NVIDIA / NVIDIA/nvcf

feat(self-managed): Tier-1 active-active defaults under highAvailability

Open
#987 0 comments 0 reactions 1 assignee View on GitHub

@shobham-nv is already working on this.

Since Aug 19, 2026.

Dominant language
Go
Stars
218
Forks
72
Avg merge
1d 12h
Merged PRs (30d)
427

Description

Description

Apply P0 Tier-1 active–active defaults when highAvailability.profile: production: replicaCount 2, soft pod anti-affinity on hostname, topology spread on topology.kubernetes.io/zone, PDB minAvailable 1, rollingUpdate maxSurge 1 / maxUnavailable 0.
In-scope services: NVCF API, grpc-proxy, http-invocation, admin-token-issuer-proxy; llm-api-gateway when the LLM addon is enabled.
Do not introduce application-level leader election for Tier-1.

Definition of Done

  • Production HA profile sets the above defaults for API, grpc-proxy, invocation, admin-token-issuer-proxy
  • llm-api-gateway follows the same pattern when enabled
  • Charts receive values via global.yaml.gotmpl (add chart hooks only if missing)
  • single-node profile remains single-replica friendly
  • Readiness probes continue to gate Service endpoints

By submitting this issue, you acknowledge that you are an assigned member of the NVCF development team and agree to follow our code of conduct and our contributing guidelines.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.