├── .gitignore ├── LICENSE ├── README.md ├── election_manager.go └── main.go /.gitignore: -------------------------------------------------------------------------------- 1 | # Compiled Object files, Static and Dynamic libs (Shared Objects) 2 | *.o 3 | *.a 4 | *.so 5 | 6 | # Folders 7 | _obj 8 | _test 9 | 10 | # Architecture specific extensions/prefixes 11 | *.[568vq] 12 | [568vq].out 13 | 14 | *.cgo1.go 15 | *.cgo2.c 16 | _cgo_defun.c 17 | _cgo_gotypes.go 18 | _cgo_export.* 19 | 20 | _testmain.go 21 | 22 | *.exe 23 | *.test 24 | *.prof 25 | 26 | .idea/ 27 | .idea/* 28 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 9 | # golang实现通过zookeeper选举master 10 | 11 | 应用程序中有一个定时任务模块，之前是单机部署的，在实现多实例部署之后就对应用程序有了如下要求： 12 | - 一个定时任务只能在一个实例上运行 13 | - 一个应用实例故障后，原本由该实例执行的定时任务需要在其它实例上继续运行 14 | 15 | Zookeeper 能够很容易实现这样的集群管理功能，它能够维护当前的集群中机器的服务状态，而且能够选出一个“总管”，让这个总管来管理集群，在这里即是让这个“总管”去执行定时任务。 16 | 17 | ## 1. go zk client准备 18 | 19 | 从网上找到 golang 的 zookeeper 客户端 go-zookeeper：https://github.com/samuel/go-zookeeper ，网上反响很不错，而且还有比较详细的文档 zk-GoDoc: https://godoc.org/github.com/samuel/go-zookeeper/zk 。 20 | 21 | ## 2. 选举 22 | 23 | 实现方式是在 zookeeper 上创建一个 EPHEMERAL 类型的目录节点，当有一个实例创建成功后，该目录节点便已经存在，其它实例再去创建该节点就会提示该节点已存在。这也是我们想要的结果，将在 zookeeper 上创建目录节点成功的实例选举为 master 。 24 | 25 | 连接到zookeeper： 26 | 27 | ``` 28 | conn, connChan, err := zk.Connect(electionManager.ZKConfig.Servers, time.Second) 29 | if err != nil { 30 | return err 31 | } 32 | // 等待连接成功 33 | for { 34 | isConnected := false 35 | select { 36 | case connEvent := <-connChan: 37 | if connEvent.State == zk.StateConnected { 38 | isConnected = true 39 | fmt.Println("connect to zookeeper server success!") 40 | } 41 | case _ = <-time.After(time.Second * 3): // 3秒仍未连接成功则返回连接超时 42 | return errors.New("connect to zookeeper server timeout!") 43 | } 44 | if isConnected { 45 | break 46 | } 47 | } 48 | ``` 49 | 50 | 开始选举： 51 | 52 | ``` 53 | path, err := electionManager.ZKClientConn.Create(masterPath, nil, zk.FlagEphemeral, zk.WorldACL(zk.PermAll)) 54 | if err == nil { // 创建成功表示选举master成功 55 | if path == masterPath { // 返回的path表示在zookeeper上创建的znode路径 56 | fmt.Println("elect master success!") 57 | electionManager.IsMasterQ <- true 58 | } else { 59 | return errors.New("Create returned different path " + masterPath + " != " + path) 60 | } 61 | } else { // 创建失败表示选举master失败 62 | fmt.Printf("elect master failure, ", err) 63 | electionManager.IsMasterQ <- false 64 | } 65 | ``` 66 | 67 | ## 3. 监听 68 | 69 | 然后每个 Server 在它们创建目录节点的父目录节点上获取并监听(getChildrenW)该节点，由于是 EPHEMERAL 目录节点，当创建它的 Server 死去，这个目录节点也随之被删除，所以 Children 将会变化，这时 getChildren上的 Watch 将会被调用，所以其它 Server 就知道已经有某台 Server 死去了。此时，执行上一步的选举步骤，即每个实例在 zookeeper 上创建目录节点，创建成功的实例被选举为 master 。 70 | 71 | ``` 72 | // watch zk根znode下面的子znode，当有连接断开时，对应znode被删除，触发事件后重新选举 73 | children, state, childCh, err := electionManager.ZKClientConn.ChildrenW(electionManager.ZKConfig.RootPath) 74 | if err != nil { 75 | fmt.Println("watch children error, ", err) 76 | } 77 | fmt.Println("watch children result, ", children, state) 78 | for { 79 | select { 80 | case childEvent := <-childCh: 81 | if childEvent.Type == zk.EventNodeDeleted { 82 | fmt.Println("receive znode delete event, ", childEvent) 83 | // 重新选举 84 | fmt.Println("start elect new master ...") 85 | err = electionManager.electMaster() 86 | if err != nil { 87 | fmt.Println("elect new master error, ", err) 88 | } 89 | } 90 | } 91 | } 92 | ``` 93 | 94 | 完整的代码实例见：https://github.com/brotherbin/elec-master-demo 95 | 96 | ## 4. 测试 97 | 98 | 从github上拉取代码，将代码目录添加到GOPATH环境变量中，执行 99 | 100 | > go get github.com/samuel/go-zookeeper/zk 101 | 102 | 获取 golang的zookeeper客户端，进入到代码目录后执行 103 | 104 | > go run main.go election_manager.go 105 | 106 | 启动程序，第一个启动显示如下日志 107 | 108 | > connect to zookeeper server success!
109 | 2017/04/13 15:03:12 Connected to 127.0.0.1:2181
110 | 2017/04/13 15:03:12 Authenticated: id=97784096665632770, timeout=4000
111 | 2017/04/13 15:03:12 Re-submitting \`0\` credentials after reconnect
112 | elect master success!
113 | do some job on master
114 | watch children result, [] &{148 148 1492066992051 1492066992051 0 0 0 97784096665632770 0 0 148}
115 | 116 | 显示选举成功。 117 | 118 | 根据选举master的步骤可想而知，一般是第一个启动的实例选举master成功。 119 | 120 | 保持该实例继续运行，在另一个命令行再次启动程序，显示日志如下： 121 | 122 | > connect to zookeeper server success!
123 | 2017/04/13 15:24:20 Connected to 127.0.0.1:2181
124 | 2017/04/13 15:24:20 Authenticated: id=97784096665632774, timeout=4000
125 | 2017/04/13 15:24:20 Re-submitting \`0\` credentials after reconnect
126 | elect master failure, %!(EXTRA \*errors.errorString=zk: node already exists)watch children result, [] &{157 157 1492068257748 1492068257748 0 0 0 9778 127 | 4096665632773 0 0 157} 128 | 129 | 表示创建的节点已存在，选举master失败，这也是想要的结果。 130 | 131 | 现在模拟master节点故障的情况，停掉第一个启动的程序实例，第二个程序实例出现如下日志： 132 | 133 | > receive znode delete event, {EventNodeDeleted Unknown /ElectMasterDemo/master }
134 | start elect new master ...
135 | 2017/04/13 15:27:50 Connected to 127.0.0.1:2181
136 | connect to zookeeper server success!
137 | 2017/04/13 15:27:50 Authenticated: id=97784096665632775, timeout=4000
138 | 2017/04/13 15:27:50 Re-submitting \`0\` credentials after reconnect
139 | elect master success!
140 | do some job on master
141 | 142 | 表示程序重新选举了，此时只有一个节点，固然能够创建节点成功并选举成master，成为“管家”继续工作。 143 | -------------------------------------------------------------------------------- /election_manager.go: -------------------------------------------------------------------------------- 1 | package main 2 | 3 | import ( 4 | "github.com/samuel/go-zookeeper/zk" 5 | "errors" 6 | "time" 7 | "fmt" 8 | ) 9 | 10 | type ZookeeperConfig struct { 11 | Servers []string 12 | RootPath string 13 | MasterPath string 14 | } 15 | 16 | type ElectionManager struct { 17 | ZKClientConn *zk.Conn 18 | ZKConfig *ZookeeperConfig 19 | IsMasterQ chan bool 20 | } 21 | 22 | func NewElectionManager(zkConfig *ZookeeperConfig, isMasterQ chan bool) *ElectionManager { 23 | electionManager := &ElectionManager{ 24 | nil, 25 | zkConfig, 26 | isMasterQ, 27 | } 28 | electionManager.initConnection() 29 | return electionManager 30 | } 31 | 32 | func (electionManager *ElectionManager) Run() { 33 | err := electionManager.electMaster() 34 | if err != nil { 35 | fmt.Println("elect master error, ", err) 36 | } 37 | electionManager.watchMaster() 38 | } 39 | 40 | // 判断是否成功连接到zookeeper 41 | func (electionManager *ElectionManager) isConnected() bool { 42 | if electionManager.ZKClientConn == nil { 43 | return false 44 | } else if electionManager.ZKClientConn.State() != zk.StateConnected { 45 | return false 46 | } 47 | return true 48 | } 49 | 50 | // 初始化zookeeper连接 51 | func (electionManager *ElectionManager) initConnection() error { 52 | // 连接为空，或连接不成功，获取zookeeper服务器的连接 53 | if !electionManager.isConnected() { 54 | conn, connChan, err := zk.Connect(electionManager.ZKConfig.Servers, time.Second) 55 | if err != nil { 56 | return err 57 | } 58 | // 等待连接成功 59 | for { 60 | isConnected := false 61 | select { 62 | case connEvent := <-connChan: 63 | if connEvent.State == zk.StateConnected { 64 | isConnected = true 65 | fmt.Println("connect to zookeeper server success!") 66 | } 67 | case _ = <-time.After(time.Second * 3): // 3秒仍未连接成功则返回连接超时 68 | return errors.New("connect to zookeeper server timeout!") 69 | } 70 | if isConnected { 71 | break 72 | } 73 | } 74 | electionManager.ZKClientConn = conn 75 | } 76 | return nil 77 | } 78 | 79 | // 选举master 80 | func (electionManager *ElectionManager) electMaster() error { 81 | err := electionManager.initConnection() 82 | if err != nil { 83 | return err 84 | } 85 | // 判断zookeeper中是否存在root目录，不存在则创建该目录 86 | isExist, _, err := electionManager.ZKClientConn.Exists(electionManager.ZKConfig.RootPath) 87 | if err != nil { 88 | return err 89 | } 90 | if !isExist { 91 | path, err := electionManager.ZKClientConn.Create(electionManager.ZKConfig.RootPath, nil, 0, zk.WorldACL(zk.PermAll)) 92 | if err != nil { 93 | return err 94 | } 95 | if electionManager.ZKConfig.RootPath != path { 96 | return errors.New("Create returned different path " + electionManager.ZKConfig.RootPath + " != " + path) 97 | } 98 | } 99 | 100 | // 创建用于选举master的ZNode，该节点为Ephemeral类型，表示客户端连接断开后，其创建的节点也会被销毁 101 | masterPath := electionManager.ZKConfig.RootPath + electionManager.ZKConfig.MasterPath 102 | path, err := electionManager.ZKClientConn.Create(masterPath, nil, zk.FlagEphemeral, zk.WorldACL(zk.PermAll)) 103 | if err == nil { // 创建成功表示选举master成功 104 | if path == masterPath { 105 | fmt.Println("elect master success!") 106 | electionManager.IsMasterQ <- true 107 | } else { 108 | return errors.New("Create returned different path " + masterPath + " != " + path) 109 | } 110 | } else { // 创建失败表示选举master失败 111 | fmt.Printf("elect master failure, ", err) 112 | electionManager.IsMasterQ <- false 113 | } 114 | return nil 115 | } 116 | 117 | // 监听zookeeper中master znode，若被删除，表示master故障或网络迟缓，重新选举 118 | func (electionManager *ElectionManager) watchMaster() { 119 | // watch zk根znode下面的子znode，当有连接断开时，对应znode被删除，触发事件后重新选举 120 | children, state, childCh, err := electionManager.ZKClientConn.ChildrenW(electionManager.ZKConfig.RootPath + electionManager.ZKConfig.MasterPath) 121 | if err != nil { 122 | fmt.Println("watch children error, ", err) 123 | } 124 | fmt.Println("watch children result, ", children, state) 125 | for { 126 | select { 127 | case childEvent := <-childCh: 128 | if childEvent.Type == zk.EventNodeDeleted { 129 | fmt.Println("receive znode delete event, ", childEvent) 130 | // 重新选举 131 | fmt.Println("start elect new master ...") 132 | err = electionManager.electMaster() 133 | if err != nil { 134 | fmt.Println("elect new master error, ", err) 135 | } 136 | } 137 | } 138 | } 139 | } -------------------------------------------------------------------------------- /main.go: -------------------------------------------------------------------------------- 1 | package main 2 | 3 | import "fmt" 4 | 5 | func main() { 6 | // zookeeper配置 7 | zkConfig := &ZookeeperConfig{ 8 | Servers: []string{"127.0.0.1:2181"}, 9 | RootPath: "/ElectMasterDemo", 10 | MasterPath: "/master", 11 | } 12 | // main goroutine 和 选举goroutine之间通信的channel，同于返回选角结果 13 | isMasterChan := make(chan bool) 14 | 15 | var isMaster bool 16 | 17 | // 选举 18 | electionManager := NewElectionManager(zkConfig, isMasterChan) 19 | go electionManager.Run() 20 | 21 | for { 22 | select { 23 | case isMaster = <-isMasterChan: 24 | if isMaster { 25 | // do some job on master 26 | fmt.Println("do some job on master") 27 | } 28 | } 29 | } 30 | } --------------------------------------------------------------------------------