Howdy. You do not need torque. It's not even helpful, as far as I know. You don't need a database, but if you don't have one, you'd probably need to do a bit more work to analyze the collected data in HDFS. If you were going to be using MapReduce for analysis anyway, that's probably a non-issue for you.
We're working on documentation, but it's sort of chasing a moving target, since the Chukwa codebase and configuration interfaces are still in flux. --Ari On Tue, Feb 3, 2009 at 5:00 PM, <xavier.quint...@orange-ftgroup.com> wrote: > Hi Everybody, > > I don't know if there is a mail list for Chukwa so I apologies in > advance if this is not the right place to ask my questions. > > I have the following questions and comments: > > It was simple the configuration of the collector and the agent. > However, there is other features that are not documented it all like: > - torque (Do I have to install torque before? Yes? No? and Why?), > - database, (Do I have to have a DB?) > -what is queueinfo.properties, which kind of information provides me? > -and there is more stuff that I need to dig in the code to understand. > Could somebody update the documentation from Chukwa?. > -- Ari Rabkin asrab...@gmail.com UC Berkeley Computer Science Department