@inproceedings{GrayFailureHotOS2017, author = {Huang, Peng and Guo, Chuanxiong and Zhou, Lidong and Lorch, Jacob R. and Dang, Yingnong and Chintalapati, Murali and Yao, Randolph}, title = {Gray Failure: The {Achilles}' Heel of Cloud-Scale Systems}, booktitle = {Proceedings of the 16th Workshop on Hot Topics in Operating Systems}, series = {HotOS '17}, month = {May}, year = {2017}, isbn = {978-1-4503-5068-6}, location = {Whistler, BC, Canada}, pages = {150--155}, numpages = {6}, url = {http://doi.acm.org/10.1145/3102980.3103005}, doi = {10.1145/3102980.3103005}, acmid = {3103005}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {gray failure, differential observability, failure detection}, }