Skip to content

ci: Consolidate Spark SQL test jobs to reduce CI time #3271

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.

Sign up for GitHub

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

Merged
andygrove merged 2 commits into from
Jan 27, 2026
Merged

ci: Consolidate Spark SQL test jobs to reduce CI time #3271

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e6b7750
ci: Consolidate Spark SQL test jobs to reduce CI time
andygrove Jan 25, 2026
c2f3c63
upmerge
andygrove Jan 26, 2026
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
142 changes: 20 additions & 122 deletions .github/workflows/spark_sql_test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,12 +101,11 @@ jobs:
native/target
key: ${{ runner.os }}-cargo-ci-${{ hashFiles('native/**/Cargo.lock', 'native/**/Cargo.toml') }}

spark-sql-auto-scan:
spark-sql-test:
needs: build-native
strategy:
matrix:
os: [ubuntu-24.04]
spark-version: [{short: '3.4', full: '3.4.3', java: 11}, {short: '3.5', full: '3.5.7', java: 11}, {short: '4.0', full: '4.0.1', java: 17}]
module:
- {name: "catalyst", args1: "catalyst/test", args2: ""}
- {name: "sql_core-1", args1: "", args2: sql/testOnly * -- -l org.apache.spark.tags.ExtendedSQLTest -l org.apache.spark.tags.SlowSQLTest}
Expand All @@ -115,12 +114,23 @@ jobs:
- {name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest"}
- {name: "sql_hive-2", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.ExtendedHiveTest"}
- {name: "sql_hive-3", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.SlowHiveTest"}
# Test combinations:
# - auto scan: all Spark versions (3.4, 3.5, 4.0)
# - native_comet: Spark 3.4, 3.5
# - native_iceberg_compat: Spark 3.5 only
config:
- {spark-short: '3.4', spark-full: '3.4.3', java: 11, scan-impl: 'auto', scan-env: ''}
- {spark-short: '3.5', spark-full: '3.5.7', java: 11, scan-impl: 'auto', scan-env: ''}
- {spark-short: '4.0', spark-full: '4.0.1', java: 17, scan-impl: 'auto', scan-env: ''}
- {spark-short: '3.4', spark-full: '3.4.3', java: 11, scan-impl: 'native_comet', scan-env: 'COMET_PARQUET_SCAN_IMPL=native_comet'}
- {spark-short: '3.5', spark-full: '3.5.7', java: 11, scan-impl: 'native_comet', scan-env: 'COMET_PARQUET_SCAN_IMPL=native_comet'}
- {spark-short: '3.5', spark-full: '3.5.7', java: 11, scan-impl: 'native_iceberg_compat', scan-env: 'COMET_PARQUET_SCAN_IMPL=native_iceberg_compat'}
# Skip sql_hive-1 for Spark 4.0 due to https://github.com/apache/datafusion-comet/issues/2946
exclude:
- spark-version: {short: '4.0', full: '4.0.1', java: 17}
- config: {spark-short: '4.0', spark-full: '4.0.1', java: 17, scan-impl: 'auto', scan-env: ''}
module: {name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest"}
fail-fast: false
name: spark-sql-${{ matrix.module.name }}/${{ matrix.os }}/spark-${{ matrix.spark-version.full }}/java-${{ matrix.spark-version.java }}
name: spark-sql-${{ matrix.config.scan-impl }}-${{ matrix.module.name }}/spark-${{ matrix.config.spark-full }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
Expand All @@ -130,7 +140,7 @@ jobs:
uses: ./.github/actions/setup-builder
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.spark-version.java }}
jdk-version: ${{ matrix.config.java }}
- name: Download native library
uses: actions/download-artifact@v7
with:
Expand All @@ -139,14 +149,14 @@ jobs:
- name: Setup Spark
uses: ./.github/actions/setup-spark-builder
with:
spark-version: ${{ matrix.spark-version.full }}
spark-short-version: ${{ matrix.spark-version.short }}
spark-version: ${{ matrix.config.spark-full }}
spark-short-version: ${{ matrix.config.spark-short }}
skip-native-build: true
- name: Run Spark tests
run: |
cd apache-spark
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
ENABLE_COMET=true ENABLE_COMET_ONHEAP=true ENABLE_COMET_LOG_FALLBACK_REASONS=${{ github.event.inputs.collect-fallback-logs || 'false' }} \
ENABLE_COMET=true ENABLE_COMET_ONHEAP=true ${{ matrix.config.scan-env }} ENABLE_COMET_LOG_FALLBACK_REASONS=${{ github.event.inputs.collect-fallback-logs || 'false' }} \
build/sbt -Dsbt.log.noformat=true ${{ matrix.module.args1 }} "${{ matrix.module.args2 }}"
if [ "${{ github.event.inputs.collect-fallback-logs }}" = "true" ]; then
find . -type f -name "unit-tests.log" -print0 | xargs -0 grep -h "Comet cannot accelerate" | sed 's/.*Comet cannot accelerate/Comet cannot accelerate/' | sort -u > fallback.log
Expand All @@ -157,125 +167,13 @@ jobs:
if: ${{ github.event.inputs.collect-fallback-logs == 'true' }}
uses: actions/upload-artifact@v6
with:
name: fallback-log-spark-sql-${{ matrix.module.name }}-${{ matrix.os }}-spark-${{ matrix.spark-version.full }}-java-${{ matrix.spark-version.java }}
path: "**/fallback.log"

spark-sql-native-native-comet:
needs: build-native
strategy:
matrix:
os: [ ubuntu-24.04 ]
java-version: [ 11 ]
spark-version: [ { short: '3.4', full: '3.4.3' }, { short: '3.5', full: '3.5.7' } ]
module:
- { name: "catalyst", args1: "catalyst/test", args2: "" }
- { name: "sql_core-1", args1: "", args2: sql/testOnly * -- -l org.apache.spark.tags.ExtendedSQLTest -l org.apache.spark.tags.SlowSQLTest }
- { name: "sql_core-2", args1: "", args2: "sql/testOnly * -- -n org.apache.spark.tags.ExtendedSQLTest" }
- { name: "sql_core-3", args1: "", args2: "sql/testOnly * -- -n org.apache.spark.tags.SlowSQLTest" }
- { name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest" }
- { name: "sql_hive-2", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.ExtendedHiveTest" }
- { name: "sql_hive-3", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.SlowHiveTest" }
fail-fast: false
name: spark-sql-native-comet-${{ matrix.module.name }}/${{ matrix.os }}/spark-${{ matrix.spark-version.full }}/java-${{ matrix.java-version }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
steps:
- uses: actions/checkout@v6
- name: Setup Rust & Java toolchain
uses: ./.github/actions/setup-builder
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.java-version }}
- name: Download native library
uses: actions/download-artifact@v7
with:
name: native-lib-linux
path: native/target/release/
- name: Setup Spark
uses: ./.github/actions/setup-spark-builder
with:
spark-version: ${{ matrix.spark-version.full }}
spark-short-version: ${{ matrix.spark-version.short }}
skip-native-build: true
- name: Run Spark tests
run: |
cd apache-spark
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
ENABLE_COMET=true ENABLE_COMET_ONHEAP=true COMET_PARQUET_SCAN_IMPL=native_comet ENABLE_COMET_LOG_FALLBACK_REASONS=${{ github.event.inputs.collect-fallback-logs || 'false' }} \
build/sbt -Dsbt.log.noformat=true ${{ matrix.module.args1 }} "${{ matrix.module.args2 }}"
if [ "${{ github.event.inputs.collect-fallback-logs }}" = "true" ]; then
find . -type f -name "unit-tests.log" -print0 | xargs -0 grep -h "Comet cannot accelerate" | sed 's/.*Comet cannot accelerate/Comet cannot accelerate/' | sort -u > fallback.log
fi
env:
LC_ALL: "C.UTF-8"
- name: Upload fallback log
if: ${{ github.event.inputs.collect-fallback-logs == 'true' }}
uses: actions/upload-artifact@v6
with:
name: fallback-log-spark-sql-native-comet-${{ matrix.module.name }}-${{ matrix.os }}-spark-${{ matrix.spark-version.full }}-java-${{ matrix.java-version }}
path: "**/fallback.log"

spark-sql-native-iceberg-compat:
needs: build-native
strategy:
matrix:
os: [ubuntu-24.04]
java-version: [11]
spark-version: [{short: '3.4', full: '3.4.3'}, {short: '3.5', full: '3.5.7'}]
module:
- {name: "catalyst", args1: "catalyst/test", args2: ""}
- {name: "sql_core-1", args1: "", args2: sql/testOnly * -- -l org.apache.spark.tags.ExtendedSQLTest -l org.apache.spark.tags.SlowSQLTest}
- {name: "sql_core-2", args1: "", args2: "sql/testOnly * -- -n org.apache.spark.tags.ExtendedSQLTest"}
- {name: "sql_core-3", args1: "", args2: "sql/testOnly * -- -n org.apache.spark.tags.SlowSQLTest"}
- {name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest"}
- {name: "sql_hive-2", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.ExtendedHiveTest"}
- {name: "sql_hive-3", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.SlowHiveTest"}
fail-fast: false
name: spark-sql-iceberg-compat-${{ matrix.module.name }}/${{ matrix.os }}/spark-${{ matrix.spark-version.full }}/java-${{ matrix.java-version }}
runs-on: ${{ matrix.os }}
container:
image: amd64/rust
steps:
- uses: actions/checkout@v6
- name: Setup Rust & Java toolchain
uses: ./.github/actions/setup-builder
with:
rust-version: ${{env.RUST_VERSION}}
jdk-version: ${{ matrix.java-version }}
- name: Download native library
uses: actions/download-artifact@v7
with:
name: native-lib-linux
path: native/target/release/
- name: Setup Spark
uses: ./.github/actions/setup-spark-builder
with:
spark-version: ${{ matrix.spark-version.full }}
spark-short-version: ${{ matrix.spark-version.short }}
skip-native-build: true
- name: Run Spark tests
run: |
cd apache-spark
rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups
ENABLE_COMET=true ENABLE_COMET_ONHEAP=true COMET_PARQUET_SCAN_IMPL=native_iceberg_compat ENABLE_COMET_LOG_FALLBACK_REASONS=${{ github.event.inputs.collect-fallback-logs || 'false' }} \
build/sbt -Dsbt.log.noformat=true ${{ matrix.module.args1 }} "${{ matrix.module.args2 }}"
if [ "${{ github.event.inputs.collect-fallback-logs }}" = "true" ]; then
find . -type f -name "unit-tests.log" -print0 | xargs -0 grep -h "Comet cannot accelerate" | sed 's/.*Comet cannot accelerate/Comet cannot accelerate/' | sort -u > fallback.log
fi
env:
LC_ALL: "C.UTF-8"
- name: Upload fallback log
if: ${{ github.event.inputs.collect-fallback-logs == 'true' }}
uses: actions/upload-artifact@v6
with:
name: fallback-log-spark-sql-iceberg-compat-${{ matrix.module.name }}-${{ matrix.os }}-spark-${{ matrix.spark-version.full }}-java-${{ matrix.java-version }}
name: fallback-log-spark-sql-${{ matrix.config.scan-impl }}-${{ matrix.module.name }}-spark-${{ matrix.config.spark-full }}
path: "**/fallback.log"

merge-fallback-logs:
if: ${{ github.event.inputs.collect-fallback-logs == 'true' }}
name: merge-fallback-logs
needs: [ spark-sql-auto-scan, spark-sql-native-native-comet, spark-sql-native-iceberg-compat ]
needs: [spark-sql-test]
runs-on: ubuntu-24.04
steps:
- name: Download fallback log artifacts
Expand Down
Loading