The inadequate resource allocation, lack of I/O performance prediction and insufficient isolation are affecting the storage performance in the multi-tenant cloud storage environment. In order to guarantee the Quality of Service (QoS), Softwaredefined Storage (SDS) is an effective approach in data centers. However, the lack of intelligence, robustness and selfadjustment are blocking the applications and promotions of SDS heavily. This paper focuses on the QoS-Aware I/O resource scheduling problem to build data centers with high availability, scalability and QoS.
We will study workload characteristics, requirement analysis, the theory of QoS in SDS and I/O scheduling strategies. We obtain such goals by proposing a mathematics model of workload burstness, QoS semantic description with rule execution mechanisms and dynamic robust I/O scheduling algorithms for multi-type resources allocation. In the current progress, A QoS-Aware I/O Scheduling Framework towards SDS, qSDS has been proposed for the SSD/HDD hybrid storage. The preliminary evaluation in some benchmarks shows that qSDS can gain better performance compared with other strategies.