SYSTEMS AND METHODS FOR EFFICIENT DISTRIBUTION OF STORED DATA OBJECTS

文件类型：PDF文档
文件大小：4082K
A distributed data storage system is provided for offering shared data to one or more clients. In various embodiments, client systems operate on shared data while having a unique writeable copy of the shared data. According to one embodiment, the data storage system can be optimized for various use cases (e.g., read-mostly where writes to shared data are rare or infrequent (although writes to private data may be frequent. Some implementations of the storage system are configured to provide fault tolerance and scalability for the shared storage. For example, read-only data can be stored in (relatively) high latency, low cost, reliable storage (e.g. cloud), with multiple layers of cache supporting faster retrieval. In addition, some implementations of the data storage system offer a low-latency approach to data caching. Other embodiments improve efficiency with access modeling and conditional execution cache hints that can be distributed across the data storage system.