Invention Grant
US09146828B2 Method for adaptively determining response time distribution of transactional workloads by adjusting the midpoint of response time distribution
有权
通过调整响应时间分布的中点来自适应地确定事务工作量的响应时间分布的方法
- Patent Title: Method for adaptively determining response time distribution of transactional workloads by adjusting the midpoint of response time distribution
- Patent Title (中): 通过调整响应时间分布的中点来自适应地确定事务工作量的响应时间分布的方法
-
Application No.: US13603705Application Date: 2012-09-05
-
Publication No.: US09146828B2Publication Date: 2015-09-29
- Inventor: Nicolas X. Nardelli , Robert Vaupel
- Applicant: Nicolas X. Nardelli , Robert Vaupel
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent Stephen R. Tkacs; Stephen J. Walder, Jr.; William J. Stock
- Main IPC: G06F9/46
- IPC: G06F9/46 ; G06F11/34 ; G05B13/02 ; G05B13/04

Abstract:
An adaptive mechanism is provided that learns the response time characteristics of a workload by measuring the response times of end user transactions, classifies response times into buckets, and dynamically adjusts the response time distribution as response time characteristics of the workload change. The adaptive mechanism maintains the actual distribution across changes and, thus, helps the end user to understand changes of workload behavior that take place over a longer period of time. The mechanism is stable enough to suppress spikes and returns a constant view of workload behavior, which is required for long term, performance analysis and capacity planning. The mechanism distinguishes between an initial learning phase of establishing the distribution and one or multiple reaction periods. The reaction periods can be for example a fast reaction period for strong fluctuations of the workload behavior and a slow reaction period for small deviations.
Public/Granted literature
- US20130081035A1 Adaptively Determining Response Time Distribution of Transactional Workloads Public/Granted day:2013-03-28
Information query