Sedat Akyürek

dblp:70/4250 · DBLP profile ↗
← Back
4ranked-venue papers
4as first author
0since 2021 · last 1997
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 2 · 2 first-authorSoftware engineering, systems software and programming languages · 1 · 1 first-authorDatabases, data management, data science and information retrieval · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer architecture, parallel and distributed computing, and storage systems
3 papers
Storage systems · 84% Memory systems · 16%
Software engineering, system software, and programming languages
1 paper
Operating systems · 100%

Topics — the 7 heaviest of 7, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Storage systems › i/o optimization
disk seek time reduction
0.021995
Adaptive Block Rearrangement · ACM Trans. Comput. Syst. 1995
Adaptive Block Rearrangement · ICDE 1993
Storage systems
buffer management
0.011995
Management of Partially Safe Buffers · IEEE Trans. Computers 1995
Storage systems › i/o scheduling
disk scheduling
0.011995
Adaptive Block Rearrangement · ACM Trans. Comput. Syst. 1995
Memory systems
non-volatile memory
0.011995
Management of Partially Safe Buffers · IEEE Trans. Computers 1995
Storage systems
data placement
0.011993
Adaptive Block Rearrangement · ICDE 1993
Storage systems › magnetic storage
disk storage
0.011993
Adaptive Block Rearrangement · ICDE 1993
Operating systems › i/o › i/o subsystem
device drivers
0.011995
Adaptive Block Rearrangement · ACM Trans. Comput. Syst. 1995

Methods — techniques the papers use, named apart from their topics

trace-driven simulation · 0.1request monitoring · 0.0
YearPublicationVenuePosition
1997 Adaptive Block Rearrangement Under UNIX
abstract
An adaptive UNIX disk device driver is described. To reduce seek times, the driver copies frequently-referenced blocks from their original locations to reserved space near the center of the disk. Block reference frequencies need not be known in advance. Instead, they are estimated by monitoring the stream of arriving requests. Measurements show that the adaptive driver reduces seek times and response times substantially. © 1997 by John Wiley & Sons, Ltd.
Sedat Akyürek, Kenneth Salem
Softw. Pract. Exp.1
1995 Management of Partially Safe Buffers
abstract
Safe RAM is RAM which has been made as reliable as a disk. We consider the problem of buffer management in partially safe buffers, i.e., buffers which contain both safe RAM and volatile RAM. Buffer management techniques for partially safe buffers explicitly consider the safety of memory in deciding which data to place in the buffer, where to place it, and when to copy updates back to the disk. We present techniques for managing such buffers and study their performance using trace-driven simulations.>
Sedat Akyürek, Kenneth Salem
IEEE Trans. Computers1
1995 Adaptive Block Rearrangement
abstract
An adaptive technique for reducing disk seek times is described. The technique copies frequently referenced blocks from their original locations to reserved space near the middle of the disk. Reference frequencies need not be known in advance. Instead, they are estimated by monitoring the stream of arriving requests. Trace-driven simulations show that seek times can be cut substantially by copying only a small number of blocks using this technique. The technique has been implemented by modifying a UNIX device driver. No modifications are required to the file system that uses the driver.
Sedat Akyürek, Kenneth Salem
ACM Trans. Comput. Syst.1
1993 Adaptive Block Rearrangement
abstract
An adaptive technique for reducing disk seek times is described. The technique copies frequently referenced blocks from their original locations to reserved space near the center of the disk. Reference frequencies need not be known in advance. Instead, they are estimated by monitoring the stream of arriving requests. Results of trace-driven simulations show that seek times can be cut in half by copying only a small number of blocks using this technique. The technique is designed to be implemented in a device driver or controller. It is independent of the file system or database manager that uses the disk.>
Sedat Akyürek, Kenneth Salem
ICDE1