viirya commented on a change in pull request #32015:
URL: https://github.com/apache/spark/pull/32015#discussion_r605080264
##########
File path: core/src/test/scala/org/apache/spark/benchmark/Benchmarks.scala
##########
@@ -30,44 +31,64 @@ import com.google.common.reflect.ClassPath
*
* {{{
* 1. with spark-submit
- * bin/spark-submit --class <this class> --jars <all spark test jars>
<spark core test jar>
+ * bin/spark-submit --class <this class> --jars <all spark test jars>
+ * <spark external package jar> <spark core test jar> <glob pattern for
class>
* 2. generate result:
* SPARK_GENERATE_BENCHMARK_FILES=1 bin/spark-submit --class <this class>
--jars
- * <all spark test jars> <spark core test jar>
+ * <all spark test jars> <spark external package jar>
+ * <spark core test jar> <glob pattern for class>
* Results will be written to all corresponding files under "benchmarks/".
* Notice that it detects the sub-project's directories from jar's paths
so the provided jars
* should be properly placed under target (Maven build) or target/scala-*
(SBT) when you
* generate the files.
* }}}
*
* In Mac, you can use a command as below to find all the test jars.
+ * Make sure to do not select duplicated jars created by different versions of
builds or tools.
* {{{
- * find . -name "*3.2.0-SNAPSHOT-tests.jar" | paste -sd ',' -
+ * find . -name '*-SNAPSHOT-tests.jar' | paste -sd ',' -
* }}}
*
- * Full command example:
+ * The example below runs all benchmarks and generates the results:
* {{{
* SPARK_GENERATE_BENCHMARK_FILES=1 bin/spark-submit --class \
* org.apache.spark.benchmark.Benchmarks --jars \
- * "`find . -name "*3.2.0-SNAPSHOT-tests.jar" | paste -sd ',' -`" \
- * ./core/target/scala-2.12/spark-core_2.12-3.2.0-SNAPSHOT-tests.jar
+ * "`find . -name '*-SNAPSHOT-tests.jar' -o -name '*avro*-SNAPSHOT.jar' |
paste -sd ',' -`" \
+ * "`find . -name 'spark-core*-SNAPSHOT-tests.jar'`" \
+ * "*"
+ * }}}
+ *
+ * The example below runs all benchmarks under
"org.apache.spark.sql.execution.datasources"
+ * {{{
+ * bin/spark-submit --class \
+ * org.apache.spark.benchmark.Benchmarks --jars \
+ * "`find . -name '*-SNAPSHOT-tests.jar' -o -name '*avro*-SNAPSHOT.jar' |
paste -sd ',' -`" \
+ * "`find . -name 'spark-core*-SNAPSHOT-tests.jar'`" \
+ * "org.apache.spark.sql.execution.datasources.*"
* }}}
*/
object Benchmarks {
def main(args: Array[String]): Unit = {
+ var isBenchmarkFound = false
ClassPath.from(
Thread.currentThread.getContextClassLoader
).getTopLevelClassesRecursive("org.apache.spark").asScala.foreach { info =>
lazy val clazz = info.load
lazy val runBenchmark = clazz.getMethod("main", classOf[Array[String]])
// isAssignableFrom seems not working with the reflected class from
Guava's
// getTopLevelClassesRecursive.
+ val matcher = args.headOption.map(pattern =>
+ FileSystems.getDefault.getPathMatcher(s"glob:$pattern"))
Review comment:
Do we need to initiate this matcher for each iteration?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
