A new approach to I/O performance evaluation: self-scaling I/O benchmarks, predicted I/O performance
ACM Transactions on Computer Systems (TOCS) - Special issue on computer architecture
Internet Web servers: workload characterization and performance implications
IEEE/ACM Transactions on Networking (TON)
Generating representative Web workloads for network and server performance evaluation
SIGMETRICS '98/PERFORMANCE '98 Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Benchmarks and Standards for the Evaluation of Parallel Job Schedulers
IPPS/SPDP '99/JSSPP '99 Proceedings of the Job Scheduling Strategies for Parallel Processing
Workload Characterization Issues and Methodologies
Performance Evaluation: Origins and Directions
SHARP: an architecture for secure resource peering
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
A comprehensive model of the supercomputer workload
WWC '01 Proceedings of the Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop
Combining batch execution and leasing using virtual machines
HPDC '08 Proceedings of the 17th international symposium on High performance distributed computing
Towards characterizing cloud backend workloads: insights from Google compute clusters
ACM SIGMETRICS Performance Evaluation Review
Towards Synthesizing Realistic Workload Traces for Studying the Hadoop Ecosystem
MASCOTS '11 Proceedings of the 2011 IEEE 19th Annual International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems
A better way to negotiate for testbed resources
Proceedings of the Second Asia-Pacific Workshop on Systems
Parallel computer workload modeling with markov chains
JSSPP'04 Proceedings of the 10th international conference on Job Scheduling Strategies for Parallel Processing
| Hi-index | 0.00 |
The rise of virtual infrastructures has renewed research interest in the design and implementation of resource allocators which allow users to reserve or use combinations of (virtual) nodes, switches, and network links on a variety of virtual infrastructures ranging from network testbeds to cloud computing facilities. However, since the area is still relatively new, work on resource allocation lacks realistic benchmarks. In this paper, we suggest how to generate realistic benchmarks for virtual infrastructure, and present our workload generator as an example, which is based on a 5-year trace of experiments submitted to the popular Emulab testbed. We demonstrate the importance as well as potential applications of such benchmarks by using the generated test workload in various evaluation scenarios.