Are you on Linux? We have seen this pattern (user/sys time low and real
time high in GC time) before. In our case, the problem was due to disk
I/Os. When there are lots of dirty pages (in our case, this is caused by
log4j logging), Linux can draft user threads (in this case GC threads) to
flush the
Hi again!
I've been having this issue consistently since I first started this thread,
but it was happening infrequently enough for me to brush it aside and just
run an election to rebalance brokers.
I recently expanded (and reinstalled) our Kafka cluster so that it now has
4 brokers with a defaul
Jun,
let me see if I can fix first and then will submit back.
Daniel,
I was looking at the code some more and was thinking this might work
https://github.com/apache/kafka/blob/0.8.1/perf/src/main/scala/kafka/perf/ProducerPerformance.scala
on line 246 instead of looping to create messages I co
There are a couple of things you can try.
1. See if broker 1 and 2 are indeed registered in ZK (see Broker
registration info in
https://cwiki.apache.org/confluence/display/KAFKA/Kafka+data+structures+in+Zookeeper
).
2. Does restarting broker 1 and 2 solve the issue?
Thanks,
Jun
On Tue, Jul 1
