Paper Info
Title
RDMA-Based Direct Transfer of File Data to Remote Page Cache
Abstract
The performance of a distributed file system significantly affects data-intensive applications that frequently execute I/O operations on large amounts of data. Although many modern distributed file systems are geared to provide highly efficient I/O performance, their operations are nonetheless affected by runtime overhead in data transfer between client nodes and I/O servers. A large part of the overhead is caused by memory copies executed by the client interface using the FUSE framework or a special kernel module. In this paper, we propose a method based on InfiniBand RDMA that improves data transfer performance between client and server in a distributed file system. The major characteristic of the method is that it transfers file data directly from a server's memory to the page cache of a client node. The method minimizes memory copies that are otherwise executed in the client interface or the operating system kernel. We implemented the proposed method in the Gfarm distributed file system and tested it using I/O benchmark software and real applications. The experimental results showed that our method effected a performance improvement of up to 78.4% and 256.0% in sequential and random file reads, respectively, and an improvement of up to 6.3% in data-intensive applications.
Year
DOI
Venue
2015
10.1109/CLUSTER.2015.40
Cluster Computing
Keywords
Field
DocType
distributed file systems, InfiniBand, RDMA, high-performance computing, storage
Distributed File System,SSH File Transfer Protocol,File Control Block,Virtual file system,Self-certifying File System,Computer science,Parallel computing,Device file,Versioning file system,Memory-mapped file,Operating system
Conference
ISSN
Citations 
PageRank 
1552-5244
1
0.35
References 
Authors
17
4
Name
Order
Citations
PageRank
Shin Sasaki151.47
Kazushi Takahashi231.42
Yoshihiro Oyama324320.62
Osamu Tatebe430942.94