[VL] Enable spill-to-disk for partial aggregation (#3697)

apache · Nov 18, 2023 · 5f5d18a · 5f5d18a
1 parent bb88f4f
commit 5f5d18a
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 2 deletions.
diff --git a/.github/workflows/velox_be.yml b/.github/workflows/velox_be.yml
@@ -447,7 +447,7 @@ jobs:
             -d=OFFHEAP_SIZE:3g,spark.memory.offHeap.size=3g \
             -d=OVER_ACQUIRE:0.3,spark.gluten.memory.overAcquiredMemoryRatio=0.3 \
             -d=OVER_ACQUIRE:0.5,spark.gluten.memory.overAcquiredMemoryRatio=0.5' || true
-      - name: (To be fixed) TPC-DS SF30.0 Parquet local spark3.2 Q23A/Q23B low memory
+      - name: TPC-DS SF30.0 Parquet local spark3.2 Q23A/Q23B low memory
         run: |
           docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten/tools/gluten-it && \
           GLUTEN_IT_JVM_ARGS=-Xmx50G sbin/gluten-it.sh parameterized \
@@ -458,7 +458,7 @@ jobs:
             -d=OFFHEAP_SIZE:2g,spark.memory.offHeap.size=2g \
             -d=PARTIAL_MODE:ABANDONED,spark.gluten.sql.columnar.backend.velox.maxPartialAggregationMemoryRatio=1.0,spark.gluten.sql.columnar.backend.velox.maxExtendedPartialAggregationMemoryRatio=1.0,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinPct=0,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinRows=0 \
             -d=PARTIAL_MODE:CACHED,spark.gluten.sql.columnar.backend.velox.maxPartialAggregationMemoryRatio=1.0,spark.gluten.sql.columnar.backend.velox.maxExtendedPartialAggregationMemoryRatio=1.0,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinPct=100,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinRows=0 \
-            -d=PARTIAL_MODE:FLUSHED,spark.gluten.sql.columnar.backend.velox.maxPartialAggregationMemoryRatio=0.05,spark.gluten.sql.columnar.backend.velox.maxExtendedPartialAggregationMemoryRatio=0.1,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinPct=100,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinRows=0' || true
+            -d=PARTIAL_MODE:FLUSHED,spark.gluten.sql.columnar.backend.velox.maxPartialAggregationMemoryRatio=0.05,spark.gluten.sql.columnar.backend.velox.maxExtendedPartialAggregationMemoryRatio=0.1,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinPct=100,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinRows=0'
       - name: (To be fixed) TPC-DS SF30.0 Parquet local spark3.2 Q97 low memory
         run: |
           docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten/tools/gluten-it && \

diff --git a/tools/gluten-it/pom.xml b/tools/gluten-it/pom.xml
@@ -73,6 +73,12 @@
         <artifactId>spark-hive_${scala.binary.version}</artifactId>
         <version>${spark.version}</version>
         <scope>provided</scope>
+        <exclusions>
+          <exclusion>
+            <groupId>jline</groupId>
+            <artifactId>jline</artifactId>
+          </exclusion>
+        </exclusions>
       </dependency>
       <dependency>
         <groupId>org.apache.spark</groupId>