Norman Lim

A Constraint Programming-Based Resource Management Technique for Processing MapReduce Jobs with SLAs on Clouds

Clouds that are rapidly gaining in popularity require an effective resource manager that can harness the power of the underlying resource pool, and provide resources on demand to its users. This paper focuses on resource management on clouds for workflow requests characterized by Service Level Agreements (SLAs). Specifically, we devise a novel MapReduce constraint programming based resource manager (MRCP-RM) that can effectively perform matchmaking and scheduling of MapReduce jobs, each characterized by an SLA comprising an earliest start time, execution time, and an end-to-end deadline. Using discrete event simulation a performance evaluation of MRCP-RM is conducted for an open system subjected to a stream of job arrivals. The simulation results demonstrate the effectiveness of the resource manager and provide insights into system behaviour and performance.

Engineering resource management middleware for optimizing the performance of clouds processing mapreduce jobs with deadlines

This paper focuses on devising efficient resource management techniques used by the resource management middleware in clouds that handle MapReduce jobs with end-to-end service level agreements (SLAs) comprising an earliest start time, execution time, and a deadline. This research and development work, performed in collaboration with our industrial partner, presents the formulation of the matchmaking and scheduling problem for MapReduce jobs as an optimization problem using: Mixed Integer Linear Programming (MILP) and Constraint Programming (CP) techniques. In addition to the formulations devised, our experience in implementing the MILP and CP models using various open source as well as commercial software packages is described. Furthermore, a performance evaluation of the different approaches used to implement the formulations is conducted using a variety of different workloads.

MRCP-RM: A Technique for Resource Allocation and Scheduling of MapReduce Jobs with Deadlines

Resource allocation and scheduling on clouds are required to harness the power of the underlying resource pool such that the service provider can meet the quality of service requirements of users, which are often captured in service level agreements (SLAs). This paper focuses on resource allocation and scheduling on clouds and clusters that process MapReduce jobs with SLAs. The resource allocation and scheduling problem is modelled as an optimization problem using constraint programming, and a novel MapReduce Constraint Programming based Resource Management algorithm (MRCP-RM) is devised that can effectively process an open stream of MapReduce jobs where each job is characterized by an SLA comprising an earliest start time, a required execution time, and an end-to-end deadline. A detailed performance evaluation of MRCP-RM is conducted for an open system subjected to a stream of job arrivals using both simulation and experimentation on a real system. The experiments on a real system are performed on a Hadoop cluster (deployed on Amazon EC2) that runs our new Hadoop Constraint Programming based Resource Management algorithm (HCP-RM) that incorporates a technique for handling data locality. The results of the performance evaluation demonstrate the effectiveness of MRCP-RM/HCP-RM in generating a schedule that leads to a low proportion of jobs missing their deadlines (P) and also provide insights into system behaviour and performance. In the simulation experiments, it is observed that MRCP-RM achieves on average an 82 percent lower P compared to a technique from the existing literature when processing a synthetic workload from Facebook. Furthermore, in the experiments performed on a Hadoop cluster deployed on Amazon EC2, it is observed that HCP-RM achieved on average a 63 percent lower P compared to an EDF-Scheduler for a wide variety of workload and system parameters experimented with.

Providing Interoperability for Resource Access Using Web Services

This paper focuses on resource virtualization and interoperability required in the context of large distributed environments such as clouds and grids in which shared resources located on multiple sites are accessed by multiple users. A resource is exposed as a Web service. Techniques for handling two types of resources, a computing resource and a database resource are described. Two different Web service technologies, one based on SOAP and the other on REST are experimented with. A comparison of the two technologies including a performance comparison of two implementations (one using SOAP-based Web services and the other using RESTful Web services) of a computing system exposed as a Web service is presented.

A Constraint Programming Based Hadoop Scheduler for Handling MapReduce Jobs with Deadlines on Clouds

A novel MapReduce constraint programming based matchmaking and scheduling algorithm (MRCP) that can handle MapReduce jobs with deadlines and achieve high system performance is devised. The MRCP algorithm is incorporated into Hadoop, which is a widely used open source implementation of the MapReduce programming model, as a new scheduler called the CP-Scheduler. This paper originates from the collaborative research with our industrial partner concerning the engineering of resource management middleware for high performance. It describes our experiences and the challenges that we encountered in designing and implementing the prototype CP-based Hadoop scheduler. A detailed performance evaluation of the CP-Scheduler is conducted on Amazon EC2 to determine the CP-Schedulers effectiveness as well as to obtain insights into system behaviour and performance. In addition, the CP-Schedulers performance is also compared with an earliest deadline first (EDF) Hadoop scheduler, which is implemented by extending Hadoops default FIFO scheduler. The experimental results demonstrate the effectiveness of the CP-Schedulers ability to handle an open stream of MapReduce jobs with deadlines in a Hadoop cluster.

Resource management techniques for handling requests with service level agreements

The prominence of cloud computing that provides resources on demand to various types of users including enterprises as well as engineering and scientific institutions is growing rapidly. An effective resource management middleware is necessary to harness the power of the underlying distributed hardware in a cloud. The resource manager needs to be able to effectively perform mapping (matchmaking and scheduling) of user requests (jobs) on to resources to satisfy desired system objectives as well as users requirements for a quality of service that is often captured in a service level agreement (SLA). This paper concerns the problem of meeting an end-to-end SLA (characterized by an earliest start time, an execution time, and a deadline) for applications that require service from multiple resources (referred to as multi-stage applications) on a system subjected to an open stream of request arrivals. A new budget-based algorithm and a resource manager called MapReduce Budget-based Resource Manager (MRBB-RM) are devised for effectively performing matchmaking and scheduling of an open stream of MapReduce jobs (a popular multi-stage application) with SLAs on a distributed environment such as a cloud or a cluster. A detailed description of the algorithm and its performance analysis are presented.

Engineering SSL-based systems for enhancing system performance

Security in a distributed system often comes at the cost of a performance penalty. Due to the CPU time consuming security algorithms used, transferring data using SSL is known to be significantly slow. This paper presents an initial set of research results of a university-industry collaborative research focusing on a performance enhancement technique called security sieve that separates the classified and non-classified components in a document and sends these on a secure and a (faster) non-secure channel respectively. Experimental results presented in the paper demonstrate the effectiveness of the technique.

Techniques for Handling Error in User-estimated Execution Times During Resource Management on Systems Processing MapReduce Jobs

In our previous work, we described a resource allocation and scheduling technique for processing an open stream of MapReduce jobs with SLAs (characterized by an earliest start time, an execution time, and a deadline) called the Hadoop Constraint Programming based Resource Management technique (HCP-RM). Since the user-estimated job execution times are used to perform resource allocation and scheduling, error/inaccuracies in the execution times can hinder the ability of HCP-RM from making effective scheduling decisions, leading to a degradation in system performance. This paper focuses on improving the robustness of HCP-RM by introducing a mechanism to handle errors/inaccuracies in user estimates of job execution times that are submitted as part of the jobs SLA. A Prescheduling Error Handling technique (PSEH) is devised to adjust the user-estimated execution times of the jobs to make them more accurate before they are used by the resource management algorithm. Results of experiments conducted on a Hadoop cluster deployed on Amazon EC2 demonstrate the effectiveness of the PSEH technique in improving system performance.

A resource management technique for processing deadline-constrained multi-stage workflows

The use of cloud computing that provides resources on demand to various types of users, including enterprises as well as engineering and scientific institutions, is growing rapidly. An effective resource management middleware is necessary to harness the power of the underlying distributed hardware in a cloud. Two of the key operations provided by a resource manager are resource allocation (matchmaking) and scheduling. This paper concerns the problem of matchmaking and scheduling an open stream of multi-stage jobs (or workflows) with Service Level Agreements (SLAs) on a cloud or cluster. Multi-stage jobs require service from multiple system resources and are characterized by multiple phases of execution. This paper presents a resource allocation and scheduling technique called RM-DCWF: Resource Management Technique for Deadline-constrained Workflows that can efficiently matchmake and schedule an open stream of multi-stage jobs with SLAs, where each SLA is characterized by an earliest start time, an execution time, and a deadline. A rigorous simulation-based performance evaluation of RM-DCWF is conducted using synthetic workloads derived from real scientific workflows. In addition, the impact of various system and workload parameters on system performance is investigated. The results of this performance evaluation demonstrate the effectiveness of RM-DCWF as captured in a low number of jobs missing their deadlines.

A Run Time Technique for Handling Error in User-Estimated Execution Times on Systems Processing MapReduce Jobs with Deadlines

Effective management of resources on a cloud or cluster is crucial for achieving the quality of service requirements of users, which are typically captured in service level agreements (SLAs). This paper focuses on improving the robustness of resource allocation and scheduling techniques that process an open stream of MapReduce jobs with SLAs, by introducing techniques to handle errors/inaccuracies in user-estimated execution times that are submitted as part of the jobs SLA. Inaccuracies in the estimates of task execution times can prevent the resource allocation and scheduling algorithm from making effective scheduling decisions, leading to a degradation in system performance. Techniques for handling error during runtime are presented to handle the situation where jobs have already started executing and their estimated execution times are inaccurate. A simulation-based performance evaluation of the error handling techniques is conducted, which demonstrates that the techniques are effective in improving system performance.