Eventual Consistency Today: Limitations, Extensions, and Beyond

How can applications be built on eventually consistent infrastructure given no guarantee of safety?

PETER BAILIS AND ALI GHODSI, UC BERKELEY

In a July 2000 conference keynote, Eric Brewer, now VP of engineering at Google and a professor at the University of California, Berkeley, publicly postulated the CAP (consistency, availability, and partition tolerance) theorem, which would change the landscape of how distributed storage systems were architected.8 Brewer’s conjecture—based on his experiences building infrastructure for some of the first Internet search engines at Inktomi—states that distributed systems requiring always-on, highly available operation cannot guarantee the illusion of coherent, consistent single-system operation in the presence of network partitions, which cut communication between active servers. Brewer’s conjecture proved prescient: in the following decade, with the continued rise of large-scale Internet services, distributed-system architects frequently dropped “strong” guarantees in favor of weaker models—the most notable being eventual consistency.

Eventual Consistency Today:
Limitations, Extensions, and Beyond

Related:

Queue Video Portrait: Ang Cui

Ang Cui is a Ph.D. student at Columbia University in New York City. His research focuses on embedded devices such as routers, printers and VOIP phones. He is the inventor of a novel, host-based defense mechanism known as Symbiotes. Symbiotes are designed specifically to retrofit black-box, vulnerable, legacy embedded systems with sophisticated anti-exploitation mechanisms. In this video portrait, Ang describes how the extent of the embedded threat in real-world environments, discusses novel exploitation techniques for embedded systems–like enterprise networking equipment–and develops practical defenses for embedded systems that constitute our global communication substrate.

 

Ang Cui

 

Queue Portrait: Ang Cui

 

Join us in Lombard, IL, April 3-5, 2013, for NSDI ’13

Join us in Lombard, IL, April 3-5, 2013, for NSDI ’13.

The 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI ’13) focuses on the design principles, implementation, and practical evaluation of large-scale networked and distributed systems. The technical sessions will focus on hot topics such as pervasive computing, network integrity, data centers, performance, big data, security, privacy, and many others. NSDI ’13 also includes a poster and demo session, where presenters can showcase early research and discuss it with fellow attendees.

Register by March 13 and save. Additional discounts are available!
https://www.usenix.org/nsdi13/acmq

Idempotence Is Not a Medical Condition

An essential property for reliable systems

PAT HELLAND

The definition of distributed computing can be confusing. Sometimes, it refers to a tightly coupled cluster of computers working together to look like one larger computer. More often, however, it refers to a bunch of loosely related applications chattering together without a lot of system-level support.

http://queue.acm.org/detail.cfm?id=2187821

Related:

BASE: An Acid Alternative

A co-Relational Model of Data for Large Shared Data Banks

Testable System Administration