[
https://issues.apache.org/jira/browse/SPARK-54753?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xihuan updated SPARK-54753:
---------------------------
Description:
For Apache Spark *4.0.1* local mode, the memory is not released after long time
running, while downgrade the spark version {*}v3.5.6{*}, there is no issue.
The issue can be reproduced with simple test cases:
```
package spark;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.concurrent.Executors;
import java.util.concurrent.ScheduledExecutorService;
public class SparkApp {
private static final Logger log = LoggerFactory.getLogger(SparkApp.class);
private static final String SPARK_MASTER_URL = "local[4]";
private static final String SPARK_MEMORY = "500m";
public static void main(String[] args) {
log.debug("Starting application...");
SparkSession sparkSession = SparkSession.builder()
.appName("Test Application")
.master(SPARK_MASTER_URL)
.config("spark.driver.memory", SPARK_MEMORY)
//.config("spark.sql.sources.bucketing.autoBucketedScan.enabled", false) // To
get rid of the memory leak
.getOrCreate();
processData(sparkSession);
}
private static void processData(SparkSession sparkSession) {
while (true) {
//load from a local csv file
Dataset<Row> dataset = sparkSession.read().csv("c:/City.csv");
dataset.show(5);
log.debug("Persist dataset...");
// This is the place where the memory leak occurs
dataset.persist();
// Do something...
log.debug("Do something with the persisted dataset");
// ...and unpersist the dataset
log.debug("Unpersist dataset...");
dataset.unpersist();
log.debug("Processing data completed");
}
}
}
```
with Apache Spark 4.0.0 or 4.0.1, around 9 minutes, will encounter oom.
!screenshot-1.png!
While, with Apache Spark 3.5.6, no such issue occurs.
was:
For Apache Spark *4.0.1* local mode, the memory is not released after long time
running, while downgrade the spark version {*}v3.5.6{*}, there is no issue.
The issue can be reproduced with simple test cases:
```
package spark;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.concurrent.Executors;
import java.util.concurrent.ScheduledExecutorService;
public class SparkApp {
private static final Logger log = LoggerFactory.getLogger(SparkApp.class);
private static final String SPARK_MASTER_URL = "local[4]";
private static final String SPARK_MEMORY = "500m";
public static void main(String[] args) {
log.debug("Starting application...");
SparkSession sparkSession = SparkSession.builder()
.appName("Test Application")
.master(SPARK_MASTER_URL)
.config("spark.driver.memory", SPARK_MEMORY)
//.config("spark.sql.sources.bucketing.autoBucketedScan.enabled", false) // To
get rid of the memory leak
.getOrCreate();
processData(sparkSession);
}
private static void processData(SparkSession sparkSession) {
while (true) {
//load from a local csv file
Dataset<Row> dataset = sparkSession.read().csv("c:/City.csv");
dataset.show(5);
log.debug("Persist dataset...");
// This is the place where the memory leak occurs
dataset.persist();
// Do something...
log.debug("Do something with the persisted dataset");
// ...and unpersist the dataset
log.debug("Unpersist dataset...");
dataset.unpersist();
log.debug("Processing data completed");
}
}
}
```
with Apache Spark 4.0.0 or 4.0.1, around 9 minutes, will encounter oom.
!screenshot-1.png!
While, with Apache Spark 3.5.6, no such issue occurs.
Priority: Critical (was: Major)
> memory leak in Apache Spark 4.0.1
> ---------------------------------
>
> Key: SPARK-54753
> URL: https://issues.apache.org/jira/browse/SPARK-54753
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 4.0.1
> Reporter: xihuan
> Priority: Critical
> Attachments: image-2025-12-23-05-38-53-324.png, pom.xml,
> screenshot-1.png
>
>
> For Apache Spark *4.0.1* local mode, the memory is not released after long
> time running, while downgrade the spark version {*}v3.5.6{*}, there is no
> issue.
> The issue can be reproduced with simple test cases:
> ```
> package spark;
> import org.apache.spark.sql.Dataset;
> import org.apache.spark.sql.Row;
> import org.apache.spark.sql.SparkSession;
> import org.slf4j.Logger;
> import org.slf4j.LoggerFactory;
> import java.util.concurrent.Executors;
> import java.util.concurrent.ScheduledExecutorService;
> public class SparkApp {
> private static final Logger log = LoggerFactory.getLogger(SparkApp.class);
> private static final String SPARK_MASTER_URL = "local[4]";
> private static final String SPARK_MEMORY = "500m";
> public static void main(String[] args) {
> log.debug("Starting application...");
> SparkSession sparkSession = SparkSession.builder()
> .appName("Test Application")
> .master(SPARK_MASTER_URL)
> .config("spark.driver.memory", SPARK_MEMORY)
>
> //.config("spark.sql.sources.bucketing.autoBucketedScan.enabled", false) //
> To get rid of the memory leak
> .getOrCreate();
> processData(sparkSession);
> }
> private static void processData(SparkSession sparkSession) {
>
> while (true) {
> //load from a local csv file
> Dataset<Row> dataset = sparkSession.read().csv("c:/City.csv");
> dataset.show(5);
> log.debug("Persist dataset...");
> // This is the place where the memory leak occurs
> dataset.persist();
> // Do something...
> log.debug("Do something with the persisted dataset");
> // ...and unpersist the dataset
> log.debug("Unpersist dataset...");
> dataset.unpersist();
> log.debug("Processing data completed");
> }
> }
> }
> ```
>
> with Apache Spark 4.0.0 or 4.0.1, around 9 minutes, will encounter oom.
> !screenshot-1.png!
> While, with Apache Spark 3.5.6, no such issue occurs.
>
>
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
