Utility-driven adaptive query workload execution

Abstract

Workload management coordinates access to and use of shared computational resources; adaptive workload execution revises resource allocation decisions dynamically in response to feedback about the progress of the workload or the behavior of the resources. Where the workload contains or consists of database queries, adaptive query processing (AQP) changes the way in which a query is being evaluated while the query is running. In parallel environments, available adaptations may change the allocation of query fragments to a machine, for example to remove load imbalance or change the parallelism level. Most AQP strategies act on individual queries with the objective of reducing response times. However, where adaptations affect the usage of shared resources, or the principal goal is to meet quality of service targets rather than to minimize overall response times, locally beneficial decisions may have globally detrimental effects. This paper describes the use of utility functions to coordinate adaptations that assign resources to query fragments from multiple queries, and demonstrates how a common framework can be used to support different objectives, specifically to minimize overall query response times and to maximize the number of queries meeting quality of service goals. Experiments using simulation compare the use of utility functions with the more common heuristic control strategies, demonstrating situations in which significant benefits can be obtained.

Optimizing virtual machine placement for energy and SLA in clouds using utility functions

“…In the original proposal for utility-based adaptation [5], a controller is responsible for selecting the collection of control parameters that maximize the utility function, using a utility calculator that implements a model of the environment. Utility functions have been applied in autonomic computing for: configuring the properties of application hosting environments such as web servers [5], for selecting between alternative providers of a service [24], for managing the physical environment within data centres [9], for allocating jobs within a collection of workflows to machines on a grid [8], for optimizing resource utilization for scientific applications [25], and for balancing the load of a collection of database queries over the nodes in a cluster [26]. As the designs of these applications have various features in common, a methodology has been proposed for the development of utility-based applications [27], which we follow in "Utility-based resource allocation" section.…”

Improved Task Scheduling for Virtual Machines in the Cloud based on the Gravitational Search Algorithm

“…Obviously, finding the proper mappings between the jobs submitted by end users and the dynamic resources of the available VMs is an NP-hard optimization problem. For this problem, a variety of dynamic, static and mixed scheduling algorithms have been proposed [4][5][6][7][8][9][10]. Some of the well-known early static scheduling schemes were based on ISH, MCP and ETF algorithms [8][9][10].…”

Research and Design of Culture Compound Based on Android Platform

“…But measures to promote traditional culture have been unable to meet the people's demands for culture. Currently, with the rapid development of communication technology and computer technology, more and more new technologies are emerging, such as the Android operating system and Cloud computing technology [1] [2]. It has become an inevitable trend to use these new technologies to research the cultural promotion software.…”