The assessment of benchmarks executed on bare-metal and using para-virtualization

A full assessment of para-­virtualization is important, because without knowledge about the various overheads, users can not understand whether using virtualization is a good idea or not. In this paper we are very interested in assessing the overheads of running various benchmarks on bare-­‐metal, as well as on para-­‐virtualization. The idea is to see what the overheads of para-­‐ virtualization are, as well as looking at the overheads of turning on monitoring and logging. The knowledge from assessing various benchmarks on these different systems will help a range of users understand the use of virtualization systems. In this paper we assess the overheads of using Xen, VMware, KVM and Citrix, see Table 1. These different virtualization systems are used extensively by cloud-­‐users. We are using various Netlib1 benchmarks, which have been developed by the University of Tennessee at Knoxville (UTK), and Oak Ridge National Laboratory (ORNL). In order to assess these virtualization systems, we run the benchmarks on bare-­‐metal, then on the para-­‐virtualization, and finally we turn on monitoring and logging. The later is important as users are interested in Service Level Agreements (SLAs) used by the Cloud providers, and the use of logging is a means of assessing the services bought and used from commercial providers. In this paper we assess the virtualization systems on three different systems. We use the Thamesblue supercomputer, the Hactar cluster and IBM JS20 blade server (see Table 2), which are all servers available at the University of Reading. A functional virtualization system is multi-­‐layered and is driven by the privileged components. Virtualization systems can host multiple guest operating systems, which run on its own domain, and the system schedules virtual CPUs and memory within each Virtual Machines (VM) to make the best use of the available resources. The guest-­‐operating system schedules each application accordingly. You can deploy virtualization as full virtualization or para-­‐virtualization. Full virtualization provides a total abstraction of the underlying physical system and creates a new virtual system, where the guest operating systems can run. No modifications are needed in the guest OS or application, e.g. the guest OS or application is not aware of the virtualized environment and runs normally. Para-­‐virualization requires user modification of the guest operating systems, which runs on the virtual machines, e.g. these guest operating systems are aware that they are running on a virtual machine, and provide near-­‐native performance. You can deploy both para-­‐virtualization and full virtualization across various virtualized systems. Para-­‐virtualization is an OS-­‐assisted virtualization; where some modifications are made in the guest operating system to enable better performance. In this kind of virtualization, the guest operating system is aware of the fact that it is running on the virtualized hardware and not on the bare hardware. In para-­‐virtualization, the device drivers in the guest operating system coordinate the device drivers of host operating system and reduce the performance overheads. The use of para-­‐virtualization [0] is intended to avoid the bottleneck associated with slow hardware interrupts that exist when full virtualization is employed. It has revealed [0] that para-­‐ virtualization does not impose significant performance overhead in high performance computing, and this in turn this has implications for the use of cloud computing for hosting HPC applications. The “apparent” improvement in virtualization has led us to formulate the hypothesis that certain classes of HPC applications should be able to execute in a cloud environment, with minimal performance degradation. In order to support this hypothesis, first it is necessary to define exactly what is meant by a “class” of application, and secondly it will be necessary to observe application performance, both within a virtual machine and when executing on bare hardware. A further potential complication is associated with the need for Cloud service providers to support Service Level Agreements (SLA), so that system utilisation can be audited.

Comparison of the antidiabetic activity of Berberis lyceum root extract and berberine in alloxan-induced diabetic rats

Berberine has been shown to have hypoglycaemic activity in several in vitro and in vivo models, although the mechanism of action is not fully known. Berberis lyceum Royle root produces high concentrations of berberine, and in traditional medicine, the whole extract of this plant is used widely to treat diabetes. The antidiabetic activity of the ethanol root extract of Berberis lyceum was compared with pure berberine in normal and alloxan-diabetic rats using similar doses of each. The concentration of berberine in the extract was determined to be 80% dry weight with only trace amounts of other alkaloids present. The purpose of the study was to investigate the effects of berberine and a whole extract of Berberis lyceum on blood glucose and other parameters associated with diabetes, to compare the effects of the crude extract with those of pure berberine and thus validate its use as a therapeutic agent, and finally to identify any contribution of the other components of the extract to these effects. Oral administration of 50 mg/kg of Berberis extract and berberine to normal and experimental diabetic rats produced a significant (p < 0.05) reduction in blood glucose levels from days 3-7 days of treatment. Significant effects were also observed on the glucose tolerance, glycosylated haemoglobin, serum lipid profiles and body weight of experimental animals. Berberis extract and berberine demonstrated similar effects on all parameters measured, and although the extract was comparable in efficacy to berberine, it did not produce any effects additional to those shown by pure berberine. The results support the use of the extract in traditional medicine, and demonstrate that apart from being a highly cost-effective means of treating with berberine, the total extract does not appear to confer any additional benefits or disadvantages compared with the pure compound. Copyright (c) 2008 John Wiley & Sons, Ltd.

Impact of transmission errors in enhanced relay-enabled distributed coordination function

This paper analyzes the performance of Enhanced relay-enabled Distributed Coordination Function (ErDCF) for wireless ad hoc networks under transmission errors. The idea of ErDCF is to use high data rate nodes to work as relays for the low data rate nodes. ErDCF achieves higher throughput and reduces energy consumption compared to IEEE 802.11 Distributed Coordination Function (DCF) in an ideal channel environment. However, there is a possibility that this expected gain may decrease in the presence of transmission errors. In this work, we modify the saturation throughput model of ErDCF to accurately reflect the impact of transmission errors under different rate combinations. It turns out that the throughput gain of ErDCF can still be maintained under reasonable link quality and distance.

Performance evaluation of enhanced relay-enabled distributed coordination function

In this paper we evaluate the performance of our earlier proposed enhanced relay-enabled distributed coordination function (ErDCF) for wireless ad hoc networks. The idea of ErDCF is to use high data rate nodes to work as relays for the low data rate nodes. ErDCF achieves higher throughput and reduced energy consumption compared to IEEE 802.11 distributed coordination function (DCF). This is a result of. 1) using relay which helps to increase the throughput and lower overall blocking time of nodes due to faster dual-hop transmission, 2) using dynamic preamble (i.e. using short preamble for the relay transmission) which further increases the throughput and lower overall blocking time and also by 3) reducing unnecessary overhearing (by other nodes not involved in transmission). We evaluate the throughput and energy performance of the ErDCF with different rate combinations. ErDCF (11,11) (ie. R1=R2=11 Mbps) yields a throughput improvement of 92.9% (at the packet length of 1000 bytes) and an energy saving of 72.2% at 50 nodes.

An enhanced relay-enabled medium access control protocol for wireless ad hoc networks

In this paper we propose an enhanced relay-enabled distributed coordination function (rDCF) for wireless ad hoc networks. The idea of rDCF is to use high data rate nodes to work as relays for the low data rate nodes. The relay helps to increase the throughput and lower overall blocking time of nodes due to faster dual-hop transmission. rDCF achieves higher throughput over IEEE 802.11 distributed coordination function (DCF). The protocol is further enhanced for higher throughput and reduced energy. These enhancements result from the use of a dynamic preamble (i.e. using short preamble for the relay transmission) and also by reducing unnecessary overhearing (by other nodes not involved in transmission). We have modeled the energy consumption of rDCF, showing that rDCF provides an energy efficiency of 21.7% at 50 nodes over 802.11 DCF. Compared with the existing rDCF, the enhanced rDCF (ErDCF) scheme proposed in this paper yields a throughput improvement of 16.54% (at the packet length of 1000 bytes) and an energy saving of 53% at 50 nodes.

Modelling energy consumption of relay-enabled MAC protocols in ad hoc networks

To enhance the throughput of ad hoc networks, dual-hop relay-enabled transmission schemes have recently been proposed. Since in ad hoc networks throughput is normally related to their energy consumption, it is important to examine the impact of using relay-enabled transmissions on energy consumption. In this paper, we present an analytical energy consumption model for dual-hop relay-enabled medium access control (MAC) protocols. Based on the recently reported relay-enabled distributed coordination function (rDCF), we have shown the efficacy of the proposed analytical model. This is a generalized model and can be used to predict energy consumption in saturated relay-enabled ad hoc networks via energy decomposition. This is helpful in designing MAC protocols for cooperative communications and it is shown that using a relay results not only in a better throughput but also better energy efficiency.

Analysis of enhanced relay-enabled distributed coordination function under transmission errors

This paper analyzes the performance of enhanced relay-enabled distributed coordination function (ErDCF) for wireless ad hoc networks under transmission errors. The idea of ErDCF is to use high data rate nodes to work as relays for the low data rate nodes. ErDCF achieves higher throughput and reduces energy consumption compared to IEEE 802.11 distributed coordination function (DCF) in an ideal channel environment. However, there is a possibility that this expected gain may decrease in the presence of transmission errors. In this work, we modify the saturation throughput model of ErDCF to accurately reflect the impact of transmission errors under different rate combinations. It turns out that the throughput gain of ErDCF can still be maintained under reasonable link quality and distance.

Performance of asynchronous channel assignment scheme in non-uniform and dynamic topology WLANs

Dense deployments of wireless local area networks (WLANs) are fast becoming a permanent feature of all developed cities around the world. While this increases capacity and coverage, the problem of increased interference, which is exacerbated by the limited number of channels available, can severely degrade the performance of WLANs if an effective channel assignment scheme is not employed. In an earlier work, an asynchronous, distributed and dynamic channel assignment scheme has been proposed that (1) is simple to implement, (2) does not require any knowledge of the throughput function, and (3) allows asynchronous channel switching by each access point (AP). In this paper, we present extensive performance evaluation of this scheme when it is deployed in the more practical non-uniform and dynamic topology scenarios. Specifically, we investigate its effectiveness (1) when APs are deployed in a nonuniform fashion resulting in some APs suffering from higher levels of interference than others and (2) when APs are effectively switched `on/off' due to the availability/lack of traffic at different times, which creates a dynamically changing network topology. Simulation results based on actual WLAN topologies show that robust performance gains over other channel assignment schemes can still be achieved even in these realistic scenarios.

An asynchronous channel assignment scheme: performance evaluation

Due to its popularity, dense deployments of wireless local area networks (WLANs) are becoming a common feature of many cities around the world. However, with only a limited number of channels available, the problem of increased interference can severely degrade the performance of WLANs if an effective channel assignment scheme is not employed. In an earlier work, we proposed an improved asynchronous distributed and dynamic channel assignment scheme that (1) is simple to implement, (2) does not require any knowledge of the throughput function, and (3) allows asynchronous channel switching by each access point (AP). In this paper, we present extensive performance evaluation of the proposed scheme in practical scenarios found in densely populated WLAN deployments. Specifically, we investigate the convergence behaviour of the scheme and how its performance gains vary with different number of available channels and in different deployment densities. We also prove that our scheme is guaranteed to converge in a single iteration when the number of channels is greater than the number of neighbouring APs.

Effectiveness of asynchronous channel assignment scheme in heterogeneous WLANs

Due to their popularity, dense deployments of wireless local area networks (WLANs) are becoming a common feature of many cities around the world. However, with only a limited number of channels available, the problem of increased interference can severely degrade the performance of WLANs if an effective channel assignment scheme is not employed. Previous studies on channel assignment in WLANs almost always assume that all access points (AP) employ the same channel assignment scheme which is clearly unrealistic. On the other hand, to the best of our knowledge, the interaction between different channel assignment schemes has also not been studied before. Therefore, in this paper, we investigate the effectiveness of our earlier proposed asynchronous channel assignment scheme in these heterogeneous WLANs scenarios. Simulation results show that our proposed scheme is still able to provide robust performance gains even in these scenarios.

An asynchronous distributed dynamic channel assignment scheme for dense WLANs

Wireless local area networks (WLANs) have changed the way many of us communicate, work, play and live. Due to its popularity, dense deployments are becoming a norm in many cities around the world. However, increased interference and traffic demands can severely limit the aggregate throughput achievable if an effective channel assignment scheme is not used. In this paper, we propose an enhanced asynchronous distributed and dynamic channel assignment scheme that is simple to implement, does not require any knowledge of the throughput function, allows asynchronous channel switching by each access point (AP) and is superior in performance. Simulation results show that our proposed scheme converges much faster than previously reported synchronous schemes, with a reduction in convergence time and channel switches by tip to 73.8% and 30.0% respectively.

An improved distributed dynamic channel assignment scheme for dense WLANs

The popularity of wireless local area networks (WLANs) has resulted in their dense deployment in many cities around the world. The increased interference among different WLANs severely degrades the throughput achievable. This problem has been further exacerbated by the limited number of frequency channels available. An improved distributed and dynamic channel assignment scheme that is simple to implement and does not depend on the knowledge of the throughput function is proposed in this work. It also allows each access point (AP) to asynchronously switch to the new best channel. Simulation results show that our proposed scheme converges much faster than similar previously reported work, with a reduction in convergence time and channel switches as much as 77.3% and 52.3% respectively. When it is employed in dynamic environments, the throughput improves by up to 12.7%.