We propose initial designs based on lockstep coordination that constructs synchronous redundant processor pairs. We then leverage the hidden-update mechanisms to develop an asynchronous, distributed-redundant system. Our evaluations of common enterprise workloads show that asynchronous redundancy can achieve performance overheads averaging just 10% over a non-redundant system, while obviating the need for extensive initialization and deterministic execution found in synchronous designs.Modern processors provide hardware support for fast synchronization code with atomic memory operations and memory ordering instructions. As shown in Figure 26(right), by creating new fingerprint intervals before and after synchronizationanbsp;...
|Title||:||Increasing Processor Dependability in Distributed Shared-memory Servers|
|Author||:||Brian T. Gold|
|Publisher||:||ProQuest - 2009|