[argonium]

I've been following these benchmarks for some time, and am always shocked that Spring does so poorly (it's 7% here). I haven't had any performance issues with Spring in production, so these benchmarks are puzzling. Are the other frameworks really that much faster in practice?

[christophilus]

What kind of traffic do you see in production? Rails gets hammered in these benchmarks, but does just fine for most companies' requirements. It's pretty rare that you'd actually need to eke out the raw numbers that the top contenders get. I'm of the opinion that-- within reason-- developer ergonomics, and ability to quickly solve business problems are more important than raw performance, so long as performance is good enough by some agreed upon metric.

[argonium]

Good point. Thanks for the feedback. Our sites don't get a huge amount of traffic, so it's possible Spring doesn't have as good a concurrency story (or it's due to memory usage) as the higher-ranked frameworks, so it's been sufficient for our needs.

[atonse]

Yep I feel the same about Elixir and Phoenix. It's way down but again, the "way down" is 20k requests per second. Not too shabby. The biggest project I've worked on had 50 requests per second, and that was an E-Commerce site that brought in 9 figures a year in revenue.

I'm sure IoT workflows are mainly where you start to see these more insane RPS numbers. But still, this just tells me there's so much great choice out there for pretty much any platform you want to stick with.

I'd love to see another metric that normalizes between Cloud and Physical, like $ per request. We don't know how much the cloud server cost vs the physical, do we? I mean it's a 10x difference in performance, is it a 10x difference in price?

Update: Azure D2v3 instances (used for the cloud benchmark) are about $55 a month. ($660 a year).

Just the Xeon in the physical costs $1,500. The full server probably costs $5k? So assuming a server has a life of 3 years, you're looking at the Azure instance being $1,980, the Dell being maybe $5k? So it's about 10x performance for 3x the price.

Someone please fix my math and fill in the gaps :)

[alefteris]

I wonder how a Spring WebFlux [1] variant of the spring benchmark would perform in comparison. Also the spring benchmark has been updated to use a recent spring boot release about a month ago [2]. Before that it was using spring boot 1.3.5.

[1] https://docs.spring.io/spring/docs/current/spring-framework-... [2] https://github.com/TechEmpower/FrameworkBenchmarks/commits/m...