PriDyn: Enabling Differentiated I/O Services in Cloud Using Dynamic Priorities

Virtualization is one of the key enabling technologies for Cloud computing. Although it facilitates improved utilization of resources, virtualization can lead to performance degradation due to the sharing of physical resources like CPU, memory, network interfaces, disk controllers, etc. Multi-tenancy can cause highly unpredictable performance for concurrent I/O applications running inside virtual machines that share local disk storage in Cloud. Disk I/O requests in a typical Cloud setup may have varied requirements in terms of latency and throughput as they arise from a range of heterogeneous applications having diverse performance goals. This necessitates providing differential performance services to different I/O applications. In this paper, we present PriDyn, a novel scheduling framework which is designed to consider I/O performance metrics of applications such as acceptable latency and convert them to an appropriate priority value for disk access based on the current system state. This framework aims to provide differentiated I/O service to various applications and ensures predictable performance for critical applications in multi-tenant Cloud environment. We demonstrate through experimental validations on real world I/O traces that this framework achieves appreciable enhancements in I/O performance, indicating that this approach is a promising step towards enabling QoS guarantees on Cloud storage.

Resource usage monitoring for KVM based virtual machines

Realization of cloud computing has been possible due to availability of virtualization technologies on commodity platforms. Measuring resource usage on the virtualized servers is difficult because of the fact that the performance counters used for resource accounting are not virtualized. Hence, many of the prevalent virtualization technologies like Xen, VMware, KVM etc., use host specific CPU usage monitoring, which is coarse grained. In this paper, we present a performance monitoring tool for KVM based virtualized machines, which measures the CPU overhead incurred by the hypervisor on behalf of the virtual machine along-with the CPU usage of virtual machine itself. This fine-grained resource usage information, provided by the above tool, can be used for diverse situations like resource provisioning to support performance associated QoS requirements, identification of bottlenecks during VM placements, resource profiling of applications in cloud environments, etc. We demonstrate a use case of this tool by measuring the performance of web-servers hosted on a KVM based virtualized server.

Elastic Resources Framework in IaaS, preserving performance SLAs

Elasticity in cloud systems provides the flexibility to acquire and relinquish computing resources on demand. However, in current virtualized systems resource allocation is mostly static. Resources are allocated during VM instantiation and any change in workload leading to significant increase or decrease in resources is handled by VM migration. Hence, cloud users tend to characterize their workloads at a coarse grained level which potentially leads to under-utilized VM resources or under performing application. A more flexible and adaptive resource allocation mechanism would benefit variable workloads, such as those characterized by web servers. In this paper, we present an elastic resources framework for IaaS cloud layer that addresses this need. The framework provisions for application workload forecasting engine, that predicts at run-time the expected demand, which is input to the resource manager to modulate resource allocation based on the predicted demand. Based on the prediction errors, resources can be over-allocated or under-allocated as compared to the actual demand made by the application. Over-allocation leads to unused resources and under allocation could cause under performance. To strike a good trade-off between over-allocation and under-performance we derive an excess cost model. In this model excess resources allocated are captured as over-allocation cost and under-allocation is captured as a penalty cost for violating application service level agreement (SLA). Confidence interval for predicted workload is used to minimize this excess cost with minimal effect on SLA violations. An example case-study for an academic institute web server workload is presented. Using the confidence interval to minimize excess cost, we achieve significant reduction in resource allocation requirement while restricting application SLA violations to below 2-3%.

Performance analysis of the random early detection algorithm

In this article we consider a finite queue with its arrivals controlled by the random early detection algorithm. This is one of the most prominent congestion avoidance schemes in the Internet routers. The aggregate arrival stream from the population of transmission control protocol sources is locally considered stationary renewal or Markov modulated Poisson process with general packet length distribution. We study the exact dynamics of this queue and provide the stability and the rates of convergence to the stationary distribution and obtain the packet loss probability and the waiting time distribution. Then we extend these results to a two traffic class case with each arrival stream renewal. However, computing the performance indices for this system becomes computationally prohibitive. Thus, in the latter half of the article, we approximate the dynamics of the average queue length process asymptotically via an ordinary differential equation. We estimate the error term via a diffusion approximation. We use these results to obtain approximate transient and stationary performance of the system. Finally, we provide some computational examples to show the accuracy of these approximations.

A survey of cloud storage facilities

There are many applications such as software for processing customer records in telecom, patient records in hospitals, email processing software accessing a single email in a mailbox etc. which require to access a single record in a database consisting of millions of records. A basic feature of these applications is that they need to access data sets which are very large but simple. Cloud computing provides computing requirements for these kinds of new generation of applications involving very large data sets which cannot possibly be handled efficiently using traditional computing infrastructure. In this paper, we describe storage services provided by three well-known cloud service providers and give a comparison of their features with a view to characterize storage requirements of very large data sets as examples and we hope that it would act as a catalyst for the design of storage services for very large data set requirements in future. We also give a brief overview of other kinds of storage that have come up in the recent past for cloud computing.

Low-Cost Cloud-Based Design of Smart Rural Energy Device in Microgrid: Perspective India An Energy-On-Demand Service for Rural India

In this paper we present a combination of technologies to provide an Energy-on-Demand (EoD) service to enable low cost innovation suitable for microgrid networks. The system is designed around the low cost and simple Rural Energy Device (RED) Box which in combination with Short Message Service (SMS) communication methodology serves as an elementary proxy for Smart meters which are typically used in urban settings. Further, customer behavior and familiarity in using such devices based on mobile experience has been incorporated into the design philosophy. Customers are incentivized to interact with the system thus providing valuable behavioral and usage data to the Utility Service Provider (USP). Data that is collected over time can be used by the USP for analytics envisioned by using remote computing services known as cloud computing service. Cloud computing allows for a sharing of computational resources at the virtual level across several networks. The customer-system interaction is facilitated by a third party Telecom Service provider (TSP). The approximate cost of the RED Box is envisaged to be under USD 10 on production scale.

Finite volume TVD formulation of lattice Boltzmann simulation on unstructured mesh

A numerical scheme is presented for accurate simulation of fluid flow using the lattice Boltzmann equation (LBE) on unstructured mesh. A finite volume approach is adopted to discretize the LBE on a cell-centered, arbitrary shaped, triangular tessellation. The formulation includes a formal, second order discretization using a Total Variation Diminishing (TVD) scheme for the terms representing advection of the distribution function in physical space, due to microscopic particle motion. The advantage of the LBE approach is exploited by implementing the scheme in a new computer code to run on a parallel computing system. Performance of the new formulation is systematically investigated by simulating four benchmark flows of increasing complexity, namely (1) flow in a plane channel, (2) unsteady Couette flow, (3) flow caused by a moving lid over a 2D square cavity and (4) flow over a circular cylinder. For each of these flows, the present scheme is validated with the results from Navier-Stokes computations as well as lattice Boltzmann simulations on regular mesh. It is shown that the scheme is robust and accurate for the different test problems studied.

Moore meets maxwell

Moore's Law has driven the semiconductor revolution enabling over four decades of scaling in frequency, size, complexity, and power. However, the limits of physics are preventing further scaling of speed, forcing a paradigm shift towards multicore computing and parallelization. In effect, the system is taking over the role that the single CPU was playing: high-speed signals running through chips but also packages and boards connect ever more complex systems. High-speed signals making their way through the entire system cause new challenges in the design of computing hardware. Inductance, phase shifts and velocity of light effects, material resonances, and wave behavior become not only prevalent but need to be calculated accurately and rapidly to enable short design cycle times. In essence, to continue scaling with Moore's Law requires the incorporation of Maxwell's equations in the design process. Incorporating Maxwell's equations into the design flow is only possible through the combined power that new algorithms, parallelization and high-speed computing provide. At the same time, incorporation of Maxwell-based models into circuit and system-level simulation presents a massive accuracy, passivity, and scalability challenge. In this tutorial, we navigate through the often confusing terminology and concepts behind field solvers, show how advances in field solvers enable integration into EDA flows, present novel methods for model generation and passivity assurance in large systems, and demonstrate the power of cloud computing in enabling the next generation of scalable Maxwell solvers and the next generation of Moore's Law scaling of systems. We intend to show the truly symbiotic growing relationship between Maxwell and Moore!

An optimal weighted-average congestion based pricing scheme for enhanced QoS

Pricing is an effective tool to control congestion and achieve quality of service (QoS) provisioning for multiple differentiated levels of service. In this paper, we consider the problem of pricing for congestion control in the case of a network of nodes under a single service class and multiple queues, and present a multi-layered pricing scheme. We propose an algorithm for finding the optimal state dependent price levels for individual queues, at each node. The pricing policy used depends on a weighted average queue length at each node. This helps in reducing frequent price variations and is in the spirit of the random early detection (RED) mechanism used in TCP/IP networks. We observe in our numerical results a considerable improvement in performance using our scheme over that of a recently proposed related scheme in terms of both throughput and delay performance. In particular, our approach exhibits a throughput improvement in the range of 34 to 69 percent in all cases studied (over all routes) over the above scheme.

An optimal weighted-average congestion based pricing scheme for enhanced QoS, , LNCS 4882, 2007

Pricing is an effective tool to control congestion and achieve quality of service (QoS) provisioning for multiple differentiated levels of service. In this paper, we consider the problem of pricing for congestion control in the case of a network of nodes under a single service class and multiple queues, and present a multi-layered pricing scheme. We propose an algorithm for finding the optimal state dependent price levels for individual queues, at each node. The pricing policy used depends on a weighted average queue length at each node. This helps in reducing frequent price variations and is in the spirit of the random early detection (RED) mechanism used in TCP/IP networks. We observe in our numerical results a considerable improvement in performance using our scheme over that of a recently proposed related scheme in terms of both throughput and delay performance. In particular, our approach exhibits a throughput improvement in the range of 34 to 69 percent in all cases studied (over all routes) over the above scheme.

Resource Usage Monitoring in Clouds

Monitoring of infrastructural resources in clouds plays a crucial role in providing application guarantees like performance, availability, and security. Monitoring is crucial from two perspectives - the cloud-user and the service provider. The cloud user’s interest is in doing an analysis to arrive at appropriate Service-level agreement (SLA) demands and the cloud provider’s interest is to assess if the demand can be met. To support this, a monitoring framework is necessary particularly since cloud hosts are subject to varying load conditions. To illustrate the importance of such a framework, we choose the example of performance being the Quality of Service (QoS) requirement and show how inappropriate provisioning of resources may lead to unexpected performance bottlenecks. We evaluate existing monitoring frameworks to bring out the motivation for building much more powerful monitoring frameworks. We then propose a distributed monitoring framework, which enables fine grained monitoring for applications and demonstrate with a prototype system implementation for typical use cases.

QoS Performance Analysis of Routing Protocols in Vehicular Ad-hoc Networks

Vehicular Ad-hoc Networks (VANET), is a type of wireless ad-hoc network that aims to provide communication among vehicles. A key characteristic of VANETs is the very high mobility of nodes that result in a frequently changing topology along with the frequent breakage and linkage of the paths among the nodes involved. These characteristics make the Quality of Service (QoS) requirements in VANET a challenging issue. In this paper we characterize the performance available to applications in infrastructureless VANETs in terms of path holding time, path breakage probability and per session throughput as a function of various vehicle densities on road, data traffic rate and number of connections formed among vehicles by making use of table-driven and on-demand routing algorithms. Several QoS constraints in the applications of infrastructureless VANETs are observed in the results obtained.

Performance of New Dynamic Benefit-Weighted Scheduling Scheme in DiffServ Networks

In this paper, we design a new dynamic packet scheduling scheme suitable for differentiated service (DiffServ) network. Designed dynamic benefit weighted scheduling (DBWS) uses a dynamic weighted computation scheme loosely based on weighted round robin (WRR) policy. It predicts the weight required by expedited forwarding (EF) service for the current time slot (t) based on two criteria; (i) previous weight allocated to it at time (t-1), and (ii) the average increase in the queue length of EF buffer. This prediction provides smooth bandwidth allocation to all the services by avoiding overbooking of resources for EF service and still providing guaranteed services for it. The performance is analyzed for various scenarios at high, medium and low traffic conditions. The results show that packet loss is minimized, end to end delay is minimized and jitter is reduced and therefore meet quality of service (QoS) requirement of a network.