Skip to content

fix: [iceberg] Switch to OSS Spark and run Iceberg Spark tests in parallel #1987

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 0 additions & 11 deletions .github/actions/setup-iceberg-builder/action.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,6 @@ inputs:
iceberg-version:
description: 'The Apache Iceberg version (e.g., 1.8.1) to build'
required: true
scala-version:
description: 'The Scala short version (e.g., 2.13) to build'
required: true
spark-short-version:
description: 'The Apache Spark short version (e.g., 3.5) to build'
required: true
runs:
using: "composite"
steps:
Expand All @@ -43,8 +37,3 @@ runs:
run: |
cd apache-iceberg
git apply ../dev/diffs/iceberg/${{inputs.iceberg-version}}.diff

- name: Build Comet
shell: bash
run: |
PROFILES="-Pspark-${{inputs.spark-short-version}} -Pscala-${{inputs.scala-version}}" make release
48 changes: 0 additions & 48 deletions .github/actions/setup-spark-local-jar/action.yaml

This file was deleted.

97 changes: 86 additions & 11 deletions .github/workflows/iceberg_spark_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ env:
RUST_VERSION: stable

jobs:
iceberg-spark-sql:
iceberg-spark:
if: contains(github.event.pull_request.title, '[iceberg]')
strategy:
matrix:
Expand All @@ -50,7 +50,7 @@ jobs:
spark-version: [{short: '3.5', full: '3.5.6'}]
scala-version: ['2.13']
fail-fast: false
name: iceberg-spark-sql/${{ matrix.os }}/iceberg-${{ matrix.iceberg-version.full }}/spark-${{ matrix.spark-version.full }}/scala-${{ matrix.scala-version }}/java-${{ matrix.java-version }}
name: iceberg-spark/${{ matrix.os }}/iceberg-${{ matrix.iceberg-version.full }}/spark-${{ matrix.spark-version.full }}/scala-${{ matrix.scala-version }}/java-${{ matrix.java-version }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
Expand All @@ -63,24 +63,99 @@ jobs:
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.java-version }}
- name: Build Comet
shell: bash
run: |
PROFILES="-Pspark-${{matrix.spark-version.short}} -Pscala-${{matrix.scala-version}}" make release
- name: Setup Iceberg
uses: ./.github/actions/setup-iceberg-builder
with:
iceberg-version: ${{ matrix.iceberg-version.full }}
scala-version: ${{ matrix.scala-version }}
spark-short-version: ${{ matrix.spark-version.short }}
- name: Build local Spark jar with comet patch
uses: ./.github/actions/setup-spark-local-jar
with:
spark-short-version: ${{ matrix.spark-version.short }}
spark-version: ${{ matrix.spark-version.full }}
scala-version: ${{ matrix.scala-version }}
- name: Run Iceberg Spark tests
run: |
cd apache-iceberg
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
./gradlew spotlessApply
ENABLE_COMET=true ./gradlew -DsparkVersions=${{ matrix.spark-version.short }} -DscalaVersion=${{ matrix.scala-version }} -DflinkVersions= -DkafkaVersions= \
:iceberg-spark:iceberg-spark-${{ matrix.spark-version.short }}_${{ matrix.scala-version }}:check \
-Pquick=true -x javadoc

iceberg-spark-extensions:
if: contains(github.event.pull_request.title, '[iceberg]')
strategy:
matrix:
os: [ubuntu-24.04]
java-version: [11, 17]
iceberg-version: [{short: '1.8', full: '1.8.1'}]
spark-version: [{short: '3.5', full: '3.5.6'}]
scala-version: ['2.13']
fail-fast: false
name: iceberg-spark-extensions/${{ matrix.os }}/iceberg-${{ matrix.iceberg-version.full }}/spark-${{ matrix.spark-version.full }}/scala-${{ matrix.scala-version }}/java-${{ matrix.java-version }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
env:
SPARK_LOCAL_IP: localhost
steps:
- uses: actions/checkout@v4
- name: Setup Rust & Java toolchain
uses: ./.github/actions/setup-builder
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.java-version }}
- name: Build Comet
shell: bash
run: |
PROFILES="-Pspark-${{matrix.spark-version.short}} -Pscala-${{matrix.scala-version}}" make release
- name: Setup Iceberg
uses: ./.github/actions/setup-iceberg-builder
with:
iceberg-version: ${{ matrix.iceberg-version.full }}
- name: Run Iceberg Spark extensions tests
run: |
cd apache-iceberg
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
./gradlew spotlessApply
ENABLE_COMET=true ./gradlew -DsparkVersions=${{ matrix.spark-version.short }} -DscalaVersion=${{ matrix.scala-version }} -DflinkVersions= -DkafkaVersions= \
:iceberg-spark:iceberg-spark-extensions-${{ matrix.spark-version.short }}_${{ matrix.scala-version }}:check \
:iceberg-spark:iceberg-spark-runtime-${{ matrix.spark-version.short }}_${{ matrix.scala-version }}:check \
-Pquick=true -x javadoc

iceberg-spark-runtime:
if: contains(github.event.pull_request.title, '[iceberg]')
strategy:
matrix:
os: [ubuntu-24.04]
java-version: [11, 17]
iceberg-version: [{short: '1.8', full: '1.8.1'}]
spark-version: [{short: '3.5', full: '3.5.6'}]
scala-version: ['2.13']
fail-fast: false
name: iceberg-spark-runtime/${{ matrix.os }}/iceberg-${{ matrix.iceberg-version.full }}/spark-${{ matrix.spark-version.full }}/scala-${{ matrix.scala-version }}/java-${{ matrix.java-version }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
env:
SPARK_LOCAL_IP: localhost
steps:
- uses: actions/checkout@v4
- name: Setup Rust & Java toolchain
uses: ./.github/actions/setup-builder
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.java-version }}
- name: Build Comet
shell: bash
run: |
PROFILES="-Pspark-${{matrix.spark-version.short}} -Pscala-${{matrix.scala-version}}" make release
- name: Setup Iceberg
uses: ./.github/actions/setup-iceberg-builder
with:
iceberg-version: ${{ matrix.iceberg-version.full }}
- name: Run Iceberg Spark runtime tests
run: |
cd apache-iceberg
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
./gradlew spotlessApply
ENABLE_COMET=true ./gradlew -DsparkVersions=${{ matrix.spark-version.short }} -DscalaVersion=${{ matrix.scala-version }} -DflinkVersions= -DkafkaVersions= \
:iceberg-spark:iceberg-spark-runtime-${{ matrix.spark-version.short }}_${{ matrix.scala-version }}:check \
-Pquick=true -x javadoc
Loading
Loading