Hey Druids. By my understanding : a broker http (jetty) thread receives query and then passes execution of to worker thread which further passes the same to historical jetty further to historical worker thread. The jetty threads remain active while its worker thread remains active. Thus IMO number of jetty threads active are an indication of number of worker threads being used. When viewing our Druid metrics on Datadog we see historical jetty threads active as : Broker generally 2 Historical 1 and 2 generally 6 each Does this mean we are only serving 2 queries at a time? Because that seems pretty incorrect as querying logic sends multiple queries at a time just for 1 visualisation. Our thread configurations are Broker: druid_broker_http_numConnections: 40 druid_processing_numMergeBuffers: 10 #Should be equal to numMergeBuffers in historical druid_server_http_numThreads: 45 Historical druid_processing_numMergeBuffers: 10 druid_segmentCache_numLoadingThreads: 20 druid_segmentCache_numBootstrapThreads: 20 druid_server_http_numThreads: 60 We're using a query node of size : 2 Vcpus and 16GB ram and historicals of size : 16vcpus and 128 gb ram Our query node is also hosting a router service Kindly lemme know if this is an incorrect assessment or if my configurations seem incorrect. Any understanding of how to measure my query parallelism would be extremely appreciated.