• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.5
• /
• pp.529-539
• /
• 2000

This paper proposes a prefetch-based disk buffer management algorithm, which we call W2R (Veighingjwaiting Room). Instead of using elaborate prefetching schemes to decide which blockto prefetch and when, we simply follow the LRU-OBL (One Block Lookahead) approach and prefetchthe logical next block along with the block that is being referenced. The basic difference is that theW2R algorithm logically partitions the buffer into two rooms, namely, the Weighing Room and theWaiting Room. The referenced, hence fetched block is placed in the Weighing Room, while theprefetched logical next block is placed in the Waiting Room. By so doing, we alleviate some inherentdeficiencies of blindly prefetching the logical next block of a referenced block. Specifically, a prefetchedblock that is never used may replace a possibly valuable block and a prefetched block, thoughreferenced in the future, may replace a block that is used earlier than itself. We show through tracedriven simulation that for the workloads and the environments considered the W2R algorithm improvesthe hit rate by a maximum of 23.19 percentage points compared to the 2Q algorithm and a maximumof 10,25 percentage feints compared to the LRU-OBL algorithm.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.163-170
• /
• 2002

Previous buffer cache schemes for continuous media file system only exploited the sequentiality of continuous media accesses and didn't consider looping references. However, in some video applications like foreign language learning, users mark the scene as loop area and then application automatically playbacks the scene several times. In this paper, we propose a novel buffer cache scheme for continuous media file system that sequential and looping references exist together. Proposed scheme increases the cache hit ratio by detecting reference pattern of files and appling an appropriate replacement policy to each file.

• The KIPS Transactions:PartD
• /
• v.16D no.2
• /
• pp.153-160
• /
• 2009

Efficient buffer management is closely related to system performance. Thus, much research has been performed on various buffer management techniques. However, many of the proposed techniques utilize the temporal locality of access patterns. In spatial database environments, there exists not only the temporal locality but also spatial locality, where the objects in the recently accessed regions will be accessed again in the near future. Thus, in this paper, we present a buffer management technique, called BEAT, which utilizes both the temporal locality and spatial locality in spatial database environments. The experimental results with real-life and synthetic data demonstrate the efficiency of BEAT.

• Journal of KIISE:Databases
• /
• v.28 no.2
• /
• pp.153-167
• /
• 2001

다차원 온라인 분석처리(Multidimensional On-Line Analytical Processing: MOLAP)에서 집계 연산은 중요한 기본 연산이다. 기존의 MOLAP 집계 연산은 다차원 배열 구조를 기반으로 한 파일 구조에 대해서 연구되어 왔다. 이러한 파일 구조는 편중된 분포를 갖는 데이터에서는 잘 동작하지 못한다는 단점이 있다. 본 논문에서는 편중된 분포에도 잘 동작하는 다차원 파일구조를 사용한 집계 알고리즘을 제안한다. 먼저, 새로운 분리-포함 분할이라는 개념을 사용한 집계 연산 처리 모델을 제안한다. 집계 연산 처리에서 분리-포함 분할 개념을 사용하면 페이지들의 액세스 순서를 미리 알아 낼 수 있다는 특징을 가진다. 그리고, 제안한 모델에 기반하여 원-패스 버퍼 크기(one-pass buffer size)를 사용하여 집계 연산을 처리하는 원-패스 집계 알고리즘을 제안한다. 원-패스 버퍼 크기란 페이지 당 한 번의 디스크 액세스를 보장하기 위해 필요한 최소 버퍼 크기이다. 또한, 제안한 집계 연산 처리 모델 하에서 제안된 알고리즘이 최소의 원-패스 버퍼 크기를 갖는다는 것을 증명한다. 마지막으로, 많은 실험을 통하여 이론적으로 구한 원-패스 버퍼 크기가 실제 환경에서 정확히 동작함을 실험적으로 확인하였다. 리 알고리즘은 미리 알려진 페이지 액세스 순서를 이용하는 버퍼 교체 정책을 사용함으로써 최적의 원-패스 버퍼 크기를 달성한다. 제안하는 알고리즘을 여 러 집계 질의가 동시에 요청되는 다사용자 환경에서 특히 유용하다. 이는 이 알고리즘이 정규화 된 디스크 액세스 횟수를 1.0으로 유지하기 위해 반드시 필요한 크기의 버퍼만을 사용하기 때문이다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.9
• /
• pp.1083-1095
• /
• 1999

최근 처리기와 입출력 시스템의 속도 차이가 점점 커짐에 따라 버퍼 캐쉬의 효율적인 관리가 더욱 중요해지고 있다. 버퍼 캐쉬는 블록 교체 정책과 선반입 정책에 의해 관리되며, 각 정책은 버퍼 캐쉬에서 블록의 가치 즉 어떤 블록이 더 가까운 미래에 참조될 것인가를 결정해야 한다. 블록의 가치는 응용들의 블록 참조 패턴의 특성에 기반하며, 블록 참조 패턴의 특성에 대한 정확한 분석은 올바른 결정을 가능하게 하여 버퍼 캐쉬의 효율을 높일 수 있다. 본 논문은 각 응용들의 블록 참조 패턴에 대한 특성을 분석하고 이를 자동으로 발견하는 기법을 제안한다. 제안된 기법은 블록의 속성과 미래 참조 거리간의 관계를 이용해 블록 참조 패턴을 발견한다. 이 기법은 2 단계 파이프라인 방법을 이용하여 온라인으로 참조 패턴을 발견할 수 있으며, 참조 패턴의 변화가 발생하면 이를 인식할 수 있다. 본 논문에서는 8개의 실제 응용 트레이스를 이용해 블록 참조 패턴의 발견을 실험하였으며, 제안된 기법이 각 응용의 블록 참조 패턴을 정확히 발견함을 확인하였다. 그리고 발견된 참조 패턴 정보를 블록 교체 정책에 적용해 보았으며, 실험 결과 기존의 대표적인 블록 교체 정책인 LRU에 비해 최대 57%까지 디스크 입출력 횟수를 줄일 수 있었다.Abstract As the speed gap between processors and disks continues to increase, the role of the buffer cache located in main memory is becoming increasingly important. The buffer cache is managed by block replacement policies and prefetching policies and each policy should decide the value of block, that is which block will be accessed in the near future. The value of block is based on the characteristics of block reference patterns of applications, hence accurate characterization of block reference patterns may improve the performance of the buffer cache. In this paper, we study the characteristics of block reference behavior of applications and propose a scheme that automatically detects the block reference patterns. The detection is made by associating block attributes of a block with the forward distance of the block. With the periodic detection using a two-stage pipeline technique, the scheme can make on-line detection of block reference patterns and monitor the changes of block reference patterns. We measured the detection capability of the proposed scheme using 8 real workload traces and found that the scheme accurately detects the block reference patterns of applications. Also, we apply the detected block reference patterns into the block replacement policy and show that replacement policies appropriate for the detected block reference patterns decreases the number of DISK I/Os by up to 57%, compared with the traditional LRU policy.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.4
• /
• pp.395-404
• /
• 1999

포인터 스위즐링 기법은 포인터 스위즐링과 언스위즐링으로 이루어지며, 포인터 스위즐링은 객체 접근 시 객체 식별자를 해당 객체의 메모리 주소로 교체하는 것을 말하며, 언스위즐링은 객체 교체 또는 객체 저장 시에 스위즐링된 포인터를 원래의 객체 식별자로 환원하는 것을 말한다. 본 연구에서는 시스템 버퍼 구조에 따라 여러 포인터 스위즐링 기법을 분류하여 장단점을 분석하였으며, 이중 버퍼 구조 상에서 적극/소극, 직접/간접 스위즐링, 언스위즐링 모듈을 설계, 구현하였다. 또한 제한된 크기의 객체 버퍼 상에서 각 포인터 스위즐링 모듈의 성능을 평가하였다. 이 성능 평가의 결과로는 사용하지 않는 포인터는 스위즐링하지 않으며 언스위즐링 부담이 적은 소극 간접 스위즐링 기법이 일반적으로 뛰어난 성능을 나타냄을 알 수 있게 되었다.Abstract The pointer swizzling methods consist of pointer swizzling and unswizzling. Pointer swizzling replaces the OID of a object to the memory address of the object at object access time and unswizzling replaces the swizzling pointer of the OID at object replacement time or object save time. In this research, the different techniques for pointer swizzling are classified according to the system buffer structure and analyzed the pros and cons. In addition, eager/lazy, direct/indirect swizzling, unswizzling modules are designed and implemented on a dual buffering structure. Also, we evaluate the performance of pointer swizzling modules on the restricted object buffer size. The results of performance evaluation show that the performance of lazy indirect pointer swizzling technique is generally good because unused pointers are not swizzled, and unswizzling overhead is minimized.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.4
• /
• pp.410-419
• /
• 2003

The buffer cache of general operating systems such as Linux manages file data by using global block replacement policy and read ahead. As a result, multimedia data with a low locality of reference and various consumption rate have low cache hit ratio and consume additional buffers because of read ahead. In this paper we have designed and implemented a new buffer allocation algorithm for multimedia data on Linux. Our approach keeps one read-ahead cache per every opened multimedia file and dynamically changes the read-ahead group size based on the buffer consumption rate of the file. This distributes resources fairly and optimizes the buffer consumption. This paper compares the system performance with that of Linux 2.4.17 in terms of buffer consumption and buffer hit ratio.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1375-1385
• /
• 1996

As there has been much demands for processing multimedia data, a storage manager for multimedia data makes much effects on system performance. Because the size of multimedia data is usually very large, disk I/O for the data consumes much time and causes the system performance to be decreased. Therefore, it makes a better effect on system performance that a multimedia data storage manager decreases its disk I/O by the buffer management of multimedia data. This paper proposes a buffer management technique which allocates the buffer to be equal to its corresponding segment which consists of physically continuous disk page set and is disk management unit for multimedia data in many multimedia data storage manager. As the size of buffer varies, it also proposes a buffer replacement policy which consider not only reference behavior of buffer but also buffer size The proposed multimedia data buffer management technique is implemented in KORED/STORM which is a storage manager for multimedia data.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.913-917
• /
• 2009

Flash memories have asymmetric I/O costs for read and write in terms of latency and energy consumption. However, the ratio of these costs is dependent on the type of storage. Moreover, it is becoming more common to use two flash memories on a system as an internal memory and an external memory card. For this reason, buffer cache replacement algorithms should consider I/O costs of device as well as possibility of reference. This paper presents WWCLOCK(Write-Weighted CLOCK) algorithm which directly uses I/O costs of devices along with recency and frequency of cache blocks to selecting a victim to evict from the buffer cache. WWCLOCK can be used for wide range of storage devices with different I/O cost and for systems that are using two or more memory devices at the same time. In addition to this, it has low time and space complexity comparable to CLOCK algorithm. Trace-driven simulations show that the proposed algorithm reduces the total I/O time compared with LRU by 36.2% on average.

• The KIPS Transactions:PartD
• /
• v.18D no.1
• /
• pp.1-8
• /
• 2011

The cache structure, which is designed for assuring fast accesses to frequently accessed data, resides on the various levels of computer system hierarchies. Many studies on this cache structure have been conducted and thus many page-replacement algorithms have been proposed. Most of page-replacement algorithms are designed on the basis of heuristic methods by using their own criteria such as how recently pages are accessed and how often they are accessed. This data-retrieval process in computer systems is analogous to human memory retrieval process since the retrieval process of human memory depends on frequency and recency of the retrieval events as well. A recent study regarding human memory cognition revealed that the possibility of the retrieval success and the retrieval latency have a strong correlation with the frequency and recency of the previous retrieval events. In this paper, we propose a novel page-replacement algorithm by utilizing the knowledge from the recent research regarding human memory cognition. Through a set of experiments, we demonstrated that our new method presents better hit-ratio than the LRFU algorithm which has been known as the best performing page-replacement algorithm for DBMS caches.