Adaptive memory management techniques for multiprogramming operating systems are described. Page replacement during execution and initial page assignment are the factors affecting optimal memory usage. Modifications t...
详细信息
Adaptive memory management techniques for multiprogramming operating systems are described. Page replacement during execution and initial page assignment are the factors affecting optimal memory usage. Modifications to a time-shared operating system (Michigan Terminal System) that would allow implementation of the Page Fault Frequency replacement Algorithm are discussed. Additional modifications to this system are suggested that would subordinate job initiation to memory availability.
This paper discusses the implementation of a database buffer manager as a component of a DBMS. The interface between calling components of higher system layers and the buffer manager is described; the principal differ...
详细信息
This paper discusses the implementation of a database buffer manager as a component of a DBMS. The interface between calling components of higher system layers and the buffer manager is described; the principal differences between virtual memory paging and database buffer management are outlined; the notion of referencing versus addressing of database pages is introduced; and the concept of fixing pages in the buffer to prevent uncontrolled replacement is *** basic tasks have to be performed by the buffer manager: buffer search, allocation of frames to concurrent transactions, and page replacement. For each of these tasks, implementation alternatives are discussed and illustrated by examples from a performance evaluation project of a CODASYL DBMS.
Effective I/O buffering is a performance-critical task in database management systems. Accordingly, systems usually employ various special-purpose buffers to align, e.g., device speed, page size, and replacement polic...
详细信息
Effective I/O buffering is a performance-critical task in database management systems. Accordingly, systems usually employ various special-purpose buffers to align, e.g., device speed, page size, and replacement policies with the actual data and workload. However, such partitioning of available buffer memory results in complex optimization problems for database administrators and also in fragile configurations which quickly deteriorate on workload shifts. Reliable forecasts of I/O costs enable a system to evaluate alternative configurations to continuously optimize its buffer memory allocation at runtime. So far, all techniques proposed for the prediction of buffer performance focus solely on hit ratio gains for increased buffer sizes to identify buffers which promise the greatest benefit. These approaches, however, assume that their forecast allows to extrapolate the effect for buffer downsizing, too. As we will show, this comes along with a severe risk of wrong tuning decisions, which may heavily impact system performance. Thus, we emphasize the importance of reliably forecasting the penalty to expect for shrinking buffers in favor of others. We explore the use of lightweight extensions for widely used buffer algorithms to perform on-the-fly simulation of buffer performance of smaller and larger buffer sizes simultaneously. Furthermore, we present a simple cost model and demonstrate how to compose these concepts into a self-tuning component for dynamic buffer reallocation.
Consider a two-level storage system operating with the least recently used (LRU) or the first-in, first-out (FIFO) replacement strategy. Accesses to the main storage are described by the independent reference model (I...
详细信息
Consider a two-level storage system operating with the least recently used (LRU) or the first-in, first-out (FIFO) replacement strategy. Accesses to the main storage are described by the independent reference model (IRM). Using the FKG inequality, we prove that the miss ratio for LRU is smaller than or equal to the miss ratio for FIFO.
The operation of 'folding' a program into the available memory is discussed. Measurements by Brawn et al. and by Nelson on an automatic folding mechanism of simple design, a demand paging unit built at the IBM...
详细信息
The operation of 'folding' a program into the available memory is discussed. Measurements by Brawn et al. and by Nelson on an automatic folding mechanism of simple design, a demand paging unit built at the IBM Research Center by Belady, Nelson, O'Neill, and others, permitting its quality to be compared with that of manual folding, are discussed, and it is shown that given some care in use the unit performs satisfactorily under the conditions tested, even though it is operating across a memory-to-storage interface with a very large speed difference. The disadvantages of prefolding, which is required when the folding is manual, are examined, and a number of the important troubles which beset computing today are shown to arise from, or be aggravated by, this source. It is concluded that a folding mechanism will probably become a normal part of most computing systems. [ABSTRACT FROM AUTHOR]
Clustering provides a viable approach to building scalable Web systems with increased computing power and abundant storage space for data and contents. In this paper, we present a pure-Java-based parallel Web server s...
详细信息
Clustering provides a viable approach to building scalable Web systems with increased computing power and abundant storage space for data and contents. In this paper, we present a pure-Java-based parallel Web server system, p-Jigsaw, which operates on a cluster and uses the technique of cooperative caching to achieve high performance. We introduce the design of an in-memory cache layer, called Global Object Space (GOS), for dynamic caching of frequently requested Web objects. The GOS provides a unified view of cluster-wide memory resources for achieving location-transparent Web object accesses. The GOS relies on cooperative caching to minimize disk accesses. A requested Web object can be fetched from a server node's local cache or a peer node's local cache, with the disk serving only as the last resort. A prototype system based on the W3C Jigsaw server has been implemented on a 16-node PC cluster. Three cluster-aware cache replacement algorithms were tested and evaluated. The benchmark results show good speedups with a real-life access log, proving that cooperative caching can have significant positive impacts on the performance of cluster-based parallel Web servers. Copyright (C) 2003 John Wiley Sons, Ltd.
暂无评论