可恢复的可流产互斥
Recoverable Mutual Exclusion with Abortability
摘要：
非易失性主存储器（NVRAM）技术的最新进展促进了对设计具有进程崩溃弹性的算法的研究。本文是我们的会议论文\cite{jayanti:rmeabort}的完整版本，它提出了第一个可恢复的互斥（RME）算法，支持可中止性。我们的算法只使用读，写和CAS操作，这是通常支持的多处理器。它满足FCFS和其他标准属性。我们的算法也是自适应的。在DSM和Relaxed-CC多处理器上，进程在一个通道中产生$O(\min(k, \log n))$ RMR，在一次尝试中产生$O(f+ \min(k, \log n))$ RMR，其中$n$是算法设计用于的进程数，$k$是通道或尝试的点争用，$f$是$p$在尝试期间崩溃的次数。在严格CC多处理器上，通道和尝试复杂度分别为$O(n)$和$O(f+n)$。Attiya等人证明，对于任何互斥算法，如果算法只使用读、写和CAS操作\cite{Attiya:lbound}，则进程在一个通道中至少会导致$Ω(\log n)$ RMR。这个下限意味着，我们的算法的最坏情况下的RMR复杂度是最佳的DSM和松弛CC多处理器。
英文摘要：
Recent advances in non-volatile main memory (NVRAM) technology have spurred research on designing algorithms that are resilient to process crashes. This paper is a fuller version of our conference paper \cite{jayanti:rmeabort}, which presents the first Recoverable Mutual Exclusion (RME) algorithm that supports abortability. Our algorithm uses only the read, write, and CAS operations, which are commonly supported by multiprocessors. It satisfies FCFS and other standard properties. Our algorithm is also adaptive. On DSM and Relaxed-CC multiprocessors, a process incurs $O(\min(k, \log n))$ RMRs in a passage and $O(f+ \min(k, \log n))$ RMRs in an attempt, where $n$ is the number of processes that the algorithm is designed for, $k$ is the point contention of the passage or the attempt, and $f$ is the number of times that $p$ crashes during the attempt. On a Strict CC multiprocessor, the passage and attempt complexities are $O(n)$ and $O(f+n)$. Attiya et al. proved that, with any mutual exclusion algorithm, a process incurs at least $Ω(\log n)$ RMRs in a passage, if the algorithm uses only the read, write, and CAS operations \cite{Attiya:lbound}. This lower bound implies that the worst-case RMR complexity of our algorithm is optimal for the DSM and Relaxed CC multiprocessors.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
