Create networking blog post #43
Closed
Conversation
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
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR creates a new blog post about WATcloud's networking architecture, detailing their dual-network design that separates campus connectivity from high-performance cluster communication. The post covers the evolution from complex software overlay networks to simplified physical infrastructure.
Key changes:
- Added asset configuration for blog post images (square and wide formats)
- Created comprehensive blog post covering network architecture, performance optimizations, and engineering decisions
- Documented the transition from Yggdrasil overlay networks to reliable physical infrastructure
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| scripts/asset-config.json | Added image asset configurations for the networking blog post |
| pages/blog/networking.mdx | New blog post covering WATcloud's dual-network architecture and design evolution |
| - **Suitability**: Good for low-traffic environments; may need to switch to external load balancer for high-traffic scenarios | ||
|
|
||
| #### Cluster Traffic Strategy | ||
| For cluster communication, we use DNS round-robin with health-aware routing. Our [custom-built Automatic DNS Failover Agent](https://github.com/WATonomous/automatic-dns-failover) continuously monitors node health and dynamically updates DNS records, adding or removing entries as nodes become available or go offline. |
There was a problem hiding this comment.
[nitpick] This paragraph appears to be disconnected from the surrounding context about external traffic strategy. Consider restructuring this content or adding transitional text to improve flow.
Suggested change
| For cluster communication, we use DNS round-robin with health-aware routing. Our [custom-built Automatic DNS Failover Agent](https://github.com/WATonomous/automatic-dns-failover) continuously monitors node health and dynamically updates DNS records, adding or removing entries as nodes become available or go offline. | |
| While external traffic is funneled through a single highly available entry point, internal cluster communication requires a different approach to ensure resilience and scalability. For cluster communication, we use DNS round-robin with health-aware routing. Our [custom-built Automatic DNS Failover Agent](https://github.com/WATonomous/automatic-dns-failover) continuously monitors node health and dynamically updates DNS records, adding or removing entries as nodes become available or go offline. |
Co-authored-by: Copilot <[email protected]>
Member
Author
|
Moved to internal repo: https://github.com/WATonomous/infra-config/pull/4487 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.