Why Do Computers Stop and What Can Be Done About It?

@inproceedings{citeulike:1525429, abstract = {An analysis of the failure statistics of a commercially available fault-tolerant system shows that administration and software are the major contributors to failure. Various approaches to software fault-tolerance are then discussed -- notably process-pairs, transactions and reliable storage. It is pointed out that faults in production software are often soft (transient) and that a transaction mechanism combined with persistent processpairs provides fault-tolerant execution -- the key to...}, author = {Gray, Jim }, booktitle = {Symposium on Reliability in Distributed Software and Database Systems}, citeulike-article-id = {1525429}, keywords = {design, distributed, systems}, pages = {3--12}, posted-at = {2007-07-31 16:55:38}, priority = {2}, title = {Why Do Computers Stop and What Can Be Done About It?}, url = {http://citeseer.ist.psu.edu/gray85why.html}, year = {1986} }

TY - CONF ID - citeulike:1525429 L3 - citeulike-article-id:1525429 TI - Why Do Computers Stop and What Can Be Done About It? T2 - Symposium on Reliability in Distributed Software and Database Systems SP - 3 EP - 12 N2 - An analysis of the failure statistics of a commercially available fault-tolerant system shows that administration and software are the major contributors to failure. Various approaches to software fault-tolerance are then discussed -- notably process-pairs, transactions and reliable storage. It is pointed out that faults in production software are often soft (transient) and that a transaction mechanism combined with persistent processpairs provides fault-tolerant execution -- the key to... KW - design KW - distributed KW - systems AU - Gray, Jim PY - 1986/// UR - http://citeseer.ist.psu.edu/gray85why.html ER -