Direct-Virtio: A New Direct Virtualized I/O Framework for NVMe SSDs

Virtualization is a core technology for cloud computing, server consolidation and multi-platform support. However, there is a concern regarding performance degradation due to the duplicated I/O stacks virtualization environments. In this paper, we propose a new I/O framework, we refer to it as Direct-Virtio, that manipulates storage directly, which makes it feasible to avoid the duplicated overhead. In addition, we devise two novel mechanisms, called vectored I/O and adaptive polling, to process multiple I/O requests collectively and to check I/O completion efficiently. Real implementation-based evaluation shows that our proposal can enhance performance for both micro and macro benchmarks.

NetAP: Adaptive Polling Technique for Network Packet Processing in Virtualized Environments

In cloud systems, computing resources, such as the CPU, memory, network, and storage devices, are virtualized and shared by multiple users. In recent decades, methods to virtualize these resources efficiently have been intensively studied. Nevertheless, the current virtualization techniques cannot achieve effective I/O virtualization when packets are transferred between a virtual machine and a host system. For example, VirtIO, which is a network device driver for KVM-based virtualization, adopts an interrupt-based packet-delivery mechanism, and incurs frequent switch overheads between the virtual machine and the host system. Therefore, VirtIO wastes valuable CPU resources and decreases network performance. To address this limitation, this paper proposes an adaptive polling-based network I/O processing technique, called NetAP, for virtualized environments. NetAP processes network requests via a periodical polling-based mechanism. For this purpose, NetAP adopts the golden-section search algorithm to determine the near-optimal polling interval for various workloads with different characteristics. We implement NetAP in a Linux kernel and evaluated it with up to six virtual machines. The evaluation results show that NetAP can improve the network performance of virtual machines by up to 31.16%, while only using 32.92% of the host CPU time used by VirtIO for packet processing.

Adaptive Polling Medium Access Control Protocol for Optic Wireless Networks

The emergence of optical wireless networks (OWNs) is a potential solution to the quest for the increasing bandwidth demand. Existing bandwidth assignment strategies are not suitable for OWNs, considering factors such as differences between the physical properties of radio networks and OWNs. In order to eliminate collision, minimize delay and enhance system utilization and fairness, we propose the non-contention bandwidth assignment protocol called adaptive polling medium access control (APMAC) protocol for OWNs. The APMAC protocol involves association, data transmission and dissociation phases. Moreover, the APMAC protocol exploits features of the IEEE 802.15.7 visible light communication (VLC) standard. While assigning bandwidth to the visible light nodes (VLNs), the visible light access point (VLAP) establishes a polling table that contains the identity, buffer size and round-trip time of each VLN that issued bandwidth request. The contents of the polling table enable the computation of the maximum transmission unit and time-slot for each VLN that requests bandwidth assignment. In order to achieve convincing results, we simulate the protocol under varying network sizes ranging from 1 to 10 VLNs per access point, then we compare the results against the medium transparent medium access control (MT–MAC) protocol that is a non-contention MAC protocol. We demonstrate numerical results of our study considering average waiting time, packet collision, system utilization and fairness. Numerical results reveal that the APMAC protocol outperforms the MT–MAC protocol.

Adaptive Scheduling Mechanism with Variable Bit Rate Traffic in EPON

In Ethernet Passive Optical Network, with Load Adaptive Polling Sequence Arrangement (LASA) method, the Optical Line Terminal assigns delayed polling sequence arrangement for a set of Optical Network Units (ONUs) over the cycles. This arrangement has resulted in identical cycle time with Constant Bit Rate traffic. In addition, the LASA through its arrangement provides sleep mode to different set of ONUs over the cycles and provides maximum sleep time for ONUs. With these advantages of LASA and keeping the scenario with different cycle times for the ONUs, in this work, the Variable Bit Rate (VBR) based LASA method is analyzed. The variation in the cycle times has resulted in two cases and in each case by varying the maximum (Mxi) and the minimum (Mni) idle times, a maximum of 40.6% reduction in power consumption is observed in LASA with VBR scheduling method than traditional one.