On Tue, Apr 9, 2013 at 4:41 AM, Bing Jiang <[EMAIL PROTECTED]> wrote:
> There are some physical machines which each one contains a large ssd(2T)
> and general disk(4T),
> and we want to build our hdfs and hbase environment.
What kind of workload do you intend to run on these machines? Do you have
enough space running all of your work load on SSD? At an extreme, you
could have two clusters -- one running on SSDs for low latency workloads
and the other on spinning disk -- and perhaps your segregation is such that
having to copy between the two systems is rare, etc., etc.