[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129260 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) + * [Additional Types of Policies](#Policy_Types) + * [BlockPlacementPolicyRackFaultTolerant](#Block_PlacementPolicy_RackFaultTolerant) + * [BlockPlacementPolicyWithNodeGroup](#BlockPlacementPolicy_With_NodeGroup) + * [BlockPlacementPolicyWithUpgradeDomain](#BlockPlacementPolicy_With_UpgradeDomain) Review comment: whitespace:tabs in line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129263 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) + * [Additional Types of Policies](#Policy_Types) + * [BlockPlacementPolicyRackFaultTolerant](#Block_PlacementPolicy_RackFaultTolerant) + * [BlockPlacementPolicyWithNodeGroup](#BlockPlacementPolicy_With_NodeGroup) + * [BlockPlacementPolicyWithUpgradeDomain](#BlockPlacementPolicy_With_UpgradeDomain) + +##Introduction +By default HDFS supports BlockPlacementPolicyDefault. Where one block on local and copy on 2 different nodes of same remote rack. Additional to this HDFS supports 3 different pluggable block placement policies. Users can choose the policy based on their infrastructre and use case. This document describes the detailed information about the type of policies with its use cases and configuration. + + +### BlockPlacementPolicyRackFaultTolerant + +BlockPlacementPolicyRackFaultTolerant can be used to split the placement of blocks across multiple rack.By default with replication of 3 BlockPlacementPolicyDefault will put one replica on the local machine if the writer is on a datanode, otherwise on a random datanode in the same rack as that of the writer, another replica on a node in a different (remote) rack, and the last on a different node in the same remote rack. So totally 2 racks will be used, in sceneraio like 2 racks going down at the same time will cause data inavailability where using BlockPlacementPolicyRackFaultTolerant will helop in placing 3 blocks on 3 different racks. +https://issues.apache.org/jira/browse/HDFS-7891 + + + +Configration + +hdfs-site.xml + +```xml + + dfs.block.replicator.classname + org.apache.hadoop.hdfs.server.namenode.BlockPlacementPolicyRackFaultTolerant + +``` + + +### BlockPlacementPolicyWithNodeGroup + +With new 3 layer hierarchical topology, a node group level got introduced, which maps well onto a infrastructure that is based on a virtulized environment. In Virtualized environment multiple vm's will be hosted on same physical machine. Vm's on the same physical host are affected by the same hardware failure. So mapping the physical host a node groups this block placement gurantees that it will never place more than one replica on the same node group (physical host), in case of node group failure, only one replica will be lost at the maximum. Review comment: whitespace:end of line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129216 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) + * [Additional Types of Policies](#Policy_Types) Review comment: whitespace:tabs in line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129199 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) Review comment: whitespace:tabs in line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129229 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) + * [Additional Types of Policies](#Policy_Types) + * [BlockPlacementPolicyRackFaultTolerant](#Block_PlacementPolicy_RackFaultTolerant) Review comment: whitespace:tabs in line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[GitHub] [hadoop] hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc
hadoop-yetus commented on a change in pull request #1562: HDFS-14546-Block Placement Policy Doc URL: https://github.com/apache/hadoop/pull/1562#discussion_r330129245 ## File path: hadoop-hdfs-project/hadoop-hdfs/src/site/markdown/HdfsBlockPlacementPolicies.md ## @@ -0,0 +1,98 @@ + + +BlockPlacementPolicies +== +* [Block Placement Policies](#Block_Placement_Policies) + * [Introduction](#Introduction) + * [Additional Types of Policies](#Policy_Types) + * [BlockPlacementPolicyRackFaultTolerant](#Block_PlacementPolicy_RackFaultTolerant) + * [BlockPlacementPolicyWithNodeGroup](#BlockPlacementPolicy_With_NodeGroup) Review comment: whitespace:tabs in line This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
