The Experts below are selected from a list of 373860 Experts worldwide ranked by ideXlab platform
Bhuvan Urgaonkar - One of the best experts on this subject based on the ideXlab platform.
-
dftl a flash translation layer employing demand based selective caching of page level address mappings
Architectural Support for Programming Languages and Operating Systems, 2009Co-Authors: Aayush Gupta, Bhuvan UrgaonkarAbstract:Recent technological advances in the development of flash-memory based devices have consolidated their leadership position as the preferred storage media in the embedded Systems market and opened new vistas for deployment in enterprise-scale storage Systems. Unlike hard disks, flash devices are free from any mechanical moving parts, have no seek or rotational delays and consume lower power. However, the internal idiosyncrasies of flash technology make its performance highly dependent on workload characteristics. The poor performance of random writes has been a cause of major concern, which needs to be addressed to better utilize the potential of flash in enterprise-scale environments. We examine one of the important causes of this poor performance: the design of the Flash Translation Layer (FTL), which performs the virtual-to-physical address translations and hides the erase-before-write characteristics of flash. We propose a complete paradigm shift in the design of the core FTL engine from the existing techniques with our Demand-based Flash Translation Layer (DFTL), which selectively caches page-level address mappings. We develop a flash simulation framework called FlashSim. Our experimental evaluation with realistic enterprise-scale workloads endorses the utility of DFTL in enterprise-scale storage Systems by demonstrating: (i) improved performance, (ii) reduced garbage collection overhead and (iii) better overload behavior compared to state-of-the-art FTL schemes. For example, a predominantly random-write dominant I/O trace from an OLTP application running at a large financial institution shows a 78% improvement in average Response Time (due to a 3-fold reduction in operations of the garbage collector), compared to a state-of-the-art FTL scheme. Even for the well-known read-dominant TPC-H benchmark, for which DFTL introduces additional overheads, we improve System Response Time by 56%.
Sajal K Das - One of the best experts on this subject based on the ideXlab platform.
-
a game theory based pricing strategy to support single multiclass job allocation schemes for bandwidth constrained distributed computing Systems
IEEE Transactions on Parallel and Distributed Systems, 2007Co-Authors: Preetam Ghosh, Kalyan Basu, Sajal K DasAbstract:Today's distributed computing Systems incorporate different types of nodes with varied bandwidth constraints which should be considered while designing cost-optimal job allocation schemes for better System performance. In this paper, we propose a fair pricing strategy for job allocation in bandwidth-constrained distributed Systems. The strategy formulates an incomplete information, alternating-offers bargaining game on two variables, such as price per unit resource and percentage of bandwidth allocated, for both single and multiclass jobs at each node. We present a cost-optimal job allocation scheme for single-class jobs that involve communication delay and, hence, the link bandwidth. For fast and adaptive allocation of multiclass jobs, we describe three efficient heuristics and compare them under different network scenarios. The results show that the proposed algorithms are comparable to existing job allocation schemes in terms of the expected System Response Time over all jobs
-
a pricing strategy for job allocation in mobile grids using a non cooperative bargaining theory framework
Journal of Parallel and Distributed Computing, 2005Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Due to their inherent limitations in computational and battery power, storage and available bandwidth, mobile devices have not yet been widely integrated into grid computing platforms. However, millions of laptops, PDAs and other portable devices remain unused most of the Time, and this huge repository of resources can be potentially utilized, leading to what is called a mobile grid environment. In this paper, we propose a game theoretic pricing strategy for efficient job allocation in mobile grids. By drawing upon the Nash bargaining solution, we show how to derive a unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. In particular, we characterize a two-player, non-cooperative, alternating-offer bargaining game between the Wireless Access Point Server and the mobile devices to determine a fair pricing strategy which is then used to effectively allocate jobs to the mobile devices with a goal to maximize the revenue for the grid users. Simulation results show that the proposed job allocation strategy is comparable to other task allocation schemes in terms of the overall System Response Time.
-
a game theory based pricing strategy for job allocation in mobile grids
International Parallel and Distributed Processing Symposium, 2004Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Summary form only given. This article realizes the vision of mobile grid computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices has not yet been integrated into grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. However, millions of laptops, PDAs and other mobile devices remain unused most of the Time and this huge resource repository can be potentially utilized in the grid environment. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash bargaining solution (NBS), we show that we can obtain an unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. The advantage of this framework is that we have a precise mathematical characterization of the solutions and their properties. Our current endeavor characterizes a two-player alternating-offer bargaining game between the wireless access point (WAP) server and the mobile devices to determine the pricing strategy. This pricing strategy is then made use of to effectively distribute jobs to the mobile devices. Our job allocation scheme maximizes the revenue of the grid user, and yet is comparable to the overall System Response Time of other load balancing schemes.
Aayush Gupta - One of the best experts on this subject based on the ideXlab platform.
-
dftl a flash translation layer employing demand based selective caching of page level address mappings
Architectural Support for Programming Languages and Operating Systems, 2009Co-Authors: Aayush Gupta, Bhuvan UrgaonkarAbstract:Recent technological advances in the development of flash-memory based devices have consolidated their leadership position as the preferred storage media in the embedded Systems market and opened new vistas for deployment in enterprise-scale storage Systems. Unlike hard disks, flash devices are free from any mechanical moving parts, have no seek or rotational delays and consume lower power. However, the internal idiosyncrasies of flash technology make its performance highly dependent on workload characteristics. The poor performance of random writes has been a cause of major concern, which needs to be addressed to better utilize the potential of flash in enterprise-scale environments. We examine one of the important causes of this poor performance: the design of the Flash Translation Layer (FTL), which performs the virtual-to-physical address translations and hides the erase-before-write characteristics of flash. We propose a complete paradigm shift in the design of the core FTL engine from the existing techniques with our Demand-based Flash Translation Layer (DFTL), which selectively caches page-level address mappings. We develop a flash simulation framework called FlashSim. Our experimental evaluation with realistic enterprise-scale workloads endorses the utility of DFTL in enterprise-scale storage Systems by demonstrating: (i) improved performance, (ii) reduced garbage collection overhead and (iii) better overload behavior compared to state-of-the-art FTL schemes. For example, a predominantly random-write dominant I/O trace from an OLTP application running at a large financial institution shows a 78% improvement in average Response Time (due to a 3-fold reduction in operations of the garbage collector), compared to a state-of-the-art FTL scheme. Even for the well-known read-dominant TPC-H benchmark, for which DFTL introduces additional overheads, we improve System Response Time by 56%.
Preetam Ghosh - One of the best experts on this subject based on the ideXlab platform.
-
a game theory based pricing strategy to support single multiclass job allocation schemes for bandwidth constrained distributed computing Systems
IEEE Transactions on Parallel and Distributed Systems, 2007Co-Authors: Preetam Ghosh, Kalyan Basu, Sajal K DasAbstract:Today's distributed computing Systems incorporate different types of nodes with varied bandwidth constraints which should be considered while designing cost-optimal job allocation schemes for better System performance. In this paper, we propose a fair pricing strategy for job allocation in bandwidth-constrained distributed Systems. The strategy formulates an incomplete information, alternating-offers bargaining game on two variables, such as price per unit resource and percentage of bandwidth allocated, for both single and multiclass jobs at each node. We present a cost-optimal job allocation scheme for single-class jobs that involve communication delay and, hence, the link bandwidth. For fast and adaptive allocation of multiclass jobs, we describe three efficient heuristics and compare them under different network scenarios. The results show that the proposed algorithms are comparable to existing job allocation schemes in terms of the expected System Response Time over all jobs
-
a pricing strategy for job allocation in mobile grids using a non cooperative bargaining theory framework
Journal of Parallel and Distributed Computing, 2005Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Due to their inherent limitations in computational and battery power, storage and available bandwidth, mobile devices have not yet been widely integrated into grid computing platforms. However, millions of laptops, PDAs and other portable devices remain unused most of the Time, and this huge repository of resources can be potentially utilized, leading to what is called a mobile grid environment. In this paper, we propose a game theoretic pricing strategy for efficient job allocation in mobile grids. By drawing upon the Nash bargaining solution, we show how to derive a unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. In particular, we characterize a two-player, non-cooperative, alternating-offer bargaining game between the Wireless Access Point Server and the mobile devices to determine a fair pricing strategy which is then used to effectively allocate jobs to the mobile devices with a goal to maximize the revenue for the grid users. Simulation results show that the proposed job allocation strategy is comparable to other task allocation schemes in terms of the overall System Response Time.
-
a game theory based pricing strategy for job allocation in mobile grids
International Parallel and Distributed Processing Symposium, 2004Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Summary form only given. This article realizes the vision of mobile grid computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices has not yet been integrated into grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. However, millions of laptops, PDAs and other mobile devices remain unused most of the Time and this huge resource repository can be potentially utilized in the grid environment. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash bargaining solution (NBS), we show that we can obtain an unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. The advantage of this framework is that we have a precise mathematical characterization of the solutions and their properties. Our current endeavor characterizes a two-player alternating-offer bargaining game between the wireless access point (WAP) server and the mobile devices to determine the pricing strategy. This pricing strategy is then made use of to effectively distribute jobs to the mobile devices. Our job allocation scheme maximizes the revenue of the grid user, and yet is comparable to the overall System Response Time of other load balancing schemes.
Kalyan Basu - One of the best experts on this subject based on the ideXlab platform.
-
a game theory based pricing strategy to support single multiclass job allocation schemes for bandwidth constrained distributed computing Systems
IEEE Transactions on Parallel and Distributed Systems, 2007Co-Authors: Preetam Ghosh, Kalyan Basu, Sajal K DasAbstract:Today's distributed computing Systems incorporate different types of nodes with varied bandwidth constraints which should be considered while designing cost-optimal job allocation schemes for better System performance. In this paper, we propose a fair pricing strategy for job allocation in bandwidth-constrained distributed Systems. The strategy formulates an incomplete information, alternating-offers bargaining game on two variables, such as price per unit resource and percentage of bandwidth allocated, for both single and multiclass jobs at each node. We present a cost-optimal job allocation scheme for single-class jobs that involve communication delay and, hence, the link bandwidth. For fast and adaptive allocation of multiclass jobs, we describe three efficient heuristics and compare them under different network scenarios. The results show that the proposed algorithms are comparable to existing job allocation schemes in terms of the expected System Response Time over all jobs
-
a pricing strategy for job allocation in mobile grids using a non cooperative bargaining theory framework
Journal of Parallel and Distributed Computing, 2005Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Due to their inherent limitations in computational and battery power, storage and available bandwidth, mobile devices have not yet been widely integrated into grid computing platforms. However, millions of laptops, PDAs and other portable devices remain unused most of the Time, and this huge repository of resources can be potentially utilized, leading to what is called a mobile grid environment. In this paper, we propose a game theoretic pricing strategy for efficient job allocation in mobile grids. By drawing upon the Nash bargaining solution, we show how to derive a unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. In particular, we characterize a two-player, non-cooperative, alternating-offer bargaining game between the Wireless Access Point Server and the mobile devices to determine a fair pricing strategy which is then used to effectively allocate jobs to the mobile devices with a goal to maximize the revenue for the grid users. Simulation results show that the proposed job allocation strategy is comparable to other task allocation schemes in terms of the overall System Response Time.
-
a game theory based pricing strategy for job allocation in mobile grids
International Parallel and Distributed Processing Symposium, 2004Co-Authors: Preetam Ghosh, Sajal K Das, Nirmalya Roy, Kalyan BasuAbstract:Summary form only given. This article realizes the vision of mobile grid computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices has not yet been integrated into grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. However, millions of laptops, PDAs and other mobile devices remain unused most of the Time and this huge resource repository can be potentially utilized in the grid environment. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash bargaining solution (NBS), we show that we can obtain an unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. The advantage of this framework is that we have a precise mathematical characterization of the solutions and their properties. Our current endeavor characterizes a two-player alternating-offer bargaining game between the wireless access point (WAP) server and the mobile devices to determine the pricing strategy. This pricing strategy is then made use of to effectively distribute jobs to the mobile devices. Our job allocation scheme maximizes the revenue of the grid user, and yet is comparable to the overall System Response Time of other load balancing schemes.
