chore: switch to http tracing

[davidwallacejackson]

Summary by CodeRabbit

• Chores
  • Updated the system’s version to 0.26.1.
• New Features
  • Adjusted resource allocations to better support system performance.
  • Refined the tracing service configuration by switching its communication protocol from gRPC to HTTP and updating the connection port.

[coderabbitai]

Walkthrough

This update makes several adjustments to the Helm chart for the WandB operator. The chart version was incremented in the main Chart.yaml file. Resource allocations in the nested agent values file have been increased for both CPU and memory, and the configuration for the tracing service in the values file has been updated to use a different port and protocol.

Changes

File(s)	Change Summary
charts/operator-wandb/Chart.yaml	Updated chart version from 0.26.0 to 0.26.1.
charts/operator-wandb/charts/otel/charts/agent/values.yaml	Increased resource requests: CPU from 200m to 300m and memory from 200Mi to 400Mi; increased resource limits: CPU from 500m to 600m and memory from 500Mi to 1Gi.
charts/operator-wandb/values.yaml	Modified otel.traces configuration: port changed from 4317 to 4318 and protocol from "grpc" to "http".

Poem

Hopping through charts with a cheerful beat,
I nibble on changes both crisp and neat.
Versions and resources, a delightful tune,
Ports and protocols dance under the moon.
With whiskered joy, I code by day and night –
A bunny’s tale of upgrades, pure delight!

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 8c5dc23 and 6b3b954.

📒 Files selected for processing (3)

• charts/operator-wandb/Chart.yaml (1 hunks)
• charts/operator-wandb/charts/otel/charts/agent/values.yaml (1 hunks)
• charts/operator-wandb/values.yaml (1 hunks)

✅ Files skipped from review due to trivial changes (1)

• charts/operator-wandb/Chart.yaml

⏰ Context from checks skipped due to timeout of 90000ms (1)

• GitHub Check: lint-test

🔇 Additional comments (2)

charts/operator-wandb/charts/otel/charts/agent/values.yaml (1)

74-80: Resource allocation adjustments look appropriate.

The increased resource allocations align well with the switch to HTTP tracing. The changes provide:

• 50% more CPU requests (200m → 300m)
• 100% more memory requests (200Mi → 400Mi)
• 20% more CPU limits (500m → 600m)
• 100% more memory limits (500Mi → 1Gi)

charts/operator-wandb/values.yaml (1)

83-86: Tracing configuration changes look correct.

The changes properly configure the switch to HTTP tracing:

• Port 4318 is the standard port for OTLP/HTTP (changed from 4317 which was for OTLP/gRPC)
• Protocol correctly changed from "grpc" to "http"

Let's verify these are the standard ports for OTLP:

✅ Verification successful

🌐 Web query:

What are the standard ports for OTLP/HTTP and OTLP/gRPC in OpenTelemetry?

💡 Result:

The OpenTelemetry Protocol (OTLP) uses standardized ports for its two main transport protocols:

• OTLP/gRPC: Default port 4317
• OTLP/HTTP: Default port 4318

These defaults are defined in the OpenTelemetry Specification and widely adopted across implementations[1][2][3][6][9].

Key Configuration Details:

• gRPC uses Protocol Buffers (binary format) over HTTP/2 on port 4317[2][5].
• HTTP supports Protobuf or JSON payloads over HTTP/1.1/2 on port 4318[2][5].

Protocol	Port	Typical Use Case
gRPC	4317	High-throughput scenarios requiring bidirectional streaming
HTTP	4318	Environments with HTTP-only infrastructure (e.g., web browsers)

Implementation Notes:

• Ports can be customized in collector configurations[1][4].
• When using HTTPS/TLS, ports typically remain unchanged unless explicitly modified[1][4].
• Signal-specific endpoints (e.g., /v1/traces) are appended automatically when using standard environment variables like OTEL_EXPORTER_OTLP_ENDPOINT[5][7].

For example, a basic OTLP/HTTP exporter configuration might use:

export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318

Citations:

• 1: https://bindplane.com/docs/resources/sources/opentelemetry
• 2: https://opentelemetry.io/docs/specs/otlp/
• 3: https://signoz.io/comparisons/opentelemetry-grpc-vs-http/
• 4: https://opentelemetry.io/docs/collector/configuration/
• 5: https://opentelemetry.io/docs/languages/sdk-configuration/otlp-exporter/
• 6: https://docs.newrelic.com/docs/opentelemetry/best-practices/opentelemetry-otlp/
• 7: https://opentelemetry.io/docs/specs/otel/protocol/exporter/
• 8: https://github.com/open-telemetry/opentelemetry-collector/blob/main/receiver/otlpreceiver/README.md
• 9: https://betterstack.com/community/guides/observability/otlp/
• 10: https://docs.splunk.com/observability/en/gdi/opentelemetry/exposed-endpoints.html

---

Tracing configuration changes confirmed as correct.

The snippet correctly sets the default OTLP/HTTP port to 4318 and the protocol to "http", which matches the OpenTelemetry specifications—OTLP/gRPC uses port 4317 and OTLP/HTTP uses port 4318.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[danielpanzella]

Since this will break if they are not on a very recent version of the server image, I'm hesitant to make the change here and we should instead make the change here https://deploy.wandb.ai/v2/admin/channels/9205b19d-9103-4ef6-88e3-4d7a6eda61a7 when we are sure that the server version with the code to support this is deployed fleet wide

[davidwallacejackson]

Since this will break if they are not on a very recent version of the server image, I'm hesitant to make the change here and we should instead make the change here https://deploy.wandb.ai/v2/admin/channels/9205b19d-9103-4ef6-88e3-4d7a6eda61a7 when we are sure that the server version with the code to support this is deployed fleet wide

@danielpanzella that makes sense. We roll out every release fleet-wide, right? If so I can just wait for the next release.

[danielpanzella]

@danielpanzella that makes sense. We roll out every release fleet-wide, right? If so I can just wait for the next release.

Yup, should be next week I believe.