The Experts below are selected from a list of 5550 Experts worldwide ranked by ideXlab platform
Youngjae Kim - One of the best experts on this subject based on the ideXlab platform.
-
An empirical study of Redundant Array of independent solid-state drives (RAIS)
Cluster Computing, 2015Co-Authors: Youngjae KimAbstract:Solid-state drives (SSD) are popular storage media devices alongside magnetic hard disk drives (HDD). SSD flash chips are packaged in HDD form factors and SSDs are compatible with regular HDD device drivers and I/O buses. This compatibility allows easy replacement of individual HDDs with SSDs in existing storage systems. However, under certain circumstances, SSD write performance can be significantly slowed by garbage collection (GC) processes. The frequency of GC activity is directly correlated with the frequency of inside-SSD write operations and the amount of data written to it. GC scheduling is locally controlled by an internal SSD logic. This paper studies the feasibility of Redundant Arrays of Independent Flash-based Solid-state drives (RAIS). We empirically analyze the RAIS performance using commercially-off-the-shelf (COTS) SSDs. We investigate the performance of various RAIS configurations under a variety of I/O access patterns. Finally, we present our performance and cost comparisons of RAIS with a fast, PCIe-based COTS SSD, in terms of performance and cost.
Michael Wolfe - One of the best experts on this subject based on the ideXlab platform.
-
PLDI - Elimination of Redundant Array subscript range checks
Proceedings of the ACM SIGPLAN 1995 conference on Programming language design and implementation - PLDI '95, 1995Co-Authors: Priyadarshan Kolte, Michael WolfeAbstract:This paper presents a compiler optimization algorithm to reduce the run time overhead of Array subscript range checks in programs without compromising safety. The algorithm is based on partial redundancy elimination and it incorporates previously developed algorithms for range check optimization. We implemented the algorithm in our research compiler, Nascent, and conducted experiments on a suite of 10 benchmark programs to obtain four results: (1) the execution overhead of naive range checking is high enough to merit optimization, (2) there are substantial differences between various optimizations, (3) loop-based optimizations that hoist checks out of loops are effective in eliminating about 98% of the range checks, and (4) more sophisticated analysis and optimization algorithms produce very marginal benefits.
Priyadarshan Kolte - One of the best experts on this subject based on the ideXlab platform.
-
PLDI - Elimination of Redundant Array subscript range checks
Proceedings of the ACM SIGPLAN 1995 conference on Programming language design and implementation - PLDI '95, 1995Co-Authors: Priyadarshan Kolte, Michael WolfeAbstract:This paper presents a compiler optimization algorithm to reduce the run time overhead of Array subscript range checks in programs without compromising safety. The algorithm is based on partial redundancy elimination and it incorporates previously developed algorithms for range check optimization. We implemented the algorithm in our research compiler, Nascent, and conducted experiments on a suite of 10 benchmark programs to obtain four results: (1) the execution overhead of naive range checking is high enough to merit optimization, (2) there are substantial differences between various optimizations, (3) loop-based optimizations that hoist checks out of loops are effective in eliminating about 98% of the range checks, and (4) more sophisticated analysis and optimization algorithms produce very marginal benefits.
A.k. Sahai - One of the best experts on this subject based on the ideXlab platform.
-
Performance aspects of RAID architectures
1997 IEEE International Performance Computing and Communications Conference, 1Co-Authors: A.k. SahaiAbstract:RAID (Redundant Array of Inexpensive Disks) concept was introduced to provide high performance I/O subsystem by striping data across multiple low cost disk drives and storing parity information on one of the disks to generate the original data in case of a disk failure. However, only CPU and disk drives were considered in the evaluation of system architecture of the original RAID investigation. Later, more studies to address RAID performance have been reported but they fail to provide an approach to complete evaluation of RAID I/O subsystems. This paper attempts to provide an approach to comprehensive evaluation of RAID architectures. It considers the complete I/O subsystem consisting of CPU, operating system, data bus, I/O controller, controller cache, disk paths and SCSI disk drives. Analytical models are developed to analyze the performance of different RAID designs. The main conclusions of the paper are: (1) Performance of I/O subsystems depends on data management in the cache (CPU, Storage Controller and Disk) and disk, and (2) RAID architectures provide high data availability but NOT necessarily high performance.
David J Richardson - One of the best experts on this subject based on the ideXlab platform.
-
Specifying Component Method Properties for Component State Recovery in RAIC
2002Co-Authors: Chang Liu, David J RichardsonAbstract:Redundant Arrays of Independent Components (RAIC) is a technology that uses groups of similar or identical distributed components to provide reliable services to applications [7]. RAIC controllers use the just-in-time component testing technique to detect component failures. RAIC also allows components in a Redundant Array to be added or removed dynamically at run-time. Component state recovery techniques are used to bring replacement components or newly added components up-to-date. Two types of state recovery techniques are used in RAIC: a snapshot-based approach and an invocation-history-based approach. Component method properties are used to optimize invocation-history-based component state recovery. This position paper gives a brief overview of RAIC and discusses the component state recovery techniques used in RAIC. A proofof-concept example is given to illustrate how a problem occurs in a component is detected and how a replacement component is brought up-to-date automatically to substitute the fail component.
-
RAIC: Architecting Dependable Systems through Redundancy and Just-In-Time Testing
2002Co-Authors: Chang Liu, David J RichardsonAbstract:Redundant Arrays of Independent Components (RAIC) is a technology that uses groups of similar or identical distributed components to provide dependable services. RAIC allows components in a Redundant Array to be added or removed dynamically during run-time, effectively making software components “hot-swappable” and thus achieves greater overall dependability. RAIC controllers use the just-in-time component testing technique to detect component failures and the component state recovery technique to bring replacement components up-to-date. This position paper gives a brief overview of RAIC and a proof-of-concept example to illustrate how problems occur during run-time can be masked by RAIC and would not affect smooth operations of the application.
-
COMPSAC - Using RAIC for dependable on-line upgrading of distributed systems
Proceedings 26th Annual International Computer Software and Applications, 1Co-Authors: Chang Liu, David J RichardsonAbstract:The technology of Redundant Arrays of independent components (RAIC) uses groups of similar or identical distributed components to provide dependable services (Liu and Richardson, 2002). RAIC allows components in the Redundant Array to be added or removed dynamically during run-time. This paper gives a brief overview of RAIC and discusses its special application for dependable on-line upgrading of distributed systems. A proof-of-concept example is given to illustrate how problems that occur during upgrading can be masked by RAIC and thus not affect smooth operations of the system-under-upgrade.
