perf: Improve string expression microbenchmarks

.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

.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:

.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:

.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:
@@ -59,6 +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 }}

spark/src/test/scala/org/apache/spark/sql/benchmark/CometStringExpressionBenchmark.scala

@@ -35,13 +35,13 @@ case class StringExprConfig(
     query: String,
     extraCometConfigs: Map[String, String] = Map.empty)
 
-// spotless:off
 /**
  * Benchmark to measure performance of Comet string expressions. To run this benchmark:
- * `SPARK_GENERATE_BENCHMARK_FILES=1 make benchmark-org.apache.spark.sql.benchmark.CometStringExpressionBenchmark`
+ * {{{
+ *   SPARK_GENERATE_BENCHMARK_FILES=1 make benchmark-org.apache.spark.sql.benchmark.CometStringExpressionBenchmark
+ * }}}
  * Results will be written to "spark/benchmarks/CometStringExpressionBenchmark-**results.txt".
  */
-// spotless:on
 object CometStringExpressionBenchmark extends CometBenchmarkBase {
 
   /**
@@ -50,7 +50,7 @@ object CometStringExpressionBenchmark extends CometBenchmarkBase {
   def runStringExprBenchmark(config: StringExprConfig, values: Int): Unit = {
     withTempPath { dir =>
       withTempTable("parquetV1Table") {
-        prepareTable(dir, spark.sql(s"SELECT REPEAT(CAST(value AS STRING), 100) AS c1 FROM $tbl"))
+        prepareTable(dir, spark.sql(s"SELECT REPEAT(CAST(value AS STRING), 20) AS c1 FROM $tbl"))
 
         val extraConfigs =
           Map(CometConf.COMET_CASE_CONVERSION_ENABLED.key -> "true") ++ config.extraCometConfigs
@@ -62,23 +62,36 @@ object CometStringExpressionBenchmark extends CometBenchmarkBase {
 
   // Configuration for all string expression benchmarks
   private val stringExpressions = List(
-    StringExprConfig("Substring", "select substring(c1, 1, 100) from parquetV1Table"),
     StringExprConfig("ascii", "select ascii(c1) from parquetV1Table"),
-    StringExprConfig("bitLength", "select bit_length(c1) from parquetV1Table"),
-    StringExprConfig("octet_length", "select octet_length(c1) from parquetV1Table"),
-    StringExprConfig("upper", "select upper(c1) from parquetV1Table"),
-    StringExprConfig("lower", "select lower(c1) from parquetV1Table"),
+    StringExprConfig("bit_length", "select bit_length(c1) from parquetV1Table"),
     StringExprConfig("chr", "select chr(c1) from parquetV1Table"),
+    StringExprConfig("concat", "select concat(c1, c1) from parquetV1Table"),
+    StringExprConfig("concat_ws", "select concat_ws(' ', c1, c1) from parquetV1Table"),
+    StringExprConfig("contains", "select contains(c1, '123') from parquetV1Table"),
+    StringExprConfig("endswith", "select endswith(c1, '9') from parquetV1Table"),
     StringExprConfig("initCap", "select initCap(c1) from parquetV1Table"),
-    StringExprConfig("trim", "select trim(c1) from parquetV1Table"),
-    StringExprConfig("concatws", "select concat_ws(' ', c1, c1) from parquetV1Table"),
+    StringExprConfig("instr", "select instr(c1, '123') from parquetV1Table"),
     StringExprConfig("length", "select length(c1) from parquetV1Table"),
+    StringExprConfig("like", "select c1 like '%123%' from parquetV1Table"),
+    StringExprConfig("lower", "select lower(c1) from parquetV1Table"),
+    StringExprConfig("lpad", "select lpad(c1, 150, 'x') from parquetV1Table"),
+    StringExprConfig("ltrim", "select ltrim(c1) from parquetV1Table"),
+    StringExprConfig("octet_length", "select octet_length(c1) from parquetV1Table"),
+    StringExprConfig(
+      "regexp_replace",
+      "select regexp_replace(c1, '[0-9]', 'X') from parquetV1Table"),
     StringExprConfig("repeat", "select repeat(c1, 3) from parquetV1Table"),
-    StringExprConfig("reverse", "select reverse(c1) from parquetV1Table"),
-    StringExprConfig("instr", "select instr(c1, '123') from parquetV1Table"),
     StringExprConfig("replace", "select replace(c1, '123', 'ab') from parquetV1Table"),
+    StringExprConfig("reverse", "select reverse(c1) from parquetV1Table"),
+    StringExprConfig("rlike", "select c1 rlike '[0-9]+' from parquetV1Table"),
+    StringExprConfig("rpad", "select rpad(c1, 150, 'x') from parquetV1Table"),
+    StringExprConfig("rtrim", "select rtrim(c1) from parquetV1Table"),
     StringExprConfig("space", "select space(2) from parquetV1Table"),
-    StringExprConfig("translate", "select translate(c1, '123456', 'aBcDeF') from parquetV1Table"))
+    StringExprConfig("startswith", "select startswith(c1, '1') from parquetV1Table"),
+    StringExprConfig("substring", "select substring(c1, 1, 100) from parquetV1Table"),
+    StringExprConfig("translate", "select translate(c1, '123456', 'aBcDeF') from parquetV1Table"),
+    StringExprConfig("trim", "select trim(c1) from parquetV1Table"),
+    StringExprConfig("upper", "select upper(c1) from parquetV1Table"))
 
   override def runCometBenchmark(mainArgs: Array[String]): Unit = {
     val values = 1024 * 1024;