Update PrestoSQL to 346

README.md

@@ -17,7 +17,7 @@ To deploy in Docker Swarm:
     docker stack deploy -c docker-compose.yml hive
 ```
 
-To run a PrestoDB 0.181 with Hive connector:
+To run PrestoSQL 346 with Hive connector:
 
 ```
   docker-compose up -d presto-coordinator
@@ -34,10 +34,10 @@ Load data into Hive:
   > LOAD DATA LOCAL INPATH '/opt/hive/examples/files/kv1.txt' OVERWRITE INTO TABLE pokes;
 ```
 
-Then query it from PrestoDB. You can get [presto.jar](https://prestosql.io/docs/current/installation/cli.html) from PrestoDB website:
+Then query it from PrestoDB. You can get [presto.jar](https://prestosql.io/docs/current/installation/cli.html) from PrestoSQL website:
 ```
-  $ wget https://repo1.maven.org/maven2/io/prestosql/presto-cli/308/presto-cli-308-executable.jar
-  $ mv presto-cli-308-executable.jar presto.jar
+  $ wget https://repo1.maven.org/maven2/io/prestosql/presto-cli/346/presto-cli-346-executable.jar
+  $ mv presto-cli-346-executable.jar presto.jar
   $ chmod +x presto.jar
   $ ./presto.jar --server localhost:8080 --catalog hive --schema default
   presto> select * from pokes;
@@ -47,3 +47,4 @@ Then query it from PrestoDB. You can get [presto.jar](https://prestosql.io/docs/
 * Ivan Ermilov [@earthquakesan](https://github.com/earthquakesan) (maintainer)
 * Yiannis Mouchakis [@gmouchakis](https://github.com/gmouchakis)
 * Ke Zhu [@shawnzhu](https://github.com/shawnzhu)
+* Eric Semeniuc [@esemeniuc](https://github.com/esemeniuc)

docker-compose.yml

@@ -42,7 +42,11 @@ services:
   hive-metastore-postgresql:
     image: bde2020/hive-metastore-postgresql:2.3.0
   presto-coordinator:
-    image: shawnzhu/prestodb:0.181
+    build: ./presto
+    depends_on:
+      - hive-server
+      - namenode
+      - datanode
     ports:
       - "8080:8080"
 

presto/Dockerfile

@@ -0,0 +1,22 @@
+FROM bde2020/hadoop-base:latest
+
+ENV PRESTO_VERSION=346
+ENV PRESTO_HOME=/opt/presto
+WORKDIR ${PRESTO_HOME}
+
+#need java 11 (requires backports for stretch) and python for recent presto
+RUN echo "deb http://deb.debian.org/debian stretch-backports main" >> /etc/apt/sources.list && \
+    apt update && \
+    apt install -y openjdk-11-jre python && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN set -xe && curl -L https://repo1.maven.org/maven2/io/prestosql/presto-server/${PRESTO_VERSION}/presto-server-${PRESTO_VERSION}.tar.gz | tar xz && \
+    mv presto-server-${PRESTO_VERSION}/* . && \
+    rmdir presto-server-${PRESTO_VERSION} && \
+    mkdir -p ${PRESTO_HOME}/data
+
+COPY etc ${PRESTO_HOME}/etc
+VOLUME ["${PRESTO_HOME}/etc", "${PRESTO_HOME}/data"]
+EXPOSE 8080
+
+CMD ["bin/launcher", "run"]

presto/etc/catalog/hive.properties

@@ -0,0 +1,5 @@
+connector.name=hive-hadoop2
+hive.metastore.uri=thrift://hive-metastore:9083
+hive.allow-register-partition-procedure=true
+hive.allow-drop-table=true
+hive.config.resources=/etc/hadoop/core-site.xml,/etc/hadoop/hdfs-site.xml

presto/etc/config.properties

@@ -0,0 +1,7 @@
+coordinator=true
+node-scheduler.include-coordinator=true
+http-server.http.port=8080
+query.max-memory=5GB
+query.max-memory-per-node=1GB
+discovery-server.enabled=true
+discovery.uri=http://presto-coordinator:8080

presto/etc/jvm.config

@@ -0,0 +1,13 @@
+-server
+-Xmx16G
+-XX:-UseBiasedLocking
+-XX:+UseG1GC
+-XX:G1HeapRegionSize=32M
+-XX:+ExplicitGCInvokesConcurrent
+-XX:+ExitOnOutOfMemoryError
+-XX:+HeapDumpOnOutOfMemoryError
+-XX:ReservedCodeCacheSize=512M
+-XX:PerMethodRecompilationCutoff=10000
+-XX:PerBytecodeRecompilationCutoff=10000
+-Djdk.attach.allowAttachSelf=true
+-Djdk.nio.maxCachedBufferSize=2000000

presto/etc/node.properties

@@ -0,0 +1,3 @@
+node.environment=development
+node.id=presto-coordinator
+node.data-dir=/opt/presto/data