Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for deploying storage system resources through learning from running workloads

A workload and storage system technology, applied in the field of deploying storage system resources, can solve the problems of not having artificial intelligence and being unable to learn and adapt

Active Publication Date: 2019-11-05
PROPHETSTOR DATA SERVICES
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The important thing is that the control server 1 does not have artificial intelligence and cannot learn how to adapt itself, it can only rely on the instructions of the management personnel

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for deploying storage system resources through learning from running workloads
  • Method for deploying storage system resources through learning from running workloads
  • Method for deploying storage system resources through learning from running workloads

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be described more specifically with reference to the following embodiments.

[0061] The concept of the present invention is to find out the optimal resource deployment for the workloads in the storage system according to the observed and predicted performance parameter deviation percentages according to the resource requirements of the running workloads. After a learning period, the storage system will know how to dynamically allocate "enough" resources to each workload at any time, so that all workloads will not violate the requirements of the service level agreement (Service Level Agreement, SLA). The learning phase is to learn the requirements of the workload within a predetermined period of time to make optimal resource allocation for the storage system. Preferably, the learning period is longer than 5 hours, so as to obtain enough learning data and minimize waste of resources. Wherein, the performance parameters refer to delay time, thr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method for deploying resources of a storage system by learning workload in execution. The method is applied to the storage system. By utilizing a state-action fuzzy rule and an action-reward fuzzy rule, the performance parameters of the workload are learnt to obtain optimal dynamic deployment of the resources, without manual operation, so that the workload of a storage system administrator is reduced and the performance of the storage system is enhanced.

Description

technical field [0001] The present invention relates to a method for deploying storage system resources, in particular to a method for deploying storage system resources by learning the workload in execution. Background technique [0002] Traditionally, storage system administrators have been troubled by a problem: how to allocate "enough" resources to all the workloads running on the storage system. The storage system can be used in private network or cloud service. For example, if a system accesses storage device resources to execute email services and ERP (Enterprise Resource Planning, Enterprise Resource Planning) service workloads, a control server must properly deploy all storage devices and other resources, such as CPU (Central Resource Planning) Processing Unit, central processing unit) usage rate and SSD (Solid State Disk, solid state drive) cache size, so that when the workload is loaded, the work performance, such as the number of input and output operations per ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F9/50
CPCG06F9/5011G06F9/5027G06F9/5044G06F2209/501G06F2209/5019
Inventor 陈文贤黄明仁
Owner PROPHETSTOR DATA SERVICES