hadoop-hdfs-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ravi Prakash <ravi...@ymail.com>
Subject Re: speed of replication for under replicated blocks by namenode
Date Tue, 13 May 2014 05:58:59 GMT

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi Chandra!

Replication is done according to priority (e.g. where only 1 block out
of 3 remains is higher priority than when only 2 out of 3 remain).
Every time a DN heartbeats into the NN, it *may* be assigned some
replication work according to some criteria. See
dfs.namenode.replication.work.multiplier.per.iteration .
The list of blocks that need to be replicated is calculated once every
dfs.namenode.replication.interval

HTH
Ravi

On 05/11/14 07:20, chandra kant wrote:
> Hi,
>
> Some of my blocks are under replicated. Can anybody tell me at what speed
> namenode replicates it so that dfs.replication factor is satisfied and
> blocks become normal again? Or does it solely depend upon load factor on
> namenode and it can't be measured accurately?
>
> thanx
> Chandra
>

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/
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=RCPv
-----END PGP SIGNATURE-----


Mime
View raw message