Github user chenghao-intel commented on a diff in the pull request:

    https://github.com/apache/spark/pull/10225#discussion_r48699693
  
    --- Diff: 
core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala ---
    @@ -53,35 +53,98 @@ private[spark] class DiskBlockManager(blockManager: 
BlockManager, conf: SparkCon
     
       private val shutdownHook = addShutdownHook()
     
    +  private abstract class FileAllocationStrategy {
    +    def apply(filename: String): File
    +
    +    protected def getFile(filename: String, storageDirs: Array[File]): 
File = {
    +      require(storageDirs.nonEmpty, "could not find file when the 
directories are empty")
    +
    +      // Figure out which local directory it hashes to, and which 
subdirectory in that
    +      val hash = Utils.nonNegativeHash(filename)
    +      val dirId = localDirs.indexOf(storageDirs(hash % storageDirs.length))
    +      val subDirId = (hash / storageDirs.length) % subDirsPerLocalDir
    +
    +      // Create the subdirectory if it doesn't already exist
    +      val subDir = subDirs(dirId).synchronized {
    +        val old = subDirs(dirId)(subDirId)
    +        if (old != null) {
    +          old
    +        } else {
    +          val newDir = new File(localDirs(dirId), "%02x".format(subDirId))
    +          if (!newDir.exists() && !newDir.mkdir()) {
    +            throw new IOException(s"Failed to create local dir in 
$newDir.")
    +          }
    +          subDirs(dirId)(subDirId) = newDir
    +          newDir
    +        }
    +      }
    +
    +      new File(subDir, filename)
    +    }
    +  }
    +
       /** Looks up a file by hashing it into one of our local subdirectories. 
*/
       // This method should be kept in sync with
       // 
org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getFile().
    --- End diff --
    
    We need to sync up the 
`org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getFile()`, so 
this feature can also be used within the external shuffle service in dynamic 
allocation of yarn.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to