Scale Out PoC

This document tracks the milestones, tasks and ideas related to scale out Arktos.

Tasks

Milestone 1 (One tenant partition, One resource partition, API Gateway)

API gateway:

• Setup a proxy to statically route requests: 1) for "nodes" and "nodeLeases", redirect to resource partition. 2) for everything else, redirect to tenant partition
• Workaround: redirect some requests (for common system-level URLs) based on client IP

Build&Test Scripts:

• Have simple scripts to launch a tenant partition, a resource partition and an API gateway.
  • For tenant partition, disable node controller and workload controller manager, add deployment and replicaSet controllers into controller manager (https://kubernetes.io/docs/reference/command-line-tools-reference/kube-controller-manager/)
  • for resource partition, disable scheduler, workload controller manager and other controllers except node lifecycle controller
• Do we need nodeIPAM controller?
• Update Kubemark and perf test to work with the scale-out design.
• The service token issue in NodeLifecycle controller?
• A new branch for scale-out PoC
• Prometheus settings for multi API Servers

Investigation:

• Why is there a huge latency delay -- (Added HTTP 1.1)
• Intermittent timeout for watch requests on proxy
• Node sometimes get not ready
• Manual e2e tests for key flows
• scheduler: node informer using a new client
• kubelet: node and lease update using a new client

Milestone 2 (More partitions)

• Proxy configuration changes to support multiple tenant partitions
• Kubelet changes
  • Use multiple kube clients to watch all tenant partitions
  • Use the right kube client to update pod status
• Node controller changes
  • Use multiple kube clients to watch pods/daemonSets
• Support multi-tenants in perf tests (can be hard-coded tenant names)

Future Milestones

• TP API Server needs to get node objects for commands like "kubectl attach/log/.."
• Update node controller to use a separate client for objects in tenant partition
• Improve Kubemark to simulate more than 20K nodes.
• Change Proxy (API Gateway) to use dynamic map lookup instead of static configuration.
• Reduce the number of watch connections on a tenant partition.
• One scheduler instance can't cache unlimited nodes. need optimizations like node preferences.
• Scheduler sampling to improve scheduling throughput.
• Reduce scheduling conflicts (still node preference?)
• Some controllers in tenant partitions also cache all nodes. Needs change as well.
• Current node controller caches all pods and statefulsets.
• Try to avoid aggregated watch on API gateway -- does "node.podList" help?
• Do we still need to coordinate etcd revisions among partitions? Probably not. But need more detailed analysis and some changes.