• KIISE Transactions on Computing Practices
• /
• v.23 no.1
• /
• pp.80-84
• /
• 2017

Existing operating systems experience scalability issues as the number of cores increases. The network I/O performance on manycore systems is faced with the major limiting factors of cache consistency costs and locking overheads. Legacy methods resolve this issue include the new microkernel-like operating system or modification of existing kernels; however, these solutions are not fully application transparent. In this study, we proposed a library that improves the network performance by separating system call context from user context and by applying the core affinity without any kernel and application modifications. Experiment results showed that our implementation can improve the network throughput of Apache by up to 30%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.23-26
• /
• 2002

클라이언트/서버 데이타베이스 시스템 환경이 대중화됨에 따라 클라이언트 캐쉬 데이터의 일관성을 유지하기 위한 기법들이 많이 제안되고 있다. 기존의 회피-기반 기법들은 갱신의도(write intuition) 선언을 동기적(synchronous)으로 수행하는 CB(Callback) 기법과 지연(defereed)하는 O2PL(Optimistic 2-Phase Locking) 기법을 기반으로 연구가 이루어졌다. 본 논문에서는 회피-기반(avoidance-based)에서 서버에게 갱신의도 선언을 비동기적으로 수행하는 캐쉬 일관성 유지 기법을 제안한다. 본 논문에서 제안한 기법은 갱신의도 선언을 비동기적으로 수행함으로 서버의 응답을 기다리지 않고 트랜잭션 처리를 수행함으로써 좋은 성능을 보이고, 트랜잭션 철회(abort)율이 낮다는 장점을 갖는다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.1276-1279
• /
• 2008

최근 모바일 장치의 증가와 무선 네트워크 환경의 발전은 모바일 애드혹 네트워크에 대한 관심을 증가시키고 있다. 최근까지의 연구는 모바일 애드혹 네트워크에서 데이터 접근성(Accessibility) 향상을 위해 복제의 활용이 효율적임을 증명하고 있다. 복제 기법이 모바일 애드혹 네트워크에서 실제로 활용되기 위해서는 원본과 복제본 사이에 일관성(Consistency)이 확보되어야만 한다. 기존의 연구에서는 일관성 확보를 위해 원본을 가진 노드에게 확인하는 기법을 활용하고 있다. 그러나, 시간제약을 가지는 응용의 경우 원본을 가진 노드에게 확인하는 기법은 효율적이지 못하며, 때로는 심각한 문제를 일으킬 수도 있다. 본 논문에서는 시간제약응용을 위한 캐쉬 무효화 기법을 제안하고 있다. 제안하는 기법을 통해 기존의 일관성 확인 기법에서 일어나는 '롤백(Rollback)' 문제를 해결할 수 있었으며, 접근시간(Access time) 측면에서 성능향상을 얻을 수 있었다. 실험 결과는 본 논문의 접근시간 측면에서의 효율적임을 증명하여 준다.

• Journal of KIISE:Software and Applications
• /
• v.26 no.9
• /
• pp.1073-1084
• /
• 1999

이동 컴퓨팅 환경에서 이동 호스트는 제한된 대역폭을 효율적으로 사용하고 이동 트랜잭션의 응답 시간을 향상시키기 위하여 캐쉬를 이용한다. 그리고 이동 호스트에 캐슁된 데이타가 이동 지구국에서 갱신되면 이동 호스트의 캐쉬 일관성을 유지하기 위하여 이동 지구국은 무효화 메시지를 방송한다. 그러나 이동 지구국에서 주기적으로 무효화 메시지를 방송하는 방법은 이동 트랜잭션의 빠른 처리를 위하여 이동 지구국으로부터 데이타를 즉시 캐슁하는 경우에 이동 트랜잭션의 직렬가능한 수행을 보장할 수 없는 경우가 발생한다. 본 연구에서는 캐슁된 데이타를 이용하여 이동 트랜잭션을 수행하는 경우에 록을 이용하여 이동 트랜잭션의 직렬가능한 수행을 보장하는 UCL-MT 방법과 록 관리 방법을 제안한다. 제안하는 UCL-MT 방법은 이동 트랜잭션을 완료하기 이전에 이동 트랜잭션이 접근한 데이타 정보를 이용하여 지구국에서 사이클을 탐지함으로써 이동 트랜잭션의 직렬가능한 수행을 보장한다. 또한 제안하는 록 관리 방법은 이용할 수 있는 대역폭의 크기에 따른 무효화 메시지 내용의 변화에 유연하게 적용될 수 있다. Abstract In mobile computing environments, a mobile host caches the data to use the narrow bandwidth efficiently and improve the response time of a mobile transaction. If the cached data in mobile host is updated at a mobile support station, the mobile support station broadcasts an invalidation message for maintaining the cache consistency of a mobile host. But when a mobile transaction accesses the data which is not in cache, if a mobile host caches the data immediately from a mobile support station for processing a mobile transaction rapidly, the method that a mobile support station broadcasts an invalidation message periodically, happens to the case that can not guarantee the serializable execution of a mobile transaction. In this paper, we propose the UCL-MT method and lock management method, as a mobile transaction is executed using cached data. Since, using the data a mobile transaction accessed, the UCL-MT method detects a cycle in a mobile support station before the completion of the mobile transaction, it guarantees the serializable execution of the mobile transaction. Also, proposing lock management method can be adapted flexibly at the change of invalidation message content, according to the available bandwidth.

• Journal of KIISE:Databases
• /
• v.30 no.6
• /
• pp.629-640
• /
• 2003

A shared disk (SD) cluster couples multiple nodes for high performance transaction processing, and all the coupled nodes share a common database at the disk level. In the SD cluster, a transaction routing corresponds to select a node for an incoming transaction to be executed. An affinity-based routing can increase local buffer hit ratio of each node by clustering transactions referencing similar data to be executed on the same node. However, the affinity-based routing is very much non-adaptive to the changes in the system load, and thus a specific node will be overloaded if transactions in some class are congested. In this paper, we propose a dynamic transaction routing scheme that can achieve an optimal balance between affinity-based routing and dynamic load balancing of all the nodes in the SD cluster. The proposed scheme is novel in the sense that it can improve the system performance by increasing the local buffer hit ratio and reducing the buffer invalidation overhead.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.537-541
• /
• 2008

Log-Structured File System(LFS) is a disk based file system that is optimized for improving the write performance. LFS gathers dirty data in memory as long as possible, and flushes all dirty data sequentially at once. In a real system, however, maintaining dirty data in memory should be flushed into a disk to meet file system consistency issues even if more memory is still available. This synchronizations increase the cleaner overhead of LFS and make LFS to write down more metadata into a disk. In this paper, by adapting Non-volatile RAM(NV-RAM) we modifies LFS and virtual memory subsystem to guarantee that LFS could gather enough dirty data in the memory and reduce small disk writes. By doing so, we improves the performance of LFS by around 2.5 times than the original LFS.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.6
• /
• pp.414-423
• /
• 2014

The number and size of resource constituting the web page has been increasing steadily, and this circumstance leads to rapidly falling quality of web service in mobile network that offer relatively higher delay. Moreover, Improving the quality of a web services protocol is difficult to provide network function because the current network architecture has closed structure. In this paper, we suggest schemes to enhance web performance in mobile network, which are Check Coded DOM scheme and Functional JavaScript Transmission scheme, and then try to seek idea which can be provided suggested schemes as a network function using NFV(Network Function Virtualization). For the performance evaluation and analysis about the suggested schemes, we perform network simulation using SMPL library. We confirm that suggested schemes offer better performance in term of page loading time, the number of message and the amount of traffic in the network than HTTP Protocol.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.1
• /
• pp.1-10
• /
• 1999

A mobile computing environment is one that support user's mobility through the wireless communication technology. Users access the database and get results what they want by running mobile transactions. To run the mobile transaction correctly and to maintain the consistency I database, we need a concurrency control method to schedule transactions, a caching method to manage the cache, and a recovery method to construct a fault tolerant system. A mobile computing system is based on the existing distributed system, but we can't use recovery methods of the existing distributed system directly because of the user's mobility and the features of wireless media. So this paper presents a recovery mechanism to construct a fault tolerant mobile computing systems. Especially. we develop and analyze a recovery algorithm for server failure among types of failure which can arise in mobile computing environments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.77-82
• /
• 2023

Multi-cloud rendering has been attracting attention recently as the computational load of rendering fluctuates over time and each rendering process can be performed independently. However, it is challenging in multi-cloud rendering to deliver large amounts of input data instantly with consistency constraints. In this paper, we develop a new distributed file system for multi-cloud rendering. In our file system, a local machine maintains a file server that manages versions of rendering input files, and each cloud node maintains a rendering cache manager, which performs distributed cooperative caching by considering file versions. Measurement studies with rendering workloads show that the proposed file system performs better than NFS and the uploading schemes by 745% and 56%, respectively, in terms of I/O throughput and execution time.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.5
• /
• pp.133-138
• /
• 2022

Recently, as GPU performance has improved in HPC and artificial intelligence, its use is becoming more common, but GPU programming is still a big obstacle in terms of productivity. In particular, due to the difficulty of managing host memory and GPU memory separately, research is being actively conducted in terms of convenience and performance, and various CPU-GPU memory transfer programming methods are suggested. Meanwhile, recently many SoC (System on a Chip) products such as Apple M1 and NVIDIA Tegra that bundle CPU, GPU, and integrated memory into one large silicon package are emerging. In this study, data between CPU and GPU devices are used in such an integrated memory device and performance-related research is conducted during transmission. It shows different characteristics from the existing environment in which the host memory and GPU memory in the CPU are separated. Here, we want to compare performance by CPU-GPU data transmission method in NVIDIA SoC chips, which are integrated memory devices, and NVIDIA SMX-based V100 GPU devices. For the experimental workload for performance comparison, a two-dimensional matrix transposition example frequently used in HPC applications was used. We analyzed the following performance factors: the difference in GPU kernel performance according to the CPU-GPU memory transfer method for each GPU device, the transfer performance difference between page-locked memory and pageable memory, overall performance comparison, and performance comparison by workload size. Through this experiment, it was confirmed that the NVIDIA Xavier can maximize the benefits of integrated memory in the SoC chip by supporting I/O cache consistency.