Rights statement: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Accepted author manuscript, 3.2 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Reliable computing service in massive-scale systems through rapid low-cost failover
AU - Yang, Renyu
AU - Zhang, Yang
AU - Garraghan, Peter
AU - Feng, Yihui
AU - Ouyang, Jin
AU - Xu, Jie
AU - Zhang, Zhuo
AU - Li, Chao
N1 - © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
PY - 2017/11
Y1 - 2017/11
N2 - Large-scale distributed systems in Cloud datacenter are capable of provisioning service to consumers with diverse business requirements. Providers face pressure to provision uninterrupted reliable services while reducing operational costs due to significant software and hardware failures. A widely used means to achieve such a goal is using redundant system components to implement usertransparent failover, yet its effectiveness must be balanced carefully without incurring heavy overhead when deployed – an important practical consideration for complex large-scale systems. Failover techniques developed for Cloud systems often suffer serious limitations, including mandatory restart leading to poor cost-effectiveness, as well as solely focusing on crash failures, omitting other important types, e.g. timing failures and simultaneous failures. This paper addresses these limitations by presenting a new approach to user-transparent failover for massive-scale systems. The approach uses soft-state inference to achieve rapid failure recovery and avoid unnecessary restart, with minimal system resource overhead. It also copes with different failures, including correlated and simultaneous events. The proposed approach was implemented, deployed and evaluated within Fuxi system, the underlying resource management system used within Alibaba Cloud. Results demonstrate that our approach tolerates complex failure scenarios while incurring at worst 228.5 microsecond instance overhead with 1.71% additional CPU usage.
AB - Large-scale distributed systems in Cloud datacenter are capable of provisioning service to consumers with diverse business requirements. Providers face pressure to provision uninterrupted reliable services while reducing operational costs due to significant software and hardware failures. A widely used means to achieve such a goal is using redundant system components to implement usertransparent failover, yet its effectiveness must be balanced carefully without incurring heavy overhead when deployed – an important practical consideration for complex large-scale systems. Failover techniques developed for Cloud systems often suffer serious limitations, including mandatory restart leading to poor cost-effectiveness, as well as solely focusing on crash failures, omitting other important types, e.g. timing failures and simultaneous failures. This paper addresses these limitations by presenting a new approach to user-transparent failover for massive-scale systems. The approach uses soft-state inference to achieve rapid failure recovery and avoid unnecessary restart, with minimal system resource overhead. It also copes with different failures, including correlated and simultaneous events. The proposed approach was implemented, deployed and evaluated within Fuxi system, the underlying resource management system used within Alibaba Cloud. Results demonstrate that our approach tolerates complex failure scenarios while incurring at worst 228.5 microsecond instance overhead with 1.71% additional CPU usage.
KW - Failover
KW - Cloud computing
KW - Resource management
KW - Reliability
KW - Services
U2 - 10.1109/TSC.2016.2544313
DO - 10.1109/TSC.2016.2544313
M3 - Journal article
VL - 10
SP - 969
EP - 983
JO - IEEE Transactions on Services Computing
JF - IEEE Transactions on Services Computing
SN - 1939-1374
IS - 6
ER -