Despite the fast growth and increased adoption of cloud databases the lack of application-specific Service-Level-Agreements (SLAs) hinders the adoption of cloud data services by large-scale enterprises. Defining application-specific QoS objectives and constraints, monitoring the performance factors to ensure acceptable QoS levels and isolating the source of QoS degradation, are some of the critical tasks that are still addressed through custom, ad-hoc tools at the application level, which drastically increases the application development and maintenance overhead. In this work-in-progress paper, we argue that performance management of data management applications should itself be offered as a service. Towards this goal, we present XCloud, a suite of SLA management services for cloud databases that enables the definition and monitoring of application-specific performance criteria and customizable performance SLAs.
[1]
Jignesh M. Patel,et al.
Towards Multi-Tenant Performance SLOs
,
2012,
IEEE Transactions on Knowledge and Data Engineering.
[2]
Donald E. Knuth,et al.
The Genesis of Attribute Grammars
,
1990,
WAGA.
[3]
Amr El Abbadi,et al.
ElasTraS: An Elastic Transactional Data Store in the Cloud
,
2009,
HotCloud.
[4]
Carlo Curino,et al.
Relational Cloud: a Database Service for the cloud
,
2011,
CIDR.
[5]
Jignesh M. Patel,et al.
When Free Is Not Really Free: What Does It Cost to Run a Database Workload in the Cloud?
,
2011,
TPCTC.
[6]
Calton Pu,et al.
Intelligent management of virtualized resources for database systems in cloud environment
,
2011,
2011 IEEE 27th International Conference on Data Engineering.