FAST '08 – Abstract
Pp. 297–312 of the Proceedings
SWEEPER: An Efficient Disaster Recovery Point Identification Mechanism
Akshat Verma, IBM India Research; Kaladhar Voruganti, Network Appliance;
Ramani Routray, IBM Almaden Research; Rohit Jain, Yahoo India
Abstract
Data corruption is one of the key problems that is on top of the radar
screen of most CIOs. Continuous Data Protection (CDP) technologies help
enterprises deal with data corruption by maintaining multiple versions of data
and facilitating recovery by allowing an administrator restore to an earlier
clean version of data. The aim of the recovery process after data corruption is
to quickly traverse through the backup copies (old versions), and retrieve a
clean copy of data. Currently, data recovery is an ad-hoc, time consuming and
frustrating process with sequential brute force approaches, where recovery time
is proportional to the number of backup copies examined and the time to check a
backup copy for data corruption.
In this paper, we present the design and implementation of SWEEPER
architecture and backup copy selection algorithms that specifically tackle the
problem of quickly and systematically identifying a good recovery point. We
monitor various system events and generate checkpoint records that help in
quickly identifying a clean backup copy. The SWEEPER methodology
dynamically determines the selection algorithm based on user specified recovery
time and recovery point objectives, and thus, allows system administrators to
perform trade-offs between recovery time and data currentness. We have
implemented our solution as part of a popular Storage Resource Manager product
and evaluated SWEEPER under many diverse settings. Our study clearly
establishes the effectiveness of SWEEPER as a robust strategy to
significantly reduce recovery time.
- View the full text of this paper in HTML and PDF.
Listen to the presentation in
MP3 format.
The Proceedings are published as a collective work, © 2008 by the USENIX Association. All Rights Reserved. Rights to individual papers remain with the author or the author's employer. Permission is granted for the noncommercial reproduction of the complete work for educational or research purposes. USENIX acknowledges all trademarks within this paper.
|