Storage Management Problem Research Articles

The general two-level storage management problem: A reconsideration of the KTNS-rule

A two-level storage management problem arising in flexible manufacturing systems is studied. We consider the case of several different types of PCBs (printed circuit board) to be processed with a component assembly machine. The PCB processing order is fixed and all components to be assembled to a PCB should be in the feeder of the machine before starting the processing of the PCB in question. Our task is to perform the component switches between the primary storage (feeder) and the secondary storage (component reel shelves) so that the overall switching cost of the component reels is minimal. The component reel switches are necessary because of the limited capacity of the machine feeder. The “Keep Tool Needed Soonest” policy is known to be optimal when component reel widths are equal. A more general problem in which different component reels have different widths is considered here. In contrast to previous studies by Matzliach and Tzur [The online tool switching problem with non-uniform tool size, International Journal of Production Research 36 (12) (1998) 3407–3420] we assume that reorganizations of the feeder are necessary in order to place a wider component reel into the feeder where the free space is fragmented into smaller pieces. In PCB assembly the reorganization costs are substantial. The objective is then to minimize the sum of the costs for component switches between the two storage levels and the reorganizations of the feeder.

Design and Implementation of a Fibre Channel Target Driver Supporting SCSI

Fibre channel storage area networks (FC-SAN) are effective solutions to address storage management problems caused by very large volumes of data. But the expense of fibre channel devices limits FC-SAN applications. The use of IP networks instead of fibre channel networks will reduce SAN cost, but will also reduce the performance. Therefore, small computer system interface (SCSI) devices were considered to replace FC disks to reduce the SAN cost. A driver for the FC network adapter and the FC target, designed and implemented to support this structure, obeys the SCSI protocol and works in target mode with 200 MB/s bandwidth. The FC target architecture and implementation were compared with the FC initiator. The SCSI command transfer process in the FC layer was described. The performance test results show that the maximum I/O throughput reachs 167 MB/s for read requests and 196 MB/s for write requests (FC bandwidth is 200 MB/s), verifying that the FC target is very efficient. The modularization, efficiency, and low cost of the FC target will enable SAN and fibre channel to be more widely used in applications.

A Genetic Approach for Setting Parameters of Reorder Point Systems

In this paper, we consider the packing storage management problems for an Italian machine-manufacturing company. Because of the limitations of a material requirements planning approach for this particular firm, the packing purchase process is managed by adopting the economic order quantity (EOQ) philosophy. Considering the number of packing types and the constraints that concern the purchase phase, a genetic algorithm approach is proposed to calculate the EOQ and reorder point values for each product. The validity of this approach was tested using a deterministic simulation based on historical data relevant to the packing consumption. This methodology has proved to be very efficient, simple and useful in practice for the definition of good packing inventory management.

Storage management of items in two levels of availability

This paper is concerned with the problem of storage management of non-consumable items in two warehouses having different levels of availability. The items are used in a given process, which incurs a cost whenever the required item is not immediately available. We analyze the storage management problem in which items have non-equal size and prove that the problem is NP-Complete. We present two heuristic algorithms which are inspired by two integer programming formulations. The two heuristics are based on different approaches and provide insight that enhances our understanding of the problem. Our numerical study demonstrates that these heuristics perform very well, and therefore provide satisfactory solutions to the problem.

Towards effective and efficient free space management

An important problem faced by many database management systems is the "online object placement problem"--the problem of choosing a disk page to hold a newly allocated object. In the absence of clustering criteria, the goal is to maximize storage utilization. For main-memory based systems, simple heuristics exist that provide reasonable space utilization in the worst case and excellent utilization in typical cases. However, the storage management problem for databases includes significant additional challenges, such as minimizing I/O traffic, coping with crash recovery, and gracefully integrating space management with locking and logging.We survey several object placement algorithms, including techniques that can be found in commercial and research database systems. We then present a new object placement algorithm that we have designed for use in Shore, an object-oriented database system under development at the University of Wisconsin--Madison. Finally, we present results from a series of experiments involving actual Shore implementations of some of these algorithms. Our results show that while current object placement algorithms have serious performance deficiencies, including excessive CPU or main memory overhead, I/O traffic, or poor disk utilization, our new algorithm consistently excellent performance in all of these areas.

Competitive algorithms for the weighted server problem

In this paper we deal with a generalization of the k-server problem (Manasse 1988), in which the servers are unequal. In the weighted server model each of the servers is assigned a positive weight. The cost associated with moving a server equals the product of the distance traversed and the server weight. A weighted k-server algorithm is called competitive if the competitive ratio depends only upon the number of servers (i.e., the competitive ratio is independent of the weights associated with the servers and the number of points in the metric space). For the uniform metric space, we give super exponential 2 2 O( k) -competitive algorithms for any set of weights. If the servers have one of two possible weights, we give deterministic exponential ( k O( k) ) competitive algorithms and randomized polynomial Õ( k 3) competitive algorithms. We use the MIN operator for both algorithms. This is the first true application of the randomized MIN operator (Fiat 1991). We show that for any metric space there exists some set of weights such that the deterministic competitive ratio must be exponential ( k Ω( k) ). If the servers are limited to be one of two possible weights then there exist two such weights such that the competitive ratio has a lower bound of 2 Ω( k) . With the randomized upper bound above, this shows a clear separation between deterministic and randomized algorithms for the problem of two weights. One can model the problem of storage management for RAM and E 2PROM type memories as a weighted server problem with two weights on the uniform metric space.

Thermodynamics and garbage collection

We discuss the principles of statistical thermodynamics and their application to storage management problems. We point out problems which result from impercise usage of the terms information, state, reversible, conservative , etc.

Optimal memory management for time warp parallel simulation

Recently there has been a great deal of interest in performance evalution of parallel simulation. Most work is devoted to the time complexity and assumes that the amount of memory available for parallel simulation is unlimited. This paper studies the space complexity of parallel simulation. Our goal is to design an efficient memory management protocol which guarantees that the memory consumption of parallel simulation is of the same order as sequential simulation. (Such an algorithm is referred to as a optimal .) First, we derive the relationships among the space complexities of sequential simulation, Chandy-Misra simulation [2], and Time Warp simulation [7]. We show that Chandy-Misra may consume more storage than sequential simulation, or vice versa. Then we show that Time Warp never consumes less memory than sequential simulation. Then we describe cancelback , an optimal Time Warp memory management protocol proposed by Jefferson. Although cancelback is considered to be complete solution for the storage management problem in Time Warp, some efficiency issues in implementing this algorithm must be considered. We propose an optimal algorithm called artifical rollback . We show that this algorithm is easy to implement and analyze. An implementation of artificial rollback is given, which is integrated with processor scheduling to adjust the memory consumption rate based on the amount of free storage available in the system.