Implementing fault-tolerant services using the state machine approach: a tutorial
ACM Computing Surveys (CSUR)
ACM Transactions on Computer Systems (TOCS)
The SMART way to migrate replicated stateful services
Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006
The cost of a cloud: research problems in data center networks
ACM SIGCOMM Computer Communication Review
Paxos replicated state machines as the basis of a high-performance data store
Proceedings of the 8th USENIX conference on Networked systems design and implementation
| Hi-index | 0.00 |
There are a variety of factors such as massive commodity computers, storage, network devices and complex management tasks running behind web services which make web services not available. Replication is an effective solution in that case. There are a variety of replication protocols, and which has been used most is called Paxos. For high available web services, we introduce Paxos as replication protocol and have done a series of optimization work. Firstly, we find that there exists exchangeability between requests to web services and the exchangeability can be used to improve the performance of Paxos. Secondly, in the light of the characteristics of web services with business processes, we find the exchangeable relationship between operations. The exchangeability between operations and the exchangeability between requests can be one-to-one correspondence. Thirdly, we apply the exchangeability to the optimization of Paxos for high available web services. Finally, we have implemented some experiments and experimental results show its effectiveness and performance advantages compared with other replication methods.