Resource Identification in Database Workloads


The KIPS Transactions:PartD, Vol. 13, No. 2, pp. 183-190, Apr. 2006
10.3745/KIPSTD.2006.13.2.183,   PDF Download:

Abstract

Database workloads may show different resource usages for database applications. Database administrators can enhance the DBMS performances through resource management that reflects workload characteristics. We provide a method that can identify tunable resources from analyzing the relationship between performance indicators and resources. First, we select which performance indicators increase or decrease by expanding resources using a correlation coefficient and a significance level test. Next, we identify resources that can affect the DBMS performances by using increasing or decreasing performance indicators. We evaluated our method in the TPC-C and TPC-W environments.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
J. S. Oh and S. H. Lee, "Resource Identification in Database Workloads," The KIPS Transactions:PartD, vol. 13, no. 2, pp. 183-190, 2006. DOI: 10.3745/KIPSTD.2006.13.2.183.

[ACM Style]
Jeong Seok Oh and Sang Ho Lee. 2006. Resource Identification in Database Workloads. The KIPS Transactions:PartD, 13, 2, (2006), 183-190. DOI: 10.3745/KIPSTD.2006.13.2.183.