Person:
Smith, Keith

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Smith

First Name

Keith

Name

Smith, Keith

Filters

19942

Settings

Author's Publications: search.filters.isAuthorOfPublication.4975c5a6-7e9a-4154-aa44-1d3dada170be

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    VINO: The 1994 Fall Harvest
    (1994) Endo, Yasuhiro; Seltzer, Margo; Small, Christopher; Smith, Keith
    Current operating systems are designed to provide least-common-denominator service to a variety of applications. They export few internal kernel facilities, and those which are exported have irregular interfaces. As a result, resource intensive applications such as database management systems and multimedia applications, are often poorly served by the operating system. These applications often go to great lengths to bypass normal kernel mechanisms to achieve acceptable performance. We describe a new kernel architecture, the VINO kernel, which addresses the limitations of conventional operating systems. The VINO design is driven by three principles: 1.) Application Directed Policy: the operating system provides a collection of mechanisms, but applications dictate the policies applied to those mechanisms. 2.) Kernel as Toolbox: applications can reuse the kernel's primitives. 3.) Universal Resource Access: all resources are accessed through a single, common interface. VINO's power and flexibility make it an ideal platform for research in operating systems and resource intensive applications.
  • Thumbnail Image
    Publication
    File Layout and File System Performance
    (1994) Smith, Keith; Seltzer, Margo
    Most contemporary implementations of the Berkeley Fast File System optimize file system throughput by allocating logically sequential data to physically contiguous disk blocks. This clustering is effective when there are many contiguous free blocks on the file system. But the repeated creation and deletion of files of varying sizes that occurs over time on active file systems is likely to cause fragmentation of free space, limiting the ability of the file system to allocate data contiguously and therefore degrading performance. This paper presents empirical data and the analysis of allocation and fragmentation in the SunOS 4.1.3 file system (a derivative of the Berkeley Fast File System). We have collected data from forty-eight file systems on four file servers over a period of ten months. Our data show that small files are more fragmented than large files, with fewer than 35% of the blocks in two block files being allocated optimally, but more than 80% of the blocks in files larger than 256 kilobytes being allocated optimally. Two factors are responsible for this difference in fragmentation, an uneven distribution of free space within file system cylinder groups and a disk allocation algorithm which frequently allocates the last block of a file discontiguously from the rest of the file. Performance measurements on replicas of active file systems show that they seldom perform as well as comparable empty file systems but that this performance degradation is rarely more than 10–15%. This decline in performance is directly correlated to the amount of fragmentation in the files used by the benchmark programs. Both file system utilization and the amount of fragmentation in existing files on the file system influence the amount of fragmentation in newly created files. Characteristics of the file system workload also have a significant impact of file system fragmentation and performance, with typical news server workloads causing extreme fragmentation.