1.背景

一个测试环境，这个环境的资源不足，很卡。

docker外查看下

root@node1 ~]# free -g
              total        used        free      shared  buff/cache   available
Mem:            250         199           3           3          47          44
Swap:             0           0           0
您在 /var/spool/mail/root 中有新邮件
[root@node1 ~]# docker ps
CONTAINER ID        IMAGE               COMMAND                  CREATED             STATUS              PORTS                                                                    NAMES
0e54c7ac6567                                       stupefied_galois
e23340b7b4c3    
777f9d78734a    
d26183c7b06d    
89fc1de7c90a    
ca9d3dc93045    
5b04a6c90e07    
8f97c3256946    
330b990f5f7b    
adb29b7e5860    
45dc7b47e787    
0fd97f7809d8    
9b15b6bdf463    
767a1445897e    
68ea719829e1    
9e57de952b02    
0132cfb90221    
f00c295adc4d    
ff27f52f55a0    
1cbb63f3343e    
7c58d554ef7e    
97a1781cb762    
[root@node1 ~]#

Docker内查看一下

[root@1 /]# free -g
             total       used       free     shared    buffers     cached
Mem:           250        246          4          3          0         41
-/+ buffers/cache:        204         46
Swap:            0          0          0
[root@1 /]#

然后运行flink 1.6.2 任务报错

2020-12-02 09:19:00,281 WARN  org.apache.flink.streaming.connectors.kafka.internal.Kafka09Fetcher  - Error while closing Kafka consumer
java.lang.NullPointerException
	at org.apache.flink.streaming.connectors.kafka.internal.KafkaConsumerThread.run(KafkaConsumerThread.java:286)
2020-12-02 09:19:00,289 INFO  org.apache.flink.runtime.taskmanager.Task                     - Source: kafkaSource (1/1) (f76005135e137a38ac34ed492de51e03) switched from RUNNING to FAILED.


2020-12-02 09:17:29,512 INFO  org.apache.kafka.clients.producer.KafkaProducer               - [Producer clientId=producer-3] Closing the Kafka producer with timeoutMillis = 9223372036854775807 ms.
2020-12-02 09:17:29,513 ERROR org.apache.kafka.clients.producer.KafkaProducer               - [Producer clientId=producer-3] Interrupted while joining ioThread
java.lang.InterruptedException
	at java.lang.Object.wait(Native Method)
	at java.lang.Thread.join(Thread.java:1257)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1169)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1146)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1124)
	at com.dbapp.es5.sink.KafkaSinkFunction.close(KafkaSinkFunction.java:492)
	at org.apache.flink.api.common.functions.util.FunctionUtils.closeFunction(FunctionUtils.java:43)
	at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.dispose(AbstractUdfStreamOperator.java:117)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.disposeAllOperators(StreamTask.java:477)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:378)
	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:711)
	at java.lang.Thread.run(Thread.java:745)
2020-12-02 09:17:29,513 INFO  org.apache.flink.runtime.taskmanager.Task                     - Attempting to cancel task Sink: auto esSink (1/1) (48d8f009fc6b9f202ef10ca33daf4b57).
2020-12-02 09:17:29,513 INFO  org.apache.kafka.clients.producer.KafkaProducer               - [Producer clientId=producer-3] Proceeding to force close the producer since pending requests could not be completed within timeout 9223372036854775807 ms.
2020-12-02 09:17:29,513 INFO  org.apache.flink.runtime.taskmanager.Task                     - Sink: auto esSink (1/1) (48d8f009fc6b9f202ef10ca33daf4b57) switched from RUNNING to CANCELING.
2020-12-02 09:17:29,514 ERROR org.apache.flink.streaming.runtime.tasks.StreamTask           - Error during disposal of stream operator.
org.apache.kafka.common.errors.InterruptException: java.lang.InterruptedException
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1171)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1146)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1124)
	at com.dbapp.es5.sink.KafkaSinkFunction.close(KafkaSinkFunction.java:492)
	at org.apache.flink.api.common.functions.util.FunctionUtils.closeFunction(FunctionUtils.java:43)
	at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.dispose(AbstractUdfStreamOperator.java:117)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.disposeAllOperators(StreamTask.java:477)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:378)
	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:711)
	at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.InterruptedException
	at java.lang.Object.wait(Native Method)
	at java.lang.Thread.join(Thread.java:1257)
	at org.apache.kafka.clients.producer.KafkaProducer.close(KafkaProducer.java:1169)
	... 9 more
2020-12-02 09:17:29,515 INFO  org.apache.flink.runtime.taskmanager.Task                     - alipha.garbage.mail (1/1) (4d1143d26f1b392bcff31899e4bfc7aa) switched from CANCELING to CANCELED.
2020-12-02 09:17:29,515 INFO  org.apache.flink.runtime.taskmanager.Task                     - Freeing task resources for alipha.garbage.mail (1/1) (4d1143d26f1b392bcff31899e4bfc7aa).