• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.84-94
• /
• 2021

Graph databases have been developed to efficiently store and query graph data composed of vertices and edges to express relationships between objects. Since the query types of graph database show very different characteristics from traditional NoSQL databases, benchmarking tools suitable for graph databases to verify the performance of the graph database are needed. In this paper, we propose an efficient graph database benchmarking system that supports diversity in graph inputs and queries. The proposed system utilizes OrientDB to conduct benchmarking for graph databases. In order to support the diversity of input graphs and query graphs, we use LDBC that is an existing graph data generation tool. We demonstrate the feasibility and effectiveness of the proposed scheme through analysis of benchmarking results. As a result of performance evaluation, it has been shown that the proposed system can generate customizable synthetic graph data, and benchmarking can be performed based on the generated graph data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1432-1440
• /
• 2022

Recently, as Virtual Desktop Infrastructure(VDI) is widely used not only in office work environments but also in workloads that use high-spec multi-core-based applications, the requirements for real-time and stability of VDI are increasing. Accordingly, the display protocol used for remote access in VDI and performance optimization of virtual machines have also become more important. In this paper, we propose two ways to configure desktop virtualization for multi-core-based application operation. First, we propose a codec configuration of a display protocol with optimal performance in a high load situation due to multi-processing. Second, we propose a virtual CPU scheduling optimization method to reduce scheduling delay in case of CPU contention between virtual machines. As a result of the test, it was confirmed that the H.264 codec of Blast Extreme showed the best and stable frame, and the scheduling performance of the virtual CPU was improved through scheduling optimization.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1551-1558
• /
• 2022

We propose a two-tier cooperative computing system comprised of a mobile device and an edge server for partial offloading of multi-branch structures in Fog/Edge Computing environments in this paper. The proposed system includes an algorithm for splitting up application service processing by using reconstructive linearization techniques for multi-branch structures, as well as an optimal collaboration algorithm based on partial offloading between mobile device and edge server. Furthermore, we formulate computation offloading and CNN layer scheduling as latency minimization problems and simulate the effectiveness of the proposed system. As a result of the experiment, the proposed algorithm is suitable for both DAG and chain topology, adapts well to different network conditions, and provides efficient task processing strategies and processing time when compared to local or edge-only executions. Furthermore, the proposed system can be used to conduct research on the optimization of the model for the optimal execution of application services on mobile devices and the efficient distribution of edge resource workloads.

• 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.12
• /
• pp.419-428
• /
• 2022

Since in-place updates for pages are not allowed in flash memory, all new page writes should be written in an out-of-place manner. The old overwritten pages are invalidated. Such invalidated pages eventually trigger the costly garbage collection process. Since the garbage collection causes numerous read and write operations, it is one of the flash memory's major performance issues. In 2R, it modified the garbage collection algorithm, which applies the I/O characteristics of the On-Line Transaction Process workload to improve the Write Amplification Factor. However, this algorithm has a region pollution problem. Therefore, in this paper, we developed 2R++ that additionally separates pages with long access intervals to solve the region pollution problem. 2R++ introduces an extra bit per block to separate warm pages based on a second chance mechanism. Prevents warm pages from being misidentified as cold pages to solve region pollution problem. We conducted the experiments on TPC-C and Linkbench to make the performance comparison. The experiment showed that 2R++ achieved a Write Amplification Factor improvement of 57.8% and 13.8% compared to 2R, respectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.57-62
• /
• 2022

Recently, fast storage media such as phage-change memory (PCM) emerge, and memory management policies for slow disk storage need to be revisited. In this paper, we propose a new page replacement policy that makes use of PCM as a swap device of virtual memory systems. The proposed policy aims at reducing write traffic to the swap device as well as reducing the number of page faults pursued by traditional page replacement policies. This is because a write operation in PCM is slow and PCM has limited write endurances. Specifically, the proposed policy focuses on the reduction of page faults when the memory load of the system is high, but it aims at reducing write traffic to storage when free memory space is sufficient. Simulation experiments with various memory reference traces show that the proposed policy reduces write traffic to PCM without performance degradations.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.961-973
• /
• 2023

With the changes in the modern computing landscape, securing containerized workloads and addressing the complexities of container networking have become critical issues. In particular, the complexity of network policy settings and the lack of cloud security architecture cause various security issues. This paper focuses on the importance of network security and efficiency in containerized environments, and analyzes the security features and performance of various container network interface plugins. In particular, the features and functions of Cilium, Calico, Weave Net, and Kube-router were compared and evaluated, and the Layer 3/4 and Layer 7 network policies and performance features provided by each plugin were analyzed. We found that Cilium and Calico provide a wide range of security features, including Layer 7 protocols, while Weave Net and Kube-router focus on Layer 3/4. We also found a decrease in throughput when applying Layer 3/4 policies and an increase in latency due to complex processing when applying Layer 7 policies. Through this analysis, we expect to improve our understanding of network policy and security configuration and contribute to building a safer and more efficient container networking environment in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1299-1306
• /
• 2023

In this paper, we present a system for undesignated cultural heritage management and real-time theft chase, which uses flash-based large-capacity storage. The proposed system is composed of 3 parts, such as a cultural management device, a flash-based server, and a monitoring service for managing cultural heritages and chasing thefts using IoT technologies. However flash-based storage needs methods to overcome the limited lifespan. Therefore, in this paper, we present a system, which uses the disk buffer in flash-based storage to overcome the disadvantage, and evaluate the system performance in various environments. In our experiments, LRU policy shows the number of direct writes in the flash-based storage by 10.7% on average compared with CLOCK and FCFS.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.6
• /
• pp.185-196
• /
• 2015

Energy aware server clusters aim to reduce power consumption at maximum while keeping QoS(Quality of Service) compared to energy non-aware server clusters. They adjust the power mode of each server in a fixed or variable time interval to let only the minimum number of servers needed to handle current user requests ON. Previous studies on energy aware server cluster put efforts to reduce power consumption further or to keep QoS, but they do not consider energy efficiency well. In this paper, we propose an energy efficient cluster management based on autonomous learning for energy aware server clusters. Using parameters optimized through autonomous learning, our method adjusts server power mode to achieve maximum performance with respect to power consumption. Our method repeats the following procedure for adjusting the power modes of servers. Firstly, according to the current load and traffic pattern, it classifies current workload pattern type in a predetermined way. Secondly, it searches learning table to check whether learning has been performed for the classified workload pattern type in the past. If yes, it uses the already-stored parameters. Otherwise, it performs learning for the classified workload pattern type to find the best parameters in terms of energy efficiency and stores the optimized parameters. Thirdly, it adjusts server power mode with the parameters. We implemented the proposed method and performed experiments with a cluster of 16 servers using three different kinds of load patterns. Experimental results show that the proposed method is better than the existing methods in terms of energy efficiency: the numbers of good response per unit power consumed in the proposed method are 99.8%, 107.5% and 141.8% of those in the existing static method, 102.0%, 107.0% and 106.8% of those in the existing prediction method for banking load pattern, real load pattern, and virtual load pattern, respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.508-519
• /
• 2007

Flash memory based storage has been used in various mobile systems and now is to be used in Laptop computers in the name of Solid State Disk. The Flash memory has not only merits in terms of weight, shock resistance, and power consumption but also limitations like erase-before-write property. To overcome these limitations, Flash memory based storage requires special address mapping software called FTL(Flash-memory Translation Layer), which often performs merge operation for block recycling. In order to reduce block recycling cost in NAND Flash memory based storage, we introduce another block recycling scheme which we call migration. As a result, the FTL can select either merge or migration depending on their costs for each block recycling. Experimental results with Postmark benchmark and embedded system workload show that this cost-based selection of migration/merge operation improves the performance of Flash memory based storage. Also, we present a solution of macroscopic optimal migration/merge sequence that minimizes a block recycling cost for each migration/merge combination period. Experimental results show that the performance of Flash memory based storage can be more improved by the macroscopic optimization than the simple cost-based selection.