Alex Bordei (@alexandrubordei), our Product Manager has benchmarked Elasticsearch on a wide range of Full Metal Clusters, in order to find the infrastructure setup that provides the best price/performance.
We went from clusters of just 2 very powerful Full Metal Compute Instances (192 GB RAM) to clusters with 14 small instances (8 GB RAM) – and tested pretty much everything in between.
This presentation summarizes our most interesting findings. It really might help you make better decisions about the architecture of your Elasticsearch cluster, as it shows how Elasticsearch scales vertically and horizontally and when it might be worth it to do either.
If you have any questions, let us know and we’ll do our best to answer.