Analytical response time estimation in parallel relational database systems

Tomov, Neven; Dempster, Euan W.; Williams, M. Howard; Burger, Albert; Taylor, Hamish; King, Peter J. B.; Broughton, Phil

doi:10.1016/j.parco.2003.11.003

Cited by 14 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RSPC checks whether the given QEP satisfies SLO RT based on the estimation of RT Q . For this aim, the costs of all resources required for the execution of Q are estimated as given in Formula (2) (Tomov et al, 2004). Thus, the costs of processing Q (CPU_Q_Cost), data access Input/Output (IO_Q_Cost) and data transfer between nodes (Transf_Q_Cost) are estimated before the execution of Q.…”

Section: Query Response Time Estimationmentioning

confidence: 99%

A data replication strategy with tenant performance and provider economic profit guarantees in Cloud data centers

Mokadem

Hameurlain

2020

Journal of Systems and Software

View full text Add to dashboard Cite

Meeting tenant performance requirements through data replication while ensuring an economic profit is very challenging for cloud providers. For this purpose, we propose a data Replication Strategy that satisfies Performance tenant objective and provider profit in Cloud data centers (RSPC). Before the exe cution of e.ach tenant query Q. data replication is considered only if: (i) the estimated Response Time of Q (RT Q) exceeds a critical RT threshold (per-query replication), or (ii) more often, if RT Q exceeds another (lower) RT threshold for a given number of times (replication per set of queries). Then, a new replica is really created only if a suitable replica placement is heuristically found so that the RT requirement is satisfied again while ensuring an economic profit for the provider. Both the provider's revenues and expenditures are also estimated while penalties and replication costs are taken into account. Further more, the replica factor is dynamically adjusted in order to reduce the resource consumption. Compared to four other strategies, RSPC best satisfies the RT requirement under high loads, complex queries and strict RT thresholds. Moreover, penalty and data transfer costs are significantly reduced, which impacts the provider profit.

show abstract

Section: Query Response Time Estimationmentioning

confidence: 99%

A data replication strategy with tenant performance and provider economic profit guarantees in Cloud data centers

Mokadem

Hameurlain

2020

Journal of Systems and Software

View full text Add to dashboard Cite

show abstract

“…Parallel relational database system performance evaluation. Tomov et al [28] describe an analytical methodology for response time estimation. The queries analyzed execute within a shared-nothing parallel DBMS.…”

Section: Database System Performance Evaluation Modelsmentioning

confidence: 99%

Performance Modeling of Database Systems: a Survey

Krajewska¹

2018

JTIT

View full text Add to dashboard Cite

This paper presents a systematic survey of the existing database system performance evaluation models based on the queueing theory. The continuous evolution of the methodologies developed is classiﬁed according to the mathematical modeling language used. This survey covers formal models – from queueing systems and queueing networks to queueing Petri nets. Some fundamentals of the queueing system theory are presented and queueing system models are classiﬁed according to service time distribution. The paper introduces queueing networks and considers several classiﬁcation criteria applicable to such models. This survey distinguishes methodologies, which evaluate database performance at the integrated system level. Finally, queueing Petri nets are introduced, which combine modeling power of queueing networks and Petri nets. Two performance models within this formalism are investigated. We ﬁnd that an insuﬃcient amount of research eﬀort is directed into the area of NoSQL data stores. Vast majority of models developed focus on traditional relational models. These models should be adapted to evaluate performance of non-relational data stores.

show abstract

“…An option to cover this gap is by adopting analytic models. For example, in (Tomov et al, 2004) it has been proposed a queuing network model to estimate the response time of database transactions. Furthermore, in (Osman and Knottenbelt, 2012) it has been compared the performance of different database designs via modeling.…”

Section: Related Literaturementioning

confidence: 99%

Resources Planning in Database Infrastructures

Dosciatti

Teixeira

Ribeiro

et al. 2016

Proceedings of the 18th International Conference on Enterprise Information Systems

View full text Add to dashboard Cite

Anticipating resources consumption is essential to project robust database infrastructures able to support transactions to be processed with certain quality levels. In Database-as-a-Service (DBaaS), for example, it could help to construct Service Level Agreements (SLA) to intermediate service customers and providers. A proper database resources assessment can avoid mistakes when choosing technology, hardware, network, client profiles, etc. However, to be properly evaluated, a database transaction usually requires the physical system to be measured, which can be expensive an time consuming. As most information about resource consumption are useful at design time, before developing the whole system, is essential to have mechanisms that partially open the black box hiding the in-operation system. This motivates the adoption of predictive evaluation models. In this paper, we propose a simulation model that can be used to estimate performance and availability of database transactions at design time, when the system is still being conceived. By not requiring real time inputs to be simulated, the model can provide useful information for resources planning. The accuracy of the model is checked in the context of a SLA composition process, in which database operations are simulated and model estimations are compared to measurements collected from a real database system.

show abstract

Analytical response time estimation in parallel relational database systems

Cited by 14 publications

References 16 publications

A data replication strategy with tenant performance and provider economic profit guarantees in Cloud data centers

A data replication strategy with tenant performance and provider economic profit guarantees in Cloud data centers

Performance Modeling of Database Systems: a Survey

Resources Planning in Database Infrastructures

Contact Info

Product

Resources

About