Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
How to Scale Transactional Storage Systems Liuba Shrira, Barbara Liskov, Miguel Castro and Atul Adya
 

Summary: How to Scale Transactional Storage Systems
Liuba Shrira, Barbara Liskov, Miguel Castro and Atul Adya
Laboratory for Computer Science, MIT
Cambridge, MA 02139
Abstract
Applications of the future will need to support large numbers of clients and will require scalable
storage systems that allow state to be shared reliably. Recent research in distributed le systems provides
technology that increases the scalability of storage systems. But le systems only support sharing with
weak consistency guarantees and can not support applications that require transactional consistency.
The challenge is how to provide scalable storage systems that support transactional applications.
We are developing technology for scalable transactional storage systems. Our approach combines
scalable caching and coherence techniques developed in serverless le systems and DSM systems, with
recovery techniques developed in traditional databases. This position paper describes the design ra-
tionale for split caching, a new scalable memory management technique for network-based transactional
object storage systems, and fragment reconstruction, a new coherence protocol that supports ne-grained
sharing.
1 Introduction
The distributed applications of tomorrow will need to provide reliable service to a large number of users
and manipulate complex user-de ned data objects. Therefore, these applications will require large-scale
distributed storage systems that provide scalable performance, high reliability, and support user-de ned

  

Source: Adya, Atul - Google Labs

 

Collections: Computer Technologies and Information Sciences