mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Sean Owen <sro...@gmail.com>
Subject Re: Server sizing Hadoop + Mahout
Date Wed, 30 May 2012 10:17:47 GMT
You haven't even said what algorithm. It even depends on the distribution
of your data, in addition to amount, not to mention the type of servers,
configuration, etc. It's impossible to give a meaningful baseline. You can
run your real data on a real cluster to get some notion. Run-time and
requirements generally scale up linearly.

On Wed, May 30, 2012 at 10:32 AM, jcuencaa
<jordi.cuenca.aubets@everis.com>wrote:

> Hello!
> I need to do a capacity planning or a server sizing for a Mahout + Hadoop
> server, it means, plan how many servers and hardware (CPU, memory, etc.) do
> I need to accomplish with the maximum amount of work that my organization
> requires in a given period.
> I haven’t found documentation regarding to this in the Mahout or Hadoop
> site
> or, at least, which things should be taken into account for doing the
> server
> sizing. It’s obvious that sizing depends on many factors but, in example,
> in
> Application servers or Web Servers normally sizing is done inferring
> hardware needs using some benchmarks as a baseline.
> So I’d be pleased if someone can help me.
> Thanks in advance.
>
>
> --
> View this message in context:
> http://lucene.472066.n3.nabble.com/Server-sizing-Hadoop-Mahout-tp3986807.html
> Sent from the Mahout User List mailing list archive at Nabble.com.
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message