Hadoop副本选择机制

HDFS 上的文件对应的 Block 保存多个副本，且提供容错机制，副本丢失或者宕机自动恢复，默认是存 3 个副本。

2.8.x之前的副本策略

官方文档说明：

https://hadoop.apache.org/docs/r2.8.0/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html#Data_Replication

For the common case, when the replication factor is three, HDFS’s placement policy is to put one replica on one node in the local rack, another on a different node in the local rack, and the last on a different node in a different rack. This policy cuts the inter-rack write traffic which generally improves write performance. The chance of rack failure is far less than that of node failure; this policy does not impact data reliability and availability guarantees. However, it does reduce the aggregate network bandwidth used when reading data since a block is placed in only two unique racks rather than three. With this policy, the replicas of a file do not evenly distribute across the racks. One third of replicas are on one node, two thirds of replicas are on one rack, and the other third are evenly distributed across the remaining racks. This policy improves write performance without compromising data reliability or read performance.

第一副本：放置在上传文件的 DataNode 上；如果是集群外提交，则随机挑选一个磁盘不太慢、CPU 不太忙的节点。

第二副本：放置在与第一个副本相同的机架的节点上。

第三副本：与前二个副本不同机架的不同节点上。

如果还有更多的副本：随机放在节点上，同时需要保持每个机架的副本数低于上限，基本上是((replicas - 1) / racks + 2）。

因为 NameNode 不允许 DataNodes 拥有同一个 Block 的多个副本，所以能创建的最大副本数就是当时 DataNodes 的总数。

2.9.x之后及3.x的副本策略

官方文档说明：

https://hadoop.apache.org/docs/r3.0.0/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html#Data_Replication

https://hadoop.apache.org/docs/r2.9.0/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html#Data_Replication

For the common case, when the replication factor is three, HDFS’s placement policy is to put one replica on the local machine if the writer is on a datanode, otherwise on a random datanode, another replica on a node in a different (remote) rack, and the last on a different node in the same remote rack. This policy cuts the inter-rack write traffic which generally improves write performance. The chance of rack failure is far less than that of node failure; this policy does not impact data reliability and availability guarantees. However, it does reduce the aggregate network bandwidth used when reading data since a block is placed in only two unique racks rather than three. With this policy, the replicas of a file do not evenly distribute across the racks. One third of replicas are on one node, two thirds of replicas are on one rack, and the other third are evenly distributed across the remaining racks. This policy improves write performance without compromising data reliability or read performance.

第一副本：放置在上传文件的 DataNode 上；如果是集群外提交，则随机挑选一个磁盘不太慢、CPU 不太忙的节点。

第二副本：放置在与第一个副本不同的机架的节点上。

第三副本：与第二个副本相同机架的不同节点上。

如果还有更多的副本：随机放在节点上，同时需要保持每个机架的副本数低于上限，基本上是((replicas - 1) / racks + 2）。

因为 NameNode 不允许 DataNodes 拥有同一个 Block 的多个副本，所以能创建的最大副本数就是当时 DataNodes 的总数。