• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.131-136
• /
• 2013

Multi-core processors can improve parallelism of application processes and thus can enhance the system throughput. Researchers have recently revealed that the processor affinity is an important factor to determine network I/O performance due to architectural characteristics of multi-core processors; thus, many researchers are trying to suggest a scheme to decide an optimal processor affinity. Existing schemes to dynamically decide the processor affinity are able to transparently adapt for system changes, such as modifications of application and upgrades of hardware, but these have limited access to characteristics of application behavior and run-time information that can be collected heuristically. Thus, these can provide only sub-optimal processor affinity. In this paper, we define meaningful system variables for determining optimal processor affinity and suggest a tool to gather such information. We show that the implemented tool can overcome limitations of existing schemes and can improve network bandwidth.

• 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 Microbiological Society of Korea Conference
• /
• 2002.10a
• /
• pp.159-161
• /
• 2002

Bacteriophage lambda integrase carries out the site-specific recombination of lambda. Integrase contains two DNA binding domains with distinct sequence specificity, namely arm-type binding and core-type binding domains. The amino-terminal arm-binding domain is structurally related to the three-stranded $\beta-sheet$ family of DNA-binding domains. Integrase binding to the high affinity arm-type site by the amino-terminal domain facilitates Int binding to the low affinity core-type site, where the cleavage and strand exchange occurs. The amino-terminal domain of Int also modulates the core-binding and catalysis through intramolecular domain-domain interaction and/or intermolecular interactions between Int monomers. In addition, the amino-terminal domain interacts cooperatively with excisionase during excision. This indicates that amino-terminal domain of Int plays an important role in formation of proper higher-order nucleoprotein structure required for lambda site-specific recombination.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.204-206
• /
• 2012

SMP(Symmetric Multi-Processing)는 Shared memory bus 를 사용함으로써 scalability 가 제한적이었다. 이런 SMP의 scalability 제한을 극복하기 위해 제안 된 것이 NUMA(Non Uniform Memory Access)이다. NUMA는 memory bus 를 CPU 별 local 하게 가지고 있어 자신이 가지는 memory 영역에 대해서는 다른 영역을 접근하는 것 보다 더 빠른 latency 를 가지는 구조이다. Local 한 memory 영역의 존재는 scalability를 높여 주었지만 서버 가상화 환경에서 VM을 동적으로 scheduling 을 하였을 때 VM의 page 가 실행되는 core 의 local 한 메모리 영역에 존재하지 않게 되면 remote access로 인해 local access보다 성능이 떨어진다. 이 논문에서는 서버 가상화 환경에서 최신 architecture인 AMD bulldozer에서 NUMA affinity가 위반되었을 때 발생하는 성능 저하와 어떤 상황에서 이런 NUMA affinity가 위반되어도 성능저하가 없는지 연구하였다.

• Mass Spectrometry Letters
• /
• v.9 no.2
• /
• pp.51-55
• /
• 2018

Capture of non-glycoproteins during lectin affinity chromatography is frequently observed, although it would seem to be anomalous. In actuality, lectin affinity chromatography works at post-translational modification (PTM) sites on a glycoprotein which is not involved in protein-protein interactions (PPIs). In this study, serial affinity column set (SACS) using lectins followed by proteomics methods was used to identify PPI mechanisms of captured proteins in human plasma. MetaCore, STRING, Ingenuity Pathway Analysis (IPA), and IntAct were individually used to elucidate the interactions of the identified abundant proteins and to obtain the corresponding interaction maps. The abundant non-glycoproteins were captured with the binding to the selected glycoproteins. Therefore, depletion process in sample pretreatment for abundant protein removal should be considered with more caution because it may lose precious disease-related low abundant proteins through PPIs of the removed abundant proteins in human plasma during the depletion process in biomarker discovery. Glycoproteins bearing specific glycans are frequently associated with cancer and can be specifically isolated by lectin affinity chromatography. Therefore, SACS using Lycopersicon esculentum lectin (LEL) can also be used to study disease interactomes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.65-67
• /
• 2013

The recent high-performance network equipment is required, and also require high network bandwidth utilization. It is a trend to develop increasingly using multi-core processors for high-performance network servers. Propose a method to improve the performance of the network sub-system, considering the characteristics of multi-core as a way to improve these high-performance and high network throughput. In this paper, we confirm through experiments on how to improve the communication performance, optimize performance and take full advantage of multi-core by Network communication process to improve the performance of the multi-core processor architecture, the process of concentration, the overhead for each core, based on network traffic according to the interrupt affinity in this process to determine the optimal core to give. The experiments were implemented in the Linux kernel, and experiments to improve the network throughput up to 30%, bringing reduces the Linux communication process to improve the performance of the processor overhead of up to 10%.

• Preventive Nutrition and Food Science
• /
• v.4 no.2
• /
• pp.145-151
• /
• 1999

Apolipoprotein B-100 (apo B-100) is an important component in plasma low density lipoproteins (LDL). It function as the ligand for the LDL receptor in peripheral cells. The LDLs are removed from the circulation by both high-affinity receptor-mediated and receptor-independant pathways. LDLs are heterogeneous in their lipid content, size and density and certain LDL subspecies increase risk of atherosclerosis due to differences in the conformation of apo B in the particle. In the present study , surface and core peptide fraction of Apo B-100 have been characterized by comparing peptide-mapping and fluorescence spectroscopy. Surface fragments of apo B-100 were generated by digestion of LDL with either trypsin , pronase, or pancreatin elastase. Surface fractions were fractionated on a Sephadex G-50 column. The remaining core fragments were delipidated and redigested with the above enzymes, and the resulting core peptides were compared with surface peptides. Results from peptide-mapping by HPLC showed pronase-digestion was more extensive than trypsin -digestion to remove surface peptide fraction from LDL. Fluorescence spectra showed that core fractions contained higher amount of tryptophan than surface fractions, and it indicated that core fraction wa smore hydrophobic than surface fractions. A comparison of the behavior of the core and surface provided informations about the regions of apo B-100 involved in LDL metabolism and also about the structural features concerning the formation of atherosclerosis.

• BMB Reports
• /
• v.40 no.1
• /
• pp.82-87
• /
• 2007

Our heterologous expression system of the human ferritin H-chain gene (hfH) allowed us to characterize the cellular effects of ferritin in yeasts. The recombinant Saccharomyces cerevisiae (YGH2) evidenced impaired growth as compared to the control, which was correlated with ferritin expression and with the formation of core minerals. Growth was recovered via the administration of iron supplements. The modification of cellular iron metabolism, which involved the increased expression of high-affinity iron transport genes (FET3 and FTR1), was detected via Northern blot analysis. The findings may provide some evidence of cytosolic iron deficiency, as the genes were expressed transcriptionally under iron-deficient conditions. According to our results examining reactive oxygen species (ROS) generation via the fluorescence method, the ROS levels in YGH2 were decreased compared to the control. It suggests that the expression of active H-ferritins reduced the content of free iron in yeast. Therefore, present results may provide new insights into the regulatory network and pathways inherent to iron depletion conditions.

• Molecules and Cells
• /
• v.20 no.2
• /
• pp.297-302
• /
• 2005

The integrity and proper functioning of telomeres require association of telomeric DNA sequences with specific binding proteins. We have characterized PLP-1, a $PUR{\alpha}$ homolog encoded by F45E4.2, which we previously identified as a candidate double stranded telomere binding protein, by affinity chromatography followed by mass spectrometry. PLP-1 bound double-stranded telomeric DNA in vitro as shown by competition assays. Core binding was provided by the third and fourth nucleotides of the TTAGGC telomeric repeat. This is quite different from the binding sequence of CEH-37, another C. elegans telomere binding protein, suggesting that multiple proteins may bind nematode telomeric DNA simultaneously in vivo.