A scalability hierarchical fault tolerance strategy: Community Fault Tolerance

摘要

Most of hierarchical fault tolerance strategies did not pay much attention to scalability of fault tolerance. In distributed system, scalability is a very important feature. To tolerant failures when the scale of the system changing is a normal and important scenario. Especially in nowadays, almost all the cloud computing companies provide their computing services elastically. To add extra devices or remove devices in order to provide different services happens all the time. In such a scenario, it is very important that the fault tolerance strategy is scalable. In this paper, we introduce dynamic programming thoughts to build hierarchical regions as communities for fault tolerance strategy and apply different strategies based on communities instead of a single process. We call this fault tolerance strategy as Community Fault Tolerance. It cannot only reduce the memory overload by eliminating the number of records of messages inside the community region, but also provides a good characteristic of scalability. The scalability property of our strategy makes it handle with the scenario of adding devices or removing devices in the distributed system easily.