Talk Abstract
Flash storage is making inroads into data centers, enabling a new class of applications that require persistence as well as extreme performance. Clusters of flash can satisfy millions of I/Os per second at sub-millisecond latencies while consuming significantly less power than disk clusters. Unfortunately, current designs for scalable storage systems are predicated on the properties of hard disks, and can be inefficient or unreliable when used with flash clusters. New abstractions are required to fully realize the potential of flash clusters. We drew foundational lessons from designing Falcon, a new transactional storage cluster which works at the speed of flash. In this keynote, we describe the challenges and design choices we made.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Balakrishnan, M., Malkhi, D., Prabhakaran, V., Wobber, T. (2011). DISC 2011 Invited Lecture by Dahlia Malkhi: Going beyond Paxos. In: Peleg, D. (eds) Distributed Computing. DISC 2011. Lecture Notes in Computer Science, vol 6950. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24100-0_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-24100-0_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24099-7
Online ISBN: 978-3-642-24100-0
eBook Packages: Computer ScienceComputer Science (R0)