docs: document controller scaling and multiple replicas - #2055
Merged
nacx merged 3 commits intoApr 16, 2026
Conversation
Document that the AIGW controller should be configured with multiple replicas to distribute extension server load. Explain how leader election applies only to the k8s controller portion while the extension server runs on all replicas, provide Helm and plain-Deployment configuration examples, and include an HPA example for dynamic workloads. Fixes envoyproxy#1215 Signed-off-by: Varun Nuthalapati <nuthalapativarun@gmail.com>
dosubot
Bot
added
the
size:L
|
Related Documentation 1 document(s) may need updating based on files changed in this PR: Envoy's Space index
|
Signed-off-by: Varun Nuthalapati <nuthalapativarun@gmail.com>
nacx
approved these changes
Apr 16, 2026
nacx
enabled auto-merge (squash)
April 16, 2026 07:54
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Adds a new doc page explaining how and why to run the AI Gateway controller with multiple replicas.
The controller has two independent components:
Since EG's xDS server communicates with all Envoy instances and each EG replica calls the AIGW extension server, running a single AIGW replica can become a bottleneck. This doc explains the architecture, provides Helm and plain-Deployment configuration examples, and includes an HPA example for dynamic scaling.
Note: This doc was written with AI assistance (Claude Code).
Related Issues/PRs (if applicable)
Fixes #1215
Special notes for reviewers (if applicable)
The new page is at
site/docs/capabilities/scaling.md(sidebar position 3, autogenerated). The Helm values (controller.replicaCount,controller.leaderElection.enabled) were verified againstmanifests/charts/ai-gateway-helm/values.yaml.