Research Interests:
Research Interests:
Research Interests:
In this paper, we propose a mechanism to eliminate the per- formance anomaly of IEEE 802.11b. Performance anomaly happens when nodes that have difierent transmission rates are in the same wireless cell. All the nodes in the cell might... more
In this paper, we propose a mechanism to eliminate the per- formance anomaly of IEEE 802.11b. Performance anomaly happens when nodes that have difierent transmission rates are in the same wireless cell. All the nodes in the cell might experience the same throughput even though their transmission rates are difierent because DCF of WLAN provides equal probability of channel access, but it does not guarantee the equal utilization of the wireless channel among the nodes. To reduce such a performance anomaly, we adjust the frame size proportionally depending on the bit rate. Additionally, our scheme eliminates the per- formance anomaly in multi-hop case. Simulation study shows that our scheme achieves an improvement in the aggregate throughput and the fairness.
Research Interests:
ABSTRACT Enterprise servers require customized solid-state drives (SSDs) to satisfy their specialized I/O performance and reliability requirements. For effective use of SSDs for enterprise purposes, SSDs must be designed considering... more
ABSTRACT Enterprise servers require customized solid-state drives (SSDs) to satisfy their specialized I/O performance and reliability requirements. For effective use of SSDs for enterprise purposes, SSDs must be designed considering requirements such as those related to performance, lifetime, and cost constraints. However, SSDs have numerous hardware and software design options, such as flash memory types and block allocation methods, which have not been well analyzed yet, but on which the SSD performance depends. Furthermore, there is no methodology for determining the optimal design for a particular I/O workload. This paper proposes SSD-Tailor, a customization tool for SSDs. SSD-Tailor determines a near-optimal set of design options for a given workload. SSD designers can use SSD-Tailor to customize SSDs in the early design stage to meet the customer requirements. We evaluate SSD-Tailor with nine I/O workload traces collected from real-world enterprise servers. We observe that SSD-Tailor finds near-optimal SSD designs for these workloads by exploring only about 1% of the entire set of design candidates. We also show that the near-optimal designs increase the average I/O operations per second by up to 17% and decrease the average response time by up to 163% as compared to an SSD with a general design.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Computer Science, Mobile Ad Hoc Networks, Computational Modeling, Computer Networks, Routing protocols, and 13 moreMobile Computing, Mobile Ad Hoc Network, Ad Hoc Networks, Ad hoc network, Routing Protocol, Tcp, Packet Loss, Network Topology, Wireless Application Protocol, Telephony, Transport Protocols, Wireless Ad Hoc Network, and Retransmission
Research Interests:
Research Interests: Simulation Study and ICN
Research Interests:
Research Interests:
Research Interests:
ABSTRACT This paper investigates the feasibility of real-time scheduling with mobile hypervisor, Xen-ARM. Particularly for mobile virtual machines, real-time support is in high demand. However, it is difficult to guarantee real-time... more
ABSTRACT This paper investigates the feasibility of real-time scheduling with mobile hypervisor, Xen-ARM. Particularly for mobile virtual machines, real-time support is in high demand. However, it is difficult to guarantee real-time scheduling with virtual machines because inter-VM and intra-VM schedulability have to be determined in multi-OS environments. To address the schedulability, first, this paper presents a definition of a real-time virtual machine. Second, this paper analyzes intra-VM schedulability, taking quantization overhead into account. Quantization overhead comes from tick-based scheduling of Xen-ARM, which requires integer presentation of scheduling period and execution slice. Third, to minimize quantization overhead, this paper provides a new algorithm, called SH-quantization that provides accurate and efficient parameterization of a real-time virtual machine. Fourth, this paper presents an inter-VM schedulability test for incorporating multiple real-time virtual machines. To evaluate the approach, we implement the SH-quantization algorithm in Xen-ARM and paravirtualize a real-time OS, called xeno- (mu ) C/OS-II. We ran extensive experiments with various configurations of real-time tasks on a real hardware platform in order to characterize the scheduling behavior of real-time virtual machine with quantization. The results show that quantization overhead consumes additional CPU bandwidth up to 90% and the proposed algorithm guarantees intra/inter-VM schedulability with minimal CPU bandwidth.
Research Interests:
ABSTRACT Proposed is a new I/O scheduling for SSD, proportional work-conserving. The proposed scheduling algorithm provides proportional fairness among tasks. To provide proportional fairness, proportional work-conserving differentiates... more
ABSTRACT Proposed is a new I/O scheduling for SSD, proportional work-conserving. The proposed scheduling algorithm provides proportional fairness among tasks. To provide proportional fairness, proportional work-conserving differentiates probability to fully utilise the task's quantum, which is controlled by adjusting opportunistic waiting time. Its proportional fairness is formally proveds and its validity through numerical evaluation and experimental results from Linux implementation are presented.
Research Interests:
Research Interests:
Multicast is a multiuser communication scheme. Till now, multicast has been studied to handle one multicast group at a time. However new applications such as online games need to handle multiple groups simultaneously. This paper proposes... more
Multicast is a multiuser communication scheme. Till now, multicast has been studied to handle one multicast group at a time. However new applications such as online games need to handle multiple groups simultaneously. This paper proposes BO-multicast; Boolean operation multicast. Through NS2 simulation, we show that Boolean operations can improve the performance by 610 percent in delay and 210 percent in routing table size
Research Interests:
Recently, system virtualization has been applied to consumer electronics such as smart mobile phones. Although multi-core processors have become a viable solution for complex applications on consumer electronics, how to utilize the... more
Recently, system virtualization has been applied to consumer electronics such as smart mobile phones. Although multi-core processors have become a viable solution for complex applications on consumer electronics, how to utilize the multi-core resources in virtualization layer is not researched sufficiently. In this paper, we present the hypervisor design and implementation for multi-core CE devices; the hypervisor targets to improve network performance by fully utilizing the multi-core processor.
Research Interests:
This paper addresses the I/O latency issue within Xen-ARM. Although Xen-ARM's split driver presents reliable driver isolation, it requires additional inter-VM scheduling. Consequently, the credit scheduler within... more
This paper addresses the I/O latency issue within Xen-ARM. Although Xen-ARM's split driver presents reliable driver isolation, it requires additional inter-VM scheduling. Consequently, the credit scheduler within Xen-ARM results in unsatisfactory I/O latency for real-time guest OS. This paper analyzes the I/O latency in Xen-ARM's interrupt path, and proposes a new scheduler to bound I/O latency. Our scheduler dynamically assigns