Scale and performance in a distributed file system
ACM Transactions on Computer Systems (TOCS)
Improving Disk Performance Via Latency Reduction
IEEE Transactions on Computers
A new approach to I/O performance evaluation: self-scaling I/O benchmarks, predicted I/O performance
SIGMETRICS '93 Proceedings of the 1993 ACM SIGMETRICS conference on Measurement and modeling of computer systems
The process-flow model: examining I/O performance from the system's point of view
SIGMETRICS '93 Proceedings of the 1993 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A General Model for the Performance of Disk Systems
Journal of the ACM (JACM)
Hi-index | 0.00 |
This paper describes an approach to measuring bus contention and quantifying the resulting performance degradation. The focus is contention for a single I/O bus resulting from accesses to multiple heterogeneous I/O device types in an MP system. Heterogeneous device types are defined as devices that have widely different characteristics, such as video, network, and disk devices. Correlation analysis is used to characterize the contention and then the corresponding loss in performance is quantified using actual trace data.