See the details on: https://issues.apache.org/jira/browse/CASSANDRA-11363
You may need to add -Dcassandra.max_queued_native_transport_requests=4096 as a startup parameter. YMMV though, I suggest reading through the above to get a complete picture. On Mon, Mar 20, 2017 at 11:10 PM, Roland Otta <roland.o...@willhaben.at> wrote: > > well. i checked it now. > > we have some stw collections from 100 to 200ms every 5 to 60 seconds. > i am not sure whether the blocked threads are related to that but anyway these pauses are too long for low latency applications. > > so i wil check gc tuning first and will check afterwards whether the blocked threads still exist afterwards. > > > > On Mon, 2017-03-20 at 08:55 +0100, benjamin roth wrote: > > Did you check STW GCs? > You can do that with 'nodetool gcstats', by looking at the gc.log or observing GC related JMX metrics. > > 2017-03-20 8:52 GMT+01:00 Roland Otta <roland.o...@willhaben.at>: > > we have a datacenter which is currently used exlusively for spark batch > jobs. > > in case batch jobs are running against that environment we can see very > high peaks in blocked native transport requests (up to 10k / minute). > > i am concerned because i guess that will slow other queries (in case > other applications are going to use that dc as well). > > i already tried increasing native_transport_max_threads + > concurrent_reads without success. > > during the jobs i cant find any resource limitiations on my hardware > (iops, disk usage, cpu, ... is fine). > > am i missing something? any suggestions how to cope with that? > > br// > roland > > > > > -- ----------------- Nate McCall Wellington, NZ @zznate CTO Apache Cassandra Consulting http://www.thelastpickle.com
