Hi all, Now, we are running the benchmark of Hive +Tez+LLAP and Apache Tez in TPC-DS with 3TB orc data. But the result of Hive +Tez+LLAP is almost similar with hive+Tez and some queries may be poorer than hive+tez .
The following is our cluster and llap configuration, Cluster: 1 master + 7 slave Yarn configuration: yarn.nodemanager.resource.memory-mb 235520(230g) yarn.nodemanager.resource.cpu-vcores 81 LLAP configuration: hive --service llap --name llap_service --instances 7 --size 210g --xmx 180g --loglevel INFO --cache 20g --iothreads 81 --executors 81 --slider-am-container-mb 4096 --args " -XX:+UseG1GC -XX:+ResizeTLAB -XX:+UseNUMA -XX:-ResizePLAB -Xmx180g" Software version Hadoop: hadoop-2.7.3 Hive: hive-2.2.0 JDK: 1.8.0_112 Please help us find whether we use the wrong configuration. Thanks for your help. Regards, Jia Ke