From bd2c0755244d2206ba14fb805bd163c547975214 Mon Sep 17 00:00:00 2001 From: Andy Grove Date: Fri, 2 Jan 2026 10:29:34 -0700 Subject: [PATCH 1/3] improve date/time microbenchmarks --- .../CometDatetimeExpressionBenchmark.scala | 42 +++++-------------- 1 file changed, 11 insertions(+), 31 deletions(-) diff --git a/spark/src/test/scala/org/apache/spark/sql/benchmark/CometDatetimeExpressionBenchmark.scala b/spark/src/test/scala/org/apache/spark/sql/benchmark/CometDatetimeExpressionBenchmark.scala index 47eff41bbd..18f292ff24 100644 --- a/spark/src/test/scala/org/apache/spark/sql/benchmark/CometDatetimeExpressionBenchmark.scala +++ b/spark/src/test/scala/org/apache/spark/sql/benchmark/CometDatetimeExpressionBenchmark.scala @@ -30,16 +30,15 @@ import org.apache.spark.sql.internal.SQLConf */ object CometDatetimeExpressionBenchmark extends CometBenchmarkBase { - def dateTruncExprBenchmark(values: Int, useDictionary: Boolean): Unit = { + def dateTruncExprBenchmark(values: Int): Unit = { withTempPath { dir => withTempTable("parquetV1Table") { prepareTable( dir, spark.sql( s"select cast(timestamp_micros(cast(value/100000 as integer)) as date) as dt FROM $tbl")) - Seq("YEAR", "YYYY", "YY", "MON", "MONTH", "MM").foreach { level => - val isDictionary = if (useDictionary) "(Dictionary)" else "" - val name = s"Date Truncate $isDictionary - $level" + Seq("YEAR", "MONTH").foreach { level => + val name = s"Date Truncate - $level" val query = s"select trunc(dt, '$level') from parquetV1Table" runExpressionBenchmark(name, values, query) } @@ -47,30 +46,17 @@ object CometDatetimeExpressionBenchmark extends CometBenchmarkBase { } } - def timestampTruncExprBenchmark(values: Int, useDictionary: Boolean): Unit = { + def timestampTruncExprBenchmark(values: Int): Unit = { withTempPath { dir => withTempTable("parquetV1Table") { prepareTable( dir, spark.sql(s"select timestamp_micros(cast(value/100000 as integer)) as ts FROM $tbl")) - Seq( - "YEAR", - "YYYY", - "YY", - "MON", - "MONTH", - "MM", - "DAY", - "DD", - "HOUR", - "MINUTE", - "SECOND", - "WEEK", - "QUARTER").foreach { level => - val isDictionary = if (useDictionary) "(Dictionary)" else "" - val name = s"Timestamp Truncate $isDictionary - $level" - val query = s"select date_trunc('$level', ts) from parquetV1Table" - runExpressionBenchmark(name, values, query) + Seq("YEAR", "MONTH", "DAY", "HOUR", "MINUTE", "SECOND", "WEEK", "QUARTER").foreach { + level => + val name = s"Timestamp Truncate - $level" + val query = s"select date_trunc('$level', ts) from parquetV1Table" + runExpressionBenchmark(name, values, query) } } } @@ -85,16 +71,10 @@ object CometDatetimeExpressionBenchmark extends CometBenchmarkBase { "spark.sql.parquet.datetimeRebaseModeInWrite" -> "CORRECTED") { runBenchmarkWithTable("DateTrunc", values) { v => - dateTruncExprBenchmark(v, useDictionary = false) - } - runBenchmarkWithTable("DateTrunc (Dictionary)", values, useDictionary = true) { v => - dateTruncExprBenchmark(v, useDictionary = true) + dateTruncExprBenchmark(v) } runBenchmarkWithTable("TimestampTrunc", values) { v => - timestampTruncExprBenchmark(v, useDictionary = false) - } - runBenchmarkWithTable("TimestampTrunc (Dictionary)", values, useDictionary = true) { v => - timestampTruncExprBenchmark(v, useDictionary = true) + timestampTruncExprBenchmark(v) } } } From 9af4184357a436b0a9ab00900d6267dd1d6de1d8 Mon Sep 17 00:00:00 2001 From: Andy Grove Date: Fri, 2 Jan 2026 12:20:51 -0700 Subject: [PATCH 2/3] skip some CI workflows for benchmark changes --- .github/workflows/pr_benchmark_check.yml | 85 ++++++++++++++++++++++++ .github/workflows/pr_build_linux.yml | 6 ++ .github/workflows/pr_build_macos.yml | 6 ++ .github/workflows/spark_sql_test.yml | 6 ++ 4 files changed, 103 insertions(+) create mode 100644 .github/workflows/pr_benchmark_check.yml diff --git a/.github/workflows/pr_benchmark_check.yml b/.github/workflows/pr_benchmark_check.yml new file mode 100644 index 0000000000..b7475b9076 --- /dev/null +++ b/.github/workflows/pr_benchmark_check.yml @@ -0,0 +1,85 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +# Lightweight CI for benchmark-only changes - verifies compilation and linting +# without running full test suites + +name: PR Benchmark Check + +concurrency: + group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }} + cancel-in-progress: true + +on: + push: + paths: + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" + pull_request: + paths: + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" + workflow_dispatch: + +env: + RUST_VERSION: stable + +jobs: + benchmark-check: + name: Benchmark Compile & Lint Check + runs-on: ubuntu-latest + 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: 17 + + - name: Check Cargo fmt + run: | + cd native + cargo fmt --all -- --check --color=never + + - name: Check Cargo clippy + run: | + cd native + cargo clippy --color=never --all-targets --workspace -- -D warnings + + - name: Check benchmark compilation + run: | + cd native + cargo check --benches + + - name: Cache Maven dependencies + uses: actions/cache@v4 + with: + path: | + ~/.m2/repository + /root/.m2/repository + key: ${{ runner.os }}-benchmark-maven-${{ hashFiles('**/pom.xml') }} + restore-keys: | + ${{ runner.os }}-benchmark-maven- + + - name: Check Scala compilation and linting + run: | + ./mvnw -B compile test-compile scalafix:scalafix -Dscalafix.mode=CHECK -Psemanticdb -DskipTests diff --git a/.github/workflows/pr_build_linux.yml b/.github/workflows/pr_build_linux.yml index e3b0e40566..beb5f9dcf7 100644 --- a/.github/workflows/pr_build_linux.yml +++ b/.github/workflows/pr_build_linux.yml @@ -27,11 +27,17 @@ on: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" pull_request: paths-ignore: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" # manual trigger # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow workflow_dispatch: diff --git a/.github/workflows/pr_build_macos.yml b/.github/workflows/pr_build_macos.yml index 0ad40c1932..9a45fe022d 100644 --- a/.github/workflows/pr_build_macos.yml +++ b/.github/workflows/pr_build_macos.yml @@ -27,11 +27,17 @@ on: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" pull_request: paths-ignore: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" # manual trigger # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow workflow_dispatch: diff --git a/.github/workflows/spark_sql_test.yml b/.github/workflows/spark_sql_test.yml index d143ef83a0..1ff6fa952c 100644 --- a/.github/workflows/spark_sql_test.yml +++ b/.github/workflows/spark_sql_test.yml @@ -27,11 +27,17 @@ on: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" pull_request: paths-ignore: - "doc/**" - "docs/**" - "**.md" + - "native/core/benches/**" + - "native/spark-expr/benches/**" + - "spark/src/test/scala/org/apache/spark/sql/benchmark/**" # manual trigger # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow workflow_dispatch: From 6869f79709dff276c22154a4ba0201700db5ba19 Mon Sep 17 00:00:00 2001 From: Andy Grove Date: Fri, 2 Jan 2026 15:14:21 -0700 Subject: [PATCH 3/3] skip failing suite --- .github/workflows/spark_sql_test.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/spark_sql_test.yml b/.github/workflows/spark_sql_test.yml index 1ff6fa952c..2fe5fefe1a 100644 --- a/.github/workflows/spark_sql_test.yml +++ b/.github/workflows/spark_sql_test.yml @@ -65,6 +65,10 @@ 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"} + # 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} + 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 }} runs-on: ${{ matrix.os }}