hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Konstantin Shvachko (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-8999) Namenode need not wait for {{blockReceived}} for the last block before completing a file.
Date Tue, 22 Dec 2015 20:24:46 GMT

    [ https://issues.apache.org/jira/browse/HDFS-8999?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15068676#comment-15068676
] 

Konstantin Shvachko commented on HDFS-8999:
-------------------------------------------

Before commenting on suggested solutions let me ask the following questions:
# Has anybody tried to run the same workload on the same size cluster with a version of HDFS
that has HDFS-1172 in it?
Again, HDFS-1172 reduced the replication load on NN in extreme case (1-block files) by a factor
of at least 2. Did it help?
# Has anybody tried to set minimum replication to 0 on the same size cluster? Did it help?
Asking this, because it is easy to change configuration, while the performance will be the
same as with the discussed proposal.
So if the config change doesn't help the proposed change won't help either.
# Does anybody have material estimates on scalability gains with this fix?

> Namenode need not wait for {{blockReceived}} for the last block before completing a file.
> -----------------------------------------------------------------------------------------
>
>                 Key: HDFS-8999
>                 URL: https://issues.apache.org/jira/browse/HDFS-8999
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: namenode
>            Reporter: Jitendra Nath Pandey
>            Assignee: Tsz Wo Nicholas Sze
>
> This comes out of a discussion in HDFS-8763. Pasting [~jingzhao]'s comment from the jira:
> {quote}
> ...whether we need to let NameNode wait for all the block_received msgs to announce the
replica is safe. Looking into the code, now we have
>    # NameNode knows the DataNodes involved when initially setting up the writing pipeline
>    # If any DataNode fails during the writing, client bumps the GS and finally reports
all the DataNodes included in the new pipeline to NameNode through the updatePipeline RPC.
>    # When the client received the ack for the last packet of the block (and before the
client tries to close the file on NameNode), the replica has been finalized in all the DataNodes.
> Then in this case, when NameNode receives the close request from the client, the NameNode
already knows the latest replicas for the block. Currently the checkReplication call only
counts in all the replicas that NN has already received the block_received msg, but based
on the above #2 and #3, it may be safe to also count in all the replicas in the BlockUnderConstructionFeature#replicas?
> {quote}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message