• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.251-258
• /
• 2016

Recently, the demand for fast storage devices is rapidly increasing in cloud platforms, social network services, etc. Despite the development of fast storage devices, the traditional Linux I/O stack is not able to exploit the full extent of the performance improvement since it has been optimized for disk-based storage devices. In this paper, we propose an optimized I/O stack which can fully utilize the I/O bandwidth and latency of fast storage devices. To this end, we design a new I/O interface to replace the current block I/O interface and optimize our I/O interface. Our optimized I/O interface bypasses operations/layers in block I/O subsystems of the current Linux I/O stack to fully exploit fast storage devices. We also optimize the Linux file systems such as ext2 and ext4 to run on our I/O interface. We evaluate our I/O stack with multiple benchmarks and the experimental results show that our I/O stack achieves 1.7 times better throughput compared to traditional Linux I/O stack.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.687-690
• /
• 2004

Fabrication and characterization of dye-sensitized TiO2 solar cells(DSSC) consisting of spray-coated TiO2 electrode, an electrolyte containing I-/I3- redox couple, and a Pt-coated counter electrode carried out, using mainly FE-SEM and solar simulator. Also, effect of rapid thermal annealing(RTA) temperatue on I-V curves of DSSCS consisting of approximately 10m thickness and $5{\times}5mm2$ active area. No significant difference in the apparent size of TiO2 clusters was observed with increasing RTA temperature. Also, an open circuit voltage(Voc) of approximately 0.70V and a short-circuit photocurrent(Jsc) of 8 to 12mA/cm2 were observed in the TiO2 solar cell. With increasing RTA temperature upto 550oC, photocurrent density of dye-sensitized solar cells was enhanced, leading to enhancing the efficiency of dye-sensitized solar cells having Pt-electroplated counter electrode.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.5
• /
• pp.229-235
• /
• 2006

High speed PC-based DIO(Digital I/O) system that consists of a master device and slave I/O devices is developed. The PCI interfaced master device controls all of serial communications, reducing the load on the CPU to a minimum. The slave device is connected from the master device and another slave device is connected to the slave device, it can repeated to maximum 64 slave devices. The slave device has 3 types I/O mode, such as 16 bits input-only, 16 bits output-only, and 8bits input-output. The master device has 2 rings which can take 64 slaves each. Therefore, total I/O points covered by the master is 2048 points. The slave features 3 types of input/output function interchangeability by DIP switch settings. Library, application, and device driver software for the DIO system that have a secure and a convenient functionality are developed.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.702-706
• /
• 2010

In this paper, we propose a framework to change local devices to networked devices by using web browser. Network devices will be used in the virtual desktop. Management software maintains a pool of devices to manage network devices. Whenever user's request is occured, virtual desktop s/w which manages desktop's I/O access device pool. Then virtual desktop s/w selects proper device and forwards I/O to desktop. In this paper, we choose RIA solution for install-free environment. Consequently, user easily enrolls and revokes their devices. User easily commands virtual desktop s/w. In the second half of this paper, we explain usage scenario and evaluate our framework to show efficiency and flexibility of the framework.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.27-34
• /
• 2013

NAND Flash Memory has been used in several devices by low cost and high capacity, and the demand for mass NAND Flash Memory has increased due to the multimedia extension of mobile devices. The JFFS2, NILFS2, and YAFFS2 file systems are used mainly in NAND Flash Memory. In this paper, the performance of Sequential read/write of the 3 file systems are analyzed for the 4 I/O schedulers : CFQ(Complete Fair Queuing) I/O scheduler, NOOP(No Operation) I/O scheduler, Anticipatory I/O scheduler, and Deadline I/O scheduler. In JFFS2 file system, Anticipatory I/O scheduler has the best performance by 8% decreasing speed in writing time and 1.5% decreasing speed in reading time compared to the other I/O scheduler. In YAFFS2 file system, it results are similar to performance in reading and writing for the 4 I/O schedulers. In NILFS2 file system, NOOP I/O scheduler has 2% faster in writing and Deadline I/O scheduler has 6% faster in reading than other I/O schedulers.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.4
• /
• pp.249-254
• /
• 2011

A user desktop service can be made available on internet or local area network with the help of virtualization and cloud technologies. The service is usually called a virtual desktop or a desktop cloud. However, a user interface is limited to I/O capabilities of a user's mobile terminal. In order to enhance a user interface on a remote virtual desktop, it is important to connect full-featured I/O devices which are founded locally. Our previous work called SoD (System-on- Demand) has proposed a technique to associate local full-featured I/O devices with a remote virtual desktop in Xen. On the technique, it is required to install a SoD client agent in a user's mobile terminal for connecting a remote virtual desktop. In this paper, we propose a new framework called Web-SoD that does not require any explicit installation to make SoD service available. The SoD client agent is provided by the web technology so that the agent can be installed transparently, and the platform independency is also achieved. Due to insufficient network socket performance of current web technologies, we extend Native Client (NaCl) proposed by Google to support a network functionality by modifying a NaCl library and a service runtime. With conducted experiment, we show that the network extension supports a full socket functionality over the compromised overhead on the web environment.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.736-743
• /
• 2016

Several studies have reported the impact of core affinity on the network I/O performance of multi-core systems. As the network bandwidth increases significantly, it becomes more important to determine the effective core affinity. Although a framework for dynamic core affinity that considers both network and disk I/O has been suggested, the multiple queues provided by high-speed I/O devices are not properly supported. In this paper, we extend the existing framework of dynamic core affinity to efficiently support the multiple queues of high-speed I/O devices, such as 40 Gigabit Ethernet and NVM Express. Our experimental results show that the extended framework can improve the HDFS file upload throughput by up to 32%, and can provide improved scalability in terms of the number of cores. In addition, we analyze the impact of the assignment policy of multiple I/O queues across a number of cores.

• 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 the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.19-32
• /
• 1993

This paper suggests the new high-speed input/output techniques in a shared memory multiprocessor system. The high-speed I/O processor which can connect the different kinds of large sized I/O periperal devices, the communication protocol to the main processing units for I/O operations, and the job scheduling scheme are addressed. This paper also introduces the disk cache technique which supports the slow I/O devices comparing with the main processing units. These techniques were implemented in the TICOM system. The performance evaluation statistics were collected and analyzed for the suggested high-speed I/O processing techniques. These statistics show the superiority of the suggested techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.37.5-37
• /
• 2002

$\textbullet$ Wearable I/O Devices relieve the restriction of working space to the worker. $\textbullet$ And They permit very active work achievement to the worker. $\textbullet$ But, current Wearable I/O Devices still have some controversial points. $\textbullet$ The worker needs serie system operations to wear and take off devices. $\textbullet$ Also, it is not easy to change any device which is currently used when the worker uses some devices. $\textbullet$ So, we propose the Compact Wireless Communication Module to solve these problem. $\textbullet$ For that purpose, we implemented the proposed module, and proved the efficiency and convenience.