I would be also very interested in node level shard results reduction but not for scalability but precision reasons. I would like to have an option for a node to do complete aggregations on its shards so the results are exact rather than approximate. There are many use cases when corpus of data is reltively small to fit one powerful node and exactness is a MUST. With 48 core servers and ssd drives such node can process good deal of data and produce exact results which is a must for traditional datamart-like apps. Having this option will allow for this class of apps to be built. And in myltinode setup it wull provide better precision too
-- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to elasticsearch+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/d3fb8f8d-4563-4e97-b0fd-3cc220f252bc%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.