yaronhaviv

check: https://github.com/nuclio/nuclio high-perf serverless runs over (standalone) docker or Kubernetes or Cloud services

Great idea, we suggested to create an open benchmark at CNCF, a bunch of members opposed, we can come with a joint proposal. You can use our test tool https://github.com/v3io/http_blaster, it can generate a workload of > 600K http req/sec with one client and is programable.

I benchmarked all the frameworks in cold & warm, Warm is also very slow, no concurrency etc'. how many events/sec can u do with a warm Riff instance e.g. in Go & Py? whats the latency?

nuclio is using a real-time arch (no context switch, zero copy, no Ser/Des, parallelism, .. ) Go function serves 400K events/sec/proc, Py does 70K events/sec/proc, this is faster than running your own function with standard HTTP serving on a bare-metal server.

for comparison most serverless frameworks do 1-5k events/sec and up to 100x higher latency.

disclosure: i work on nuclio

nuclio auto-scale today (use k8s HPA), the roadmap item is to scale-down to zero (today holds one instance when idle and will soon be able to shut it down when idle).

nuclio latency is as low as 30 microsec in Py & Go vs 10s of milisec in Lambda

to some extent in the detailed arch: https://github.com/nuclio/nuclio/blob/master/docs/architectu... The point is that there is a lot of parallelism, reduced locks and context switches, zero-copy and buffer reuse (less GC), async IO, Etc. things that most developers wont implement (unless they are perf optimization savvy), so you get that for free and can run 400K events/sec on a process using standard server (with Go functions)

Kennu, projects like OpenStack & Cloud Foundry struggle doing 10% of AWS. unlike AWS & Azure, OSS doesn't have central control. if we learn from Linux the stack is composed of many independent elements (storage, networking, configuration, security, ..) and the way they all work together is because the community agreed on abstractions/APIs between those elements. that's what i suggested in my post, in most cases linux can have few file systems, few protocols, .. since in an open environments people can innovate, but all those adhere to the layers & APIs of the stack

BTW the problem is that you use AWS APIs in small scale, than you grow and have to pay quite a bit to AWS, and its too hard to move to the half-baked open source frameworks

Yaron Haviv (iguazio)