One usual reason for region servers to shut down is because of garbage collecting taking way too long. Please have a look at http://wiki.apache.org/hadoop/PerformanceTuning
Also did you make sure that you changed the number of maximum file descriptors on your machines? What are those configurations you tried? Thx, J-D On Sat, May 23, 2009 at 5:17 PM, llpind <[email protected]> wrote: > > I see similar behavior in my small cluster. (1 master, 3 datanodes) > > I am also planning on trying this RC version. I've tried various > configurations, and I continue to lose Regions with intensive writes. I > really hope something like this will work, because we are starting to > consider other options now. > > -- > View this message in context: > http://www.nabble.com/HBase-looses-regions.-tp23657983p23688361.html > Sent from the HBase User mailing list archive at Nabble.com. > >
