[
https://issues.apache.org/jira/browse/HADOOP-14319?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ravi Prakash resolved HADOOP-14319.
-----------------------------------
Resolution: Invalid
Please send your queries to hdfs-user mailing list.
https://hadoop.apache.org/mailing_lists.html
To answer your query please look at dfs.namenode.replication.max-streams ,
dfs.namenode.replication.max-streams-hard-limit,
dfs.namenode.replication.work.multiplier.per.iteration etc.
> Under replicated blocks are not getting re-replicated
> -----------------------------------------------------
>
> Key: HADOOP-14319
> URL: https://issues.apache.org/jira/browse/HADOOP-14319
> Project: Hadoop Common
> Issue Type: Bug
> Affects Versions: 2.7.2
> Reporter: Anil
>
> Under replicated blocks are not getting re-replicated
> In production Hadoop cluster of 5 Manangement + 5 Data Nodes, under
> replicated blocks are not re-replicated even after 2 days.
> Here is quick view of required configurations;
> Default replication factor: 3
> Average block replication: 3.0
> Corrupt blocks: 0
> Missing replicas: 0 (0.0 %)
> Number of data-nodes: 5
> Number of racks: 1
> After bringing one of the DataNodes down, the replication factor for the
> blocks allocated on the Data Node became 2. It is observed that, even after 2
> days the replication factor remains as 2. Under replicated blocks are not
> getting re-replicated to another DataNodes in the cluster.
> If a Data Node goes down, HDFS will try to replicate the blocks from Dead DN
> to other nodes and the priority. Are there any configuration changes to speed
> up the re-replication process for the under replicated blocks?
> When tested for blocks with replication factor 1, the re-replication happened
> to 2 overnight in around 10 hours of time. But blocks with 2 replication
> factor are not being re-replicated to default replication factor 3.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-dev-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-dev-h...@hadoop.apache.org
