Donna N. Dillenberger

Adaptive algorithms for managing a distributed data processing workload

Workload management, a function of the OS/390™ operating system base control program, allows installations to define business objectives for a clustered environment (Parallel Sysplex™ in OS/390). This business policy is expressed in terms that relate to business goals and importance, rather than the internal controls used by the operating system. OS/390 ensures that system resources are assigned to achieve the specified business objectives. This paper presents algorithms developed to simplify performance management, dynamically adjust computing resources, and balance work across parallel systems. We examine the types of data the algorithms require and the measurements that were devised to assess how well work is achieving customer-set goals. Two examples demonstrate how the algorithms adjust system resource allocations to enable a smooth adaptation to changing processing conditions. To the customer, these algorithms provide a single-system image to manage competing workloads running across multiple systems.

Building a Java virtual machine for server applications: the Jvm on 0S/390

As the use of the JavaTM language and virtual machines proliferates beyond the sphere of applets into the space of server programs, developers are requiring better performance, availability, and transactional and scalability features. This paper describes the work done for the Operating System/390 (OS/390®) Java virtual machine to improve performance and serviceability, to introduce security and performance enhancements, and to redesign parts of the virtual machine to enable it to run server programs efficiently and safely. Although OS/390 was the motivating platform for these changes, Java server programs on any platform can benefit from these features.

Allocating non-real-time and soft real-time jobs in multiclusters

This paper addresses workload allocation techniques for two types of sequential jobs that might be found in multicluster systems, namely, non-real-time jobs and soft real-time jobs. Two workload allocation strategies, the optimized mean response time (ORT) and the optimized mean miss rate (OMR), are developed by establishing and numerically solving two optimization equation sets. The ORT strategy achieves an optimized mean response time for non-real-time jobs, while the OMR strategy obtains an optimized mean miss rate for soft real-time jobs over multiple clusters. Both strategies take into account average system behaviors (such as the mean arrival rate of jobs) in calculating the workload proportions for individual clusters and the workload allocation is updated dynamically when the change in the mean arrival rate reaches a certain threshold. The effectiveness of both strategies is demonstrated through theoretical analysis. These strategies are also evaluated through extensive experimental studies and the results show that when compared with traditional strategies, the proposed workload allocation schemes significantly improve the performance of job scheduling in multiclusters, both in terms of the mean response time (for non-real-time jobs) and the mean miss rate (for soft real-time jobs).

Database analytics acceleration using FPGAs

Business growth and technology advancements have resulted in growing amounts of enterprise data. To gain valuable business insight and competitive advantage, businesses demand the capability of performing real-time analytics on such data. This, however, involves expensive query operations that are very time consuming on traditional CPUs. Additionally, in traditional database management systems (DBMS), the CPU resources are dedicated to mission-critical transactional workloads. Offloading expensive analytics query operations to a co-processor can allow efficient execution of analytics workloads in parallel with transactional workloads. In this paper, we present a Field Programmable Gate Array (FPGA) based acceleration engine for database operations in analytics queries. The proposed solution provides a mechanism for a DBMS to seamlessly harness the FPGA compute power without requiring any changes in the application or the existing data layout. Using a software-programmed query control block, the accelerator can be tailored to execute different queries without reconfiguration. Our prototype is implemented in a PCIe-attached FPGA system and is integrated into a commercial DBMS platform. The results demonstrate up to 94% CPU savings on real customer data compared to the baseline software cost with up to an order of magnitude speedup in the offloaded computations and up to 6.2× improvement in end-to-end performance.

Crowdsourced estimation of cognitive decline and resilience in Alzheimer's disease

Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimers disease. The Alzheimers disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state‐of‐the‐art in predicting cognitive outcomes in Alzheimers disease based on high dimensional, publicly available genetic and structural imaging data. This meta‐analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.

IBM research division cloud computing initiative

Cloud computing represents the latest phase in the evolution of Internet-based computing. In this paper, we describe the fundamental building blocks of cloud computing and the initiative undertaken by the IBM Research Division in this area, which includes work on Internet-scale data centers, virtualization, scalable storage, and cloud computing services. The focus of this project has been the Research Compute Cloud, an environment for cloud computing research that is also used as a computing resource by various groups in the IBM Research Division.

An Investigation into the Application of Different Performance Prediction Methods to Distributed Enterprise Applications

Response time predictions for workload on new server architectures can enhance Service Level Agreement–based resource management. This paper evaluates two performance prediction methods using a distributed enterprise application benchmark. The historical method makes predictions by extrapolating from previously gathered performance data, while the layered queuing method makes predictions by solving layered queuing networks. The methods are evaluated in terms of: the systems that can be modelled; the metrics that can be predicted; the ease with which the models can be created and the level of expertise required; the overheads of recalibrating a model; and the delay when evaluating a prediction. The paper also investigates how a prediction-enhanced resource management algorithm can be tuned so as to compensate for predictive inaccuracy and balance the costs of SLA violations and server usage.

Managing Dynamic Enterprise and Urgent Workloads on Clouds Using Layered Queuing and Historical Performance Models

The automatic allocation of enterprise workload to resources can be enhanced by being able to make what–if response time predictions whilst different allocations are being considered. We experimentally investigate an historical and a layered queuing performance model and show how they can provide a good level of support for a dynamic-urgent cloud environment. Using this we define, implement and experimentally investigate the effectiveness of a prediction-based cloud workload and resource management algorithm. Based on these experimental analyses we: (i) comparatively evaluate the layered queuing and historical techniques; (ii) evaluate the effectiveness of the management algorithm in different operating scenarios; and (iii) provide guidance on using prediction-based workload and resource management.

A Hardware/Software Approach for Database Query Acceleration with FPGAs

Complex analytics queries often involve expensive operations that may require large computational runtimes leading to slow query responsiveness and hampering real-time performance. Moreover, running these expensive analytics queries inside traditional online transaction processing (OLTP) systems for real-time analytics can affect the performance of mission-critical OLTP queries. On the other hand, support for real-time analytics is considered vital for important business insights and improved market responsiveness. In this paper, we try to address the needs of real-time analytics by enabling hardware acceleration of complex database query operations such as predicate evaluation, sort and projection. While projection helps reduce the amount of data being processed by subsequent query operations, sort is central to most database queries, even those not involving an explicit sort operation. Our system involves FPGA-based composable accelerator for offloading the analytics queries from the host CPU running the OLTP workload. The FPGA-accelerated database system contains accelerator kernels for various database operations and automatic transformation of query operations into calls to these hardware kernels for seamless integration of the accelerator into the database system. Based on the query semantics, each accelerator kernel can be tailored by software to execute specific database operations and different kernels can be fused together to compose a query accelerator. Our query transformation algorithm creates a query-specific control block to customize the accelerator without requiring FPGA-reconfiguration.

Resource management of enterprise cloud systems using layered queuing and historical performance models

The automatic allocation of enterprise workload to resources can be enhanced by being able to make ‘what-if’ response time predictions, whilst different allocations are being considered. It is important to quantitatively compare the effectiveness of different prediction techniques for use in cloud infrastructures. To help make the comparison of relevance to a wide range of possible cloud environments it is useful to consider the following. 1.) urgent cloud customers such as the emergency services that can demand cloud resources at short notice (e.g. for our FireGrid emergency response software). 2.) dynamic enterprise systems, that must rapidly adapt to frequent changes in workload, system configuration and/or available cloud servers. 3.) The use of the predictions in a coordinated manner by both the cloud infrastructure and cloud customer management systems. 4.) A broad range of criteria for evaluating each technique. However, there have been no previous comparisons meeting these requirements. This paper, meeting the above requirements, quantitatively compares the layered queuing and (“HYDRA”) historical techniques - including our initial thoughts on how they could be combined. Supporting results and experiments include the following: i.) defining, investigating and hence providing guidelines on the use of a historical and layered queuing model; ii.) using these guidelines showing that both techniques can make low overhead and typically over 70% accurate predictions, for new server architectures for which only a small number of benchmarks have been run; and iii.) defining and investigating tuning a prediction-based cloud workload and resource management algorithm