Active block layout: a high performance disk layout mechanism

In traditional computer infrastructure, almost all the files that can be randomly accessed are stored on the disk. This paper presents a new Active Block Layout (ABL) mechanism. Basing on this mechanism, the friequently accessed data blocks are automatically copied and optimizedly distributed on the disk. By improving the access speed of these data blocks, we can enhance the performance of the storage system. Meanwhile, this paper presents the concept of the disk potential bandwidth. Using this concept, we could copy and synchronize the data efficiently without degrading the disk's response time significantly. In this paper, we introduce the disk scheduling, the disk potential bandwidth and heat-release mechanism. The experiment results of ABL are also provided. The experiments prove that the ABL mechanism can greatly shorten the access delay of the disk files and improve the performance of the file system.

[1]  Jeffrey Scott Vitter,et al.  Optimal disk I/O with parallel block transfer , 1990, STOC '90.

[2]  John Wilkes,et al.  An introduction to disk drive modeling , 1994, Computer.

[3]  David Wayne Jensen Disk I/O in high-performance computing systems , 1993 .

[4]  Garth A. Gibson Redundant disk arrays: Reliable, parallel secondary storage. Ph.D. Thesis , 1990 .

[5]  John Wilkes,et al.  UNIX Disk Access Patterns , 1993, USENIX Winter.

[6]  Mendel Rosenblum,et al.  The design and implementation of a log-structured file system , 1991, SOSP '91.

[7]  Garth A. Gibson,et al.  RAID: high-performance, reliable secondary storage , 1994, CSUR.

[8]  M. Frans Kaashoek,et al.  Embedded Inodes and Explicit Grouping: Exploiting Disk Bandwidth for Small Files , 1997, USENIX Annual Technical Conference.

[9]  Gregory R. Ganger,et al.  Towards higher disk head utilization: extracting free bandwidth from busy disk drives , 2000, OSDI.

[10]  Gregory R. Ganger,et al.  Track-Aligned Extents: Matching Access Patterns to Disk Drive Characteristics , 2002, FAST.

[11]  A. L. Narasimha Reddy,et al.  An Evaluation of Multiple-Disk I/O Systems , 1989, IEEE Trans. Computers.

[12]  Robert Geist,et al.  A continuum of disk scheduling algorithms , 1987, TOCS.

[13]  Toby J. Teorey,et al.  A comparative analysis of disk scheduling policies , 1972, CACM.

[14]  Mary Baker,et al.  Measurements of a distributed file system , 1991, SOSP '91.

[15]  Yossi Azar,et al.  The competitiveness of on-line assignments , 1992, SODA '92.

[16]  Asit Dan,et al.  Buffering and caching in large-scale video servers , 1995, Digest of Papers. COMPCON'95. Technologies for the Information Superhighway.

[17]  Xiang Yu,et al.  Trading capacity for performance in a disk array , 2000, OSDI.

[18]  Neil C. Wilhelm An anomaly in disk scheduling: a comparison of FCFS and SSTF seek scheduling using an empirical model for disk accesses , 1976, CACM.

[19]  Yale N. Patt,et al.  Soft updates: a solution to the metadata update problem in file systems , 2000 .