|
- Ph.D. Computer Science and Engineering
University of Minnesota, Twin Cities 2009-2015
- B.S. Computer Science and Engineering
Nankai University, China 2005-2009
- Teaching Assistant for CSCI4131 Internet Programming, Spring 2011
- D. Park, W. He and D. Du, "Hot Data Identification with Multiple Bloom Filters: Block-level Decision vs. I/O Request-level Decision", Journal of Computer Science and Technology (JCST), Jan. 2018
- A. Haghdoost, W. He, J. Fredin, D. Du, "hfplayer: Scalable Replay for Intensive Block I/O Workloads", ACM Transaction on Storage (TOS), Dec. 2017
- A. Haghdoost, W. He, J. Fredin, D. Du, "On the Accuracy and Scalability of Intensive I/O Workload Replay", 2014 USENIX Conference on File and Storage Technolgies (FAST), Feb. 2017
- W. He, D. Du, "SMaRT: An Approach to Shingled Magnetic Recording Translation", 2014 USENIX Conference on File and Storage Technolgies (FAST), Feb. 2017
- W. He, D. Du, S. B. Narasimhamurthy, "PIONEER: A Solution to Parallel I/O Workload Characterization and Generation", CCGrid 2015
- W. He, D. Du, "Novel Address Mappings for Shingled Write Disks", HotStorage 2014, Jun. 2014
- A. Haghdoost, W. He, J. Fredin, D. Du, "hfplayer: High Fidelity Block I/O Trace Replay Tool", 2014 USENIX Conference on File and Storage Technolgies (FAST), WiP report, Feb. 2014
- C. Lin, D. Park, W. He, D. H. Du, "H-SWD: Incorporating Hot Data Identification into
Shingled Write Disks", 2012 IEEE 20th International Symposium on Modeling, Analysis &
Simulation of Computer and Telecommunication Systems (MASCOTS), Aug. 2012
- NetApp, Inc. Summer 2012
I was working to develop a high fidelity I/O workload replay engine, in the Advanced
Development Department of Array Product Group. We defined high fidelity as being able to
provide extremely high workload injection rate to the array controller, as well as the capability to
preserve precise arrival pattern and inter-request dependencies as the same time.
- Dell | Compellent, Summer 2013
The project is about storage center I/O workload capture, replay and analysis. I was working in the core software team to build a workload recorder inside the storage center. The recorder aims to capture IO requests at different software layers, including virtulization, RAID, and disk manager, etc.
- Email: weihe at cs dot umn dot edu
- Office: DTC B34
|