Skip to content

Instantly share code, notes, and snippets.

@codope
Last active March 17, 2022 06:39
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save codope/3dd986de5e54f0650dd74b6032e4456c to your computer and use it in GitHub Desktop.
Save codope/3dd986de5e54f0650dd74b6032e4456c to your computer and use it in GitHub Desktop.
Hudi Docker ARM64
diff --git a/docker/compose/docker-compose_hadoop284_hive233_spark244.yml b/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
index 05790963b..31e3b6dac 100644
--- a/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
+++ b/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
@@ -19,6 +19,7 @@ services:
namenode:
image: apachehudi/hudi-hadoop_2.8.4-namenode:latest
+ platform: linux/arm64
hostname: namenode
container_name: namenode
environment:
@@ -36,6 +37,7 @@ services:
datanode1:
image: apachehudi/hudi-hadoop_2.8.4-datanode:latest
+ platform: linux/arm64
container_name: datanode1
hostname: datanode1
environment:
@@ -58,6 +60,7 @@ services:
historyserver:
image: apachehudi/hudi-hadoop_2.8.4-history:latest
+ platform: linux/arm64
hostname: historyserver
container_name: historyserver
environment:
@@ -79,7 +82,8 @@ services:
- historyserver:/hadoop/yarn/timeline
hive-metastore-postgresql:
- image: bde2020/hive-metastore-postgresql:2.3.0
+ image: menorah84/hive-metastore-postgresql:2.3.0
+ platform: linux/arm64
+ environment:
+ - POSTGRES_HOST_AUTH_METHOD=trust
volumes:
- hive-metastore-postgresql:/var/lib/postgresql
hostname: hive-metastore-postgresql
@@ -87,6 +91,7 @@ services:
hivemetastore:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3:latest
+ platform: linux/arm64
hostname: hivemetastore
container_name: hivemetastore
links:
@@ -110,6 +115,7 @@ services:
hiveserver:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3:latest
+ platform: linux/arm64
hostname: hiveserver
container_name: hiveserver
env_file:
@@ -129,6 +135,7 @@ services:
sparkmaster:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkmaster_2.4.4:latest
+ platform: linux/arm64
hostname: sparkmaster
container_name: sparkmaster
env_file:
@@ -146,6 +153,7 @@ services:
spark-worker-1:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkworker_2.4.4:latest
+ platform: linux/arm64
hostname: spark-worker-1
container_name: spark-worker-1
env_file:
@@ -163,7 +171,8 @@ services:
- "namenode"
zookeeper:
- image: 'bitnami/zookeeper:3.4.12-r68'
+ image: 'arm64v8/zookeeper:3.4.12'
+ platform: linux/arm64
hostname: zookeeper
container_name: zookeeper
ports:
@@ -172,7 +181,8 @@ services:
- ALLOW_ANONYMOUS_LOGIN=yes
kafka:
- image: 'bitnami/kafka:2.0.0'
+ image: 'wurstmeister/kafka:2.12-2.0.1'
+ platform: linux/arm64
hostname: kafkabroker
container_name: kafkabroker
ports:
@@ -185,6 +195,7 @@ services:
container_name: presto-coordinator-1
hostname: presto-coordinator-1
image: apachehudi/hudi-hadoop_2.8.4-prestobase_0.217:latest
+ platform: linux/arm64
ports:
- '8090:8090'
environment:
@@ -204,6 +215,7 @@ services:
container_name: presto-worker-1
hostname: presto-worker-1
image: apachehudi/hudi-hadoop_2.8.4-prestobase_0.217:latest
+ platform: linux/arm64
depends_on: ["presto-coordinator-1"]
environment:
- PRESTO_JVM_MAX_HEAP=512M
@@ -221,17 +233,18 @@ services:
- ${HUDI_WS}:/var/hoodie/ws
command: worker
- graphite:
- container_name: graphite
- hostname: graphite
- image: graphiteapp/graphite-statsd
- ports:
- - 80:80
- - 2003-2004:2003-2004
- - 8126:8126
+# graphite:
+# container_name: graphite
+# hostname: graphite
+# image: graphiteapp/graphite-statsd
+# ports:
+# - 80:80
+# - 2003-2004:2003-2004
+# - 8126:8126
adhoc-1:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkadhoc_2.4.4:latest
+ platform: linux/arm64
hostname: adhoc-1
container_name: adhoc-1
env_file:
@@ -253,6 +266,7 @@ services:
adhoc-2:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkadhoc_2.4.4:latest
+ platform: linux/arm64
hostname: adhoc-2
container_name: adhoc-2
env_file:
diff --git a/docker/compose/docker-compose_hadoop284_hive233_spark244.yml b/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
index 05790963b..31e3b6dac 100644
--- a/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
+++ b/docker/compose/docker-compose_hadoop284_hive233_spark244.yml
@@ -19,6 +19,7 @@ services:
namenode:
image: apachehudi/hudi-hadoop_2.8.4-namenode:latest
+ platform: linux/arm64
hostname: namenode
container_name: namenode
environment:
@@ -36,6 +37,7 @@ services:
datanode1:
image: apachehudi/hudi-hadoop_2.8.4-datanode:latest
+ platform: linux/arm64
container_name: datanode1
hostname: datanode1
environment:
@@ -58,6 +60,7 @@ services:
historyserver:
image: apachehudi/hudi-hadoop_2.8.4-history:latest
+ platform: linux/arm64
hostname: historyserver
container_name: historyserver
environment:
@@ -79,7 +82,8 @@ services:
- historyserver:/hadoop/yarn/timeline
hive-metastore-postgresql:
- image: bde2020/hive-metastore-postgresql:2.3.0
+ image: menorah84/hive-metastore-postgresql:2.3.0
+ platform: linux/arm64
volumes:
- hive-metastore-postgresql:/var/lib/postgresql
hostname: hive-metastore-postgresql
@@ -87,6 +91,7 @@ services:
hivemetastore:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3:latest
+ platform: linux/arm64
hostname: hivemetastore
container_name: hivemetastore
links:
@@ -110,6 +115,7 @@ services:
hiveserver:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3:latest
+ platform: linux/arm64
hostname: hiveserver
container_name: hiveserver
env_file:
@@ -129,6 +135,7 @@ services:
sparkmaster:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkmaster_2.4.4:latest
+ platform: linux/arm64
hostname: sparkmaster
container_name: sparkmaster
env_file:
@@ -146,6 +153,7 @@ services:
spark-worker-1:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkworker_2.4.4:latest
+ platform: linux/arm64
hostname: spark-worker-1
container_name: spark-worker-1
env_file:
@@ -163,7 +171,8 @@ services:
- "namenode"
zookeeper:
- image: 'bitnami/zookeeper:3.4.12-r68'
+ image: 'arm64v8/zookeeper:3.4.12'
+ platform: linux/arm64
hostname: zookeeper
container_name: zookeeper
ports:
@@ -172,7 +181,8 @@ services:
- ALLOW_ANONYMOUS_LOGIN=yes
kafka:
- image: 'bitnami/kafka:2.0.0'
+ image: 'wurstmeister/kafka:2.12-2.0.1'
+ platform: linux/arm64
hostname: kafkabroker
container_name: kafkabroker
ports:
@@ -185,6 +195,7 @@ services:
container_name: presto-coordinator-1
hostname: presto-coordinator-1
image: apachehudi/hudi-hadoop_2.8.4-prestobase_0.217:latest
+ platform: linux/arm64
ports:
- '8090:8090'
environment:
@@ -204,6 +215,7 @@ services:
container_name: presto-worker-1
hostname: presto-worker-1
image: apachehudi/hudi-hadoop_2.8.4-prestobase_0.217:latest
+ platform: linux/arm64
depends_on: ["presto-coordinator-1"]
environment:
- PRESTO_JVM_MAX_HEAP=512M
@@ -221,17 +233,18 @@ services:
- ${HUDI_WS}:/var/hoodie/ws
command: worker
- graphite:
- container_name: graphite
- hostname: graphite
- image: graphiteapp/graphite-statsd
- ports:
- - 80:80
- - 2003-2004:2003-2004
- - 8126:8126
+# graphite:
+# container_name: graphite
+# hostname: graphite
+# image: graphiteapp/graphite-statsd
+# ports:
+# - 80:80
+# - 2003-2004:2003-2004
+# - 8126:8126
adhoc-1:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkadhoc_2.4.4:latest
+ platform: linux/arm64
hostname: adhoc-1
container_name: adhoc-1
env_file:
@@ -253,6 +266,7 @@ services:
adhoc-2:
image: apachehudi/hudi-hadoop_2.8.4-hive_2.3.3-sparkadhoc_2.4.4:latest
+ platform: linux/arm64
hostname: adhoc-2
container_name: adhoc-2
env_file:
diff --git a/docker/hoodie/hadoop/base/Dockerfile b/docker/hoodie/hadoop/base/Dockerfile
index 2c98ce624..280c38146 100644
--- a/docker/hoodie/hadoop/base/Dockerfile
+++ b/docker/hoodie/hadoop/base/Dockerfile
@@ -15,7 +15,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-FROM openjdk:8u212-jdk-slim-stretch
+FROM arm64v8/openjdk:8u212-jdk-slim-stretch
MAINTAINER Hoodie
USER root
diff --git a/docker/hoodie/hadoop/datanode/Dockerfile b/docker/hoodie/hadoop/datanode/Dockerfile
index 79dd798f7..8afa2cf2c 100644
--- a/docker/hoodie/hadoop/datanode/Dockerfile
+++ b/docker/hoodie/hadoop/datanode/Dockerfile
@@ -17,7 +17,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HADOOP_DN_PORT=50075
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
ENV HADOOP_DN_PORT ${HADOOP_DN_PORT}
diff --git a/docker/hoodie/hadoop/historyserver/Dockerfile b/docker/hoodie/hadoop/historyserver/Dockerfile
index e08adbb05..91fa552af 100644
--- a/docker/hoodie/hadoop/historyserver/Dockerfile
+++ b/docker/hoodie/hadoop/historyserver/Dockerfile
@@ -17,7 +17,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HADOOP_HISTORY_PORT=8188
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
ENV HADOOP_HISTORY_PORT ${HADOOP_HISTORY_PORT}
diff --git a/docker/hoodie/hadoop/hive_base/Dockerfile b/docker/hoodie/hadoop/hive_base/Dockerfile
index 8d85fd5b5..01ff0cf11 100644
--- a/docker/hoodie/hadoop/hive_base/Dockerfile
+++ b/docker/hoodie/hadoop/hive_base/Dockerfile
@@ -16,7 +16,7 @@
# limitations under the License.
ARG HADOOP_VERSION=2.8.4
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
ENV HIVE_HOME /opt/hive
ENV PATH $HIVE_HOME/bin:$PATH
@@ -33,7 +33,7 @@ ENV HIVE_URL ${HIVE_URL}
RUN echo "Hive URL is :${HIVE_URL}" && wget ${HIVE_URL} -O hive.tar.gz && \
tar -xzvf hive.tar.gz && mv *hive*-bin hive && \
ln -s /usr/share/java/mysql-connector-java.jar $HIVE_HOME/lib/mysql-connector-java.jar && \
- wget https://jdbc.postgresql.org/download/postgresql-9.4.1212.jar -O $HIVE_HOME/lib/postgresql-jdbc.jar && \
+ wget --no-check-certificate https://jdbc.postgresql.org/download/postgresql-9.4.1212.jar -O $HIVE_HOME/lib/postgresql-jdbc.jar && \
rm hive.tar.gz && mkdir -p /var/hoodie/ws/docker/hoodie/hadoop/hive_base/target/
#Spark should be compiled with Hive to be able to use it
diff --git a/docker/hoodie/hadoop/namenode/Dockerfile b/docker/hoodie/hadoop/namenode/Dockerfile
index d89c30eff..757e895ac 100644
--- a/docker/hoodie/hadoop/namenode/Dockerfile
+++ b/docker/hoodie/hadoop/namenode/Dockerfile
@@ -17,7 +17,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HADOOP_WEBHDFS_PORT=50070
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest
ENV HADOOP_WEBHDFS_PORT ${HADOOP_WEBHDFS_PORT}
diff --git a/docker/hoodie/hadoop/prestobase/Dockerfile b/docker/hoodie/hadoop/prestobase/Dockerfile
index 43b989e6b..3a22e8c88 100644
--- a/docker/hoodie/hadoop/prestobase/Dockerfile
+++ b/docker/hoodie/hadoop/prestobase/Dockerfile
@@ -20,7 +20,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HIVE_VERSION=2.3.3
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest as hadoop-base
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-base:latest as hadoop-base
ARG PRESTO_VERSION=0.217
diff --git a/docker/hoodie/hadoop/spark_base/Dockerfile b/docker/hoodie/hadoop/spark_base/Dockerfile
index 7eeab093a..91c53e8d8 100644
--- a/docker/hoodie/hadoop/spark_base/Dockerfile
+++ b/docker/hoodie/hadoop/spark_base/Dockerfile
@@ -17,7 +17,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HIVE_VERSION=2.3.3
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}
ENV ENABLE_INIT_DAEMON true
ENV INIT_DAEMON_BASE_URI http://identifier/init-daemon
diff --git a/docker/hoodie/hadoop/sparkadhoc/Dockerfile b/docker/hoodie/hadoop/sparkadhoc/Dockerfile
index a114cf0fb..b387a30b4 100644
--- a/docker/hoodie/hadoop/sparkadhoc/Dockerfile
+++ b/docker/hoodie/hadoop/sparkadhoc/Dockerfile
@@ -18,7 +18,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HIVE_VERSION=2.3.3
ARG SPARK_VERSION=2.4.4
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
ARG PRESTO_VERSION=0.217
COPY adhoc.sh /opt/spark
diff --git a/docker/hoodie/hadoop/sparkmaster/Dockerfile b/docker/hoodie/hadoop/sparkmaster/Dockerfile
index aaeb03f39..3e5e7eddf 100644
--- a/docker/hoodie/hadoop/sparkmaster/Dockerfile
+++ b/docker/hoodie/hadoop/sparkmaster/Dockerfile
@@ -18,7 +18,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HIVE_VERSION=2.3.3
ARG SPARK_VERSION=2.4.4
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
COPY master.sh /opt/spark
diff --git a/docker/hoodie/hadoop/sparkworker/Dockerfile b/docker/hoodie/hadoop/sparkworker/Dockerfile
index ba867f2d3..81f2013c5 100644
--- a/docker/hoodie/hadoop/sparkworker/Dockerfile
+++ b/docker/hoodie/hadoop/sparkworker/Dockerfile
@@ -18,7 +18,7 @@
ARG HADOOP_VERSION=2.8.4
ARG HIVE_VERSION=2.3.3
ARG SPARK_VERSION=2.4.4
-FROM apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
+FROM --platform=linux/arm64 apachehudi/hudi-hadoop_${HADOOP_VERSION}-hive_${HIVE_VERSION}-sparkbase_${SPARK_VERSION}
COPY worker.sh /opt/spark
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment