Merge pull request datafold#41 from datafold/presto-docker

Author: sirupsen

Dockerfile

@@ -5,7 +5,7 @@ RUN apt-get update && apt-get install -y \
 RUN pip install --no-cache-dir poetry==1.1.13
 COPY . /app
 WORKDIR /app
-# For now while we are in heavy development we install the latest with Poetry 
+# For now while we are in heavy development we install the latest with Poetry
 # and execute directly with Poetry. Later, we'll move to the released Pip package.
-RUN poetry install -E preql -E mysql -E pgsql -E snowflake
+RUN poetry install
 ENTRYPOINT ["poetry", "run", "python3", "-m", "data_diff"]

dev/Dockerfile.prestosql.340

@@ -0,0 +1,25 @@
+FROM openjdk:11-jdk-slim-buster
+
+ENV PRESTO_VERSION=340
+ENV PRESTO_SERVER_URL=https://repo1.maven.org/maven2/io/prestosql/presto-server/${PRESTO_VERSION}/presto-server-${PRESTO_VERSION}.tar.gz
+ENV PRESTO_CLI_URL=https://repo1.maven.org/maven2/io/prestosql/presto-cli/${PRESTO_VERSION}/presto-cli-${PRESTO_VERSION}-executable.jar
+ENV PRESTO_HOME=/opt/presto
+ENV PATH=${PRESTO_HOME}/bin:${PATH}
+
+WORKDIR $PRESTO_HOME
+
+RUN set -xe \
+ && apt-get update \
+ && apt-get install -y curl less python \
+ && curl -sSL $PRESTO_SERVER_URL | tar xz --strip 1 \
+ && curl -sSL $PRESTO_CLI_URL > ./bin/presto \
+ && chmod +x ./bin/presto \
+ && apt-get remove -y curl \
+ && rm -rf /var/lib/apt/lists/*
+
+VOLUME /data
+
+EXPOSE 8080
+
+ENTRYPOINT ["launcher"]
+CMD ["run"]

dev/presto-conf/standalone/catalog/jmx.properties

@@ -0,0 +1 @@
+connector.name=jmx

dev/presto-conf/standalone/catalog/memory.properties

@@ -0,0 +1 @@
+connector.name=memory

dev/presto-conf/standalone/catalog/postgresql.properties

@@ -0,0 +1,4 @@
+connector.name=postgresql
+connection-url=jdbc:postgresql://postgres:5432/postgres
+connection-user=postgres
+connection-password=Password1

dev/presto-conf/standalone/catalog/tpcds.properties

@@ -0,0 +1 @@
+connector.name=tpcds

dev/presto-conf/standalone/catalog/tpch.properties

@@ -0,0 +1 @@
+connector.name=tpch

dev/presto-conf/standalone/config.properties

@@ -0,0 +1,8 @@
+coordinator=true
+node-scheduler.include-coordinator=true
+http-server.http.port=8080
+query.max-memory=5GB
+query.max-memory-per-node=1GB
+query.max-total-memory-per-node=2GB
+discovery-server.enabled=true
+discovery.uri=http://127.0.0.1:8080

dev/presto-conf/standalone/jvm.config

@@ -0,0 +1,9 @@
+-server
+-Xmx16G
+-XX:+UseG1GC
+-XX:G1HeapRegionSize=32M
+-XX:+UseGCOverheadLimit
+-XX:+ExplicitGCInvokesConcurrent
+-XX:+HeapDumpOnOutOfMemoryError
+-XX:+ExitOnOutOfMemoryError
+-XX:OnOutOfMemoryError=kill -9 %p

dev/presto-conf/standalone/log.properties

@@ -0,0 +1 @@
+com.facebook.presto=INFO