allegro/bigcache
8,140 स्टार्स·608 फोर्क्स·Go·Apache-2.0·11 व्यूज़allegro.tech/2016/03/writing-fast-cache-service-in-go.html↗
Bigcache
Bigcache is a thread-safe, in-memory key-value store for Go designed to minimize garbage collection pauses. It functions as a memory-optimized cache capable of storing gigabytes of data while maintaining low latency during high-volume operations.
The system avoids garbage collection overhead by managing memory through large byte arrays and manual allocation. It utilizes a circular-buffer layout to reuse space and lock-striped sharding to reduce contention during concurrent read and write access.
The project provides capabilities for high-volume in-memory caching and low-latency data retrieval, specifically targeting the management of massive datasets within distributed system environments.
Features
- In-Memory Caches - Provides a high-performance in-memory cache capable of storing gigabytes of data with minimal latency.
- GC-Aware Memory Management - Manages massive in-memory datasets in Go specifically to avoid frequent garbage collection cycles.
- GC-Optimized Caching - Avoids Go garbage collector pauses by managing cache memory in large byte arrays.
- Key-Value Stores - Implements a thread-safe in-memory key-value store for fast access across multiple goroutines.
- Low-Latency Data Retrieval - Enables rapid access to frequently used datasets from memory to reduce database load and response times.
- Circular Memory Buffers - Utilizes a circular-buffer memory layout to reuse space by overwriting the oldest entries when the cache fills.
- Manual Memory Management - Allocates large chunks of memory upfront to bypass the Go runtime heap allocation overhead.
- GC-Optimized Byte Storage - Implements data storage in large contiguous byte slices to significantly reduce garbage collection overhead.
- Lock-Striped Sharding - Employs lock-striped sharding to minimize contention during concurrent read and write operations.
- Distributed Caches - Provides a high-performance local cache for shared data to minimize network calls in distributed environments.
- In-Memory Data Stores - Stores gigabytes of data in memory while bypassing garbage collection overhead to maintain high performance.
- Offset-Based Addressing - Uses relative byte offsets within a large memory block to provide fast, zero-copy access to stored values.
- Zero-Copy - Returns views into the underlying byte array instead of allocating new memory for retrieved values.
- Caching Libraries - Efficient in-memory cache.
- डेटाबेस - Efficient key-value cache for large datasets.
