Albert Chang, Mark F. Mergen, Robert K. Rader, Jeffrey A. Roberts, and Scott L. Porter. Evolution of storage facilities in AIX version 3 for RISC system/6000 processors. IBM Journal of Research and Development, 34(1):105--110, 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....[1, 7, 12, 18] by many different groups. Much of the work done to improve both LFS and LFS cleaners is directly applicable to CVFS. While journal based metadata is a new concept, journal14 ing has been used in several different file systems to provide metadata consistency guarantees efficiently [8, 9, 11, 39, 42]. Similarly to journal based metadata, LFS s segment summary block contains all of the metadata for the data in a segment, but is stored in an uncompressed format. Zebra s deltas improved upon this by storing only the changes to the metadata, but were designed exclusively for roll forward (a ....

A. Chang, M. F. Mergen, R. K. Rader, J. A. Roberts, and S. L. Porter. Evolution of storage facilities in AIX Version 3 for RISC System/6000 processors. IBM Journal of Research and Development, 34(1):105--110, January 1990.

....used [1, 7, 12, 17] by many different groups. Much of the work done to improve both LFS and LFS cleaners is directly applicable to CVFS. While journal based metadata is a new concept, journaling has been used in several different file systems to provide metadata consistency guarantees efficiently [8, 9, 11, 39, 42]. Database systems also use the roll back and roll forward concepts to ensure consistency during transactions [13] Several systems have used copy on write and differencing techniques that are common to versioning systems to decrease the bandwidth required during system backup or distributed ....

A. Chang, M. F. Mergen, R. K. Rader, J. A. Roberts, and S. L. Porter. Evolution of storage facilities in AIX Version 3 for RISC System/6000 processors. IBM Journal of Research and Development, 34(1):105--110, January 1990.

....existence of a sequential log allows for efficient file system recovery; the log can be read and processed from its last checkpoint, avoiding the more conventional scanning of the entire disk. Several of today s file systems have adopted this logging technique in an attempt to improve performance. [13, 106]. There have been two main approaches to the use of logging in file systems. The first, called journaling file systems, uses an auxiliary data structure, or log, to keep a record of the file system activity. This log is an append only structure which can be written to disk very efficiently. The ....

....be written to disk very efficiently. The actual data are written back to the file system at 18 some later point when the disk accesses will not impact performance. There have been several variants of the journaling file systems and they have become widely accepted in the commercial marketplace [13, 59, 106] The second class of file systems are called log structured, and they replace the entire file system with a single log based representation of the file system. While the logging file systems write small log records to disk when data in the cache is dirtied, the log structured systems (LFS) ....

A. Chang, M. Mergen, R. Rader, J. Roberts, and S. Porter. Evolution of storage facilities in aix version 3 for risc system/6000 processors. IBM Journal of Research and Development, 34(1), January 1990.

....vendors. 2 ATTRIBUTE MANAGED STORAGE Most existing approaches to storage management operate at too low a level: they require people to allocate and configure disks or disk arrays to particular pieces of work, but provide little help to them in doing so. For example, logical volume managers [Chang90] provide a number of low level mechanisms to allow multiple disks to be grouped together Elizabeth Shriver was supported by the NFS grant CCR 9504175. Contact author: Mirjana Spasojevic, Hewlett Packard Labs, MS 1U 13, 1501 Page Mill Road, Palo Alto, Ca 94304, USA. E mail: ....

A. Chang, M. F. Mergen, R. K. Rader, J. A. Roberts, and S. L. Porter. Evolution of storage facilities in AIX Version 3 for RISC System/6000 processors. IBM Journal of Research and Development, 34(1):105--10, January 1990.

....take little time. The rest of this section further analyzes the main components of the recovery time. JFS log redo AIX Journaled File System (JFS) writes meta data changes to a write ahead log to optimize disk utilization as well as to reduce the time to check consistency of the file system [7]. For example, when JFS creates or removes a file, or when makes certain inode changes, it creates log records reflecting these changes. When the UNIX sync operation executes, JFS writes actual data and meta data to permanent locations on the disk and then truncates the write ahead log ....

A. Chang, M. F. Mergen, R. K. Rader, J. A. Roberts, and S. L. Porter. Evolution of Storage Facilities in AIX Version 3 for RISC System/6000 Processors. IBM Journal Research and Development, 34(1), January 1990.

No context found.

Albert Chang, Mark F. Mergen, Robert K. Rader, Jeffrey A. Roberts, and Scott L. Porter. Evolution of storage facilities in AIX version 3 for RISC system/6000 processors. IBM Journal of Research and Development, 34(1):105--110, 1990.

No context found.

A. Chang, M. Mergen, R. Rader, J. Roberts, and S. Porter. Evolution of storage facilities in AIX version 3 for RISC System/6000 processors. IBM Journal of Research and Development, 34(1), January 1990.

No context found.

CHA 90 A. Chang, M. F. Mergen, R. K. Rader, J. A. Roberts, and S. L. Porter. Evolution of storage facilities in AIX Version 3 for RISC System/6000 processors. IBM Journal of Research and Development, Vol. 34, No. 1, January 1990.

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