COSCAnet-FT: Transparent network support for highly available cloud services

More and more applications move to the cloud, even critical systems that need high availability. In current clouds, faults can be handled for stateless HTTP applications. Other protocols and stateful applications cannot be supported. Highly-available stateful services could use active replication, but it typically needs client-side code for supporting complex totally-ordered multicasts. This paper first presents a transport-level router as a service in the network that transparently multicasts TCP traffic to actively replicated service instances. Second, it demonstrates the integration of this concept into a PaaS cloud as a value-added service to customers so that applications can be replicated on demand. Finally, an evaluation of our prototype shows reasonable throughput, latency and recovery time.