add HBase

hbase/1.2.6/Dockerfile

@@ -0,0 +1,25 @@
+FROM newnius/hadoop:2.7.4
+
+MAINTAINER Newnius <newnius.cn@gmail.com>
+
+USER root
+
+# Install Apche HBase
+RUN wget -O apache-hbase.tar.gz http://mirrors.ocf.berkeley.edu/apache/hbase/1.2.6/hbase-1.2.6-bin.tar.gz && \
+tar xzvf apache-hbase.tar.gz -C /usr/local/ && rm apache-hbase.tar.gz
+
+# Create a soft link to make future upgrade transparent
+RUN ln -s /usr/local/hbase-1.2.6 /usr/local/hbase
+
+ENV HBASE_HOME /usr/local/hbase
+ENV PATH $PATH:$HBASE_HOME/bin
+
+# Add default conf files of 1 master, 2 back server, 3 engionserver
+ADD hbase-site.xml $HBASE_HOME/conf
+ADD hbase-env.sh $HBASE_HOME/conf
+ADD regionservers $HBASE_HOME/conf
+ADD backup-masters $HBASE_HOME/conf
+
+WORKDIR /usr/local/hbase
+
+CMD ["/etc/bootstrap.sh", "-d"]

hbase/1.2.6/README.md

@@ -0,0 +1,82 @@
+Run Aapache HBase with Docker
+
+## Create a hadoop cluster with HBase installed in swarm mode
+
+`--hostname` needs 1.13 or higher
+
+```bash
+docker service create \
+--name hadoop-master \
+--network swarm-net \
+--hostname hadoop-master \
+--replicas 1 \
+--detach=true \
+--mount type=bind,source=/etc/localtime,target=/etc/localtime \
+--endpoint-mode vip \
+newnius/hbase:1.2.6
+```
+
+```bash
+docker service create \
+--name hadoop-slave1 \
+--network swarm-net \
+--hostname hadoop-slave1 \
+--replicas 1 \
+--detach=true \
+--mount type=bind,source=/etc/localtime,target=/etc/localtime \
+--endpoint-mode vip \
+newnius/hbase:1.2.6
+```
+
+```bash
+docker service create \
+--name hadoop-slave2 \
+--network swarm-net \
+--hostname hadoop-slave2 \
+--replicas 1 \
+--detach=true \
+--mount type=bind,source=/etc/localtime,target=/etc/localtime \
+--endpoint-mode vip \
+newnius/hbase:1.2.6
+```
+
+```bash
+docker service create \
+--name hadoop-slave3 \
+--network swarm-net \
+--hostname hadoop-slave3 \
+--replicas 1 \
+--detach=true \
+--mount type=bind,source=/etc/localtime,target=/etc/localtime \
+--endpoint-mode vip \
+newnius/hbase:1.2.6
+```
+
+## Init && Test
+
+#### Start Hadoop
+Read [newnius/hadoop](https://hub.docker.com/r/newnius/hadoop/) to learn how to run & init hadoop
+
+#### Start Zookeeper cluster
+```bash
+ZOOKEEPER_NUM=3
+for i in $( seq 1 $ZOOKEEPER_NUM )
+do
+  docker service create \
+  -e MYID=${i} \
+  -e SERVERS=${zookeeper_str} \
+  --replicas 1 \
+  --network swarm-net \
+  --endpoint-mode dnsrr \
+  --name=zookeeper_node${i} \
+  mesoscloud/zookeeper:3.4.8-ubuntu-14.04
+done
+```
+
+#### Start HBase
+```bash
+bash bin/start-hbase.sh
+```
+
+#### Browse
+Now you can see HBase cluster in `http://hadoop-master:16010` in browser. (`[newnius/docker-proxy](https://hub.docker.com/r/newnius/docker-proxy/)` needed.)

hbase/1.2.6/backup-masters

@@ -0,0 +1 @@
+hadoop-slave1

hbase/1.2.6/hbase-env.sh

@@ -0,0 +1,137 @@
+#
+#/**
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+# Set environment variables here.
+
+# This script sets variables multiple times over the course of starting an hbase process,
+# so try to keep things idempotent unless you want to take an even deeper look
+# into the startup scripts (bin/hbase, etc.)
+
+# The java implementation to use.  Java 1.7+ required.
+export JAVA_HOME=/usr/lib/jvm/java-1.8-openjdk/
+
+# Extra Java CLASSPATH elements.  Optional.
+# export HBASE_CLASSPATH=
+
+# The maximum amount of heap to use. Default is left to JVM default.
+# export HBASE_HEAPSIZE=1G
+
+# Uncomment below if you intend to use off heap cache. For example, to allocate 8G of 
+# offheap, set the value to "8G".
+# export HBASE_OFFHEAPSIZE=1G
+
+# Extra Java runtime options.
+# Below are what we set by default.  May only work with SUN JVM.
+# For more on why as well as other possible settings,
+# see http://wiki.apache.org/hadoop/PerformanceTuning
+export HBASE_OPTS="-XX:+UseConcMarkSweepGC"
+
+# Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+
+export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
+export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
+
+# Uncomment one of the below three options to enable java garbage collection logging for the server-side processes.
+
+# This enables basic gc logging to the .out file.
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"
+
+# This enables basic gc logging to its own file.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"
+
+# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"
+
+# Uncomment one of the below three options to enable java garbage collection logging for the client processes.
+
+# This enables basic gc logging to the .out file.
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"
+
+# This enables basic gc logging to its own file.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"
+
+# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"
+
+# See the package documentation for org.apache.hadoop.hbase.io.hfile for other configurations
+# needed setting up off-heap block caching. 
+
+# Uncomment and adjust to enable JMX exporting
+# See jmxremote.password and jmxremote.access in $JRE_HOME/lib/management to configure remote password access.
+# More details at: http://java.sun.com/javase/6/docs/technotes/guides/management/agent.html
+# NOTE: HBase provides an alternative JMX implementation to fix the random ports issue, please see JMX
+# section in HBase Reference Guide for instructions.
+
+# export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=false -Dcom.sun.management.jmxremote.authenticate=false"
+# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10101"
+# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10102"
+# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10103"
+# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10104"
+# export HBASE_REST_OPTS="$HBASE_REST_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10105"
+
+# File naming hosts on which HRegionServers will run.  $HBASE_HOME/conf/regionservers by default.
+# export HBASE_REGIONSERVERS=${HBASE_HOME}/conf/regionservers
+
+# Uncomment and adjust to keep all the Region Server pages mapped to be memory resident
+#HBASE_REGIONSERVER_MLOCK=true
+#HBASE_REGIONSERVER_UID="hbase"
+
+# File naming hosts on which backup HMaster will run.  $HBASE_HOME/conf/backup-masters by default.
+# export HBASE_BACKUP_MASTERS=${HBASE_HOME}/conf/backup-masters
+
+# Extra ssh options.  Empty by default.
+# export HBASE_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HBASE_CONF_DIR"
+
+# Where log files are stored.  $HBASE_HOME/logs by default.
+# export HBASE_LOG_DIR=${HBASE_HOME}/logs
+
+# Enable remote JDWP debugging of major HBase processes. Meant for Core Developers 
+# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8070"
+# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8071"
+# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8072"
+# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8073"
+
+# A string representing this instance of hbase. $USER by default.
+# export HBASE_IDENT_STRING=$USER
+
+# The scheduling priority for daemon processes.  See 'man nice'.
+# export HBASE_NICENESS=10
+
+# The directory where pid files are stored. /tmp by default.
+# export HBASE_PID_DIR=/var/hadoop/pids
+
+# Seconds to sleep between slave commands.  Unset by default.  This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HBASE_SLAVE_SLEEP=0.1
+
+# Tell HBase whether it should manage it's own instance of Zookeeper or not.
+export HBASE_MANAGES_ZK=false
+
+# The default log rolling policy is RFA, where the log file is rolled as per the size defined for the 
+# RFA appender. Please refer to the log4j.properties file to see more details on this appender.
+# In case one needs to do log rolling on a date change, one should set the environment property
+# HBASE_ROOT_LOGGER to "<DESIRED_LOG LEVEL>,DRFA".
+# For example:
+# HBASE_ROOT_LOGGER=INFO,DRFA
+# The reason for changing default to RFA is to avoid the boundary case of filling out disk space as 
+# DRFA doesn't put any cap on the log size. Please refer to HBase-5655 for more context.

hbase/1.2.6/hbase-site.xml

@@ -0,0 +1,44 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+-->
+<configuration>
+  <property>
+    <name>hbase.cluster.distributed</name>
+    <value>true</value>
+  </property>
+  <property>
+    <name>hbase.rootdir</name>
+    <value>hdfs://hadoop-master:8020/hbase</value>
+  </property>
+  <property>
+    <name>hbase.master</name>
+    <value>hadoop-master:60000</value>
+  </property>
+  <property>
+    <name>hbase.zookeeper.quorum</name>
+    <value>zookeeper_node1,zookeeper_node2,zookeeper_node3</value>
+  </property>
+  <property>
+    <name>hbase.regionserver.dns.interface</name>
+    <value>eth0</value>
+  </property>
+</configuration>

hbase/1.2.6/regionservers

@@ -0,0 +1,3 @@
+hadoop-slave1
+hadoop-slave2
+hadoop-slave3