kubeflow / kubeflow/katib

[feature] Add GRPC Retry Logic to Metrics Collector

Open
#882 4 comments 0 reactions 0 assignees View on GitHub
kind/feature lifecycle/frozen priority/p3
Dominant language
Python
Stars
1.7k
Forks
542
PR merge metrics
No merged PRs in 30d

Description

/kind feature

**Describe the solution you'd like**
[A clear and concise description of what you want to happen.]

Metrics collector collects the metrics from main container and report them to manager via GRPC. We should have sort of retry logic for GRPC calls.

**Anything else you would like to add:**
[Miscellaneous information that will assist in solving the issue.]

Contributor guide

Open the contributing guide

Research direction

Start by locating the metrics collector entry point and the existing gRPC calls that report metrics to the manager. Review any nearby tests or error-handling conventions, then clarify retry conditions, limits, and backoff before implementing; done means transient gRPC failures are retried without disrupting metric collection.

Written by the indexing model from the issue text.

Assessment

Tech stack
grpc, python
Domain
distributed-systems, observability
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.