Dockerize gremlin-server.sh with JanusGraph

.gitignore

@@ -14,6 +14,7 @@ target/
 /output/
 /scripts/
 /elasticsearch/
+/docker/*.zip
 # When executing tests in alphabetical order, Maven generates temporary
 # files with names like this:
 #

AUTHORS.txt

@@ -11,6 +11,7 @@
 
 # Please keep the list sorted.
 
+Amazon
 Aurelius
 DataStax
 Dylan Bethune-Waddell <dylan.bethune.waddell@mail.utoronto.ca>

BUILDING.md

@@ -30,6 +30,37 @@ To build with only the TinkerPop tests\*:
 mvn clean install -Dtest.skip.tp=false -DskipTests=true
 ```
 
+## Building Docker Image for JanusGraph Gremlin Server
+
+To build and run Docker images with JanusGraph and Gremlin Server, configured 
+to run the BerkeleyJE backend and Elasticsearch (requires [Docker Compose](https://docs.docker.com/compose/)):
+
+```bash
+mvn clean install -Pjanusgraph-release -Dgpg.skip=true -DskipTests=true && mvn docker:build -Pjanusgraph-docker -pl janusgraph-dist
+docker-compose -f janusgraph-dist/janusgraph-dist-hadoop-2/docker-compose.yml up
+```
+
+Note the above `docker-compose` call launches containers in the foreground and is convenient for monitoring logs but add "-d" to instead run in the background.
+
+To connect to the server in the same container on the console:
+
+```bash
+docker exec -i -t janusgraph /var/janusgraph/bin/gremlin.sh
+```
+
+Then you can interact with the graph on the console through the `:remote` interface:
+
+```groovy
+gremlin> :remote connect tinkerpop.server conf/remote.yaml
+==>Configured localhost/127.0.0.1:8182
+gremlin> :remote console
+==>All scripts will now be sent to Gremlin Server - [localhost/127.0.0.1:8182] - type ':remote console' to return to local mode
+gremlin> GraphOfTheGodsFactory.load(graph)
+==>null
+gremlin> g = graph.traversal()
+==>graphtraversalsource[standardjanusgraph[berkeleyje:db/berkeley], standard]
+```
+
 ## Building on Eclipse IDE
 Note that this has only been tested on Eclipse Neon.2 Release (4.6.2) with m2e (1.7.0.20160603-1933) and m2e-wtp (1.3.1.20160831-1005) plugin.
 

README.md

@@ -1,6 +1,9 @@
 ![JanusGraph logo](janusgraph.png)
 
-JanusGraph is a highly scalable [graph database](http://en.wikipedia.org/wiki/Graph_database) optimized for storing and querying large graphs with billions of vertices and edges distributed across a multi-machine cluster. JanusGraph is a transactional database that can support thousands of concurrent users, complex traversals, and analytic graph queries.
+JanusGraph is a highly scalable [graph database](http://en.wikipedia.org/wiki/Graph_database)
+optimized for storing and querying large graphs with billions of vertices and edges
+distributed across a multi-machine cluster. JanusGraph is a transactional database that
+can support thousands of concurrent users, complex traversals, and analytic graph queries.
 
 [![Build Status][travis-shield]][travis-link]
 [![Maven][maven-shield]][maven-link]
@@ -18,7 +21,8 @@ JanusGraph is a highly scalable [graph database](http://en.wikipedia.org/wiki/Gr
 
 ## Learn More
 
-The [project homepage](http://janusgraph.org) contains more information on JanusGraph and provides links to documentation, getting-started guides and release downloads.
+The [project homepage](http://janusgraph.org) contains more information on JanusGraph and
+provides links to documentation, getting-started guides and release downloads.
 
 ## Community
 

janusgraph-dist/janusgraph-dist-hadoop-2/Dockerfile

@@ -0,0 +1,11 @@
+FROM openjdk:8
+
+ARG server_zip
+ADD ${server_zip} /var
+
+RUN apt-get update -y && apt-get install -y zip && \
+    server_base=`basename ${server_zip} .zip` && \
+    unzip -q /var/${server_base}.zip -d /var && \
+    ln -s /var/${server_base} /var/janusgraph
+
+WORKDIR /var/janusgraph

janusgraph-dist/janusgraph-dist-hadoop-2/docker-compose.yml

@@ -0,0 +1,24 @@
+version: '2'
+services:
+  janusgraph:
+    image: janusgraph/server:latest
+    container_name: janusgraph
+    ports:
+      - "8182:8182"
+    volumes:
+      - ./es/wait-for-es.sh:/usr/bin/wait-for-es.sh
+    depends_on:
+      - "elasticsearch"
+    command: ["wait-for-es.sh", "elasticsearch", "./bin/gremlin-server.sh", "./conf/gremlin-server/gremlin-server-berkeleyje.yaml"]
+
+  elasticsearch:
+    image: docker.elastic.co/elasticsearch/elasticsearch:5.3.2
+    environment:
+      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
+      - "http.host=0.0.0.0"
+      - "transport.host=127.0.0.1"
+    ports:
+      - "9200"
+    volumes:
+      - ./es/elasticsearch.yml:/usr/share/elasticsearch/config/elasticsearch.yml
+

janusgraph-dist/janusgraph-dist-hadoop-2/es/elasticsearch.yml

@@ -0,0 +1,10 @@
+cluster.name: "docker-cluster"
+network.host: 0.0.0.0
+
+# minimum_master_nodes need to be explicitly set when bound on a public IP
+# set to 1 to allow single node clusters
+# Details: https://github.com/elastic/elasticsearch/pull/17288
+discovery.zen.minimum_master_nodes: 1
+
+xpack.security.enabled : false
+

janusgraph-dist/janusgraph-dist-hadoop-2/es/wait-for-es.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+set -e
+
+host="$1"
+
+shift
+cmd="$@"
+
+until $(curl --output /dev/null --silent --head --fail http://$host:9200); do
+  printf '.'
+  sleep 5
+done
+
+>&2 echo "Elasticsearch is up"
+
+exec $cmd
+

janusgraph-dist/pom.xml

@@ -39,6 +39,7 @@
         <pkgtools.dir>${project.basedir}/..</pkgtools.dir>
 
         <skipDefaultDistroIT>${it.skip}</skipDefaultDistroIT>
+        <docker.maven.version>0.4.13</docker.maven.version>
     </properties>
 
     <modules>
@@ -622,6 +623,32 @@
             </build>
         </profile>
 
+        <profile>
+            <id>janusgraph-docker</id>
+            <build>
+                <pluginManagement>
+                    <plugins>
+                        <plugin>
+                            <groupId>com.spotify</groupId>
+                            <artifactId>docker-maven-plugin</artifactId>
+                            <version>${docker.maven.version}</version>
+                            <configuration>
+                                <dockerDirectory>${project.basedir}/janusgraph-dist-hadoop-2</dockerDirectory>
+                                <buildArgs>
+                                    <server_zip>target/janusgraph-${project.version}-hadoop2.zip</server_zip>
+                                </buildArgs>
+                                <forceTags>true</forceTags>
+                                <imageName>janusgraph/server</imageName>
+                                <imageTags>
+                                    <imageTag>${project.version}</imageTag>
+                                </imageTags>
+                            </configuration>
+                        </plugin>
+                    </plugins>
+                </pluginManagement>
+            </build>
+        </profile>
+
         <profile>
             <id>janusgraph-release</id>
 

janusgraph-dist/src/assembly/static/conf/gremlin-server/gremlin-server-berkeleyje.yaml

@@ -0,0 +1,39 @@
+host: localhost
+port: 8182
+scriptEvaluationTimeout: 30000
+channelizer: org.apache.tinkerpop.gremlin.server.channel.WebSocketChannelizer
+graphs: {
+  graph: conf/gremlin-server/janusgraph-berkeleyje-es-server.properties}
+plugins:
+  - janusgraph.imports
+scriptEngines: {
+  gremlin-groovy: {
+    imports: [java.lang.Math],
+    staticImports: [java.lang.Math.PI],
+    scripts: [scripts/empty-sample.groovy]}}
+serializers:
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GryoMessageSerializerV1d0, config: { ioRegistries: [org.janusgraph.graphdb.tinkerpop.JanusGraphIoRegistry] }}
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GryoLiteMessageSerializerV1d0, config: {ioRegistries: [org.janusgraph.graphdb.tinkerpop.JanusGraphIoRegistry] }}
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GryoMessageSerializerV1d0, config: { serializeResultToString: true }}
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GraphSONMessageSerializerGremlinV1d0, config: { ioRegistries: [org.janusgraph.graphdb.tinkerpop.JanusGraphIoRegistry] }}
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GraphSONMessageSerializerGremlinV2d0, config: { ioRegistries: [org.janusgraph.graphdb.tinkerpop.JanusGraphIoRegistry] }}
+  - { className: org.apache.tinkerpop.gremlin.driver.ser.GraphSONMessageSerializerV1d0, config: { ioRegistries: [org.janusgraph.graphdb.tinkerpop.JanusGraphIoRegistry] }}
+processors:
+  - { className: org.apache.tinkerpop.gremlin.server.op.session.SessionOpProcessor, config: { sessionTimeout: 28800000 }}
+  - { className: org.apache.tinkerpop.gremlin.server.op.traversal.TraversalOpProcessor, config: { cacheExpirationTime: 600000, cacheMaxSize: 1000 }}
+metrics: {
+  consoleReporter: {enabled: true, interval: 180000},
+  csvReporter: {enabled: true, interval: 180000, fileName: /tmp/gremlin-server-metrics.csv},
+  jmxReporter: {enabled: true},
+  slf4jReporter: {enabled: true, interval: 180000},
+  gangliaReporter: {enabled: false, interval: 180000, addressingMode: MULTICAST},
+  graphiteReporter: {enabled: false, interval: 180000}}
+maxInitialLineLength: 4096
+maxHeaderSize: 8192
+maxChunkSize: 8192
+maxContentLength: 65536
+maxAccumulationBufferComponents: 1024
+resultIterationBatchSize: 64
+writeBufferLowWaterMark: 32768
+writeBufferHighWaterMark: 65536
+

janusgraph-dist/src/assembly/static/conf/gremlin-server/janusgraph-berkeleyje-es-server.properties

@@ -0,0 +1,12 @@
+# JanusGraph configuration sample: BerkeleyDB JE and embedded Elasticsearch
+#
+# This file opens a BDB JE instance in the directory
+# db/berkeley.  It also starts a local Elasticsearch
+# service inside the same JVM running JanusGraph, persisted at
+# db/es.
+
+gremlin.graph=org.janusgraph.core.JanusGraphFactory
+storage.backend=berkeleyje
+storage.directory=db/berkeley
+index.search.backend=elasticsearch
+index.search.hostname=elasticsearch

pom.xml

@@ -111,13 +111,15 @@
         <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
         <janusgraph.testdir>${project.build.directory}/janusgraph-test</janusgraph.testdir>
         <gpg.skip>false</gpg.skip>
+        <maven.gpg.version>1.4</maven.gpg.version>
         <perf.jvm.opts />
         <default.test.jvm.opts>-Xms256m -Xmx768m -XX:+HeapDumpOnOutOfMemoryError -ea ${test.extra.jvm.opts}</default.test.jvm.opts>
         <mem.jvm.opts>-Xms256m -Xmx256m -ea -XX:+HeapDumpOnOutOfMemoryError ${test.extra.jvm.opts}</mem.jvm.opts>
         <test.extra.jvm.opts />
         <test.skip.default>false</test.skip.default>
         <test.skip.tp>true</test.skip.tp>
         <top.level.basedir>${basedir}</top.level.basedir>
+        <maven.javadoc.version>2.10.4</maven.javadoc.version>
         <compiler.source>1.8</compiler.source>
         <compiler.target>1.8</compiler.target>
         <test.excluded.groups>org.janusgraph.testcategory.MemoryTests,org.janusgraph.testcategory.PerformanceTests,org.janusgraph.testcategory.BrittleTests</test.excluded.groups>
@@ -383,7 +385,7 @@
                 </plugin>
                 <plugin>
                     <artifactId>maven-javadoc-plugin</artifactId>
-                    <version>2.9.1</version>
+                    <version>${maven.javadoc.version}</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-assembly-plugin</artifactId>
@@ -407,7 +409,7 @@
                 </plugin>
                 <plugin>
                     <artifactId>maven-gpg-plugin</artifactId>
-                    <version>1.4</version>
+                    <version>${maven.gpg.version}</version>
                 </plugin>
                 <plugin>
                     <groupId>org.codehaus.mojo</groupId>
@@ -1113,7 +1115,7 @@
                     <plugin>
                         <groupId>org.apache.maven.plugins</groupId>
                         <artifactId>maven-javadoc-plugin</artifactId>
-                        <version>2.7</version>
+                        <version>${maven.javadoc.version}</version>
                         <executions>
                             <execution>
                                 <id>attach-javadocs</id>
@@ -1123,7 +1125,7 @@
                     </plugin>
                     <plugin>
                         <artifactId>maven-gpg-plugin</artifactId>
-                        <version>1.1</version>
+                        <version>${maven.gpg.version}</version>
                         <executions>
                             <execution>
                                 <id>sign-artifacts</id>