All of the nodes appear to be out of file handles. When using LevelDB,
did you try setting {max_open_files, 20} (or some such) to ensure you
didn't exceed available ulimit -n? (This will be the default in RC2).D. On Fri, Sep 23, 2011 at 8:01 AM, Phil Sorber <[email protected]> wrote: > Here are the logs from all 4 machines. > > On Fri, Sep 23, 2011 at 7:47 AM, David Smith <[email protected]> wrote: >> On Thu, Sep 22, 2011 at 7:07 PM, Phil Sorber <[email protected]> wrote: >>> >>> From watching top when the nodes crashed, it looked IO related. The IO >>> wait went up and then there was only one thread of beam.smp running >>> and it was using 100% CPU. Sometimes the nodes would recover after the >>> benchmark was stopped, sometimes one or two nodes would completely >>> crash. riak, not the OS. >> >> Hi Phil, >> >> Do you have any log files, core files or other backtrace information >> from the crash? It's a little hard to have anything of substance to >> say without more context. :) >> >> Thanks, >> >> D. >> >> -- >> Dave Smith >> Director, Engineering >> Basho Technologies, Inc. >> [email protected] >> > -- Dave Smith Director, Engineering Basho Technologies, Inc. [email protected] _______________________________________________ riak-users mailing list [email protected] http://lists.basho.com/mailman/listinfo/riak-users_lists.basho.com
