Thanks @nkumar for your response. I have reverted my changes because there was no point in turning it ON as In-Memory Cache per Daemon was 0. I have a 5 node heterogeneous cluster hence I allocated 2 nodes (Name Nodes) to be used by LLAP, I do not know how to configure number of llap daemons. I have HiveServer2 Heap Size =16GB and can increase it to 250GB. Metastore Heap Size = 2048 and again the same can be increased to 250GB and Client Heap Size=4096 and again the same can be increased to 250GB. max memory for yarn container = 250GB, currently allocated 190GB for Node 1, 100GB for Node 2 and 60GB for the others. I created an additional queue following the llap sizing and setup document but it did not help. I even set up seperate node 1 and 2 configs in Hive and Yarn. But it is not transfering the additional horsepower even I assign the new queue to the node 1 configuration(which has 250GB), it is still showing Memory per Daemon - 53248 and In-Memory Cache per Daemon - 0 Any help would be appreciated ... View more

@Vinicius Higa Murakami, any help bud? ... View more

Hi @Vinicius Higa Murakami, I am enclosing the explain plan for the long running query. We have turned CBO on, however the explain plan is not using CBO , not sure why? explain-plan.txt ... View more

Hi @Vinicius Higa Murakami, - We are running TEZ but no llap as we have large data sets to crunch and we observed that the queries would just hang. - We are definitely using mapJoin, however I am not sure about Vertex Enable -- However if we look at the DAG details for TEZ queries, it does create multiple Vertices. - We have turned on CBO and we do run stats on our tables - We have a single partition on all our tables - All our HIVE tables are stored in the Parquet fileformat (Additionally- If you see our configuration, our edge node has only 4 cores and has 47GB RAM and also has the YARN client services. Could this be a possible bottleneck ?. Plz advise. ) Thanks for responding _/\_ ... View more