I currently have 2 clusters, each with 4 data nodes.
All nodes are VMs, running Ubuntu 16.04.
Each data node has a 2TB disk allocated to it.
Would it be better to setup one logical LUN for all the nodes to talk to, e.g. an 8TB disk or leave them with their own assigned disk?
You'd need to test really, cause it'll depend on the hardware.
I'd just use one per node.
Ok. All VMs with SAN storage. Didn't know if ES would prefer all the same logical target over separate logical targets.
ES doesn't really care about that level. If it's a slow SAN, it's a slow SAN.
It depends on your data volume and growth how you can balance between cost and performance. For ongoing operations, you should be able to provide an I/O subsystem with very low latency and high IOPS. Elasticsearch is very sensitive to this. For my relatively small data set of 1 TB, VM or SAN is always second choice. I prefer the physical machine with custom file system setup on tier 0 or tier 1 storage (preferably SSD) for maximum performance.
Yea, my setup is all VM servers but SSD storage.
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.