News for hackers. Stuff that matters.
Re:Caddy 0.10 Released by shawabawa3 on Friday April 21, 2017 @09:03AM (#14165162)
I use it exclusively as a proxy server.

I've never noticed any performance issues, I think I saw a benchmark where it said caddy can handle 2000req/s, which is at least an order of magnitude or 2 faster than any upstream service I've used it in front of.

Re:Caddy 0.10 Released by coldtea on Friday April 21, 2017 @09:25AM (#14165329)
>I think I saw a benchmark where it said caddy can handle 2000req/s

Those are application level numbers (e.g. with logic and all).

Caddy should be able to handle an order of magnitude more req/s than that easily.

Re:Caddy 0.10 Released by anc84 on Friday April 21, 2017 @10:20AM (#14165815)
Re:Caddy 0.10 Released by shawabawa3 on Friday April 21, 2017 @12:24PM (#14166950)
yeah, I clearly misremembered the benchmark

It was slightly slower than nginx, but not enough to impact typical applications

Re:Caddy 0.10 Released by StreamBright on Friday April 21, 2017 @10:10AM (#14165746)
2000 req/s is tragic. We have services with 100 000req/s so i need a reverse proxy with at least 500 000 req/s. What is the reason of this low performance?
Re:Caddy 0.10 Released by StreamBright on Friday April 21, 2017 @02:31PM (#14168057)
I am not sure why this is getting downvoted, care to explain?
Re:Caddy 0.10 Released by MichaelGG on Friday April 21, 2017 @05:21PM (#14169519)
My guess: At 500Krps on a single proxy you're probably using 40GbE or higher right? So you're a fairly niche user and should have some sort of in-depth knowledge of this space. Your current setup should already some sort of horizontal scaling system in place. Just throwing out you "need" a 500Krps came across as fake boasting/clueless/whiny.

I'm sure HN would love a more in-depth comment where you say how you're accomplishing things today and what you expect out of general purpose reverse proxies, etc.

Re:Caddy 0.10 Released by StreamBright on Saturday April 22, 2017 @04:13AM (#14171617)
If your HTTP request size is 2048 bytes and the RPS is 500000 we get 1024000000 bytes / sec that is ~ 8 Gbit/s, lets say with overhead we are hovering around 10Gbit/s. Based on the response size you can do similar calculation. As you can see in the TechEmpower benchmarks frameworks with 3M+ req/s are not uncommon.

https://www.techempower.com/benchmarks/#section=data-r12&hw=...

This is on Dell R720xd dual-Xeon E5 v2 + 10 GbE. Now if I chose technology that cuts this performance 200x times I am wasting resources.

I like to idea of Caddy but before we can consider using it in production I need to make sure it can keep up with the performance requirement we got.

Re:Caddy 0.10 Released by MichaelGG on Saturday April 22, 2017 @12:13PM (#14173168)
Yeah but as a proxy you need to add the request and response and you get that much full duplex. Those numbers are also with pipelining returning a tiny static response - basically as close to a TCP echo test as you can get.