科技报告详细信息
Procrastination Beats Prevention: Timely Sufficient Persistence for Efficient Crash Resilience
Nawab, Faisal ; Chakrabarti, Dhruva R. ; Kelly, Terence ; Morrey III, Charles B.
HP Development Company
关键词: NVRAM;    failure tolerance;   
RP-ID  :  HPL-2014-70
学科分类:计算机科学(综合)
美国|英语
来源: HP Labs
PDF
【 摘 要 】

Preserving the integrity of application data across updates in the presence of failure is an essential function of computing systems, and byte-addressable non-volatile memory (NVM) broadens the range of fault-tolerance strategies that implement it. NVM invites programs to manipulate durable data directly via load and store instructions, but overheads due to the widely used mechanisms that ensure consistent recovery from failures impair performance, e.g., the logging overheads of transactions. We introduce the concept of Timely Sufficient Persistence (TSP) mechanisms, which is relevant to both conventional and emerging computer architectures. For a broad spectrum of fault-tolerance requirements, satisfactory TSP mechanisms typically involve lower overheads during failure-free operation than their non-TSP counterparts; hardware and OS support can facilitate TSP mechanisms. We present TSP variants of programs representing two very different classes of shared-memory multi-threaded software that store application data in persistent heaps: The first employs conventional mutexes for isolation, and TSP substantially reduces the overhead of a fault-tolerance mechanism based on fine-grained logging. The second class of software employs non-blocking algorithms; remarkably, TSP is very easy to retrofit onto a non-resilient design and enjoys zero runtime overhead. Extensive experiments confirm that TSP yields robust crash resilience with substantially reduced overhead.

【 预 览 】
附件列表
Files Size Format View
RO201804100000576LZ 266KB PDF download
  文献评价指标  
  下载次数:26次 浏览次数:32次