Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/13152#discussion_r75426147
--- Diff:
core/src/main/scala/org/apache/spark/storage/BlockReplicationPrioritization.scala
---
@@ -0,0 +1,80 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.storage
+
+import scala.util.Random
+
+import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.internal.Logging
+
+/**
+ * ::DeveloperApi::
+ * BlockReplicationPrioritization provides logic for prioritizing a
sequence of peers for
+ * replicating blocks. BlockManager will replicate to each peer returned
in order until the
+ * desired replication order is reached. If a replication fails,
prioritize() will be called
+ * again to get a fresh prioritization.
+ */
+@DeveloperApi
+trait BlockReplicationPrioritization {
+
+ /**
+ * Method to prioritize a bunch of candidate peers of a block
+ *
+ * @param blockManagerId Id of the current BlockManager for self
identification
+ * @param peers A list of peers of a BlockManager
+ * @param peersReplicatedTo Set of peers already replicated to
+ * @param blockId BlockId of the block being replicated. This can be
used as a source of
+ * randomness if needed.
+ * @return A prioritized list of peers. Lower the index of a peer,
higher its priority
+ */
+ def prioritize(
+ blockManagerId: BlockManagerId,
+ peers: Seq[BlockManagerId],
+ peersReplicatedTo: Set[BlockManagerId],
+ blockId: BlockId): Seq[BlockManagerId]
+}
+
+@DeveloperApi
+class DefaultBlockReplicationPrioritization
+ extends BlockReplicationPrioritization
+ with Logging {
+
+ /**
+ * Method to prioritize a bunch of candidate peers of a block. This is a
basic implementation,
+ * that just makes sure we put blocks on different hosts, if possible
+ *
+ * @param blockManagerId Id of the current BlockManager for self
identification
+ * @param peers A list of peers of a BlockManager
+ * @param peersReplicatedTo Set of peers already replicated to
+ * @param blockId BlockId of the block being replicated. This can be
used as a source of
+ * randomness if needed.
+ * @return A prioritized list of peers. Lower the index of a peer,
higher its priority
+ */
+ override def prioritize(
+ blockManagerId: BlockManagerId,
--- End diff --
so the Spark style for indentation is to have 4 spaces for function
arguments, i.e.
```scala
override def prioritize(
blockManagerId: BlockManagerId,,
peers: Seq[BlockManagerId],
peersReplicatedTo: Set[BlockManagerId],
blockId: BlockId): Seq[BlockManagerId] = {
val random = new Random(blockId.hashCode)
...
}
```
---
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
