• Journal of the Korea Society of Computer and Information
• /
• v.22 no.4
• /
• pp.25-32
• /
• 2017

Recently, the use of NAND flash memory is being increased as a secondary device to displace conventional magnetic disk. NAND flash memory, as one among non-volatile memories, has many advantages such as low power, high reliability, low access latency, and so on. However, NAND flash memory has disadvantages such as erase-before-write, unbalanced operation speed, and limited P/E cycles, unlike conventional magnetic disk. To solve these problems, NAND flash memory mainly adopted FTL (Flash Translation Layer). In particular, garbage collection technique in FTL tried to improve the system lifetime. However, previous garbage collection techniques have a sensitive property of the system lifetime according to write pattern. To solve this problem, we propose BSGC (Balanced Selection-based Garbage Collection) technique. BSGC efficiently selects a victim block using all intervals from the past information to the current information. In this work, SFL (Search First linked List), as the proposed block allocation policy, prolongs the system lifetime additionally. In our experiments, SFL and BSGC prolonged the system lifetime about 12.85% on average and reduced page migrations about 22.12% on average. Moreover, SFL and BSGC reduced the average response time of 16.88% on average.

• Journal of KIISE:Databases
• /
• v.31 no.6
• /
• pp.596-608
• /
• 2004

A lot of work has been done to reduce disk access time in I/O intensive systems, which store and handle massive amount of data, by distributing data across multiple disks and accessing them in parallel. Most of the previous work has focused on an efficient mapping from a grid cell to a disk number on the assumption that data space is regular grid-like partitioned. Although we can achieve good performance for low-dimensional data by grid-like partitioning, its performance becomes degenerate as grows the dimension of data even with a good disk allocation scheme. This comes from the fact that they partition entire data space equally regardless of distribution ratio of data objects. Most of the data in high-dimensional space exist around the surface of space. For that reason, we propose a new declustering algorithm based on the partitioning scheme which partition data space from the surface. With an unbalanced partitioning scheme, several experimental results show that we can remarkably reduce the number of data blocks touched by a query as grows the dimension of data and a query size. In this paper, we propose disk allocation schemes based on the layout of the resultant data blocks after partitioning. To show the performance of the proposed algorithm, we have performed several experiments with different dimensional data and for a wide range of number of disks. Our proposed disk allocation method gives a performance within 10 additive disk accesses compared with strictly optimal allocation scheme. We compared our algorithm with Kronecker sequence based declustering algorithm, which is reported to be the best among the grid partition and mapping function based declustering algorithms. We can improve declustering performance up to 14 times as grows dimension of data.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.10a
• /
• pp.391-394
• /
• 2009

Asymmetrical and unbalanced features such as rotor blade of helicopter, actuator of hard-disk in personal computer are usually manufactured with composite materials. In this case, mass distributions and center of gravity of the parts are important because of their static balancing. Therefore in the manufacturing processes, it is needed to check out the exact data of weight and gravity center. In this study, it has been studied experimentally the balancing of laminated rotor blade by using multiple-point weighing method and lab-view system.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.4
• /
• pp.576-581
• /
• 2010

As a super high speed small-sized centrifugal separator which is operated by the center inputting method has solved two difficulty problems, it can be made use of developing the new composition through the making of Nano particle (50~100nm) by high speed revolution and alleviation of unbalanced shapes inside the disk continuously throwing slurry in the central part. Uses the air spindle and the centrifugal machine production will be able to manufacture the Roh class fine particle under boil.

• Transactions of the Society of Information Storage Systems
• /
• v.6 no.2
• /
• pp.57-62
• /
• 2010

This paper measured and analyzed the source of total power loss of an ODD of a notebook computer. It shows that the biggest power loss is the windage loss due to the friction between rotating disk and surrounding air. It measured the power loss by the tilting motion of a rotating disc which is originated from the unbalanced mass of the rotating disc or the squareness between case-rotor and shaft. The power loss of rotating disc due to tilting motion was also calculated by using FLUENT, and it was correlated with the measured one. This paper shows that the one of the effective methods to reduce the power loss of an ODD is to reduce the tilting motion of a rotating disc.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.852-858
• /
• 2007

This paper investigates the dynamic characteristics of a tilted HDD spindle system with fluid dynamic bearings (FDBs). Tilting motion of a HDD spindle system may be caused by improper manufacturing tolerance, such as imperfect cylindricity between shaft and sleeve of FDBs, imperfect perpendicularity between shaft and thrust as well as the gyroscopic moment of the unbalanced mass of the rotating part. Tilting motion may result in the instability of the HDD spindle system and it may increase the disk run-out to limit memory capacity. This research proposes a modified Reynolds equation for the coupled journal and thrust FDBs to include the variable film thickness due to the cylindricity and the perpendicularity. Finite element method is used to solve the Reynolds equation for the pressure distribution. Reaction forces and friction torque are obtained by integrating the pressure and shear stress, respectively. The dynamic behavior is determined by solving the equations of a motion of a HDD spindle system in six degrees of freedom with the Runge-Kutta method to study whirling and tilting motions. This research shows that the cylindricity and the perpendicularity increase the tilting angle and whirl radius of the rotor.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.3
• /
• pp.51-58
• /
• 2007

The shared-nothing multiprocessor architecture has advantages in scalability, this architecture has been adopted in many multiprocessor database system. But, if the data are not uniformly distributed across the processors, load will be unbalanced. Therefore, the whole system performance will deteriorate. This is the data skew problem, which usually occurs in processing parallel hash join. Balancing the load before performing join will resolve this problem efficiently and the whole system performance can be improved. In this paper, we will present an algorithm using merit of very large memory to reduce disk access overhead in performing load balancing and to efficiently solve the data skew problem. Also, we will present analytical model of our new algorithm and present the result of some performance study we made comparing our algorithm with the other algorithms in handling data skew.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.4
• /
• pp.764-774
• /
• 2002

Dynamic behaviors are analyzed for an automatic ball balancer (ABB) with triple races, which is a device to reduce the unbalanced mass of optical disk drives (ODD) such as CD-ROM or DVD drives. The nonlinear equations of motion are derived by using Lagrange's equations with the polar coordinate system. It is shown that the polar coordinate system provides the complete stability analysis while the rectangular coordinate system used in other previous studies has limitations on the stability analysis. For the stability analysis, the equilibrium positions and the linearized perturbation equations are obtained by the perturbation method. Based on the linearized equations, the stability of the system is analyzed around the equilibrium positions; furthermore, to confirm the stability, the time responses for the nonlinear equations of motion are computed by using a time integration method and experimental analyses are performed. Theoretical and experimental results show a superiority of the ABB with triple races.

• Korean Journal of Metals and Materials
• /
• v.50 no.8
• /
• pp.549-556
• /
• 2012

The tribological behavior of CrMoN films with respect to surface chemistry was investigated by using X-ray photoelectron spectroscopy (XPS). All of the films were prepared from a hybrid PVD system consisting of DC unbalanced magnetron (UBM) sputtering and arc ion plating (AIP) sources. The tribological property of the films was evaluated by a friction coefficient using a Ball-on-disk type tribometer. The chemistry of wear track was analyzed by energy dispersive spectroscopy (EDS) and XPS. The friction coefficient was measured to be 0.4 for the CrMoN film, which is lower than that of a monolithic CrN film. EDS and XPS results imply the formation of an oxide layer on the coating surface, which was identified as molybdenum oxide phases, known to be a solid lubricant during the wear test.

• Journal of the Korean institute of surface engineering
• /
• v.49 no.6
• /
• pp.580-586
• /
• 2016

Cr-Si-Al-N coating with different Si content were deposited by hybrid physical vapor deposition (PVD) method consisting of unbalanced magnetron (UBM) sputtering and arc ion plating (AIP). The deposition temperature was $300^{\circ}C$, and the gas ratio of $Ar/N_2$ were 9:1. The CrSi alloy and aluminum targets used for arc ion plating and sputtering process, respectively. Si content of the CrSi alloy targets were varied with 1 at%, 5 at%, and 10 at%. The phase analysis, composition and microstructural analysis performed using x-ray diffraction (XRD) and field emission scanning electron microscopy (FESEM) including energy dispersive spectroscopy (EDS), respectively. All of the coatings grown with textured CrN phase (200) plane. The thickness of the Cr-Si-Al-N films were measured about $2{\mu}m$. The friction coefficient and removal rate of films were measured by a ball-on-disk test under 20N load. The friction coefficient of all samples were 0.6 ~ 0.8. Among all of the samples, the removal rate of CrSiAlN (10 at% Si) film shows the lowest values, $4.827{\times}10^{-12}mm^3/Nm$. As increasing of Si contents of the CrSiAlN coatings, the hardness and elastic modulus of CrSiAlN coatings were increased. The morphology and composition of wear track of the films was examined by scanning electron microscopy (SEM) and energy dispersive spectroscopy, respectively. The surface energy of the films were obtained by measuring of contact angle of water drop. Among all of the samples, the CrSiAlN (10 at% Si) films shows the highest value of the surface energy, 41 N/m.