4 April 2014: Large datacentre operators with sites at multiple locations design their inter-datacentre networks such that they can accommodate the maximum bandwidth needed during a day. At the same time, the demand for inter-datacentre bandwidth follows strong patterns with high peak to valley (i.e. high to low) ratios that result in poor average utilisation across a day.
We are conducting research on how to rescue unutilised bandwidth across multiple datacentres and backbone networks. The rescued bandwidth can be used by non-real-time applications, such as backups, propagation of bulky updates, and migration of data and/or virtual machines that improve fault tolerance, end-user experience, and energy/ personnel costs, respectively. Achieving the above is non-trivial since leftover bandwidth appears at different times, for different durations, and at different places in the world.
Our system gathers information about leftover resources, uses a store-and- forward algorithm to schedule data transfers, and adapts to resource fluctuations.
We have compared NetStitcher with other bulk transfer mechanisms such as direct transfer, multipath forwarding, and naive store-and-forward. Our evaluation shows that NetStitcher outperforms all other mechanisms and can rescue up to five times additional datacentre bandwidth thus making it a valuable tool for datacentre providers.
