diff --git a/Dockerfile b/Dockerfile index 8c76e27..6751394 100644 --- a/Dockerfile +++ b/Dockerfile @@ -9,9 +9,9 @@ RUN mkdir -p /assets/ && cd /assets && \ curl -OL https://downloads.datastax.com/enterprise/cqlsh-astra.tar.gz && \ tar -xzf ./cqlsh-astra.tar.gz && \ rm ./cqlsh-astra.tar.gz && \ - curl -OL https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz && \ - tar -xzf ./spark-3.5.2-bin-hadoop3-scala2.13.tgz && \ - rm ./spark-3.5.2-bin-hadoop3-scala2.13.tgz + curl -OL https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz && \ + tar -xzf ./spark-3.5.3-bin-hadoop3-scala2.13.tgz && \ + rm ./spark-3.5.3-bin-hadoop3-scala2.13.tgz RUN apt-get update && apt-get install -y openssh-server vim python3 --no-install-recommends && \ rm -rf /var/lib/apt/lists/* && \ @@ -44,7 +44,7 @@ RUN chmod +x ./get-latest-maven-version.sh && \ rm -rf "$USER_HOME_DIR/.m2" # Add all migration tools to path -ENV PATH="${PATH}:/assets/dsbulk/bin/:/assets/cqlsh-astra/bin/:/assets/spark-3.5.2-bin-hadoop3-scala2.13/bin/" +ENV PATH="${PATH}:/assets/dsbulk/bin/:/assets/cqlsh-astra/bin/:/assets/spark-3.5.3-bin-hadoop3-scala2.13/bin/" EXPOSE 22 diff --git a/README.md b/README.md index fb00908..3a209e1 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ Migrate and Validate Tables between Origin and Target Cassandra Clusters. -> :warning: Please note this job has been tested with spark version [3.5.2](https://archive.apache.org/dist/spark/spark-3.5.2/) +> :warning: Please note this job has been tested with spark version [3.5.3](https://archive.apache.org/dist/spark/spark-3.5.3/) ## Install as a Container - Get the latest image that includes all dependencies from [DockerHub](https://hub.docker.com/r/datastax/cassandra-data-migrator) @@ -18,10 +18,10 @@ Migrate and Validate Tables between Origin and Target Cassandra Clusters. ### Prerequisite - Install **Java11** (minimum) as Spark binaries are compiled with it. -- Install Spark version [`3.5.2`](https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz) on a single VM (no cluster necessary) where you want to run this job. Spark can be installed by running the following: - +- Install Spark version [`3.5.3`](https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz) on a single VM (no cluster necessary) where you want to run this job. Spark can be installed by running the following: - ``` -wget https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz -tar -xvzf spark-3.5.2-bin-hadoop3-scala2.13.tgz +wget https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz +tar -xvzf spark-3.5.3-bin-hadoop3-scala2.13.tgz ``` > :warning: If the above Spark and Scala version is not properly installed, you'll then see a similar exception like below when running the CDM jobs, diff --git a/RELEASE.md b/RELEASE.md index 8229bf7..e3b604e 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -1,4 +1,7 @@ # Release Notes +## [4.4.2] - 2024-10-TBD +- Upgraded to use Spark `3.5.3`. + ## [4.4.1] - 2024-09-20 - Added two new codecs `STRING_BLOB` and `ASCII_BLOB` to allow migration from `TEXT` and `ASCII` fields to `BLOB` fields. These codecs can also be used to convert `BLOB` to `TEXT` or `ASCII`, but in such cases the `BLOB` value must be TEXT based in nature & fit within the applicable limits. diff --git a/pom.xml b/pom.xml index d1101d9..92cc69f 100644 --- a/pom.xml +++ b/pom.xml @@ -10,7 +10,7 @@ UTF-8 2.13.14 2.13 - 3.5.2 + 3.5.3 3.5.1 5.0-rc1 5.9.1