(orc) branch main updated: ORC-1708: Support data/compress options in Hive benchmark

[william]

This is an automated email from the ASF dual-hosted git repository.

william pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/orc.git


The following commit(s) were added to refs/heads/main by this push:
     new 4c3a5543d ORC-1708: Support data/compress options in Hive benchmark
4c3a5543d is described below

commit 4c3a5543dc66fc6967d61fb80ab2dedb298bd700
Author: sychen <syc...@ctrip.com>
AuthorDate: Tue May 7 23:33:28 2024 -0700

    ORC-1708: Support data/compress options in Hive benchmark
    
    ### What changes were proposed in this pull request?
    This PR aims to support data/compress options in Hive benchmark.
    
    ### Why are the changes needed?
    Easy to do sampling tests in Hive benchmark.
    
    ### How was this patch tested?
    local test
    
    ```bash
    java -jar hive/target/orc-benchmarks-hive-*-uber.jar read-all data  -data 
taxi -compress snappy
    ```
    
    ### Was this patch authored or co-authored using generative AI tooling?
    No
    
    Closes #1924 from cxzl25/ORC-1708.
    
    Authored-by: sychen <syc...@ctrip.com>
    Signed-off-by: William Hyun <will...@apache.org>
---
 .../org/apache/orc/bench/hive/ColumnProjectionBenchmark.java  | 11 ++++++++++-
 .../src/java/org/apache/orc/bench/hive/FullReadBenchmark.java | 11 ++++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git 
a/java/bench/hive/src/java/org/apache/orc/bench/hive/ColumnProjectionBenchmark.java
 
b/java/bench/hive/src/java/org/apache/orc/bench/hive/ColumnProjectionBenchmark.java
index 9c1b7fd21..48806faff 100644
--- 
a/java/bench/hive/src/java/org/apache/orc/bench/hive/ColumnProjectionBenchmark.java
+++ 
b/java/bench/hive/src/java/org/apache/orc/bench/hive/ColumnProjectionBenchmark.java
@@ -19,6 +19,7 @@
 package org.apache.orc.bench.hive;
 
 import com.google.auto.service.AutoService;
+import org.apache.commons.cli.CommandLine;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
@@ -38,6 +39,7 @@ import org.apache.orc.TypeDescription;
 import org.apache.orc.bench.core.IOCounters;
 import org.apache.orc.bench.core.OrcBenchmark;
 import org.apache.orc.bench.core.Utilities;
+import org.apache.orc.bench.core.convert.GenerateVariants;
 import org.apache.parquet.hadoop.ParquetInputFormat;
 import org.openjdk.jmh.annotations.Benchmark;
 import org.openjdk.jmh.annotations.BenchmarkMode;
@@ -47,6 +49,7 @@ import org.openjdk.jmh.annotations.Param;
 import org.openjdk.jmh.annotations.Scope;
 import org.openjdk.jmh.annotations.State;
 import org.openjdk.jmh.runner.Runner;
+import org.openjdk.jmh.runner.options.OptionsBuilder;
 
 import java.net.URI;
 import java.util.List;
@@ -78,7 +81,13 @@ public class ColumnProjectionBenchmark implements 
OrcBenchmark {
 
   @Override
   public void run(String[] args) throws Exception {
-    new Runner(Utilities.parseOptions(args, getClass())).run();
+    CommandLine cmds = GenerateVariants.parseCommandLine(args);
+    new Runner(new OptionsBuilder()
+        .parent(Utilities.parseOptions(args, this.getClass()))
+        .param("compression", cmds.getOptionValue("compress", 
"snappy,gz,zstd").split(","))
+        .param("dataset", cmds.getOptionValue("data", 
"github,sales,taxi").split(","))
+        .build()
+    ).run();
   }
 
   @Benchmark
diff --git 
a/java/bench/hive/src/java/org/apache/orc/bench/hive/FullReadBenchmark.java 
b/java/bench/hive/src/java/org/apache/orc/bench/hive/FullReadBenchmark.java
index dc1bcca92..8f3b1cbba 100644
--- a/java/bench/hive/src/java/org/apache/orc/bench/hive/FullReadBenchmark.java
+++ b/java/bench/hive/src/java/org/apache/orc/bench/hive/FullReadBenchmark.java
@@ -25,6 +25,7 @@ import org.apache.avro.generic.GenericDatumReader;
 import org.apache.avro.generic.GenericRecord;
 import org.apache.avro.io.DatumReader;
 import org.apache.avro.mapred.FsInput;
+import org.apache.commons.cli.CommandLine;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
@@ -45,6 +46,7 @@ import org.apache.orc.bench.core.CompressionKind;
 import org.apache.orc.bench.core.IOCounters;
 import org.apache.orc.bench.core.OrcBenchmark;
 import org.apache.orc.bench.core.Utilities;
+import org.apache.orc.bench.core.convert.GenerateVariants;
 import org.apache.parquet.hadoop.ParquetInputFormat;
 import org.openjdk.jmh.annotations.Benchmark;
 import org.openjdk.jmh.annotations.BenchmarkMode;
@@ -54,6 +56,7 @@ import org.openjdk.jmh.annotations.Param;
 import org.openjdk.jmh.annotations.Scope;
 import org.openjdk.jmh.annotations.State;
 import org.openjdk.jmh.runner.Runner;
+import org.openjdk.jmh.runner.options.OptionsBuilder;
 
 import java.io.InputStream;
 import java.io.InputStreamReader;
@@ -87,7 +90,13 @@ public class FullReadBenchmark implements OrcBenchmark {
 
   @Override
   public void run(String[] args) throws Exception {
-    new Runner(Utilities.parseOptions(args, getClass())).run();
+    CommandLine cmds = GenerateVariants.parseCommandLine(args);
+    new Runner(new OptionsBuilder()
+        .parent(Utilities.parseOptions(args, this.getClass()))
+        .param("compression", cmds.getOptionValue("compress", 
"gz,snappy,zstd").split(","))
+        .param("dataset", cmds.getOptionValue("data", 
"taxi,sales,github").split(","))
+        .build()
+    ).run();
   }
 
   @Benchmark