132 | if timeout <= 0: 133 | raise OSError, "Timeout reached. Couldn't connect to Redis." 134 | logger("Can't connect to Redis. Sleeping for %d seconds..." % retry_time) 135 | timeout += retry_time 136 | sleep(retry_time) 137 | 138 | 139 | def touch(fname, times=None): 140 | with open(fname, 'a'): 141 | os.utime(fname, times) 142 | 143 | signal.signal(signal.SIGINT, signal_handler) 144 | signal.signal(signal.SIGTERM, signal_handler) 145 | 146 | logger("Redis %s %s" % (redis_host, redis_port)) 147 | redis_connection = redis.StrictRedis(host=redis_host, port=redis_port, db=0) 148 | 149 | zk_connection = KazooClient(hosts=zk_hosts) 150 | zk_connection.add_listener(zookeeper_listener) 151 | zk_connection.start() 152 | 153 | start_election_and_take_position() 154 | --------------------------------------------------------------------------------