Looking at the server side of peer-to-peer systems
LCR '04 Proceedings of the 7th workshop on Workshop on languages, compilers, and run-time support for scalable systems
Revisiting unfairness in web server scheduling
Computer Networks: The International Journal of Computer and Telecommunications Networking
On the effect of inexact size information in size based policies
ACM SIGMETRICS Performance Evaluation Review
ACM SIGMETRICS Performance Evaluation Review
Predict task running time in grid environments based on CPU load predictions
Future Generation Computer Systems
Scheduling despite inexact job-size information
SIGMETRICS '08 Proceedings of the 2008 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
The effect of local scheduling in load balancing designs
ACM SIGMETRICS Performance Evaluation Review
Improving peer-to-peer performance through server-side scheduling
ACM Transactions on Computer Systems (TOCS)
Load prediction using hybrid model for computational grid
GRID '07 Proceedings of the 8th IEEE/ACM International Conference on Grid Computing
Predicting Running Time of Grid Tasks based on CPU Load Predictions
GRID '06 Proceedings of the 7th IEEE/ACM International Conference on Grid Computing
Decoupled speed scaling: Analysis and evaluation
Performance Evaluation
Hi-index | 0.00 |
Size-based scheduling policies such as SRPT have been studied since 1960s and have been applied in various arenas including packet networks and web server scheduling. SRPT has been proven to be optimal in the sense that it yields 驴 compared to any other conceivable strategy 驴 the smallest mean value of occupancy and therefore also of waiting and delay time. One important pre-requisite to applying size-based scheduling is to know the sizes of all jobs in advance, which are unfortunately not always available. No work has been done to study the performance of size-based scheduling policies when only inaccurate scheduling information is available. In this paper, we study the performance of SRPT and FSP as a function of the correlation coefficient between the actual job sizes and estimated job sizes. We developed a simulator that supports both M/G/1/m and G/G/n/m queuing models. The simulator can be driven by trace data or synthetic data produced by a workload generator we have developed that allows us to control the correlation. The simulations show that the degree of correlation has a dramatic effect on the performance of SRPT and FSP and that a reasonably good job size estimator will make both SRPT and FSP outperform PS in both mean response time and slowdown.