• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1314-1321
• /
• 2015

Mobile devices employ buffer cache mechanisms, just as in computer systems such as desktops or servers, to mitigate the performance gap between main memory and secondary storage. However, DRAM has a problem in that it accelerates battery consumption by performing refresh operations periodically to maintain the stored data. In this paper, we propose a novel buffer cache scheme to increase the battery lifecycle in mobile devices based on a hybrid main memory architecture consisting of DRAM and non-volatile PCM. We also suggest a new buffer cache policy that allocates buffers based on process states to optimize the performance and endurance of PCM. In particular, our algorithm allocates each page to the appropriate position corresponding to the state of the application that owns the page, and tries to ensure a rapid response of foreground applications even with a small amount of DRAM memory. The experimental results indicate that the proposed scheme reduces the elapsed time of foreground applications by 58% on average and power consumption by 23% on average without negatively impacting the performance of background applications.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.9
• /
• pp.634-641
• /
• 2006

Flash memory has many advantages like non-volatility and fast I/O speed, but it has also disadvantages such as not-in-place-update data and asymmetric read/write/erase speed. For the performance of flash memory storage, it is essential for the buffer replacement algorithms to reduce the number of write operations that also affects the number of erase operations. A new buffer replacement algorithm is proposed in this paper, that delays the writes of not-cold-dirty pages in the buffer cache of flash storage. We show that this algorithm effectively decreases the number of write operations and erase operations without much degradation of hit ratio. As a result overall performance of flash I/O speed is improved.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.21-29
• /
• 2020

The use of NAND flash memory is continuously increased with the demand of mobile data in the IT industry environment. However, the erase operations in flash memory require longer latency and higher power consumption, resulting in the limited lifetime for each cell. Therefore, frequent write/erase operations reduce the performance and the lifetime of the flash memory. In order to solve this problem, management techniques for improving the performance of flash based storage by reducing write and erase operations of flash memory with using disk buffers have been studied. In this paper, we propose a CPWL to minimized the number of write operations. It is a disk buffer management that separates read and write pages according to the characteristics of the buffer memory access patterns. This technique increases the lifespan of the flash memory and decreases an energy consumption by reducing the number of writes by arranging pages according to the characteristics of buffer memory access mode of requested pages.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.143-150
• /
• 2013

Solid-state disks (SSDs) have been widely used by high-performance personal computers or servers due to its good characteristics and performance. The NAND flash-based SSDs, which take large portion of the whole NAND flash market, are the major type of SSDs. They usually integrate a cache buffer which is built from DRAM and uses the write-back policy for better performance. Unfortunately, the policy makes existing scheduling methods less effective at the I/F level of SSDs Therefore, in this paper, we propose a scheduling method for the I/F with consideration of the cache buffer. The proposed method considers the hit/miss status of cache buffer and gives higher priority to the read requests. As a result, the requests whose data is hit on the cache buffer can be handled in advance and the read requests which have larger effects on the whole system performance than write requests experience shorter latency. The experimental results show that the proposed scheduling method improves read latency by 26%.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.39 no.1
• /
• pp.20-33
• /
• 2002

Usage of ATM AAL2 packets becomes dominant to increase transmission efficiency of voice traffic in the backbone network. In case of voice service that uses AAL2 mechanism, if resources of network are enough, connection of new call is accepted. However, due to packets generated by the new call, transmission delay of packets from old calls can increase sharply. To control this behavior, in this paper we present an AAL2 buffer management scheme that allocates a virtual buffer to each call and after calculating its propagation delay variation(PDV), decides to drop packets coming from each call according to the PDV value. We show that this packet dropping algorithm can effectively prevent abrupt QoS degradation of old calls. To do this, we analyze AAL2 packet composition process to find a critical factor in the process that influences the end-to-end delay behavior and model the process by K-policy M/D/1 queueing system and MIN(K, Tc)-policy M/D/1 queueing system. From the mathematical model, we derive the probability generating function of AAL2 packets in the buffer and mean waiting time of packets in the AAL2 buffer. Analytical results show that the AAL2 packet dropping algorithm can provide stable AAL2 packetization delay and ATM cell generation time even if the number of voice sources increases dramatically. Finally we compare the analytical result to simulation data obtained by using the COMNET Ⅲ package.

• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.595-602
• /
• 2003

In this paper, we proposed new buffer management and cell scheduling scheme of GFR service for improving fairness of TCP/IP traffic in ATM networks. The proposed algorithm used untagged cell, which came to ATM switch, to decide the policy for discard of frame and what kind of VC cell it would serve. Performance analysis through the simulation present that proposed scheme can meet fairness 2 (MCR Plus equal share), which are not met by conventional scheduling mechanism such as WRR. Also, proposed scheme is superior to WRR about 30% in throughput and more efficiency in fairness criteria.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.3
• /
• pp.217-226
• /
• 2006

Intensive studies have been made in the area of N-VOD server Multimedia files in the N-VOD sever are characterized with the large volume of data, the requirements of synchronization and real-time playback of streams. The basic goal of the study is to find an efficient mechanism to allow maximum number of users under the limited resources such as Buffer size and disk bandwidth. we propose a efficient VCR-LIKE operations and buffer, disk scheduling policy for multimedia services with management of VOD sever resources. Simulation results show that the rate of buffer usage and service time of proposed scheme are about 18% performance improved than that of traditional methods. This implies that our method can allow much more users for given resources.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.12
• /
• pp.2202-2211
• /
• 2006

EXT3NS is a special-purpose file system for large scale multimedia streaming servers. It is built on top of streaming acceleration hardware device called Network-Storage card. The EXT3NS file system significantly improves streaming performance by eliminating memory-to-memory copy operations, i.e. sending video/audio from disk directly to network interface with no main memory buffering. In this paper, we design and implement a buffer cache mechanism, called PMEMCACHE, for EXT3NS file system. We also propose a buffer cache replacement method called ONS for the buffer cache mechanism. The ONS algorithm outperforms other existing buffer replacement algorithms in distributed multimedia streaming environment. In EXT3NS with PMEMCACHE, operation is 33MB/sec and random read operation is 2.4MB/sec. Also, the buffer replacement ONS algorithm shows better performance by 600KB/sec than other buffer cache replacement policies. As a result PMEMCACHE and an ONS can greatly improve the performance of multimedia steaming server which should supportmultiple client requests at the same time.

• KDI Journal of Economic Policy
• /
• v.28 no.1
• /
• pp.117-144
• /
• 2006

This study is to analyze the existence of the real buffer effect that reflects the effect of beginning-of-period inventory stocks effect on the demand for fixed investment, and the financial buffer effect indicates the substitution effect between end-of-period inventory stock and the source of financing for fixed investment. I use panel data of 361 Korean listed non-financial firms during 1990-2003. After the crisis, it also observed whether the relationship between inventory stocks and fixed investment has altered or not. I review the theoretical connection between inventory stock and fixed investment through the paper by Bo(2004) and estimate the investment model by the method of GMM-SYS. The results show negative relation between end-of-period inventory stock and fixed investment in the whole period and each period classified, also it confirms that the relation between fixed investment and end-of-period investment is significantly negative. It can be interpreted through two aspects that firms not only use inventory stock as a buffer in response to unexpectedly high demand, but also utilize inventory stock as a source of financing for fixed investment. The results imply that firm's decision-making is much correlated with production-and-inventory stock adjustment, decision-making about fixed investment, and decision-making about financial affairs.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.1
• /
• pp.130-140
• /
• 1999

This paper deals with a priority queueing model in an ATM system. Two types of customers are considered. Type-1 customers have push-put priority over type-2 customers. Type-1 customers can enter the service only when the number of type-2 customers is less than a threshold T. We derive the joint probability of the number of customers in the buffer, the mean waiting time, and the loss probabilities of each type. We also propose an optimal control policy that satisfies a given quality of service.