Erika Hunhoff

Prepare to integrate new scheduler into apache/openwhisk-deploy-kube

6

## Description I am working on integrating the new scheduler into openwhisk-deploy-kube (see this draft PR [here](https://github.com/apache/openwhisk-deploy-kube/pull/729)). While most of the changes that need to be made are within the...

Ansible version inconsistency for Ubuntu setup

3

## Environment details: * Local Deployment * Ubuntu 18.04 ## Steps to reproduce the issue: 1. View documentation & scripts ## Provide the expected results and outputs: I was trying...

Deploy with new scheduler

1

What this PR contains: - Deploy etcd and the scheduler components - Allow option to enable or disable the scheduler (similar to ansible) - Akka cluster config setup for replicating...

The pull request under review to integrate the new scheduler (https://github.com/apache/openwhisk-deploy-kube/pull/729) creates a new etcd service as part of the helm deployment. Although internally some of the plumbing is there...

Discussion: Support Dedicated Invokers

1

There is a new(ish) feature of OpenWhisk to support dedicated invokers (https://github.com/apache/openwhisk/pull/5292), that is, the ability to specify an invoker (or invokers) to handle all activations made in a namespace...

Stuck in Retransmission

2

Hello, This is probably a user error but I'm unsure how, and I've been unable to replicate it in more minimal example/unit tests. I'm seeing that a TCP connection gets...

Previously, each client kernel only had 1 RPC client. Now, we are changing to one RPC client per core per client kernel.

### Is your feature request related to a problem? Please describe. Right now, the release_core() system call does not remove/clear an executor from that core (if there is one) so...

### Describe the bug The TLB WorkQueue is currently not bounded in size. It holds both shootdown requests (which are important to handle) and advance replica work requests (which are...