You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-dev@hadoop.apache.org by "dragon (JIRA)" <ji...@apache.org> on 2016/03/15 09:16:36 UTC
[jira] [Created] (HDFS-10106) CLONE - Erasure coding: fix priority
level of UnderReplicatedBlocks for striped block
dragon created HDFS-10106:
-----------------------------
Summary: CLONE - Erasure coding: fix priority level of UnderReplicatedBlocks for striped block
Key: HDFS-10106
URL: https://issues.apache.org/jira/browse/HDFS-10106
Project: Hadoop HDFS
Issue Type: Sub-task
Reporter: dragon
Assignee: Walter Su
Fix For: HDFS-7285
Issues 1: correctly mark corrupted blocks.
Issues 2: distinguish highest risk priority and normal risk priority.
{code:title=UnderReplicatedBlocks.java}
private int getPriority(int curReplicas,
...
} else if (curReplicas == 1) {
//only on replica -risk of loss
// highest priority
return QUEUE_HIGHEST_PRIORITY;
...
{code}
For stripe blocks, we should return QUEUE_HIGHEST_PRIORITY when curReplicas == 6( Suppose 6+3 schema).
That's important. Because
{code:title=BlockManager.java}
DatanodeDescriptor[] chooseSourceDatanodes(BlockInfo block,
...
if(priority != UnderReplicatedBlocks.QUEUE_HIGHEST_PRIORITY
&& !node.isDecommissionInProgress()
&& node.getNumberOfBlocksToBeReplicated() >= maxReplicationStreams)
{
continue; // already reached replication limit
}
...
{code}
It may return not enough source DNs ( maybe 5), and failed to recover.
A busy node should not be skiped if a block has highest risk/priority. The issue is the striped block doesn't have priority.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)