CS 201: Building a High-performance Deduplication System, PETROS EFSTATHOPOULOS, Symantec Research Labs
Dec 01, 2011
from 04:15 PM to 05:45 PM
|Contact Name||Edna Todd|
|Contact Phone||310 825-4033|
|Add event to calendar||
Building a High-performance Deduplication System
Symantec Research Labs
Modern deduplication has become quite effective at eliminating duplicates in data, thus multiplying the effective capacity of disk-based backup systems, and enabling them as realistic tape replacements. Despite these improvements, single-node raw capacity is still mostly limited to tens or a few hundreds of terabytes, forcing users to resort to complex and costly multi-node systems, which usually only allow them to scale to singledigit petabytes. As the opportunities for deduplication efficiency optimizations become scarce, we are challenged with the task of designing deduplication systems that will effectively address the capacity, throughput, management and energy requirements of the petascale age.
We present a high-performance deduplication prototype, designed at SRL from the ground up to optimize overall single-node performance, by making the best possible use of a node’s resources, and achieve three important goals: scale to large capacity, provide good deduplication efficiency, and near-raw-disk throughput.
We will also discuss the requirements and challenges in designing commercial large scale cloud deduplication system.
Petros Efstathopoulos is a Sr. Principal Researcher at Symantec Research Labs in Culver City, CA. He holds a Ph.D. degree in Computer Science from the University of California, Los Angeles (UCLA, 2008) and a B.Sc. degree in Electrical and Computer Engineering from the National Technical University of Athens, Greece (NTUA).
His research interests include operating systems, security, information flow control systems, security policy management, virtualization, storage, and file systems.
Petros joined Symantec Research Labs in 2009 and is currently working on next-generation storage/backup systems, cloud storage, portable storage security, and mobile platform security.
Hosted by Prof Glenn Reinman
DATE: Tuesday, January 10
** Refreshments at 4:00pm, Speaker at 4:15pm **
TIME: 4:15 – 5:45 P.M.
PLACE: 3400 Boelter Hall