Hagmann, R. (1991). Low Latency Logging. Technical Report CSL-91-1, Xerox Corporation, Palo Alto, CA.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....a special access primitive that allows a piece of data to be written where the disk head is at that instant. Similar ideas have been implemented in IBM s WADS system [15] which uses fixed head disks (disk drums) to implement the write where the disk head is semantics, and in a paper design [7], which attempts to reduce the rotational latency by using a separate log disk [4] and by intentionally writing to a new track when the current track s utilization reaches a certain threshold. Several techniques have been proposed to improve the performance of synchronous writes. Two well known ....

.... When a log disk write is finished, the Trail driver checks the space utilization of the current track and positions the disk head to the sector on the next track that is physically the closest to the head s current position, if the current track utilization reaches certain pre defined threshold [7]. This is an optimization over the scheme in which the log disk head is moved to the next track after each disk write. When a log disk write is finished, the Trail driver positions the log disk s head to the sector on the next track that is physically the closest to the head s current position. ....

HAGMANN, R. Low latency logging. Tech. Rep. CSL-91-1, Xerox Corporation. Palo Alto, CA, February 1991.

....a special access primitive that allows a piece of data to be written where the disk head is at that instant. Similar ideas have been implemented in IBM s WADS system [46] which uses xed head disks (disk drums) to implement the write where the disk head is semantics, and in a paper design [27], which attempts to reduce the rotational latency by using a separate log disk [20] and by intentionally writing to a new track when the current track s utilization reaches a certain threshold. Several techniques have been proposed to improve the performance of synchronous writes. Two well known ....

Hagmann, R. Low latency logging. Tech. Rep. CSL-91-1, Xerox Corporation. Palo Alto, CA, February 1991.

....sequential scanning to propagate data bu ered at the log disk to the normal data disk after system failures. Similar ideas have been implemented in IBM s WADS system [15] which uses xed head disks (disk drums) to implement the write where the disk head is semantics, and in a paper design [7], which attempts to reduce the rotational latency by using a separate log disk [4] and by intentionally writing to a new track when the current track s utilization reaches a certain threshold. Several techniques have been proposed to improve the performance of synchronous writes. Two well known ....

.... When a log disk write is nished, the Trail driver checks the space utilization of the current track and positions the disk head to the sector on the next track that is physically the closest to the head s current position, if the current track utilization reaches certain pre de ned threshold [7]. This is an optimization over the scheme in which the log disk head is moved to the next track after each disk write. For example, from Track i 2 to i 3 in Figure 1, knowing the number of sectors in the current track, Trail can calculate the target block address of the physically closest ....

Hagmann, R. Low latency logging. Tech. Rep. CSL-91-1, Xerox Corporation. Palo Alto, CA, February 1991.

....By running file system code inside the disk, we can combine the precise knowledge of the file system semantics and detailed disk mechanism to perform optimizations that are otherwise impossible. The basic concept of performing writes near the disk head position is by no means a new one [5, 8, 10, 13, 23]. But these systems either do not guarantee atomic writes, have poor failure recovery times, or require NVRAM. In this work, we present the design of a virtual log, a logging strategy based on eager writing with these unusual features: Virtual logging supports fast, synchronous, and atomic ....

....[10] addresses this issue for drums (fixed head disks) by keeping some tracks completely empty. Once each track is filled with a single block, it is not re used until the data is copied out of the track into its normal location. Likewise, Hagmann places the write ahead log in its own logging disk[13], where each log append can 12 fill any open block in the cylinder until its utilization reaches a threshold. Eager writing in our system, while retaining good logging performance, assumes no dedicated logging disk and does not require copying of data from the log into its permanent location. The ....

Hagmann, R. Low Latency Logging. Tech. Rep. CSL91 -1, Xerox Corporation, Palo Alto, CA, February 1991.

....that allows a piece of data to be written where the disk head happens to be at that instant. Similar ideas have been implemented in IBM s WADS system [15] which uses fixed head disks (disk drums) to implement the write where the disk head is semantics, and in a paper design described in [16], which attempts to reduce the rotational latency by using a separate log disk [18] and by intentionally writing to a new track when the current track s utilization reaches a certain threshold. The data recovery algorithm in [1] is also relatively ine#cient in that it requires sequential scanning ....

Hagmann, R., "Low latency logging," CSL-91-1, Xerox Palo Alto Research Center, Palo Alto, CA, February 1991.

No context found.

Hagmann, R. (1991). Low Latency Logging. Technical Report CSL-91-1, Xerox Corporation, Palo Alto, CA.

No context found.

Hagmann, R. Low Latency Logging. Tech. Rep. CSL91 -1, Xerox Corporation, Palo Alto, CA, February 1991.

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