Spark job fails with org.apache.spark.shuffle.FetchFailedException exception

Question

I am running a spark job with following properties:

 "spark.driver.disk": "10g",
  "spark.driver.maxResultSize": "40g",
  "spark.driver.memory": "50g",
  "spark.driver.memoryOverhead": "85g",
  "spark.executor.cores": "5",
  "spark.executor.disk": "60g",
  "spark.executor.instances": "400",
  "spark.executor.memory": "40g",
  "spark.executor.memoryOverhead": "37g",
  "spark.kubernetes.executor.limit.cores": "5",
  "spark.kubernetes.executor.request.cores": "5",
  "spark.sql.shuffle.partitions": "4000"

But somehow while writing the dataframe to parquet it is failing with following error:

org.apache.spark.shuffle.FetchFailedException: The relative remote executor(Id: 304), which maintains the block data to fetch is dead.
    at org.apache.spark.storage.ShuffleBlockFetcherIterator.throwFetchFailedException(ShuffleBlockFetcherIterator.scala:771)
    at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:686)
    at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:70)
    at org.apache.spark.util.CompletionIterator.next(CompletionIterator.scala:29)
    at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:484)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:490)
    at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:458)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:458)
    at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225)
    at org.apache.spark.sql.execution.SortExec.$anonfun$doExecute$1(SortExec.scala:119)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)

I have tried persisting dataframe even did a count before writing but only write fails. Here output datasize is 500GB and I have defined repartition number as 1000 before writing. Any help is appreciated as I am stuck with this issue.