Over the last two decades, virtualization technologies have turned datacenter infrastructure into multitenant, dynamically provisionable, elastic resource, and formed the basis for the wide adoption of cloud computing. Many of today’s cloud applications, however, are based on continuous interactions with end users and their devices, and the trend is only expected to intensify with the expansion of the Internet of Things. The consequent bandwidth and latency requirements of these emerging workloads push the cloud boundary outside of traditional datacenters, giving rise to an ‘edge’ tier in the end-device-to-cloud-backend infrastructure. Computational resources embedded in anything from standalone microservers to WiFi routers and small cell access points, and their open APIs, present opportunities for deploying application logic and state closer to where it is being used, addressing both latency and backhaul bandwidth problems. This talk will look at the role that existing virtualization technologies can play in providing in this edge tier the required flexibility, dynamic provisioning and isolation, and will outline open problems that require development of new solutions. We will also discuss the opportunities to leverage these technologies to further deal with the diversity in the end-user device and IoT space.
Dr. Ada Gavrilovska is a Senior Research Scientist at the College of Computing and the Center for Experimental Research in Computer Systems (CERCS) at Georgia Tech. Her research is centered on innovation of the systems software stack, driven by emerging hardware technologies, and focused on supporting data- and communication-intensive applications. Recent projects include systems software innovation in light of large-scale parallelism in multicores, platform-wide compute and memory heterogeneity, novel interconnect capabilities and increases in device-level computational resource density. Gavrilovska’s research is supported by the National Science Foundation, the US Department of Energy, and industry grants, including from Cisco, HP, IBM, Intel, Intercontinental Exchange, LexisNexis, VMware, and others. She has published over 80 papers, and edited a book “High Performance Communications: A Vertical Approach”. In addition to research, she also teaches courses on operating systems and high performance communications. She has a BS degree in Computer Engineering from University Sts. Cyril and Methodius in Macedonia (’98), and a MS (’99) and PhD (’04) degrees in Computer Science from Georgia Tech.
The goal of virtual memory is an abstraction of infinite and private memory for every process. Unfortunately, the insatiable memory demands of modern applications increasingly violate this abstraction by exposing capacity, bandwidth, and performance limitations of modern hardware. Furthermore, emerging memory technologies are likely to exacerbate this problem. For instance, non-volatile memory differs from DRAM due to its asymmetric read/write performance and thus will likely be an addition rather than a drop-in replacement for DRAM. This talk will describe these problems and recent architecture and software innovations that address of some of them. If adopted, these solutions will impose substantial challenges for operating system memory management, which has evolved very slowly over the past 30 years. I will draw lessons from the past 15 years of garbage collection advances to suggest some promising directions for innovation.
Kathryn S. McKinley is a Principal Research at Microsoft. She was previously an Endowed Professor of Computer Science at The University of Texas at Austin. She is interested in creating systems that make programming easy and the resulting programs correct and efficient. She and her collaborators have produced several widely used tools: the DaCapo Java Benchmarks (30,000+ downloads), Hoard memory manager, TRIPS Compiler, MMTk memory management toolkit, and Immix garbage collector. Her awards include the ACM SIGPLAN Programming Languages Software Award and best paper and test-of-time awards from ASPLOS, OOPSLA, ICS, SIGMETRICS, IEEE Top Picks, SIGPLAN Research Highlights, and CACM Research Highlights. She currently serves on the CRA and CRA-W Boards. Dr. McKinley was honored to testify to the House Science Committee (Feb. 14, 2013). She is an IEEE and ACM Fellow and has graduated 22 PhD students. She and Scotty Strahan, her husband of 31 years, have three sons.
Emery Berger is a Professor in the College of Information and Computer Sciences at the University of Massachusetts Amherst, where he co-directs the PLASMA lab (Programming Languages and Systems at Massachusetts) and is a regular visiting researcher at Microsoft Research. He is the creator of a number of influential software systems including Hoard, a fast and scalable memory manager that accelerates multithreaded applications (used by companies including British Telecom, Cisco, Credit Suisse, Reuters, Royal Bank of Canada, SAP, and Tata, and on which the Mac OS X memory manager is based); DieHard, an error-avoiding memory manager that directly influenced the design of the Windows 7 Fault-Tolerant Heap; and DieHarder, a secure memory manager that was an inspiration for hardening changes made to the Windows 8 heap. He is currently serving / surviving as Program Chair for PLDI 2016, and maintains his blood-caffeine level at roughly 0.94.
Abhishek Bhattacharjee is an assistant professor in the department of Computer Science at Rutgers University. His research interests lie at the intersection of architectures and systems software. He received his PhD from Princeton University in 2010. His research is partly funded by an NSF Career award, and in the past, his work have been selected for IEEE Micro’s Top Picks in Computer Architecture journal.
Simon is an assistant professor at the University of Texas at Austin, where he leads research in operating systems and networks. He received a Ph.D. in Computer Science from ETH Zurich in 2012 and an MSc in Computer Science from the Carl-von-Ossietzky University Oldenburg, Germany in 2006. Before joining UT Austin in 2016, he was a research associate at the University of Washington from 2012-2016.
Kevin Pedretti is a Principal Member of Technical Staff at Sandia National Laboratories in the Center for Computing Research. His research is centered on scalable system software for extreme-scale parallel computing platforms, with specific focus on lightweight operating systems, networking, and power management. He is the lead of the Kitten Lightweight Kernel project and is a collaborator on the Palacios Virtual Machine Monitor, which together are seeking to leverage virtualization to increase the functionality and flexibility of HPC system software stacks. Recent work has explored the use of lightweight virtualization to enable application composition, allowing discrete simulation, analysis, and tool components to be composed with one another across virtual machine boundaries.
Chris Rossbach is a Senior Researcher at VMware Research Group, an Assistant Professor at the University of Texas at Austin, and an alumnus of Microsoft Research’s Silicon Valley Lab. He received his PhD in computer science from The University of Texas at Austin in 2009. Chris’s research focuses on operating system and architectural support for emerging hardware, particularly those that leverage concurrency. He is interested in concurrency in the broadest sense, but has a particular affinity for exploring abstractions that enable systems to take advantage of concurrency to improve performance and mechanisms that simplify the development of parallel programs.
Chair: Vivek Sarkar (Rice University)
Chair: Galen Hunt (Microsoft Research NExT)
Building A KVM-based Hypervisor for A Heterogeneous System Architecture
Yu-Ju Huang (National Chiao Tung University, Taiwan), Hsuan-Heng Wu (National Taiwan University, Taiwan), Yeh-Ching Chung (National Tsing Hua University, Taiwan), and Wei-Chung Hsu (National Taiwan University, Taiwan) [Presentation]
Won the Best Paper Award!
Shoot4U: Using VMM Assists to Optimize TLB Operations on Preempted vCPUs
Jiannan Ouyang, John R. Lange (University of Pittsburgh), and Haoqiang Zheng (VMware, Inc.) [Presentation]
Performance Implications of Extended Page Tables on Virtualized x86 Processors
Timothy Merrifield (University of Illinois at Chicago) and Reza Taheri (VMWare, Inc.) [Presentation]
Chair: Kevin Pedretti (Sandia National Laboratories)
On Selecting the Right Optimizations for Virtual Machine Migration
Senthil Nathan, Umesh Bellur, and Purushottam Kulkarni (IIT Bombay) [Presentation]
Urgent Virtual Machine Eviction with Enlightened Post-Copy
Yoshihisa Abe (Carnegie Mellon University), Roxana Geambasu (Columbia University), Kaustubh Joshi (AT&T Research), and Mahadev Satyanarayanan (Carnegie Mellon University) [Presentation]
SRVM: Hypervisor Support for Live Migration with Pass-through SR-IOV Network Devices
Xin Xu and Bhavesh Davda (VMware) [Presentation]
Chair: Vishakha Gupta-Cledat (Intel Labs)
Enabling Efficient Hypervisor-as-a-Service Clouds with Ephemeral Virtualization
Dan Williams (IBM T.J. Watson Research Center), Yaohui Hu (Binghamton University), Umesh Deshpande (IBM Almaden Research Center), Piush K Sinha (Binghamton University), Nilton Bila (IBM T.J. Watson Research Center), Kartik Gopalan (Binghamton University), and Hani Jamjoom (IBM T.J.Watson Research Center) [Presentation]
Abstractions for Practical Virtual Machine Replay
Anton Burtsev, David Johnson, Mike Hibler, Eric Eide, and John Regehr (University of Utah) [Presentation]
Chair: Don Porter (Stony Brook University)
Chair: John Criswell (University of Rochester)
Exploiting FIFO Scheduler to Improve Parallel Garbage Collection Performance
Junjie Qian, Witawas Srisa-an, Sharad Seth (University of Nebraska Lincoln), Hong Jiang (University of Texas Arlington), Du Li (Carnegie Mellon University), and Pan Yi (University of Nebraska Lincoln) [Presentation]
Performance Analysis and Optimization of Full Garbage Collection in Memory-hungry Environments
Yang Yu (Fudan University), Tianyang Lei, Haibo Chen, and Binyu Zang (Shanghai Jiao Tong University) [Presentation]
Leveraging Managed Runtime Systems to Build, Analyze, and Optimize Memory Graphs
Rebecca Smith and Scott Rixner (Rice University) [Presentation]
Chair: Dilma Da Silva (Texas A&M University)
The nom Profit-Maximizing Operating System
Muli Ben-Yehuda (Technion and LightBits Labs), Orna Agmon Ben-Yehuda, and Dan Tsafrir (Technion) [Presentation]
Enabling Hybrid Parallel Runtimes Through Kernel and Virtualization Support
Kyle Hale and Peter Dinda (Northwestern University) [Presentation]
Moderator: Carl Waldspurger (Independent Consultant)
- Emery Berger (University of Massachusetts at Amherst)
Abhishek Bhattacharjee (Rutgers University) [Abstract]
Kevin Pedretti (Sandia National Laboratories) [Abstract]
Simon Peter (University of Texas at Austin) [Abstract]
Chris Rossbach (VMware Research Group & University of Texas at Austin) [Abstract]