Fix jar selection: use fixed output name compactor-benchmark.jar

The benchmarks-jmh-*.jar glob expands to multiple jars (shaded +
javadoc), causing -cp to misinterpret the second jar as the main
class. Configure shade plugin outputFile to produce a fixed
compactor-benchmark.jar name. Update docs and CI workflow.

Author: dian-lun-lin

.github/workflows/run-compaction.yml

@@ -93,13 +93,10 @@ jobs:
           SAFE_BRANCH=$(echo "${{ matrix.branch }}" | sed 's/[^A-Za-z0-9_-]/_/g')
           echo "safe_branch=$SAFE_BRANCH" >> $GITHUB_OUTPUT
 
-          JMH_JAR=$(ls benchmarks-jmh/target/benchmarks-jmh-*.jar | grep -Ev -- '-(javadoc|sources)\.jar$' | head -1)
-          echo "Using JMH jar: $JMH_JAR"
-
           java --enable-native-access=ALL-UNNAMED --add-modules=jdk.incubator.vector \
             -Djvector.experimental.enable_native_vectorization=true \
             -Xmx${HALF_MEM_GB}g \
-            -cp "$JMH_JAR" \
+            -cp benchmarks-jmh/target/compactor-benchmark.jar \
             io.github.jbellis.jvector.bench.CompactorBenchmark \
             -p workloadMode=PARTITION_AND_COMPACT \
             -p datasetNames=$DATASET \

benchmarks-jmh/pom.xml

@@ -93,6 +93,7 @@
                             <goal>shade</goal>
                         </goals>
                         <configuration>
+                            <outputFile>${project.build.directory}/compactor-benchmark.jar</outputFile>
                             <transformers>
                                 <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                     <mainClass>org.openjdk.jmh.Main</mainClass>

benchmarks-jmh/src/main/java/io/github/jbellis/jvector/bench/CompactorBenchmark.md

@@ -39,7 +39,7 @@ The default mode builds partitions and immediately compacts them. Use this when
 
 ```bash
 java -Xmx220g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=PARTITION_AND_COMPACT \
   -p datasetNames=ada002-100k \
@@ -63,7 +63,7 @@ Run with a large heap since the full dataset must be loaded into memory.
 
 ```bash
 java -Xmx220g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=PARTITION_ONLY \
   -p datasetNames=ada002-100k \
@@ -81,7 +81,7 @@ The dataset is **not** loaded in this mode. Use a small `-Xmx` to measure and pr
 
 ```bash
 java -Xmx5g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=COMPACT_ONLY \
   -p datasetNames=ada002-100k \

docs/compaction.md

@@ -122,7 +122,7 @@ Adjust `-Xmx` to fit the dataset in memory (e.g., 220g for large datasets).
 
 ```bash
 java -Xmx220g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=PARTITION_AND_COMPACT \
   -p datasetNames=<dataset> \
@@ -140,7 +140,7 @@ To measure how little RAM compaction actually needs — without the dataset occu
 
 ```bash
 java -Xmx220g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=PARTITION_ONLY \
   -p datasetNames=<dataset> \
@@ -154,7 +154,7 @@ java -Xmx220g --add-modules jdk.incubator.vector \
 
 ```bash
 java -Xmx5g --add-modules jdk.incubator.vector \
-  -cp benchmarks-jmh/target/benchmarks-jmh-*.jar \
+  -cp benchmarks-jmh/target/compactor-benchmark.jar \
   io.github.jbellis.jvector.bench.CompactorBenchmark \
   -p workloadMode=COMPACT_ONLY \
   -p datasetNames=<dataset> \