Well my requests are fully random so I expected to see them distributed quite evenly across all the regions. How can I know which datanode was hosting the .META. table? I'm not running the cluster currently so I cannot check this for the moment.
Thanks for your input! Thibault Dory On Fri, May 13, 2011 at 4:06 PM, Ted Yu <[email protected]> wrote: > HBase, even the trunk version, doesn't balance load measured by read > requests. > Its balancer tries to put equal number of regions on each server - as shown > in Figure 13. > Balancing by request count is the goal for next generation balancer. > > Did you remember whether client3 was also hosting .META. table ? > > Thanks > > On Fri, May 13, 2011 at 4:06 AM, Thibault Dory <[email protected] > >wrote: > > > Hello, > > > > I have written with a few other people a paper for the ACM Symposium > > On Cloud Computing. This paper describes the methodology, > > infrastructure and configuration used as well as the results obtained > > for elasticity and scalability of three noSQL databases, of wich > > HBase. The paper can be downloaded here : > > http://www.nosqlbenchmarking.com/wp-content/uploads/2011/05/paper.pdf< > > > http://www.google.com/url?sa=D&q=http://www.nosqlbenchmarking.com/wp-content/uploads/2011/05/paper.pdf > > > > > > > > > Any feedback on the methodology used would be appreciated, we would > > like to know if HBase is used in a "fair" way in those tests. > > > > We also encountered a problem with the distribution of requests among > > region > > servers. This problem is described in section 5.4.2 and any hints on how > to > > solve this problem would be appreciated. Please note that the request > > generation is independent of the specific database layer and that we did > > not > > observe this problem for the two other databases. > > > > Regards, > > > > Thibault Dory > > >
