Soam Vasani
7d1058d7be
GenericPool is a pool of generic containers for an environment. GenericPoolManager keeps track of all GenericPools, creating them on-demand. The pool manager API is simply a "lookup" for the service URL of a function. If one exists it is returned immediately; otherwise, a generic pool is created, and then a pod is specialized from that pool. poolmgr is designed to run from within the cluster, since it connects to pod IP addresses directly. This is a first cut with many pieces missing. TODO: * Use versioned kubernetes clients instead of the unversioned one * Unit tests for GenericPoolMgr; improve unit test for GenericPool; test for API. * Handle cases where a service exists but pod backing it has failed. * On start up, use existing deployments/pods/services if they exist; in other words don't orphan resources on restart. * Kill idle resources (services, pods, even generic pools) * Autoscale generic pool (for example, by watching num ready pods)
Fission
Fission is a fast serverless framework for Kubernetes with a focus on developer productivity and high performance.
It's heavily customizable (but with sensible defaults), extensible to any language, and interoperates well with other infrastructure.
You can create and edit functions throughs a web UI, or you can use your favorite editor and upload them using a CLI. You can trigger these functions via HTTP requests to paths, or by timers.
Try it out at http://demo.example.com
Running Fission
On your own Kubernetes cluster
Setup Kubernetes
https://github.com/kubernetes/minikube
Get and Run Fission
$ wget http://example.com/fission.yaml $ kubectl create -f fission.yaml
Status
Fission is in early alpha.
Performance
The goal is to have less than 1 second latency for requests that don't have a running instance. In practice, benchmarks show this latency at TODO msec for the NodeJS environment.
Here's a simple hello world benchmark on NodeJS: TODO. It achieves TODO requests per second on a TODO-node Kubernetes cluster.
Contributions
TODO