Hacker News Reader

All benchmarks are biased because nobody does the same level of config tuning on different databases. But this GigaOm/Microsoft one is a joke. They run Citus with no replication on 12x16+1x32 vCores and the others on 14x16 vCPU (so 14x8 cores) with replication factor 3.

View on HN

Without good benchmarks it's hardly possible to compare different products.

But I agree that this benchmarks seems questionable at best then. I usually only work with on-premise deployments, so I don't know the details of all the cloud offerings. People will probably judge products on what is available on the first few search results though.

Reply on news.ycombinator.com