Github user tdas commented on a diff in the pull request:

    https://github.com/apache/spark/pull/2366#discussion_r18201230
  
    --- Diff: core/src/main/scala/org/apache/spark/storage/BlockManager.scala 
---
    @@ -787,31 +791,110 @@ private[spark] class BlockManager(
       }
     
       /**
    +   * Get peer block managers in the system.
    +   */
    +  private def getPeers(forceFetch: Boolean): Seq[BlockManagerId] = {
    +    peerFetchLock.synchronized {
    +      val cachedPeersTtl = conf.getInt("spark.storage.cachedPeersTtl", 60 
* 1000) // milliseconds
    +      val timeout = System.currentTimeMillis - lastPeerFetchTime > 
cachedPeersTtl
    +      if (cachedPeers == null || forceFetch || timeout) {
    +        cachedPeers = master.getPeers(blockManagerId).sortBy(_.hashCode)
    +        lastPeerFetchTime = System.currentTimeMillis
    +        logDebug("Fetched peers from master: " + cachedPeers.mkString("[", 
",", "]"))
    +      }
    +      cachedPeers
    +    }
    +  }
    +
    +  /**
        * Replicate block to another node.
        */
    -  @volatile var cachedPeers: Seq[BlockManagerId] = null
       private def replicate(blockId: BlockId, data: ByteBuffer, level: 
StorageLevel): Unit = {
    +    val maxReplicationFailures = 
conf.getInt("spark.storage.maxReplicationFailures", 1)
    +    val numPeersToReplicateTo = level.replication - 1
    +    val peersForReplication = new ArrayBuffer[BlockManagerId]
    +    val peersReplicatedTo = new ArrayBuffer[BlockManagerId]
    +    val peersFailedToReplicateTo = new ArrayBuffer[BlockManagerId]
         val tLevel = StorageLevel(
           level.useDisk, level.useMemory, level.useOffHeap, 
level.deserialized, 1)
    -    if (cachedPeers == null) {
    -      cachedPeers = master.getPeers(blockManagerId, level.replication - 1)
    +    val startTime = System.nanoTime
    +    val random = new Random(blockId.hashCode)
    +
    +    var replicationFailed = false
    +    var failures = 0
    +    var done = false
    +
    +    // Get cached list of peers
    +    peersForReplication ++= getPeers(forceFetch = false)
    +
    +    // Get a random peer. Note that this selection of a peer is 
deterministic on the block id.
    +    // So assuming the list of peers does not change and no replication 
failures,
    +    // if there are multiple attempts in the same node to replicate the 
same block,
    +    // the same set of peers will be selected.
    +    def getRandomPeer(): Option[BlockManagerId] = {
    +      // If replication had failed, then force update the cached list of 
peers and remove the peers
    +      // that have been already used
    +      if (replicationFailed) {
    +        peersForReplication.clear()
    +        peersForReplication ++= getPeers(forceFetch = true)
    +        peersForReplication --= peersReplicatedTo
    +        peersForReplication --= peersFailedToReplicateTo
    +      }
    +      if (!peersForReplication.isEmpty) {
    +        Some(peersForReplication(random.nextInt(peersForReplication.size)))
    +      } else {
    +        None
    +      }
         }
    -    for (peer: BlockManagerId <- cachedPeers) {
    -      val start = System.nanoTime
    -      data.rewind()
    -      logDebug(s"Try to replicate $blockId once; The size of the data is 
${data.limit()} Bytes. " +
    -        s"To node: $peer")
     
    -      try {
    -        blockTransferService.uploadBlockSync(
    -          peer.host, peer.port, blockId.toString, new 
NioByteBufferManagedBuffer(data), tLevel)
    -      } catch {
    -        case e: Exception =>
    -          logError(s"Failed to replicate block to $peer", e)
    +    // One by one choose a random peer and try uploading the block to it
    +    // If replication fails (e.g., target peer is down), force the list of 
cached peers
    +    // to be re-fetched from driver and then pick another random peer for 
replication. Also
    +    // temporarily black list the peer for which replication failed.
    +    //
    +    // This selection of a peer and replication is continued in a loop 
until one of the
    +    // following 3 conditions is fulfilled:
    +    // (i) specified number of peers have been replicated to
    +    // (ii) too many failures in replicating to peers
    +    // (iii) no peer left to replicate to
    +    //
    +    while (!done) {
    +      getRandomPeer() match {
    +        case Some(peer) =>
    +          try {
    +            val onePeerStartTime = System.currentTimeMillis
    +            data.rewind()
    +            logTrace(s"Trying to replicate $blockId of ${data.limit()} 
bytes to $peer")
    +            blockTransferService.uploadBlockSync(
    +              peer.host, peer.port, blockId.toString, new 
NioByteBufferManagedBuffer(data), tLevel)
    +            logTrace(s"Replicated $blockId of ${data.limit()} bytes to 
$peer in %f ms"
    +              .format((System.currentTimeMillis - onePeerStartTime) / 1e3))
    +            peersReplicatedTo += peer
    +            peersForReplication -= peer
    +            replicationFailed = false
    +            if (peersReplicatedTo.size == numPeersToReplicateTo) {
    +              done = true  // specified number of peers have been 
replicated to
    +            }
    +          } catch {
    +            case e: Exception =>
    --- End diff --
    
    Do you have sample code for that?


---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to