• Journal of Communications and Networks
• /
• 제17권3호
• /
• pp.306-320
• /
• 2015

Due to an explosive growth in services running in different datacenters, there is need for service selection and routing to deliver user requests to the best service instance. In current solutions, it is generally the client that must first select a datacenter to forward the request to before an internal load-balancer of the selected datacenter can select the optimal instance. An optimal selection requires knowledge of both network and server characteristics, making clients less suitable to make this decision. Information-Centric Networking (ICN) research solved a similar selection problem for static data retrieval by integrating content delivery as a native network feature. We address the selection problem for services by extending the ICN-principles for services. In this paper we present Queue and Latency, a network-driven service selection algorithm which maps user demand to service instances, taking into account both network and server metrics. To reduce the size of service router forwarding tables, we present a statistical method to approximate an optimal load distribution with minimized router state required. Simulation results show that our statistical routing approach approximates the average system response time of source-based routing with minimized state in forwarding tables.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권10호
• /
• pp.4787-4807
• /
• 2016

Although the dense interconnection datacenter networks (DCNs) (e.g. FatTree) provide multiple paths and high bisection bandwidth for each server pair, the single-path TCP (SPT) and ECMP which are widely used currently neither achieve high bandwidth utilization nor have good load balancing. Due to only one available transmission path, SPT cannot make full use of all available bandwidth, while ECMP's random hashing results in many collisions. In this paper, we present OFPT, an OpenFlow based Parallel Transport framework, which integrates precise routing and scheduling for better load balancing and higher network throughput. By adopting OpenFlow based centralized control mechanism, OFPT computes the optimal path and bandwidth provision for each flow according to the global network view. To guarantee high throughput, OFPT dynamically schedules flows with Seamless Flow Migration Mechanism (SFMM), which can avoid packet loss in flow rerouting. Finally, we test OFPT on Mininet and implement it in a real testbed. The experimental results show that the average network throughput in OFPT is up to 97.5% of bisection bandwidth, which is higher than ECMP by 36%. Besides, OFPT decreases the average flow completion time (AFCT) and achieves better scalability.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1020-1033
• /
• 2022

In this paper, we propose novel disaggregated memory module (dMM) architecture and memory access control schemes to solve the collision and contention problems of memory disaggregation, reducing the average memory access time to less than 1 ㎲. In the schemes, the distributed scheduler in each dMM determines the order of memory read/write access based on delay-sensitive priority requests in the disaggregated memory access frame (dMAF). We used the memory-intensive first (MIF) algorithm and priority-based MIF (p-MIF) algorithm that prioritize delay-sensitive and/or memory-intensive (MI) traffic over CPU-intensive (CI) traffic. We evaluated the performance of the proposed schemes through simulation using OPNET and hardware implementation. Our results showed that when the offered load was below 0.7 and the payload of dMAF was 256 bytes, the average round trip time (RTT) was the lowest, ~0.676 ㎲. The dMM scheduling algorithms, MIF and p-MIF, achieved delay less than 1 ㎲ for all MI traffic with less than 10% of transmission overhead.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2257-2285
• /
• 2022

Cyber-physical systems (CPS) have been growing exponentially due to improved cloud-datacenter infrastructure-as-a-service (CDIaaS). Incremental expandability (scalability), Quality of Service (QoS) performance, and reliability are currently the automation focus on healthy Tier 4 CDIaaS. However, stable QoS is yet to be fully addressed in Cyber-physical data centers (CP-DCS). Also, balanced agility and flexibility for the application workloads need urgent attention. There is a need for a resilient and fault-tolerance scheme in terms of CPS routing service including Pod cluster reliability analytics that meets QoS requirements. Motivated by these concerns, our contributions are fourfold. First, a Distributed Non-Recursive Cloud Model (DNRCM) is proposed to support cyber-physical workloads for remote lab activities. Second, an efficient QoS stability model with Routh-Hurwitz criteria is established. Third, an evaluation of the CDIaaS DCN topology is validated for handling large-scale, traffic workloads. Network Function Virtualization (NFV) with Floodlight SDN controllers was adopted for the implementation of DNRCM with embedded rule-base in Open vSwitch engines. Fourth, QoS evaluation is carried out experimentally. Considering the non-recursive queuing delays with SDN isolation (logical), a lower queuing delay (19.65%) is observed. Without logical isolation, the average queuing delay is 80.34%. Without logical resource isolation, the fault tolerance yields 33.55%, while with logical isolation, it yields 66.44%. In terms of throughput, DNRCM, recursive BCube, and DCell offered 38.30%, 36.37%, and 25.53% respectively. Similarly, the DNRCM had an improved incremental scalability profile of 40.00%, while BCube and Recursive DCell had 33.33%, and 26.67% respectively. In terms of service availability, the DNRCM offered 52.10% compared with recursive BCube and DCell which yielded 34.72% and 13.18% respectively. The average delays obtained for DNRCM, recursive BCube, and DCell are 32.81%, 33.44%, and 33.75% respectively. Finally, workload utilization for DNRCM, recursive BCube, and DCell yielded 50.28%, 27.93%, and 21.79% respectively.

• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.476-490
• /
• 2017

In the centralized cloud controlled environment, the decision-making and monitoring play crucial role where in the host controller (HC) manages the resources across hosts in data center (DC). HC does virtual machine (VM) and physical hosts management. The VM management includes VM creation, monitoring, and migration. If HC down, the services hosted by various hosts in DC can't be accessed outside the DC. Decentralized VM management avoids centralized failure by considering one of the hosts from DC as HC that helps in maintaining DC in running state. Each host in DC has many VM's with the threshold limit beyond which it can't provide service. To maintain threshold, the host's in DC does VM migration across various hosts. The data in migration is in the form of plaintext, the intruder can analyze packet movement and can control hosts traffic. The incorporation of security mechanism on hosts in DC helps protecting data in migration. This paper discusses an approach for dynamic HC selection, VM selection and secure VM migration over cloud environment.

• 전자통신동향분석
• /
• 제33권1호
• /
• pp.89-100
• /
• 2018

To accommodate the rapid increase in the amount of data traffic, the capacity of datacenters is expanding rapidly. Datacenter networks (DCNs) utilize electronic packet switches. However, the increases in the speed and capacity of electronic devices are slower than that of data expansion. Furthermore, electronics are too well developed to reach very near their physical limits. To achieve a breakthrough under this situation, optical switching schemes have been widely examined to replace or collaborate with incumbent electronic switches in a DCN. This report reviews the current status of such global researches on an optical DCN.

• 전자통신동향분석
• /
• 제35권3호
• /
• pp.55-65
• /
• 2020

With the development of nonvolatile memory technology, Intel has released the Optane datacenter persistent memory module (DCPMM) that can be deployed in the dual in-line memory module. The results of research and experiments on Optane DCPMMs are significantly different from the anticipated results in previous studies through emulation. The DCPMM can be used in two different modes, namely, memory mode (similar to volatile DRAM: Dynamic Random Access Memory) and app direct mode (similar to file storage). It has buffers in 256-byte granularity; this is four times the CPU (Central Processing Unit) cache line (i.e., 64 bytes). However, these properties are not easy to use correctly, and the incorrect use of these properties may result in performance degradation. Optane has the same characteristics of DRAM and storage devices. To take advantage of the performance characteristics of this device, operating systems and applications require new approaches. However, this change in computing environments will require a significant number of researches in the future.

• 전자통신동향분석
• /
• 제24권4호
• /
• pp.112-125
• /
• 2009

언제부터인가 주위는 모두 "녹색" 물결로 뒤덥혀 버렸다. 그 중에서도 IT의 존재는 녹색 물결에 휩싸여 새로운 판로를 모색하고 있다. 데이터센터 역시 그 문제점은 수 년전부터 대두되어 왔고, 정책적으로 혹은 업계 자체적으로 데이터센터의 문제점을 해결하고자 많은 솔루션을 내고 있는 실정이다. 그린 데이터센터를 위한 견해는 먼저 비 IT영역으로 공조, 항온/항습 시설, 전력 배전 시설 등의 관점에서 접근하는 견해가 있고 IT영역으로 서버 자체에 대한 관점에서 접근하는 견해가 있다. 본 고에서는 데이터센터 내에서 IT 영역에 대한 전력 관리를 위하여 해야 될 역할에 대하여 언급하고자 한다. 특히 데이터센터 내 서버 자체의 전력 절감을 위한 방법에 대하여 논하고, 앞선 업체들 특히 IBM, Google, SUN 등의 동향으로부터 그린 데이터센터를 위한 방향을 모색해 보기로 한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 춘계학술발표대회
• /
• pp.156-159
• /
• 2015

최근 콘텐츠 전송 네트워크(content delivery network, CDN)와 클라우드 컴퓨팅(cloud computing)을 결합하여 효과적으로 콘텐츠를 전달하기 위한 방법이 대두되고 있으며 이와 같이 클라우드 컴퓨팅과 결합하여 서비스되는 CDN을 클라우드 CDN 이라고 칭한다. 본 논문에서는 클라우드 CDN 환경에서의 효과적인 가상 머신 (virtual machine, VM) 관리를 위한 캐시서버(caching server)로써의 VM의 네트워크 I/O 성능 분석을 다룬다. 해당 성능 분석은 엔드 유저(end-user)들과 캐시서버 간 동영상 스트리밍(streaming)을 통하여 이루어졌으며 해당 캐시 서버의 네트워크 I/O 성능에 영향을 주는 다양한 경우에 대하여 진행되었다. 본 논문에서의 성능 분석은 클라우드 CDN 환경에서의 데이터센터(datacenter) 선택 및 요청 라우팅(routing) 등에 적용될 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.163-165
• /
• 2014

클라우드 컴퓨팅 기술의 발전 및 모바일 디바이스의 확산으로 데이터센터의 수요가 폭발적으로 증가하고 있고, 데이터 센터내 트래픽 또한 급증할 것으로 예측된다. 따라서 데이터센터 내에 서버용 확장 할 수 있고, 고장방지에 뛰어난 서버센트릭 네트워크 구조가 수많은 서버를 효율적으로 관리할 수 있는 대안으로 제시되었다. 본 논문에서는 서버센트릭 데이터센터에서 서버 배치를 통한 트래픽의 변화에 대해 분석하고 효율적으로 트래픽을 감소시키기 위한 휴리스틱(Heuristic) 접근방법을 제안한다.