[#HADOOP-5034] NameNode should send both replication and deletion requests to DataNode in one reply to a heartbeat

Hadoop Common

NameNode should send both replication and deletion requests to DataNode in one reply to a heartbeat

Created: 14/Jan/09 07:30 PM Updated: 08/Jul/09 04:43 PM

Return to search

Component/s:

None

Affects Version/s:

0.18.0

Fix Version/s:

0.19.1

Time Tracking:

Not Specified

File Attachments:

File Name	Date Attached	Attached By	Size
blockTransferInvalidate.patch	2009-01-21 09:12 PM	Hairong Kuang	12 kB
blockTransferInvalidate1.patch	2009-01-22 01:12 AM	Hairong Kuang	14 kB
blockTransferInvalidate2.patch	2009-01-26 08:04 PM	Hairong Kuang	9 kB
blockTransferInvalidate3.patch	2009-01-29 01:27 AM	Hairong Kuang	14 kB

Hadoop Flags:	Reviewed
Release Note:	This patch changes the DatanodeProtocoal version number from 18 to 19. The patch allows NameNode to send both block replication and deletion request to a DataNode in response to a heartbeat.
Resolution Date:	02/Feb/09 07:16 PM

Description

« Hide

Currently NameNode favors block replication requests over deletion requests. On reply to a heartbeat, NameNode does not send a block deletion request unless there is no block replication request.

This brings a problem when a near-full cluster loses a bunch of DataNodes. In react to the DataNode loss, NameNode starts to replicate blocks. However, replication takes a lot of cpu and a lot of replications fail because of the lack of disk space. So the administrator tries to delete some DFS files to free up space. However, block deletion requests get delayed for very long time because it takes a long time to drain the block replication requests for most DataNodes.

I'd like to propose to let NameNode to send both replication requests and deletion requests to DataNodes in one reply to a heartbeat. This also implies that the replication monitor should schedule both replication and deletion work in one iteration.

All

Comments

Work Log

Change History

Subversion Commits

Sort Order:

Repository	Revision	Date	User	Message
ASF	#740077	Mon Feb 02 19:03:12 UTC 2009	hairong	~~HADOOP-5034~~. NameNode should send both replication and deletion requests to DataNode in one reply to a heartbeat. Contributed by Hairong Kuang.
				Files Changed
				MODIFY /hadoop/core/trunk/src/test/org/apache/hadoop/hdfs/server/namenode/NNThroughputBenchmark.java MODIFY /hadoop/core/trunk/CHANGES.txt MODIFY /hadoop/core/trunk/src/hdfs/org/apache/hadoop/hdfs/server/namenode/NameNode.java MODIFY /hadoop/core/trunk/src/hdfs/org/apache/hadoop/hdfs/server/datanode/DataNode.java ADD /hadoop/core/trunk/src/test/org/apache/hadoop/hdfs/server/namenode/TestHeartbeatHandling.java MODIFY /hadoop/core/trunk/src/hdfs/org/apache/hadoop/hdfs/server/protocol/DatanodeProtocol.java MODIFY /hadoop/core/trunk/src/hdfs/org/apache/hadoop/hdfs/server/namenode/FSNamesystem.java

Repository	Revision	Date	User	Message
ASF	#740081	Mon Feb 02 19:10:30 UTC 2009	hairong	Merge -r 740076:740077 to move the change of ~~HADOOP-5034~~ from main t0 branch 0.19.
				Files Changed
				MODIFY /hadoop/core/branches/branch-0.19/src/hdfs/org/apache/hadoop/hdfs/server/protocol/DatanodeProtocol.java MODIFY /hadoop/core/branches/branch-0.19/src/hdfs/org/apache/hadoop/hdfs/server/namenode/FSNamesystem.java MODIFY /hadoop/core/branches/branch-0.19 MODIFY /hadoop/core/branches/branch-0.19/CHANGES.txt MODIFY /hadoop/core/branches/branch-0.19/src/hdfs/org/apache/hadoop/hdfs/server/namenode/NameNode.java MODIFY /hadoop/core/branches/branch-0.19/src/hdfs/org/apache/hadoop/hdfs/server/datanode/DataNode.java ADD /hadoop/core/branches/branch-0.19/src/test/org/apache/hadoop/hdfs/server/namenode/TestHeartbeatHandling.java (from /hadoop/core/trunk/src/test/org/apache/hadoop/hdfs/server/namenode/TestHeartbeatHandling.java)