CloudDB AutoAdmin - Large Scale and Big Data: Processing and Management - page 386

approaches for managing the resource provisioning challenge for cloud databases.
The black-box provisioning uses end-to-end performance results of sample query exe-
cutions, whereas white-box provisioning uses a finer grained approach that relies on
the DBMS optimizer to predict the physical resource (e.g., I/O, memory, CPU) con-
sumption for each query. Floratou et al. [10] have studied the performance and cost in
the relational database as a service environments. The results show that given a range
of pricing models and the flexibility of the allocation of resources in cloud-based
environments, it is hard for a user to figure out their actual monthly cost upfront. Soror
et al. [20] introduced a virtualization design advisor that uses information about the
database workloads to provide offline recommendations of workload-specific virtual
machines configurations. To the best of our knowledge, our approach is the first to
tackle the problem of dynamic provisioning the cloud resources of the database tier
based on consumer-centric and application-defined SLA metrics.
11.9 CONCLUSIONS
In this chapter, we presented the design and implementation details* of an end-to-
end framework that facilitates adaptive and dynamic provisioning of the database
tier of the software applications based on consumer-centric policies for satisfying
their own SLA performance requirements, avoiding the cost of any SLA violation
and controlling the monetary cost of the allocated computing resources. The frame-
work provides the consumer applications with declarative and flexible mechanisms
for defining their specific requirements for fine-grained SLA metrics at the applica-
tion level. The framework is database platform-agnostic, uses virtualization-based
database replication mechanisms and requires zero source code changes of the
cloud-hosted software applications.
REFERENCES
1. Daniel J. Abadi. Data management in the cloud: Limitations and opportunities. IEEE
Data Eng. Bull. , 32(1), 2009.
2. Michael Armbrust, Armando Fox, Rean Griffith, Anthony D. Joseph, Randy H. Katz,
Andrew Konwinski, Gunho Lee et al. Above the clouds: A berkeley view of cloud com-
puting. Technical Report UCB/EECS-2009-28, 2009.
3. Peter Bodík, Armando Fox, Michael J. Franklin, Michael I. Jordan, and David A.
Patterson. Characterizing, modeling, and generating workload spikes for stateful ser-
vices. In SoCC , pages 241-252, 2010.
4. Eric Brewer. Towards robust distributed systems. In PODC , 2000.
5. Emmanuel Cecchet, Rahul Singh, Upendra Sharma, and Prashant J. Shenoy. Dolly:
Virtualization-driven database provisioning for the cloud. In VEE , 2011.
6. Brian F. Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, and Russell
Sears. Benchmarking cloud serving systems with YCSB. In SoCC , 2010.
7. Italo S. Cunha, Jussara M. Almeida, Virgilio Almeida, and Marcos Santos. Self-adaptive
capacity management for multi-tier virtualized environments. In Integrated Network
Management , 2007.
8. Dave Durkee. Why cloud computing will never be free. Commun. ACM , 53(5), 2010.
* http://cdbslaautoadmin.sourceforge.net/.