├── spark-master ├── Dockerfile └── scripts │ └── bootstrap.sh ├── spark-slave ├── Dockerfile └── scripts │ └── bootstrap.sh ├── hdfs-datanode ├── Dockerfile └── scripts │ └── bootstrap.sh ├── hdfs-namenode ├── Dockerfile └── scripts │ └── bootstrap.sh ├── hadoop-spark ├── hadoop-conf │ ├── mapred-site.xml │ └── core-site.xml └── Dockerfile ├── README.md ├── docker-compose.yml └── LICENSE /spark-master/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM hadoop-spark 2 | MAINTAINER Venki Korukanti (venki.korukanti@gmail.com) 3 | 4 | COPY scripts /usr/bin/. 5 | 6 | ENTRYPOINT ["/usr/bin/bootstrap.sh"] 7 | -------------------------------------------------------------------------------- /spark-slave/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM hadoop-spark 2 | MAINTAINER Venki Korukanti (venki.korukanti@gmail.com) 3 | 4 | COPY scripts /usr/bin/. 5 | 6 | ENTRYPOINT ["/usr/bin/bootstrap.sh"] 7 | -------------------------------------------------------------------------------- /hdfs-datanode/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM hadoop-spark 2 | MAINTAINER Venki Korukanti (venki.korukanti@gmail.com) 3 | 4 | COPY scripts /usr/bin/. 5 | 6 | ENTRYPOINT ["/usr/bin/bootstrap.sh"] 7 | -------------------------------------------------------------------------------- /hdfs-namenode/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM hadoop-spark 2 | MAINTAINER Venki Korukanti (venki.korukanti@gmail.com) 3 | 4 | COPY scripts /usr/bin/. 5 | 6 | ENTRYPOINT ["/usr/bin/bootstrap.sh"] 7 | -------------------------------------------------------------------------------- /spark-master/scripts/bootstrap.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Start the SSH daemon 4 | service ssh restart 5 | 6 | # Setup password less ssh 7 | sshpass -p screencast ssh-copy-id root@localhost 8 | 9 | sed -i "s#localhost#$NAMENODE_HOSTNAME#g" /opt/hadoop-2.6.0/etc/hadoop/core-site.xml 10 | 11 | # Start spark master and worker services 12 | start-master.sh 13 | start-slave.sh spark://`hostname`:7077 14 | 15 | # Run in daemon mode, don't exit 16 | while true; do 17 | sleep 100; 18 | done 19 | -------------------------------------------------------------------------------- /hdfs-datanode/scripts/bootstrap.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Start the SSH daemon 4 | service ssh restart 5 | 6 | # Setup password less ssh 7 | sshpass -p screencast ssh-copy-id root@localhost 8 | 9 | # Replace "localhost" in Hadoop core-site xml with actual hostname which is passed 10 | # as NAMENODE_HOSTNAME env variable 11 | sed -i "s#localhost#$NAMENODE_HOSTNAME#g" /opt/hadoop-2.6.0/etc/hadoop/core-site.xml 12 | 13 | # Start Datanode 14 | hadoop-daemon.sh start datanode 15 | 16 | # Run in daemon mode, don't exit 17 | while true; do 18 | sleep 100; 19 | done 20 | -------------------------------------------------------------------------------- /spark-slave/scripts/bootstrap.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Start the SSH daemon 4 | service ssh restart 5 | 6 | # Setup password less ssh 7 | sshpass -p screencast ssh-copy-id root@localhost 8 | 9 | # Replace "localhost" in Hadoop core-site xml with actual hostname which is passed 10 | # as NAMENODE_HOSTNAME env variable 11 | sed -i "s#localhost#$NAMENODE_HOSTNAME#g" /opt/hadoop-2.6.0/etc/hadoop/core-site.xml 12 | 13 | # Start spark worker service 14 | start-slave.sh spark://$MASTER_HOSTNAME:7077 15 | 16 | # Run in daemon mode, don't exit 17 | while true; do 18 | sleep 100; 19 | done 20 | -------------------------------------------------------------------------------- /hdfs-namenode/scripts/bootstrap.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Start the SSH daemon 4 | service ssh restart 5 | 6 | # Setup password less ssh 7 | sshpass -p screencast ssh-copy-id root@localhost 8 | 9 | export HOSTNAME=`hostname` 10 | sed -i "s#localhost#$HOSTNAME#g" /opt/hadoop-2.6.0/etc/hadoop/core-site.xml 11 | 12 | # Format the NameNode data directory 13 | hdfs namenode -format -force 14 | 15 | # Start HDFS services 16 | start-dfs.sh 17 | 18 | # Wait for HDFS services to be up and running 19 | sleep 5 20 | 21 | # Create a tmp directory and make it accessible to everyone 22 | hadoop fs -mkdir -p /tmp 23 | hadoop fs -chmod -R 777 /tmp 24 | 25 | # Run in daemon mode, don't exit 26 | while true; do 27 | sleep 100; 28 | done 29 | -------------------------------------------------------------------------------- /hadoop-spark/hadoop-conf/mapred-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 16 | 17 | 18 | 19 | 20 | 21 | mapreduce.framework.name 22 | yarn 23 | 24 | 25 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Docker compose for spawning on demand HDFS and Spark clusters 2 | 3 | # Build the required Docker images 4 | `./build-images.sh` 5 | 6 | # Run the cluster 7 | Note: Run below commands from the directory where `docker-compose.yml` file is present. 8 | ## bring up the cluster 9 | `docker-compose up -d` 10 | ## stop the cluster 11 | `docker-compose stop` 12 | ## restart the stopped cluster 13 | `docker-compose start` 14 | ## remove containers 15 | `docker-compose rm -f` 16 | ## to scale HDFS datanode or Spark worker containers 17 | `docker-compose scale spark-slave=n` where n is the new number of containers. 18 | 19 | ## Attaching to cluster containers 20 | - HDFS NameNode container 21 | * Runs HDFS NameNode and DataNode services 22 | * `docker exec -it sparkdockercluster_hdfs-namenode_1 /bin/bash` 23 | - HDFS DataNode container(s) 24 | * Runs HDFS DataNode service 25 | * There could be multiple instances of this container. To connect to n'th container 26 | * `docker exec -it sparkdockercluster_hdfs-datanode__n_ /bin/bash` 27 | - Spark Master container 28 | * Runs Spark Master and Worker services 29 | * `docker exec -it sparkdockercluster_spark-master_1 /bin/bash` 30 | - Spark Worker container 31 | * Runs Spark Worker service 32 | * There could be multiple instances of this container. To connect to n'th container 33 | * `docker exec -it sparkdockercluster_spark-slave__n_ /bin/bash` 34 | -------------------------------------------------------------------------------- /hadoop-spark/hadoop-conf/core-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 16 | 17 | 18 | 19 | 20 | 21 | hadoop.tmp.dir 22 | /opt/data/apps/tmp 23 | A base for other temporary directories. 24 | 25 | 26 | 27 | hadoop.name.dir 28 | /opt/data/apps/dfs/name 29 | 30 | 31 | 32 | hadoop.data.dir 33 | /opt/data/apps/dfs/data 34 | 35 | 36 | 37 | fs.default.name 38 | hdfs://localhost:9000 39 | 40 | 41 | 42 | JAVA_HOME 43 | ${JAVA_HOME} 44 | 45 | 46 | 47 | -------------------------------------------------------------------------------- /docker-compose.yml: -------------------------------------------------------------------------------- 1 | # Container that runs HDFS NameNode and DataNode services 2 | hdfs-namenode: 3 | image: hdfs-namenode 4 | hostname: hdfs-namenode-host 5 | ports: 6 | # HDFS port 7 | - "9000:9000" 8 | # HDFS NameNode WebUI 9 | - "50070:50070" 10 | # Adjust according to the resources available on host machine 11 | cpu_shares: 3000 12 | mem_limit: 2g 13 | 14 | # Container that runs HDFS DataNode service 15 | hdfs-datanode: 16 | image: hdfs-datanode 17 | hostname: hdfs-datanode-host 18 | links: 19 | - hdfs-namenode 20 | environment: 21 | # NAMENODE_HOSTNAME is the hostname of the container running Namenode service 22 | - NAMENODE_HOSTNAME=hdfs-namenode-host 23 | # Adjust according to the resources available on host machine 24 | cpu_shares: 3000 25 | mem_limit: 2g 26 | 27 | # Container that runs Spark Master and Worker services 28 | spark-master: 29 | image: spark-master 30 | hostname: spark-master-host 31 | links: 32 | - hdfs-namenode 33 | ports: 34 | # Spark master WebUI port 35 | - "8080:8080" 36 | # Spark master job submission port 37 | - "7077:7077" 38 | environment: 39 | # NAMENODE_HOSTNAME is the hostname of the container running Namenode service 40 | - NAMENODE_HOSTNAME=hdfs-namenode-host 41 | # Adjust according to the resources available on host machine 42 | cpu_shares: 3000 43 | mem_limit: 2g 44 | 45 | # Container that runs Spark Worker service 46 | spark-slave: 47 | image: spark-slave 48 | hostname: spark-slave-host 49 | links: 50 | - hdfs-namenode 51 | - spark-master 52 | environment: 53 | # NAMENODE_HOSTNAME is the hostname of the container running Namenode service 54 | - NAMENODE_HOSTNAME=hdfs-namenode-host 55 | # MASTER_HOSTNAME is the hostname of the container running Spark master service 56 | - MASTER_HOSTNAME=spark-master-host 57 | # Adjust according to the resources available on host machine 58 | cpu_shares: 3000 59 | mem_limit: 2g 60 | -------------------------------------------------------------------------------- /hadoop-spark/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:14.04 2 | MAINTAINER Venki Korukanti (venki.korukanti@gmail.com) 3 | 4 | # Install. 5 | RUN \ 6 | sed -i 's/# \(.*multiverse$\)/\1/g' /etc/apt/sources.list && \ 7 | apt-get update && \ 8 | apt-get -y upgrade && \ 9 | apt-get install -y build-essential && \ 10 | apt-get install -y software-properties-common && \ 11 | apt-get install -y byobu curl git htop man unzip vim wget && \ 12 | apt-get install -y openssh-server sshpass && \ 13 | rm -rf /var/lib/apt/lists/* 14 | 15 | RUN mkdir /var/run/sshd 16 | RUN echo 'root:screencast' | chpasswd 17 | RUN sed -i 's/PermitRootLogin without-password/PermitRootLogin yes/' /etc/ssh/sshd_config 18 | RUN sed -i 's/# StrictHostKeyChecking ask/StrictHostKeyChecking no/' /etc/ssh/ssh_config 19 | 20 | # SSH login fix. Otherwise user is kicked off after login 21 | RUN sed 's@session\s*required\s*pam_loginuid.so@session optional pam_loginuid.so@g' -i /etc/pam.d/sshd 22 | 23 | # Set environment variables. 24 | ENV HOME /root 25 | 26 | # Install Java. 27 | RUN \ 28 | echo oracle-java8-installer shared/accepted-oracle-license-v1-1 select true | debconf-set-selections && \ 29 | add-apt-repository -y ppa:webupd8team/java && \ 30 | apt-get update && \ 31 | apt-get install -y oracle-java8-installer && \ 32 | rm -rf /var/lib/apt/lists/* && \ 33 | rm -rf /var/cache/oracle-jdk8-installer 34 | 35 | # Define commonly used JAVA_HOME variable 36 | ENV JAVA_HOME /usr/lib/jvm/java-8-oracle 37 | 38 | # Download Hadoop package 39 | ADD http://apache.mirrors.tds.net/hadoop/common/hadoop-2.6.0/hadoop-2.6.0.tar.gz /tmp/ 40 | 41 | # Download Spark package 42 | ADD http://d3kbcqa49mib13.cloudfront.net/spark-1.4.0-bin-hadoop2.6.tgz /tmp/ 43 | 44 | # Create /opt directory 45 | RUN mkdir -p /opt/ 46 | 47 | # Unpack hadoop into /opt/ and set HADOOP_HOME 48 | RUN tar -xzf /tmp/hadoop-2.6.0.tar.gz -C /opt/ 49 | 50 | # Copy hadoop confs 51 | ADD /hadoop-conf /opt/hadoop-2.6.0/etc/hadoop/ 52 | 53 | # Set Hadoop sepcific environment variables 54 | ENV HADOOP_HOME /opt/hadoop-2.6.0 55 | ENV HADOOP_CONF_DIR="${HADOOP_HOME}/etc/hadoop" 56 | ENV HADOOP_LIBEXEC_DIR="${HADOOP_HOME}/libexec" 57 | 58 | RUN sed -i 's/export JAVA_HOME=${JAVA_HOME}/export JAVA_HOME=\/usr\/lib\/jvm\/java-8-oracle/' /opt/hadoop-2.6.0/etc/hadoop/hadoop-env.sh 59 | 60 | RUN mkdir -p /opt/data/apps/tmp 61 | RUN mkdir -p /opt/data/apps/dfs/name 62 | RUN mkdir -p /opt/data/apps/dfs/data 63 | 64 | # Unpack spark into /opt and set SPARK_HOME 65 | RUN tar -xzf /tmp/spark-1.4.0-bin-hadoop2.6.tgz -C /opt/ 66 | ENV SPARK_HOME /opt/spark-1.4.0-bin-hadoop2.6 67 | 68 | ENV PATH $PATH:${HADOOP_HOME}/sbin/:${HADOOP_HOME}/bin:${SPARK_HOME}/sbin/:${SPARK_HOME}/bin 69 | 70 | RUN ssh-keygen -f /root/.ssh/id_rsa -t rsa -N '' 71 | 72 | # Spark ports 73 | EXPOSE 7077 6066 8080 8081 74 | 75 | # Hdfs ports 76 | EXPOSE 50010 50020 50070 50075 50090 8020 9000 77 | # Mapred ports 78 | EXPOSE 19888 79 | #Yarn ports 80 | EXPOSE 8030 8031 8032 8033 8040 8042 8088 81 | #Other ports 82 | EXPOSE 49707 2122 83 | 84 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------