Repository: spark Updated Branches: refs/heads/branch-2.3 7d96dc1ac -> 2e0c1e5f3
[SPARK-23267][SQL] Increase spark.sql.codegen.hugeMethodLimit to 65535 ## What changes were proposed in this pull request? Still saw the performance regression introduced by `spark.sql.codegen.hugeMethodLimit` in our internal workloads. There are two major issues in the current solution. - The size of the complied byte code is not identical to the bytecode size of the method. The detection is still not accurate. - The bytecode size of a single operator (e.g., `SerializeFromObject`) could still exceed 8K limit. We saw the performance regression in such scenario. Since it is close to the release of 2.3, we decide to increase it to 64K for avoiding the perf regression. ## How was this patch tested? N/A Author: gatorsmile <gatorsm...@gmail.com> Closes #20434 from gatorsmile/revertConf. (cherry picked from commit 31c00ad8b090d7eddc4622e73dc4440cd32624de) Signed-off-by: gatorsmile <gatorsm...@gmail.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2e0c1e5f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2e0c1e5f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2e0c1e5f Branch: refs/heads/branch-2.3 Commit: 2e0c1e5f3e47e4e35c14732b93a29d1a25e15662 Parents: 7d96dc1 Author: gatorsmile <gatorsm...@gmail.com> Authored: Tue Jan 30 11:33:30 2018 -0800 Committer: gatorsmile <gatorsm...@gmail.com> Committed: Tue Jan 30 11:33:37 2018 -0800 ---------------------------------------------------------------------- .../scala/org/apache/spark/sql/internal/SQLConf.scala | 11 ++++++----- .../spark/sql/execution/WholeStageCodegenSuite.scala | 4 ++-- 2 files changed, 8 insertions(+), 7 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/2e0c1e5f/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala index 54a3559..7394a0d 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala @@ -660,12 +660,13 @@ object SQLConf { val WHOLESTAGE_HUGE_METHOD_LIMIT = buildConf("spark.sql.codegen.hugeMethodLimit") .internal() .doc("The maximum bytecode size of a single compiled Java function generated by whole-stage " + - "codegen. When the compiled function exceeds this threshold, " + - "the whole-stage codegen is deactivated for this subtree of the current query plan. " + - s"The default value is ${CodeGenerator.DEFAULT_JVM_HUGE_METHOD_LIMIT} and " + - "this is a limit in the OpenJDK JVM implementation.") + "codegen. When the compiled function exceeds this threshold, the whole-stage codegen is " + + "deactivated for this subtree of the current query plan. The default value is 65535, which " + + "is the largest bytecode size possible for a valid Java method. When running on HotSpot, " + + s"it may be preferable to set the value to ${CodeGenerator.DEFAULT_JVM_HUGE_METHOD_LIMIT} " + + "to match HotSpot's implementation.") .intConf - .createWithDefault(CodeGenerator.DEFAULT_JVM_HUGE_METHOD_LIMIT) + .createWithDefault(65535) val WHOLESTAGE_SPLIT_CONSUME_FUNC_BY_OPERATOR = buildConf("spark.sql.codegen.splitConsumeFuncByOperator") http://git-wip-us.apache.org/repos/asf/spark/blob/2e0c1e5f/sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala index 28ad712..6e8d5a7 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala @@ -202,7 +202,7 @@ class WholeStageCodegenSuite extends QueryTest with SharedSQLContext { wholeStageCodeGenExec.get.asInstanceOf[WholeStageCodegenExec].doCodeGen()._2 } - test("SPARK-21871 check if we can get large code size when compiling too long functions") { + ignore("SPARK-21871 check if we can get large code size when compiling too long functions") { val codeWithShortFunctions = genGroupByCode(3) val (_, maxCodeSize1) = CodeGenerator.compile(codeWithShortFunctions) assert(maxCodeSize1 < SQLConf.WHOLESTAGE_HUGE_METHOD_LIMIT.defaultValue.get) @@ -211,7 +211,7 @@ class WholeStageCodegenSuite extends QueryTest with SharedSQLContext { assert(maxCodeSize2 > SQLConf.WHOLESTAGE_HUGE_METHOD_LIMIT.defaultValue.get) } - test("bytecode of batch file scan exceeds the limit of WHOLESTAGE_HUGE_METHOD_LIMIT") { + ignore("bytecode of batch file scan exceeds the limit of WHOLESTAGE_HUGE_METHOD_LIMIT") { import testImplicits._ withTempPath { dir => val path = dir.getCanonicalPath --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org