Recoverable Mutual Exclusion with Constant Amortized RMR Complexity from Standard Primitives
David Chan, Philipp Woelfel · 2020
Motivated by advances in non-volatile memory technology, recent research in mutual exclusion has focused on algorithms for a shared memory model, in which failed processes can recover from crashes. Golab and Ramaraju [9] defined the recoverable mutual exclusion problem, where a process may crash during a mutual exclusion protocol. Upon crashing a process's local memory is erased, and it starts a recovery procedure. The contents of the shared memory survives process failures.