Elie Krevat
Graduate Student
Department of Computer Science
Carnegie Mellon University
GHC 6221
ekrevat at cs dot cmu dot edu
Hi there! I'm a Ph.D. student in computer science at Carnegie Mellon, researching many flavors of distributed systems, storage, networks, virtual machines, and cloud computing. I'm also a member of the Parallel Data Lab where I am advised by Greg Ganger.
News
June 4, 2009
I'm spending this summer in Pittsburgh, working on a number of Cloud Computing projects! Stay tuned...
August 28, 2008
Just got back to Pittsburgh for the start of the Fall semester, where I'm excited to get back to research and to TA 15-213: Introduction to Computer Systems.
I really enjoyed my summer in Cambridge, MA working for VMware, where the people are friendly, talented, and driven. I can also finally talk a little bit about my work because they've just recently gone public with their intention to enter the cloud computing space. I helped build a prototype cloud services model and management layer that experiments with using some forward-looking Semantic Web and other web service technologies to monitor and manage virtual appliances in the cloud.
Research
My current research interests involve coordination and synchronization problems in large distributed systems with a focus on cloud computing and distributed storage. Some of my research projects are listed below.
Incast: TCP Throughput Collapse in Cluster-based Storage Systems
Building cluster-based storage systems using commodity TCP/IP and Ethernet networks is attractive because of their low cost, ease-of-use, and the desire to combine routing infrastructures for LAN, SAN, and high performance computing. However, an important barrier to their use is the problem of TCP throughput collapse, where bursty traffic from synchronized reads in cluster-based storage systems produce a one to two order magnitude TCP throughput collapse. We have studied the network conditions that cause this TCP throughput collapse in both simulation and real-world deployments, examined the effectiveness of TCP- and Ethernet-level solutions, and with our latest publication we have found reasonable solutions to the problem with high resolution timers that implement a microsecond-granularity TCP retransmission timeout. This solution is both feasible and practical for fast storage networks while also safe for wide area networks, revisiting an older assumption on spurious TCP retransmissions that no longer appears to hold true.
Performance Insulation for Shared Storage
Shared storage offers many benefits for scaling load and reducing infrastructure and management costs. However, the overhead of sharing a server across multiple workloads interferes with the performance, efficiency, and fairness of the system. The Argon project has developed a metric, the R-value, to measure the fraction of the throughput performance that a workload should receive within its scheduled time quanta. By applying techniques such as prefetching, write coalescing, and cache-partitioning, Argon has demonstrated that stronger service guarantees can be made on a single server with reasonable response times. Current work in this area extends the results from a single server to multiple servers, dealing with the coordination and synchronization of workloads for more powerful system-wide QoS guarantees.
Publications
-
- Safe and Effective Fine-grained TCP Retransmissions for Datacenter Communication.
- Vijay Vasudevan, Amar Phanishayee, Hiral Shah, Elie Krevat, David Andersen, Gregory Ganger, Garth Gibson, and Brian Mueller.
- To appear in ACM SIGCOMM.
- August 2009.
- [pdf]
-
- Tashi: Location-aware Cluster Management.
- Michael Kozuch, Michael Ryan, Richard Gass, Steven Schlosser, David O’Hallaron, James Cipar, Elie Krevat, Julio López, Michael Stroucken, and Gregory Ganger.
- In Proceedings of First Workshop on Automated Control for Datacenters and Clouds.
- June 2009.
- [pdf]
-
- Measurement and Analysis of TCP Throughput Collapse in Cluster-Based Storage Systems.
- Amar Phanishayee, Elie Krevat, Vijay Vasudevan, David Andersen, Gregory Ganger, Garth Gibson, and Srinivasan Seshan.
- In Proceedings of File and Storage Technologies (FAST).
- February 2008.
- [pdf]
-
- On Application-level Approaches to Avoiding TCP Throughput Collapse in Cluster-based Storage Systems.
- Elie Krevat, Vijay Vasudevan, Amar Phanishayee, David Andersen, Gregory Ganger, Garth Gibson, and Srinivasan Seshan.
- In Proceedings of Petascale Data Storage Workshop, Supercomputing.
- November 2007.
- [pdf] [ppt]
-
- Scheduling Algorithms to Improve Utilization in Toroidal-Interconnected Systems.
- Elie Krevat.
- MIT Master of Engineering Thesis.
- May 2003.
- [pdf]
-
- An Overview of the BlueGene/L Supercomputer.
- NR Adiga et al. (large author list).
- In ACM/IEEE conference on Supercomputing.
- November 2002.
- [pdf]
-
- Job Scheduling for the BlueGene/L System.
- Elie Krevat, Jose G. Castanos, and Jose E. Moreira.
- In Job Scheduling Strategies for Parallel Processing, 8th International Workshop (JSSPP).
- July 2002.
- [pdf]
Other Projects and Presentations
-
- Energy-Efficient Dynamic Source Routing in Ad-Hoc Wireless Networks.
- Elie Krevat and Arian Shahdadi.
- Computer Networks.
- December 2001.
- [pdf]
Teaching
I TAed 15-213: Introduction to Computer Systems in Fall '08.
I also TAed 6.033: Computer System Engineering at MIT in Spring '03 when I was earning my M.Eng. degree.
Background
Before CMU, I completed by B.S. and M.Eng. in computer science at MIT with a minor in economics. My master's thesis included work from a few summers and a semester of research at IBM T.J. Watson Research Center on system software for the Blue Gene supercomputer. I also spent 3 years working for Microsoft as a software design engineer, where I played around with pre-alpha Vista technologies and developed the first two versions of Office Accounting Professional, a stand-alone product and third-party development platform for small business accounting.
Fun
I first got excited about sailing just before I left MIT, and after taking sailing lessons in Seattle a few years ago, I was back in Boston this summer where I again had access to the MIT Sailing Pavilion.
Since sailing options in Pittsburgh are sadly limited, I've returned to playing another sport that I haven't attempted since my undergraduate days -- ice hockey! I'm not ready to crack the Penguins roster just yet, but there's no better way to improve your athletic agility than avoiding large speeding human missiles on ice.
When I can find the time, I enjoy traveling to exotic world destinations. Some of my longer trips have included Spain, Italy, Greece, Thailand, Israel, and Argentina (where I went on a month-long volunteering and solidarity trip in 2003 during their economic crisis).
I'm always on a search for good sushi restaurants - in Pittsburgh, Sushi Kim and Chaya are my favorites.
I have two wonderful and very talented sisters, Ariela and Rina, but when I tell them that Rina says "Ariela is both of them." See, they're funny too! Ariela gets many kudos for designing this web page in almost no time at all (she's a freelance graphic design artist in New York City, and promises to make it even splashier later). Rina isn't even in college yet, but her artistic abilities are already amazing. Check out Ariela's web site here and Rina's here.