Sorry for the layman question.
Whats the best way of writing data into HDFS from outside of the cluster. My
customer is looking for wire speed data ingest into HDFS. We are
considering flume, but initial performance results from flume are very
discouraging.
Thanks in advance.
Steve
Sorry for this novice question. I am trying to find the best way of moving
(Copying) data in and out of HDFS. There are bunch of tools available and I
need to pick the one which offers the easiest way. I have seen MapR
presentation, who claim to offer direct NFS mounts to feed data into HDFS.
Is
u would need close to 170 servers with 12 TB disk
pack installed on them (with replication factor of 2). Thats a conservative
estimate
> CPUs: 4 cores with 16gb of memory
>
> Namenode: 4 core with 32gb of memory should be ok.
>
>
> On Fri, Oct 21, 2011 at 5:40 PM, Steve Ed
Did you ever considered keeping a backup copy of FSImage on a NFS share?
The best practice is to have a reliable NFS storage mounted on the namenode
and instruct the site-xml to keep a copy on the NFS mount. This will prevent
FSImage loss.
-Original Message-
From: Markus Jelsma [mailto:ma
I am a newbie to Hadoop and trying to understand how to Size a Hadoop
cluster.
What are factors I should consider deciding the number of datanodes ?
Datanode configuration ? CPU, Memory
Amount of memory required for namenode ?
My client is looking at 1 PB of usable data and will be