VERITAS Software Corporation. File System White Paper, part I, II and III. http://www.veritas.com. VERITAS Software Corporation, November 1996.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....EFS [91] is an FFS with variably sized blocks called extents. EFS tries to store large files sequentially on disk to improve the sequential read and write performance. While EFS has improved on the efficiency of disk usage for large transfers, EFS still does not guarantee disk throughput. VxFS [98] is an extend based file system much like EFS. Although the layout of the VxFS file system is suitable for continuous media data storage, VxFS cannot, just like the other UNIX file systems guarantee throughput. VxFS has shown that sequential data storage is beneficial for filesystem throughput: a ....

....The chances of a partial disk failure of a disk array have increased compared to a single disk. Also, an array of disks has a much larger capacity compared to a single disk. Restoring the disk array from backup storage may take hours to days. The latter can lead to an enormous economic damage [104, 98]. Depending on the RAID form, a specific (RAID 0 4) or a variable disk (RAID 5 6) contains the redundant information of the data on the 41 other disks. If any of the disks fail, the original data is reconstructed by recalculating the failed disk. A problem with RAID technology occurs when ....

[Article contains additional citation context not shown here]

VERITAS Software Corporation. File System White Paper, part I, II and III. http://www.veritas.com. VERITAS Software Corporation, November 1996.

....into equal sized blocks, and consecutive blocks are placed on different disks in a round robin fashion. To minimize seek overhead, the block size is large (typically 256k, but can be configured between 16k and 1M) Large blocks give the same advantage as extents in file systems such as Veritas [15]: they allow a large amount of data to be retrieved in a single I O from each disk. GPFS stores small files (and the end of large files) in smaller units called subblocks, which are as small as 1 32 of the size of a full block. To exploit disk parallelism when reading a large file from a ....

....One class of file systems extends the traditional file server architecture to a storage area network (SAN) environment by allowing the file server clients to access data directly from disk through the SAN. Examples of such SAN file systems are IBM Tivoli SANergy [14] and Veritas SANPoint Direct [15]. These file systems can provide efficient data access for large files, but, unlike GPFS, all metadata updates are still handled by a centralized metadata server, which makes this type of architecture inherently less scalable. SAN file systems typically do not support concurrent write sharing, or ....

VERITAS SANPoint Direct File Access. Whitepaper, August 2000. VERITAS Software Corporation, Corporate Headquarters, 1600 Plymouth Street, Mountain View, CA 94043.

....package that provides the resiliency of RMSS Cluster. VCS detects service level failures on either node in the cluster, notifies operators and system administrators, and then institutes recovery procedures to shift the service from the failed elements of the cluster to reserve functioning elements [6]. VCS is employed on both the RMSS Cluster and the HA ACSLS Tape Library Subsystem. VCS uses agent scripts and programs as the intermediary between a service and VCS. One agent daemon runs for each configured resource type, and each type is unique to a particular hardware resource (persistent ....

) Veritas Volume Manager for Solaris, Getting Started Guide, Release 3.0.1, Veritas Software Corporation, Mountain View, CA, (C) May, 1999, P/N 100-001123

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC