This question already has answers here:
Spark java.lang.OutOfMemoryError: Java heap space
(14 answers)
Closed 1 year ago.
I am geting the above error when i run a model training pipeline with spark
`val inputData = spark.read
.option("header", true)
.option("mode","DROPMALFORMED")
.csv(input)
.repartition(500)
.toDF("b", "c")
.withColumn("b", lower(col("b")))
.withColumn("c", lower(col("c")))
.toDF("b", "c")
.na.drop()`
inputData has about 25 million rows and is about 2gb in size. the model building phase happens like so
val tokenizer = new Tokenizer()
.setInputCol("c")
.setOutputCol("tokens")
val cvSpec = new CountVectorizer()
.setInputCol("tokens")
.setOutputCol("features")
.setMinDF(minDF)
.setVocabSize(vocabSize)
val nb = new NaiveBayes()
.setLabelCol("bi")
.setFeaturesCol("features")
.setPredictionCol("prediction")
.setSmoothing(smoothing)
new Pipeline().setStages(Array(tokenizer, cvSpec, nb)).fit(inputData)
I am running the above spark jobs locally in a machine with 16gb RAM using the following command
spark-submit --class holmes.model.building.ModelBuilder ./holmes-model-building/target/scala-2.11/holmes-model-building_2.11-1.0.0-SNAPSHOT-7d6978.jar --master local[*] --conf spark.serializer=org.apache.spark.serializer.KryoSerializer --conf spark.kryoserializer.buffer.max=2000m --conf spark.driver.maxResultSize=2g --conf spark.rpc.message.maxSize=1024 --conf spark.memory.offHeap.enabled=true --conf spark.memory.offHeap.size=50g --driver-memory=12g
The oom error is triggered by (at the bottow of the stack trace)
by org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:706)
Logs :
Caused by: java.lang.OutOfMemoryError: Java heap space at java.lang.reflect.Array.newInstance(Array.java:75) at java.io.ObjectInputStream.readArray(ObjectInputStream.java:1897) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1529) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2027) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1535) org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:706)
Any suggestions will be great :)
Things I would try:
1) Removing spark.memory.offHeap.enabled=true and increasing driver memory to something like 90% of the available memory on the box. You probably are aware of this since you didn't set executor memory, but in local mode the driver and the executor all run in the same process which is controlled by driver-memory. I haven't tried it, but the offHeap feature sounds like it has limited value. Reference
2) An actual cluster instead of local mode. More nodes will obviously give you more RAM.
3a) If you want to stick with local mode, try using less cores. You can do this by specifying the number of cores to use in the master setting like --master local[4] instead of local[*] which uses all of them. Running with less threads simultaneously processing data will lead to less data in RAM at any given time.
3b) If you move to a cluster, you may also want to tweak the number of executors cores for the same reason as mentioned above. You can do this with the --executor-cores flag.
4) Try with more partitions. In your example code you repartitioned to 500 partitions, maybe try 1000, or 2000? More partitions means each partition is smaller and less memory pressure.
Usually, this error is thrown when there is insufficient space to allocate an object in the Java heap. In this case, The garbage collector cannot make space available to accommodate a new object, and the heap cannot be expanded further. Also, this error may be thrown when there is insufficient native memory to support the loading of a Java class. In a rare instance, a java.lang.OutOfMemoryError may be thrown when an excessive amount of time is being spent doing garbage collection and little memory is being freed.
How to fix error :
How to set Apache Spark Executor memory
Spark java.lang.OutOfMemoryError: Java heap space
Related
I am noticing some peculiar behaviour, i have spark job which reads the data and does some grouping ordering and join and creates an output file.
The issue is when I run the same job on yarn with memory more than what the environment has eg the cluster has 50 GB and i submit spark-submit with close to 60 GB executor and 4gb driver memory.
My results gets decreased seems like one of the data partitions or tasks are lost while processing.
driver-memory 4g --executor-memory 4g --num-executors 12
I also notice the warning message on driver -
WARN util.Utils: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.debug.maxToStringFields' in SparkEnv.conf.
but when i run with limited executors and memory example 15GB, it works and i get exact rows/data. no warning message.
driver-memory 2g --executor-memory 2g --num-executors 4
any suggestions are we missing some settings on cluster or anything?
Please note my job completes successfully in both the cases.
I am using spark version 2.2.
This is meaningless (except maybe for debugging) - the plan is larger when there are more executors involved and the warning is that it is too big to be converted into a string. if you need it you can set spark.debug.maxToStringFields to a larger number (as suggested in the warning message)
I know that when the spark cluster in the production environment is running a job, it is in the stand-alone mode.
While I was running a job, a few points of worker's memory overflow caused the worker node process to die.
I would like to ask how to analyze the error shown in the image below:
Spark Worker Fatal Error
EDIT: This is a relatively common problem please also view this if the below doesn't help you Spark java.lang.OutOfMemoryError: Java heap space.
Without seeing your code here is the process you should follow:
(1) If the issue is caused primarily from the Java allocation running out of space within the container allocation I would advise messing with your memory overhead settings (below). The current value are a little high and will cause the excess spin-up of vcores. Add the two below settings to your spark-submit and re-run.
--conf "spark.yarn.executor.memoryOverhead=4000m"
--conf "spark.yarn.driver.memoryOverhead=2000m"
(2) Adjust Executor and Driver Memory Levels. Start low and climb. Add these values to the spark-submit statement.
--driver-memory 10g
--executor-memory 5g
(3) Adjust Number of Executor Values in the spark submit.
--num-executors ##
(4) Look at the Yarn stages of the job and figure where inefficiencies in the code is present and where persistence's can be added and replaced. I would advise to heavily look into spark-tuning.
I have 2 questions on spark streaming :
I have a spark streaming application running and collection data in 20 seconds batch intervals, out of 4000 batches there are 18 batches which failed because of exception :
Could not compute split, block input-0-1464774108087 not found
I assumed the data size is bigger than spark available memory at that point, also the app StorageLevel is MEMORY_ONLY.
Please advice how to fix this.
Also in the command I use below, I use executor memory 20G(total RAM on the data nodes is 140G), does that mean all that memory is reserved in full for this app, and what happens if I have multiple spark streaming applications ?
would I not run out of memory after a few applications ? do I need that much memory at all ?
/usr/iop/4.1.0.0/spark/bin/spark-submit --master yarn --deploy-mode
client --jars /home/blah.jar --num-executors 8 --executor-cores
5 --executor-memory 20G --driver-memory 12G --driver-cores 8
--class com.ccc.nifi.MyProcessor Nifi-Spark-Streaming-20160524.jar
It seems might be your executor memory will be getting full,try these few optimization techniques like :
Instead of using StorageLevel is MEMORY_AND_DISK.
Use Kyro serialization which is fast and better than normal java serialization.f yougo for caching with memory and serialization.
Check if there are gc,you can find in the tasks being executed.
I try to save a large text file of a approx. 5GB
sc.parallelize(cfile.toString()
.split("\n"), 1)
.saveAsTextFile(new Path(path+".cs", "data").toUri.toString)
but I keep getting
java.io.IOException: Broken pipe
at sun.nio.ch.FileDispatcherImpl.write0(Native Method)
at sun.nio.ch.SocketDispatcher.write(SocketDispatcher.java:47)
at sun.nio.ch.IOUtil.writeFromNativeBuffer(IOUtil.java:93)
at sun.nio.ch.IOUtil.write(IOUtil.java:65)
...
org.apache.spark.shuffle.MetadataFetchFailedException: Missing an output location for shuffle 6
at org.apache.spark.MapOutputTracker$$anonfun$org$apache$spark$MapOutputTracker$$convertMapStatuses$2.apply(MapOutputTracker.scala:542)
at org.apache.spark.MapOutputTracker$$anonfun$org$apache$spark$MapOutputTracker$$convertMapStatuses$2.apply(MapOutputTracker.scala:538)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
I'm stuck here for ages now. Can anybody help me here and explain how I can save cfile as a textfile?
Standalone/Local/Yarn cluster?
Yarn cluster
Memory/Cores settings?
1,8 TB
285 Cores
Number of Partitions?
I am currently setting the number of partitions to 1:
The concerned lines of code for setting the number of partitions:
val model = word2vec
.setMinCount(minCount.asInstanceOf[Int])
.setVectorSize(arguments.getVectorSize)
.setWindowSize(arguments.getContextWindowSize)
.setNumPartitions(numW2vPartitions)
.setLearningRate(learningRate)
.setNumIterations(arguments.getNumIterations)
.fit(wordSequence)
spark-submit arguments:
spark-submit --master yarn
--deploy-mode cluster
--driver-memory 20G
--num-executors 5
--executor-cores 8
--driver-java-options "-Dspark.akka.frameSize=2000"
--executor-memory 20G --class
Standalone/Local/Yarn cluster?
Memory/Cores settings?
Number of Partitions?
Your error probably symptom that one of the workers are gone(OOM killer might have killed it or it got some OOM error)
I'm not sure why are you doing this: cfile.toString().split("\n") - from this I understand that you hold all 5GB content in memory and try to parallelize it ? Clearly it's not optimal.
Another problem that could be relevant - if you driver can hold all 5GB in memory somehow, but still all network layers between driver-workers won't like this amount of data - so my advice to split it into partitions.
instead you can read file with sc.textFile(..) and then save it into your new path. You also can control number of partitions(pieces) of your text file with sc.textFile(..).repartition(100).
I am processing data with spark and it works with a day worth of data (40G) but fails with OOM on a week worth of data:
import pyspark
import datetime
import operator
sc = pyspark.SparkContext()
sqc = pyspark.sql.SQLContext(sc)
sc.union([sqc.parquetFile(hour.strftime('.....'))
.map(lambda row:(row.id, row.foo))
for hour in myrange(beg,end,datetime.timedelta(0,3600))]) \
.reduceByKey(operator.add).saveAsTextFile("myoutput")
The number of different IDs is less than 10k.
Each ID is a smallish int.
The job fails because too many executors fail with OOM.
When the job succeeds (on small inputs), "myoutput" is about 100k.
what am I doing wrong?
I tried replacing saveAsTextFile with collect (because I actually want to do some slicing and dicing in python before saving), there was no difference in behavior, same failure. is this to be expected?
I used to have reduce(lambda x,y: x.union(y), [sqc.parquetFile(...)...]) instead of sc.union - which is better? Does it make any difference?
The cluster has 25 nodes with 825GB RAM and 224 cores among them.
Invocation is spark-submit --master yarn --num-executors 50 --executor-memory 5G.
A single RDD has ~140 columns and covers one hour of data, so a week is a union of 168(=7*24) RDDs.
Spark very often suffers from Out-Of-Memory errors when scaling. In these cases, fine tuning should be done by the programmer. Or recheck your code, to make sure that you don't do anything that is way too much, such as collecting all the bigdata in the driver, which is very likely to exceed the memoryOverhead limit, no matter how big you set it.
To understand what is happening you should realize when yarn decides to kill a container for exceeding memory limits. That will happen when the container goes beyond the memoryOverhead limit.
In the Scheduler you can check the Event Timeline to see what happened with the containers. If Yarn has killed a container, it will be appear red and when you hover/click over it, you will see a message like:
Container killed by YARN for exceeding memory limits. 16.9 GB of 16 GB physical memory used. Consider boosting spark.yarn.executor.memoryOverhead.
So in that case, what you want to focus on is these configuration properties (values are examples on my cluster):
# More executor memory overhead
spark.yarn.executor.memoryOverhead 4096
# More driver memory overhead
spark.yarn.driver.memoryOverhead 8192
# Max on my nodes
#spark.executor.cores 8
#spark.executor.memory 12G
# For the executors
spark.executor.cores 6
spark.executor.memory 8G
# For the driver
spark.driver.cores 6
spark.driver.memory 8G
The first thing to do is to increase the memoryOverhead.
In the driver or in the executors?
When you are overviewing your cluster from the UI, you can click on the Attempt ID and check the Diagnostics Info which should mention the ID of the container that was killed. If it is the same as with your AM Container, then it's the driver, else the executor(s).
That didn't resolve the issue, now what?
You have to fine tune the number of cores and the heap memory you are providing. You see pyspark will do most of the work in off-heap memory, so you want not to give too much space for the heap, since that would be wasted. You don't want to give too less, because the Garbage Collector will have issues then. Recall that these are JVMs.
As described here, a worker can host multiple executors, thus the number of cores used affects how much memory every executor has, so decreasing the #cores might help.
I have it written in memoryOverhead issue in Spark and Spark – Container exited with a non-zero exit code 143 in more detail, mostly that I won't forget! Another option, that I haven't tried would be spark.default.parallelism or/and spark.storage.memoryFraction, which based on my experience, didn't help.
You can pass configurations flags as sds mentioned, or like this:
spark-submit --properties-file my_properties
where "my_properties" is something like the attributes I list above.
For non numerical values, you could do this:
spark-submit --conf spark.executor.memory='4G'
It turned out that the problem was not with spark, but with yarn.
The solution is to run spark with
spark-submit --conf spark.yarn.executor.memoryOverhead=1000
(or modify yarn config).