Balaji Viswanathan

SmartScale: Automatic Application Scaling in Enterprise Clouds

Enterprise clouds today support an on demand resource allocation model and can provide resources requested by applications in a near online manner using virtual machine resizing or cloning. However, in order to take advantage of an on demand resource model, enterprise applications need to be automatically scaled in a way that makes the most efficient use of resources. In this work, we present the SmartScale automated scaling framework. SmartScale uses a combination of vertical (adding more resources to existing VM instances) and horizontal (adding more VM instances) scaling to ensure that the application is scaled in a manner that optimizes both resource usage and the reconfiguration cost incurred due to scaling. The SmartScale methodology is proactive and ensures that the application converges quickly to the desired scaling level even when the workload intensity changes significantly. We evaluate SmartScale using real production traces on Olio, an emerging cloud benchmark, running on a kvm-based cloud testbed. We present both theoretical and experimental evidence that comprehensively establish the effectiveness of SmartScale.

DECO: data replication and execution CO-scheduling for utility grids

Grids and peer-to-peer (P2P) networks have emerged as popular platforms for the next generation parallel and distributed computing. In these environments, resources are geographically distributed, managed and owned by various organizations with different policies, and interconnected by wide-area networks or the Internet. This introduces a number of resource management and application scheduling challenges in the domain of security, resource and policy heterogeneity, fault tolerance, and dynamic resource conditions. In these dynamic distributed computing environments, it is hard and challenging to carry out resource management design studies in a repeatable and controlled manner as resources and users are autonomous and distributed across multiple organizations with their own policies. Therefore, simulations have emerged as the most feasible technique for analyzing policies for resource allocation. This paper presents emerging trends in distributed computing and their promises for revolutionizing the computing field, and identifies distinct characteristics and challenges in building them. We motivate opportunities for modeling and simulation communities and present our discrete-event grid simulation toolkit, called GridSim, used by researchers world-wide for investigating the design of utility-oriented computing systems such as Data Centers and Grids. We present various case studies on the use of GridSim in modeling and simulation of Business Grids, parallel applications scheduling, workflow scheduling, and service pricing and revenue management.

CloudMap: Workload-aware placement in private heterogeneous clouds

Cloud computing has emerged as an exciting hosting paradigm to drive up server utilization and reduce data center operational costs. Even though clouds present a single unified homogeneous resource pool view to end users, the underlying server landscape may differ in terms of functionality and reconfiguration capabilities (e.g., support for shared processors, live migration). In a private cloud setting where information on the resources as well as workloads are available, the placement of applications on clouds can leverage it to achieve better consolidation with performance guarantees. In this work, we present the design and implementation of CloudMap, a provisioning system for private clouds. Given an applications resource usage patterns, we match it with a server cluster with the appropriate level of reconfiguration capability. In this cluster, we place the application on a server that has existing workloads with complementary resource usage profile. CloudMap is implemented using a hybrid architecture with a global server cluster selection module and local cluster-specific server selection modules. Using production traces from live data centers, we demonstrate the effectiveness of CloudMap over existing placement methodologies.

Design and Implementation of a Fault Tolerant Job Flow Manager Using Job Flow Patterns and Recovery Policies

Currently, many grid applications are developed as job flows that are composed of multiple jobs. The execution of job flows requires the support of a job flow manager and a job scheduler. Due to the long running nature of job flows, the support for fault tolerance and recovery policies is especially important. This support is inherently complicated due to the sequencing and dependency of jobs within a flow, and the required coordination between workflow engines and job schedulers. In this paper, we describe the design and implementation of a job flow manager that supports fault tolerance. First, we identify and label job flow patterns within a job flow during deployment time. Next, at runtime, we introduce a proxy that intercepts and resolves faults using job flow patterns and their corresponding fault-recovery policies. Our design has the advantages of separation of the job flow and fault handling logic, requiring no manipulation at the modeling time, and providing flexibility with respect to fault resolution at runtime. We validate our design with a prototypical implementation based on the ActiveBPEL workflow engine and GridWay Meta-scheduler, and Montage application as the case study.

QoS-GRAF: A Framework for QoS based Grid Resource Allocation with Failure provisioning

In this paper, it describes the QoS-GRAF, a framework for providing revenue maximization in a utility computing grid where jobs have multiple resource dependencies and differentiated QoS pricing. To solve the revenue maximization problem the linear relaxation based algorithms, MRPA and MLBA, that achieve performance within 1-5% of the optimal solution and significantly outperform alternative approaches are used. Both show better revenue earnings across small, medium and large jobs, with efficient resource utilization. As a part ongoing work, the backup algorithms for multiple failures is developed. Scheduling algorithms are incorporated to produce maximum profitable schedule considering job deadlines

A distributed job scheduling and flow management system

Grid computing, as a specific model of distributed systems, has sparked recent interest in managing job execution among distributed resource domains. Introduction of the meta-scheduler is a key feature in grid evolution, and the next step is to achieve collaborative interactions between meta-schedulers within and external to organizational boundaries to achieve scalability, balanced resource utilization, and location transparency to job submitters. This paper details a distributed system design that consists of a collaborative meta-scheduling framework, and an expanded resource model with schedulers and data as resources. With this framework, we also explore job scheduling and data management issues, and investigate job flow and meta-scheduling interactions for new applications that require job execution beyond simple sequential and conditional control.

Rapid adjustment and adoption to MIaaS clouds

Emerging Managed Infrastructure as a Service (MIaaS) clouds allow enterprises to outsource their IT infrastructure as well as their IT management needs. One of the core tenets of a MIaaS cloud is a standardized service delivery model, allowing the cloud provider to provide infrastructure management services at a lower cost. As opposed to pure IaaS clouds where arbitrary customer virtual machines can be migrated to the cloud, migration to MIaaS clouds require the customer servers to be adapted in a way such that the cloud steady state management stack can manage these virtual machines using the standardized delivery model. In this work, we address the problem of migrating customer workloads to a standardized MIaaS cloud. We present the design and implementation of Rapid Adjustment Engine (RAE). RAE captures the adjustment process across arbitrary customer servers with high diversity in a unified rule framework. It uses rapid image adjustment to reduce the end-to-end migration time and a flexible orchestrator framework to integrate diverse functionalities and associated tools in a single migration process. Our experimental evaluation establishes the ability of RAE to enable rapid, reliable and reduced cost migration to MIaaS clouds.

Building Scalable Cloud-Based Communication and Collaboration Services for SMB Enterprises

Cloud-based solutions provide an effective platform for businesses to cut cost, increase scalability, and grow their service offerings. While the viability of this model has been demonstrated by multiple IT services, there has been little work around exploring a similar approach for communication services. In particular, the use of cloud as a platform for voice, data, and video integrated seamlessly, can be an effective solution for delivering next-generation converged services. Further, a cost-effective, self-scaling, cloud-based solution can be a particularly interesting proposition for SMB enterprises that wish to benefit from such communication services. In this paper, we investigate challenges involved in building such a cloud infrastructure and propose virtualization-based approaches to address some of these challenges.

ERMIS: designing, developing, and delivering a remote managed infrastructure services solution

Remote management of IT (information technology) infrastructures, as a service, has received significant attention due to the numerous benefits it offers. In this paper, we discuss our work on taking a previously India-only remote IT infrastructure management service offering to a global audience. We first provide an overview of this IBM offering, called Express™ Remote Managed Infrastructure Services (ERMIS), and then focus on two specific aspects, service catalog and problem determination and resolution (PDR). In service catalog-based remote management, customers browse the catalog and place orders as they would using an online store. Our service catalog entries contain workflows to automate the deployment of requested applications or the configuration change of customer resources. High-level customer requirements are translated into capacity sizing and configuration parameters, which are then used to provision the final solution by making use of ITIL® (Information Technology Infrastructure Library) release and configuration management processes. PDR involves detecting, locating, and fixing anomalies. Probe-based techniques are used for targeting the problem location, while knowledge management assists with problem analysis, diagnosis, and classification. ERMIS architectural decisions have been driven by emerging-business requirements related to small and mediumsized businesses.

Data-WISE: Efficient management of data-intensive workflows in scheduled grid environments

The execution of data-intensive workflow applications in scientific and enterprise grids has gained popularity in recent times. Such applications process large and dynamic data sets, and often present scope for optimized data handling that can be exploited for performance. Traditionally, core grid middleware technologies of scheduling and orchestration, have treated data management as a background activity - decoupled from job management and handled at the storage and/or network protocol level. We believe that an important requirement for building data-aware grid technologies lies in managing data flows at the application level, in conjunction with their computation counterparts. To this end, we present Data-WISE, an end-to-end framework for management of data-intensive workflows as first class citizens, that addresses aspects of data flow orchestration, co-scheduling and runtime management. The optimizations are focused on exploiting application structure for use of data parallelism, replication, and runtime adaptations. We implement data-WISE on a real testbed and demonstrate significant improvements in terms of application response time, resource utilization, and adaptability to varying resource conditions. The proposed framework acts as an important step towards making distributed execution of data-intensive workflows a reality.