Memento: A Framework for Detectable Recoverability in Persistent Memory
Offered By: ACM SIGPLAN via YouTube
Course Description
Overview
Explore a groundbreaking framework for detectable recoverability in persistent memory through this 19-minute conference talk from PLDI 2023. Dive into Memento, a general and high-performance programming framework designed for detectably recoverable concurrent data structures in persistent memory. Learn how Memento supports primitive operations like checkpoint and compare-and-swap, and employs a timestamp-based recovery strategy for enhanced performance. Discover the framework's ability to ensure detectable recoverability during crashes while maintaining comparable performance to existing hand-tuned persistent data structures. Examine implementations of lock-free stack, list, queue, hash table, and combining queue that showcase Memento's capabilities in stress tests. Gain insights into the future of persistent memory technology and its potential impact on storage solutions combining DRAM performance with SSD durability.
Syllabus
[PLDI'23] Memento: A Framework for Detectable Recoverability in Persistent Memory
Taught by
ACM SIGPLAN
Related Courses
Stanford Seminar - The Quest for Low Storage Latency Changes EverythingStanford University via YouTube Accelerating Apache Spark Shuffle for Data Analytics on Cloud with Remote Persistent Memory Pools
Databricks via YouTube Promise and Pitfalls of Persistent Memory
Strange Loop Conference via YouTube Crimson - A New Ceph OSD for the Age of Persistent Memory and Fast NVMe Storage
USENIX via YouTube Write-Optimized Dynamic Hashing for Persistent Memory
USENIX via YouTube