You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "yaooqinn (via GitHub)" <gi...@apache.org> on 2024/01/23 07:42:28 UTC
[PR] [SPARK-46772][SQL] Benchmarking Avro with Compression Codecs [spark]
yaooqinn opened a new pull request, #44849:
URL: https://github.com/apache/spark/pull/44849
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a faster review.
7. If you want to add a new configuration, please read the guideline first for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
8. If you want to add or modify an error type or message, please read the guideline first in
'core/src/main/resources/error/README.md'.
-->
### What changes were proposed in this pull request?
<!--
Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
2. If you fix some SQL features, you can provide some references of other DBMSes.
3. If there is design documentation, please add the link.
4. If there is a discussion in the mailing list, please add the link.
-->
This PR improves AvroWriteBenchmark by adding benchmarks with codec and their extra functionalities.
- Avro compression with different codec
- Avro deflate/xz/zstandard with different levels
- buffer pool if zstandard
### Why are the changes needed?
<!--
Please clarify why the changes are needed. For instance,
1. If you propose a new API, clarify the use case for a new API.
2. If you fix a bug, you can clarify why it is a bug.
-->
performance observation.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such as the documentation fix.
If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
If possible, please also clarify if this is a user-facing change compared to the released Spark versions or within the unreleased branches such as master.
If no, write 'No'.
-->
no
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why it was difficult to add.
If benchmark tests were added, please run the benchmarks in GitHub Actions for the consistent environment, and the instructions could accord to: https://spark.apache.org/developer-tools.html#github-workflow-benchmarks.
-->
connector/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroWriteBenchmark.scala
### Was this patch authored or co-authored using generative AI tooling?
<!--
If generative AI tooling has been used in the process of authoring this patch, please include the
phrase: 'Generated-by: ' followed by the name of the tool and its version.
If no, write 'No'.
Please refer to the [ASF Generative Tooling Guidance](https://www.apache.org/legal/generative-tooling.html) for details.
-->
no
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL][TESTS] Benchmarking Avro with Compression Codecs [spark]
Posted by "yaooqinn (via GitHub)" <gi...@apache.org>.
yaooqinn commented on code in PR #44849:
URL: https://github.com/apache/spark/pull/44849#discussion_r1464210554
##########
connector/avro/benchmarks/AvroWriteBenchmark-jdk21-results.txt:
##########
@@ -1,16 +1,56 @@
-OpenJDK 64-Bit Server VM 21.0.1+12-LTS on Linux 5.15.0-1053-azure
+OpenJDK 64-Bit Server VM 21.0.2+13-LTS on Linux 5.15.0-1053-azure
AMD EPYC 7763 64-Core Processor
Avro writer benchmark: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-Output Single Int Column 1389 1404 21 11.3 88.3 1.0X
-Output Single Double Column 1522 1523 1 10.3 96.8 0.9X
-Output Int and String Column 3398 3400 3 4.6 216.0 0.4X
-Output Partitions 2855 2874 27 5.5 181.5 0.5X
-Output Buckets 3857 3903 66 4.1 245.2 0.4X
+Output Single Int Column 1433 1505 101 11.0 91.1 1.0X
+Output Single Double Column 1467 1487 28 10.7 93.3 1.0X
+Output Int and String Column 3187 3203 23 4.9 202.6 0.4X
+Output Partitions 2759 2796 52 5.7 175.4 0.5X
+Output Buckets 3760 3767 9 4.2 239.1 0.4X
-OpenJDK 64-Bit Server VM 21.0.1+12-LTS on Linux 5.15.0-1053-azure
+OpenJDK 64-Bit Server VM 21.0.2+13-LTS on Linux 5.15.0-1053-azure
AMD EPYC 7763 64-Core Processor
-Write wide rows into 20 files: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
Review Comment:
Hi @dongjoon-hyun, I did not remove it as it now becomes the SNAPPY in the codec comparison benchmarking group
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL] Benchmarking Avro with Compression Codecs [spark]
Posted by "yaooqinn (via GitHub)" <gi...@apache.org>.
yaooqinn commented on code in PR #44849:
URL: https://github.com/apache/spark/pull/44849#discussion_r1462842378
##########
connector/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroWriteBenchmark.scala:
##########
@@ -42,8 +44,8 @@ object AvroWriteBenchmark extends DataSourceWriteBenchmark {
withTempPath { dir =>
withTempTable("t1") {
val width = 1000
- val values = 500000
- val files = 20
+ val values = 100000
Review Comment:
Make it smaller as bzip2 took about 20 minutes to compress the original size of data
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL][TESTS] Benchmarking Avro with Compression Codecs [spark]
Posted by "yaooqinn (via GitHub)" <gi...@apache.org>.
yaooqinn commented on PR #44849:
URL: https://github.com/apache/spark/pull/44849#issuecomment-1907229235
Thank you @dongjoon-hyun
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL][TESTS] Benchmarking Avro with Compression Codecs [spark]
Posted by "yaooqinn (via GitHub)" <gi...@apache.org>.
yaooqinn commented on code in PR #44849:
URL: https://github.com/apache/spark/pull/44849#discussion_r1464211489
##########
connector/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroWriteBenchmark.scala:
##########
@@ -52,12 +54,48 @@ object AvroWriteBenchmark extends DataSourceWriteBenchmark {
// cache the data to ensure we are not benchmarking range or repartition
df.noop()
df.createOrReplaceTempView("t1")
- val benchmark = new Benchmark(s"Write wide rows into $files files", values, output = output)
- benchmark.addCase("Write wide rows") { _ =>
- spark.sql("SELECT * FROM t1").
- write.format("avro").save(s"${dir.getCanonicalPath}/${Random.nextLong().abs}")
+
+ def addBenchmark(
+ benchmark: Benchmark,
+ codec: String,
+ conf: Map[String, String] = Map.empty): Unit = {
+ val name = conf.map(kv => kv._1.stripPrefix("spark.sql.avro.") + "=" + kv._2)
+ .mkString(codec + ": ", ", ", "")
+ benchmark.addCase(name) { _ =>
+ withSQLConf(conf.toSeq: _*) {
+ spark
+ .table("t1")
+ .write
+ .option("compression", codec)
+ .format("avro")
+ .save(s"${dir.getCanonicalPath}/${Random.nextLong().abs}")
+ }
+ }
+ }
+
+ val bm = new Benchmark(s"Avro compression with different codec", values, output = output)
+ AvroCompressionCodec.values().sortBy(_.getCodecName).foreach { codec =>
+ addBenchmark(bm, codec.name)
+ }
+ bm.run()
+
+ AvroCompressionCodec.values().filter(_.getSupportCompressionLevel).foreach { codec =>
+ val bm = new Benchmark(
+ s"Avro ${codec.getCodecName} with different levels", values, output = output)
+ Seq(1, 3, 5, 7, 9).foreach { level =>
+ val conf = Map(s"spark.sql.avro.${codec.getCodecName}.level" -> level.toString)
+ addBenchmark(bm, codec.name, conf)
+ if (codec == AvroCompressionCodec.ZSTANDARD) {
+ val nondft =
Review Comment:
Yes, I hope the name doesn't bother you too much.：）
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL] Benchmarking Avro with Compression Codecs [spark]
Posted by "dongjoon-hyun (via GitHub)" <gi...@apache.org>.
dongjoon-hyun commented on code in PR #44849:
URL: https://github.com/apache/spark/pull/44849#discussion_r1463523930
##########
connector/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroWriteBenchmark.scala:
##########
@@ -52,12 +54,48 @@ object AvroWriteBenchmark extends DataSourceWriteBenchmark {
// cache the data to ensure we are not benchmarking range or repartition
df.noop()
df.createOrReplaceTempView("t1")
- val benchmark = new Benchmark(s"Write wide rows into $files files", values, output = output)
- benchmark.addCase("Write wide rows") { _ =>
- spark.sql("SELECT * FROM t1").
- write.format("avro").save(s"${dir.getCanonicalPath}/${Random.nextLong().abs}")
+
+ def addBenchmark(
+ benchmark: Benchmark,
+ codec: String,
+ conf: Map[String, String] = Map.empty): Unit = {
+ val name = conf.map(kv => kv._1.stripPrefix("spark.sql.avro.") + "=" + kv._2)
+ .mkString(codec + ": ", ", ", "")
+ benchmark.addCase(name) { _ =>
+ withSQLConf(conf.toSeq: _*) {
+ spark
+ .table("t1")
+ .write
+ .option("compression", codec)
+ .format("avro")
+ .save(s"${dir.getCanonicalPath}/${Random.nextLong().abs}")
+ }
+ }
+ }
+
+ val bm = new Benchmark(s"Avro compression with different codec", values, output = output)
+ AvroCompressionCodec.values().sortBy(_.getCodecName).foreach { codec =>
+ addBenchmark(bm, codec.name)
+ }
+ bm.run()
+
+ AvroCompressionCodec.values().filter(_.getSupportCompressionLevel).foreach { codec =>
+ val bm = new Benchmark(
+ s"Avro ${codec.getCodecName} with different levels", values, output = output)
+ Seq(1, 3, 5, 7, 9).foreach { level =>
+ val conf = Map(s"spark.sql.avro.${codec.getCodecName}.level" -> level.toString)
+ addBenchmark(bm, codec.name, conf)
+ if (codec == AvroCompressionCodec.ZSTANDARD) {
+ val nondft =
Review Comment:
Does this mean `non-default`?
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL] Benchmarking Avro with Compression Codecs [spark]
Posted by "dongjoon-hyun (via GitHub)" <gi...@apache.org>.
dongjoon-hyun commented on code in PR #44849:
URL: https://github.com/apache/spark/pull/44849#discussion_r1463515822
##########
connector/avro/benchmarks/AvroWriteBenchmark-jdk21-results.txt:
##########
@@ -1,16 +1,56 @@
-OpenJDK 64-Bit Server VM 21.0.1+12-LTS on Linux 5.15.0-1053-azure
+OpenJDK 64-Bit Server VM 21.0.2+13-LTS on Linux 5.15.0-1053-azure
AMD EPYC 7763 64-Core Processor
Avro writer benchmark: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-Output Single Int Column 1389 1404 21 11.3 88.3 1.0X
-Output Single Double Column 1522 1523 1 10.3 96.8 0.9X
-Output Int and String Column 3398 3400 3 4.6 216.0 0.4X
-Output Partitions 2855 2874 27 5.5 181.5 0.5X
-Output Buckets 3857 3903 66 4.1 245.2 0.4X
+Output Single Int Column 1433 1505 101 11.0 91.1 1.0X
+Output Single Double Column 1467 1487 28 10.7 93.3 1.0X
+Output Int and String Column 3187 3203 23 4.9 202.6 0.4X
+Output Partitions 2759 2796 52 5.7 175.4 0.5X
+Output Buckets 3760 3767 9 4.2 239.1 0.4X
-OpenJDK 64-Bit Server VM 21.0.1+12-LTS on Linux 5.15.0-1053-azure
+OpenJDK 64-Bit Server VM 21.0.2+13-LTS on Linux 5.15.0-1053-azure
AMD EPYC 7763 64-Core Processor
-Write wide rows into 20 files: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
Review Comment:
Why do we remove old benchmark, @yaooqinn ?
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46772][SQL][TESTS] Benchmarking Avro with Compression Codecs [spark]
Posted by "dongjoon-hyun (via GitHub)" <gi...@apache.org>.
dongjoon-hyun closed pull request #44849: [SPARK-46772][SQL][TESTS] Benchmarking Avro with Compression Codecs
URL: https://github.com/apache/spark/pull/44849
--
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.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org