HI! We have a three node cluster on three servers. According to this article we can benefit from running the second node on one of our machines:
Are you doing a lot of sorting/aggregations on analyzed strings (e.g. for word-tags, or SigTerms, etc)? Unfortunately that means you’ll need fielddata, which means you need heap space. Instead of one node with more than 512 GB of RAM, consider running two or more nodes on a single machine.
Is it possible to have this architecture (4 nodes on 3 servers)?