osdi02 - Ivy: A Read/Write Peer-to-Peer File System Athicha...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Ivy: A Read/Write Peer-to-Peer File System Athicha Muthitacharoen, Robert Morris, Thomer M. Gil, and Benjie Chen { athicha, rtm, thomer, benjie } @lcs.mit.edu MIT Laboratory for Computer Science 200 Technology Square, Cambridge, MA 02139. Abstract Ivy is a multi-user read/write peer-to-peer file system. Ivy has no centralized or dedicated components, and it provides useful integrity properties without requiring users to fully trust either the underlying peer-to-peer stor- age system or the other users of the file system. An Ivy file system consists solely of a set of logs, one log per participant. Ivy stores its logs in the DHash dis- tributed hash table. Each participant finds data by con- sulting all logs, but performs modifications by appending only to its own log. This arrangement allows Ivy to main- tain meta-data consistency without locking. Ivy users can choose which other logs to trust, an appropriate arrange- ment in a semi-open peer-to-peer system. Ivy presents applications with a conventional file sys- tem interface. When the underlying network is fully connected, Ivy provides NFS-like semantics, such as close-to-open consistency. Ivy detects conflicting modi- fications made during a partition, and provides relevant version information to application-specific conflict re- solvers. Performance measurements on a wide-area net- work show that Ivy is two to three times slower than NFS. 1 Introduction This paper describes Ivy, a distributed read/write net- work file system. Ivy presents a single file system im- age that appears much like an NFS [33] file system. In contrast to NFS, Ivy does not require a dedicated server; instead, it stores all data and meta-data in the DHash [9] peer-to-peer block storage system. DHash can distribute and replicate blocks, giving Ivy the potential to be highly available. One possible application of Ivy is to support distributed projects with loosely affiliated participants. Building a shared read-write peer-to-peer file system poses a number of challenges. First, multiple distributed writers make maintenance of consistent file system meta- data difficult. Second, unreliable participants make lock- ing an unattractive approach for achieving meta-data consistency. Third, the participants may not fully trust each other, or may not trust that the other participants machines have not been compromised by outsiders; thus there should be a way to ignore or un-do some or all modifications by a participant revealed to be untrustwor- thy. Finally, distributing file-system data over many hosts means that the system may have to cope with operation while partitioned, and may have to help applications re- pair conflicting updates made during a partition....
View Full Document

This note was uploaded on 12/08/2011 for the course CS 525 taught by Professor Gupta during the Spring '08 term at University of Illinois, Urbana Champaign.

Page1 / 14

osdi02 - Ivy: A Read/Write Peer-to-Peer File System Athicha...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online