Explore a conference talk on FORD, a Fast One-sided RDMA-based Distributed transaction system designed for disaggregated persistent memory architecture. Learn how FORD improves resource utilization and failure isolation in remote memory pools by leveraging one-sided RDMA, batching read and lock operations, and accelerating transaction commits. Discover techniques for reducing round trips, handling remote data persistency, and balancing load across primary and backup replicas. Examine experimental results demonstrating FORD's significant improvements in transaction throughput and latency compared to state-of-the-art systems.
FORD - Fast One-sided RDMA-based Distributed Transactions for Disaggregated Persistent Memory
Overview
Syllabus
Intro
Disaggregated Persistent Memory Memory disaggregation
RDMA-based Distributed Transaction
Transaction on Disaggregated PM
State-of-the-art
Challenge 1
Overview
Hitchhiked Locking Read and lock the read-write (RW) set in execution . Avoid subsequent locking and validations • No lock on the read-only data
Coalescent Commit Commit all replicas together in one round trip - In-place update: Parallel undo logging in execution phase • Prevent reading partial updates: Control data visibility
Selective Remote Flush Only issue remote flushes to backups after the final write • Ensure recoverability by backups • Reduce flushing round trips • Compatible with different flush primitives
Evaluation Benchmarks
Conclusion
Taught by
USENIX
