You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@nutch.apache.org by an...@orbita1.ru on 2006/08/18 08:22:51 UTC

some questions

I suggest to use nutch 0.8 on several computers with DFS. But I'm worried
about nutch's requirements to HDD free space.

For example, suppose I have

1)     server with job tracker and namenode
2)     5 servers with task trackers and 20 Gb HDDs
3)     5 servers with datenode and 20 Gb HDDs also (DFS, the replication
will be equal 1)

There are some questions:

1) Is this HDD space enough to run task trackers?

2) How to calculate the approximate free HDD space needed for servers with
task trackers, servers with with job trackers and name node?

3) Will I be able to increase the data storage space while increasing the
number of servers with date node? Or will it not be enough to increase the
number of date nodes?