Principle:LMCache LMCache Cluster Management
| Knowledge Sources | |
|---|---|
| Domains | Cluster_Management, Monitoring |
| Last Updated | 2026-02-09 00:00 GMT |
Overview
A REST API-based cluster management pattern that provides operations for looking up, moving, pinning, clearing, and compressing KV cache entries across instances.
Description
Cluster Management exposes the controller's KV operations as REST API endpoints. External tools or automated scripts can query cache state (lookup), migrate cache between instances (move), prevent eviction (pin), free cache (clear), or compress cache (compress). Operations are dispatched to workers via the LMCacheClusterExecutor.
Usage
Use the controller's REST API endpoints for cluster-level cache management. The API is available at the controller's --port.
Theoretical Basis
Operations follow a request-dispatch-aggregate pattern:
- Client sends REST request to controller
- KVController validates and routes to LMCacheClusterExecutor
- Executor dispatches ZMQ messages to target workers
- Workers execute the operation and return results
- Executor aggregates results and returns to client
Related Pages
Implemented By
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment