• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1151-1158
• /
• 2020

In order to investigate the speed profile of data I/O of HDD, we have developed an utility program. The application to HDD reveals the detail properties of the speed profile of HDD and the relation between the cylinder structure of HDD and the velocity profile. For the extent application, the experiment of the large volume storage was performed, and the profile of SSD media, which is known as the new rapid media, was measured. The new M.2 NVME SSD, which has the ability of over 10Gbps, we can compare the velocities between cp under linux O/S and the utility, and shows that the performance of the utility can be reliable.

• Journal of KIISE
• /
• v.44 no.5
• /
• pp.469-475
• /
• 2017

The emerging NVMe-based multi-queue SSDs provides a high bandwidth by parallel I/O, i.e., each core performs I/O through its dedicated queue in parallel with other cores. To provide a bandwidth share for each application with I/O, a fair-share scheduler that provides a bandwidth share to each core is required. In this study, we proposed a multi-core scalable fair-queuing algorithm for multi-queue SSDs. The algorithm adopts randomization to minimize the inter-core synchronization overheads and provides a weight-proportional bandwidth share to each core. The results of our experiments indicated that the proposed algorithm gives accurate bandwidth partitioning and outperforms the existing FlashFQ scheduler, regardless of the number of cores for a Linux kernel with block-mq.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1145-1152
• /
• 2021

In order to optimize the performance of 1.4P large storage, the characteristics of each chunk mode were investigated, and the chunk 512K mode was selected in terms of I/O speed. NVME storage system was configured and used to measure data server performance of large storage. By measuring the change in throughput according to the number of threads of the 1.4P large storage, the characteristics of the large storage system were identified, and it was confirmed that the performance was up to 133Gbps with a block size of 32KB. As a result of data transmission/reception experiment using globus-url-copy of GridFTP, it was found that this large storage has a throughput of 33Gbps.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.450-461
• /
• 2022

The Gen-Z protocol is a memory semantic protocol between the memory and CPU used in computer architectures with large memory pools. This study presents the implementation of the Gen-Z hardware system configured using Gen-Z specification 1.0 and reports its performance. A hardware prototype of a DDR4 Gen-Z memory pool with an optimized character, a block device driver, and a file system for the Gen-Z hardware was designed. The Gen-Z IP was targeted to the FPGA, and a 512 GB Gen-Z memory pool was configured on an ×86 server. In the experiments, the latency and throughput of the Gen-Z memory were measured and compared with those of the local memory, SATA SSD, and NVMe using character or block device interfaces. The Gen-Z hardware exhibited superior throughput and latency performance compared with SATA SSD and NVMe at block sizes under 4 kB. The MySQL and File IO benchmark of Gen-Z showed good write performance in all block sizes and threads. Besides, it showed low latency in RocksDB's fillseq dbbench using the ext4 direct access filesystem.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.2
• /
• pp.33-40
• /
• 2018

In an environment with a large network bandwidth, maximizing bandwidth utilization is an important issue to increase transmission efficiency. End-to-end transfer efficiency is significantly influenced by factors such as network, data transfer nodes, and intranet network security policies. Science DMZ is an innovative network architecture that maximizes transfer performance through optimal solution of these complex components. Among these, the data transfer node is a key factor that greatly affects the transfer performance depending on storage, network interface, operating system, and transfer application tool. However, tuning parameters constituting a data transfer node must be performed to provide high transfer efficiency. In this paper, we propose a method to enhance performance through tuning parameters of 100Gbps data transfer node. With experiment result, we confirmed that the transmission efficiency can be improved greatly in 100Gbps network environment through the tuning of Jumbo frame and CPU governor. The network performance test through Iperf showed improvement of 300% compared to the default state and NVMe SSD showed 140% performance improvement compared to hard disk.

• The Journal of the Korea Contents Association
• /
• v.18 no.4
• /
• pp.178-185
• /
• 2018

Recently, demands for computer systems with multicore CPUs and high-performance flash-based storage devices (i.e., flash SSD) have rapidly grown in cloud computing, surer-computing, and enterprise storage/database systems. Journaling file systems running on high-performance systems do not exploit the full I/O bandwidth of high-performance SSDs. In this article, we evaluate and analyze the performance of the Linux EXT4 file system with high-performance SSDs and multicore CPUs. The system used in this study has 72 cores and Intel NVMe SSD, and the flash SSD has performance up to 2800/1900 MB/s for sequential read/write operations. Our experimental results show that checkpointing in the EXT4 file system is a major overhead. Furthermore, we optimize the checkpointing procedure and our optimized EXT4 file system shows up to 92% better performance than the original EXT4 file system.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.4
• /
• pp.17-24
• /
• 2017

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.2
• /
• pp.63-69
• /
• 2019

Recently, ultra-low latency flash storage devices such as Z-SSD and Optane SSD were introduced with the significant technological improvement in the storage devices which provide much faster response time than today's other NVMe SSDs. With such ultra-low latency, $10{\mu}s$, storage devices the cost of context switch could be an overhead during interrupt-driven I/O completion process. As an interrupt-driven I/O completion process could bring an interrupt handling overhead, polling or hybrid-polling for the I/O completion is known to perform better. In this paper, we analyze tail latency problem in a polling process caused by process scheduling in data center environment where multiple applications run simultaneously under one system and we introduce our adaptive polling selection technique which dynamically selects efficient processing method between two techniques according to the system's conditions.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.79-90
• /
• 2019

Maximizing energy efficiency minimizes the energy consumption of computation, storage and communications required for IT services, resulting in economic and environmental benefits. Recent advancement of flash and next generation non-volatile memory technology and price decrease of those memories have led to the rise of so-called AFA (All-Flash Array) storage devices made of flash or next generation non-volatile memory. Currently, the AFA devices are rapidly replacing traditional storages in the high-performance servers due to their fast input/output characteristics. However, it is not well known how effective the energy efficiency of the AFA devices in the real world. This paper shows input/output performance and power consumption of the AFA devices measured on the Linux XFS file system via experiments and discusses energy efficiency of the AFA devices in the real world.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.57-67
• /
• 2021

Modern cloud computing is rapidly changing from traditional hypervisor-based virtual machines to container-based cloud-native environments. Due to limitations in I/O performance required for both virtual machines and containers, the use of high-speed storage (SSD, NVMe, etc.) is increasing, and in-memory computing using main memory is also emerging. Running a virtual environment on main memory gives better performance compared to other storage arrays. However, RAM used as main memory is expensive and due to its volatile characteristics, data is lost when the system goes down. Therefore, additional work is required to run the virtual environment in main memory. In this paper, we propose a hybrid in-memory storage that combines a block storage such as a high-speed SSD with main memory to safely operate virtual machines and containers on main memory. In addition, the proposed storage showed 6 times faster write speed and 42 times faster read operation compared to regular disks for virtual machines, and showed the average 12% improvement of container's performance tests.