Carbink - Fault-Tolerant Far Memory

This course teaches about designing a fault-tolerant far memory system called Carbink, which utilizes erasure-coding, remote memory compaction, one-sided RMAs, and offloadable parity calculations to achieve fast, storage-efficient fault tolerance. The learning outcomes include understanding the challenges of fault tolerance in far memory systems and how Carbink improves performance compared to existing systems. The course covers topics such as memory-intensive applications in data centers, application interface with remotable pointers, replication vs. erasure coding, and remote compaction for defragmentation. The intended audience for this course is individuals interested in distributed systems, memory systems, and fault tolerance mechanisms in data centers.