SLA-driven workload management for cloud databases

Despite the fast growth and increased adoption of cloud databases, challenges related to Service-Level-Agreements (SLAs) specification and management still exist. Supporting application-specific performance goals and SLAs, assigning incoming query processing workloads to the reserved resources to avoid SLA violations and monitoring performance factors to ensure acceptable QoS levels, are some of the critical tasks that have not yet been addressed by the database community. In this position paper, we argue that SLA management for cloud databases should itself be offered to developers as a cloud-based automated service. Towards this goal, we discuss the design of a framework that a) enables the specification of custom applicaton-level performance SLAs and b) offers workload management mechanisms that can automatically customize their functionality towards meeting these application-specific SLAs.