ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity
Apache Spark - A unified analytics engine for large-scale data processing
25181 commits 6 branches 181 tags 397 MiB
Scala 65.7%
Python 12.1%
Jupyter Notebook 7.3%
Java 7.3%
HiveQL 3.2%
Other 4%
Go to file
Takeshi Yamamuro 95073fb62b [SPARK-29008][SQL] Define an individual method for each common subexpression in HashAggregateExec 
### What changes were proposed in this pull request?

This pr proposes to define an individual method for each common subexpression in HashAggregateExec. In the current master, the common subexpr elimination code in HashAggregateExec is expanded in a single method; 4664a082c2/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala (L397)

The method size can be too big for JIT compilation, so I believe splitting it is beneficial for performance. For example, in a query `SELECT SUM(a + b), AVG(a + b + c) FROM VALUES (1, 1, 1) t(a, b, c)`,

the current master generates;
```
/* 098 */   private void agg_doConsume_0(InternalRow localtablescan_row_0, int agg_expr_0_0, int agg_expr_1_0, int agg_expr_2_0) throws java.io.IOException {
/* 099 */     // do aggregate
/* 100 */     // common sub-expressions
/* 101 */     int agg_value_6 = -1;
/* 102 */
/* 103 */     agg_value_6 = agg_expr_0_0 + agg_expr_1_0;
/* 104 */
/* 105 */     int agg_value_5 = -1;
/* 106 */
/* 107 */     agg_value_5 = agg_value_6 + agg_expr_2_0;
/* 108 */     boolean agg_isNull_4 = false;
/* 109 */     long agg_value_4 = -1L;
/* 110 */     if (!false) {
/* 111 */       agg_value_4 = (long) agg_value_5;
/* 112 */     }
/* 113 */     int agg_value_10 = -1;
/* 114 */
/* 115 */     agg_value_10 = agg_expr_0_0 + agg_expr_1_0;
/* 116 */     // evaluate aggregate functions and update aggregation buffers
/* 117 */     agg_doAggregate_sum_0(agg_value_10);
/* 118 */     agg_doAggregate_avg_0(agg_value_4, agg_isNull_4);
/* 119 */
/* 120 */   }
```

On the other hand, this pr generates;
```
/* 121 */   private void agg_doConsume_0(InternalRow localtablescan_row_0, int agg_expr_0_0, int agg_expr_1_0, int agg_expr_2_0) throws java.io.IOException {
/* 122 */     // do aggregate
/* 123 */     // common sub-expressions
/* 124 */     long agg_subExprValue_0 = agg_subExpr_0(agg_expr_2_0, agg_expr_0_0, agg_expr_1_0);
/* 125 */     int agg_subExprValue_1 = agg_subExpr_1(agg_expr_0_0, agg_expr_1_0);
/* 126 */     // evaluate aggregate functions and update aggregation buffers
/* 127 */     agg_doAggregate_sum_0(agg_subExprValue_1);
/* 128 */     agg_doAggregate_avg_0(agg_subExprValue_0);
/* 129 */
/* 130 */   }
```

I run some micro benchmarks for this pr;
```
(base) maropu~:$system_profiler SPHardwareDataType
Hardware:
    Hardware Overview:
      Processor Name: Intel Core i5
      Processor Speed: 2 GHz
      Number of Processors: 1
      Total Number of Cores: 2
      L2 Cache (per Core): 256 KB
      L3 Cache: 4 MB
      Memory: 8 GB

(base) maropu~:$java -version
java version "1.8.0_181"
Java(TM) SE Runtime Environment (build 1.8.0_181-b13)
Java HotSpot(TM) 64-Bit Server VM (build 25.181-b13, mixed mode)

(base) maropu~:$ /bin/spark-shell --master=local[1] --conf spark.driver.memory=8g --conf spark.sql.shurtitions=1 -v

val numCols = 40
val colExprs = "id AS key" +: (0 until numCols).map { i => s"id AS _c$i" }
spark.range(3000000).selectExpr(colExprs: _*).createOrReplaceTempView("t")

val aggExprs = (2 until numCols).map { i =>
  (0 until i).map(d => s"_c$d")
    .mkString("AVG(", " + ", ")")
}

// Drops the time of a first run then pick that of a second run
timer { sql(s"SELECT ${aggExprs.mkString(", ")} FROM t").write.format("noop").save() }

// the master
maxCodeGen: 12957
Elapsed time: 36.309858661s

// this pr
maxCodeGen=4184
Elapsed time: 2.399490285s
```

### Why are the changes needed?

To avoid the too-long-function issue in JVMs.

### Does this PR introduce any user-facing change?

No.

### How was this patch tested?

Added tests in `WholeStageCodegenSuite`

Closes #25710 from maropu/SplitSubexpr.

Authored-by: Takeshi Yamamuro <yamamuro@apache.org>
Signed-off-by: Takeshi Yamamuro <yamamuro@apache.org>
2019-09-17 11:09:55 +09:00
.github [SPARK-29079][INFRA] Enable GitHub Action on PR 2019-09-13 21:50:06 +00:00
assembly [SPARK-27300][GRAPH] Add Spark Graph modules and dependencies 2019-06-09 00:26:26 -07:00
bin [SPARK-28525][DEPLOY] Allow Launcher to be applied Java options 2019-07-30 12:45:32 -07:00
build [SPARK-28963][BUILD] Fall back to archive.apache.org in build/mvn for older releases 2019-09-04 13:11:09 +09:00
common [SPARK-28932][BUILD][FOLLOWUP] Switch to scala-library compile dependency for JDK11 2019-09-16 00:13:07 -07:00
conf [SPARK-29032][CORE] Add PrometheusServlet to monitor Master/Worker/Driver 2019-09-13 21:31:21 +00:00
core [SPARK-29072][CORE] Put back usage of TimeTrackingOutputStream for UnsafeShuffleWriter and SortShuffleWriter 2019-09-16 09:08:25 -05:00
data [SPARK-22666][ML][SQL] Spark datasource for image format 2018-09-05 11:59:00 -07:00
dev [SPARK-28906][BUILD] Fix incorrect information in bin/spark-submit --version 2019-09-11 08:12:44 -05:00
docs [SPARK-29052][DOCS][ML][PYTHON][CORE][R][SQL][SS] Create a Migration Guide tap in Spark documentation 2019-09-15 11:17:30 -07:00
examples [SPARK-28980][CORE][SQL][STREAMING][MLLIB] Remove most items deprecated in Spark 2.2.0 or earlier, for Spark 3 2019-09-09 10:19:40 -05:00
external [SPARK-23539][SS][FOLLOWUP][TESTS] Add UT to ensure existing query doesn't break with default conf of includeHeaders 2019-09-16 15:22:04 -05:00
graph [SPARK-27300][GRAPH] Add Spark Graph modules and dependencies 2019-06-09 00:26:26 -07:00
graphx [SPARK-29042][CORE] Sampling-based RDD with unordered input should be INDETERMINATE 2019-09-13 14:07:00 -07:00
hadoop-cloud [SPARK-28903][STREAMING][PYSPARK][TESTS] Fix AWS JDK version conflict that breaks Pyspark Kinesis tests 2019-08-31 10:29:46 -05:00
launcher [SPARK-29080][CORE][SPARKR] Support R file extension case-insensitively 2019-09-15 00:17:11 -07:00
licenses [SPARK-27557][DOC] Add copy button to Python API docs for easier copying of code-blocks 2019-05-01 11:26:18 -05:00
licenses-binary [SPARK-28737][CORE] Update Jersey to 2.29 2019-08-16 15:08:04 -07:00
mllib [SPARK-29007][MLLIB][FOLLOWUP] Remove duplicated dependency 2019-09-13 11:54:46 -07:00
mllib-local [SPARK-28421][ML] SparseVector.apply performance optimization 2019-07-23 20:20:22 -05:00
project [SPARK-28980][CORE][SQL][STREAMING][MLLIB] Remove most items deprecated in Spark 2.2.0 or earlier, for Spark 3 2019-09-09 10:19:40 -05:00
python [SPARK-28969][PYTHON][ML] OneVsRestParams parity between scala and python 2019-09-13 12:29:19 -05:00
R [MINOR][DOCS] Fix few typos in the java docs 2019-09-12 09:30:03 +09:00
repl [SPARK-28601][CORE][SQL] Use StandardCharsets.UTF_8 instead of "UTF-8" string representation, and get rid of UnsupportedEncodingException 2019-08-05 20:45:54 -07:00
resource-managers [SPARK-29080][CORE][SPARKR] Support R file extension case-insensitively 2019-09-15 00:17:11 -07:00
sbin [SPARK-28164] Fix usage description of start-slave.sh 2019-06-26 12:42:33 -05:00
sql [SPARK-29008][SQL] Define an individual method for each common subexpression in HashAggregateExec 2019-09-17 11:09:55 +09:00
streaming [SPARK-29087][CORE][STREAMING] Use DelegatingServletContextHandler to avoid CCE 2019-09-15 10:15:49 -07:00
tools [SPARK-25956] Make Scala 2.12 as default Scala version in Spark 3.0 2018-11-14 16:22:23 -08:00
.gitattributes [SPARK-3870] EOL character enforcement 2014-10-31 12:39:52 -07:00
.gitignore [SPARK-27371][CORE] Support GPU-aware resources scheduling in Standalone 2019-08-09 07:49:03 -05:00
appveyor.yml [SPARK-28759][BUILD] Upgrade scala-maven-plugin to 4.2.0 and fix build profile on AppVeyor 2019-08-30 09:39:15 -07:00
CONTRIBUTING.md [MINOR][DOCS] Tighten up some key links to the project and download pages to use HTTPS 2019-05-21 10:56:42 -07:00
LICENSE [SPARK-27557][DOC] Add copy button to Python API docs for easier copying of code-blocks 2019-05-01 11:26:18 -05:00
LICENSE-binary [SPARK-28921][BUILD][K8S] Upgrade kubernetes client to 4.4.2 2019-09-02 16:50:58 -07:00
NOTICE [SPARK-23654][BUILD] remove jets3t as a dependency of spark 2018-08-16 12:34:23 -07:00
NOTICE-binary [SPARK-17875][CORE][BUILD] Remove dependency on Netty 3 2019-08-21 21:27:56 -07:00
pom.xml [SPARK-29075][BUILD] Add enforcer rule to ban duplicated pom dependency 2019-09-13 14:35:02 -07:00
README.md [SPARK-28473][DOC] Stylistic consistency of build command in README 2019-07-23 16:29:46 -07:00
scalastyle-config.xml [SPARK-25986][BUILD] Add rules to ban throw Errors in application code 2018-11-14 13:05:18 -08:00

README.md

Apache Spark

Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.

https://spark.apache.org/

Jenkins Build AppVeyor Build PySpark Coverage

Online Documentation

You can find the latest Spark documentation, including a programming guide, on the project web page. This README file only contains basic setup instructions.

Building Spark

Spark is built using Apache Maven. To build Spark and its example programs, run:

./build/mvn -DskipTests clean package

(You do not need to do this if you downloaded a pre-built package.)

You can build Spark using more than one thread by using the -T option with Maven, see "Parallel builds in Maven 3". More detailed documentation is available from the project site, at "Building Spark".

For general development tips, including info on developing Spark using an IDE, see "Useful Developer Tools".

Interactive Scala Shell

The easiest way to start using Spark is through the Scala shell:

./bin/spark-shell

Try the following command, which should return 1,000,000,000:

scala> spark.range(1000 * 1000 * 1000).count()

Interactive Python Shell

Alternatively, if you prefer Python, you can use the Python shell:

./bin/pyspark

And run the following command, which should also return 1,000,000,000:

>>> spark.range(1000 * 1000 * 1000).count()

Example Programs

Spark also comes with several sample programs in the examples directory. To run one of them, use ./bin/run-example <class> [params]. For example:

./bin/run-example SparkPi

will run the Pi example locally.

You can set the MASTER environment variable when running examples to submit examples to a cluster. This can be a mesos:// or spark:// URL, "yarn" to run on YARN, and "local" to run locally with one thread, or "local[N]" to run locally with N threads. You can also use an abbreviated class name if the class is in the examples package. For instance:

MASTER=spark://host:7077 ./bin/run-example SparkPi

Many of the example programs print usage help if no params are given.

Running Tests

Testing first requires building Spark. Once Spark is built, tests can be run using:

./dev/run-tests

Please see the guidance on how to run tests for a module, or individual tests.

There is also a Kubernetes integration test, see resource-managers/kubernetes/integration-tests/README.md

A Note About Hadoop Versions

Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported storage systems. Because the protocols have changed in different versions of Hadoop, you must build Spark against the same version that your cluster runs.

Please refer to the build documentation at "Specifying the Hadoop Version and Enabling YARN" for detailed guidance on building for a particular distribution of Hadoop, including building for particular Hive and Hive Thriftserver distributions.

Configuration

Please refer to the Configuration Guide in the online documentation for an overview on how to configure Spark.

Contributing

Please review the Contribution to Spark guide for information on how to get started contributing to the project.