CN104636198B - A kind of nearly data source moving method of calculating task based on OSGi - Google Patents

Abstract

The present invention proposes an OSGi-based computing task near-data source migration method. Based on the computing task decision module, computing task detection module and computing task migration module, the computing task is OSGi componentized, so that it has the flexibility and heat of OSGi. With the advantages of plugging and unplugging, on the premise of making full use of OSGi context management, find the best near data source that is most suitable for computing tasks, and migrate computing tasks to near data sources for computing, achieving the purpose of high efficiency and low power consumption.

Description

An OSGi-based Migration Method for Computing Tasks Near Data Sources

technical field

The invention relates to the Internet field, in particular to an OSGi-based method for migrating computing tasks near data sources.

Background technique

The task migration near the data source allows computing tasks to be executed near the data source, eliminating the need for end-to-end data transmission, which greatly improves the efficiency of computing tasks and saves the computing resource consumption of the original computing subject. The techniques closest to the present invention are:

(1), CloneCloud: It can copy computing tasks and data from mobile devices to strong computing nodes, and return computing results;

(2) CloudLet: Use virtual machine technology to instantiate service instances on nearby CloudLet to reduce space network transmission time and bandwidth limitations.

Among them, CloneCloud needs to modify the JVM, so it is not realistic in practical applications; CloudLet lacks the distribution and management of computing tasks and data among different nodes. Moreover, CloneCloud and CloudLet are not implemented based on OSGi technical specifications, which makes them not have the advantages of highly modularized, flexible, and hot-swappable OSGi. At the same time, based on the calculation of near data sources, the existing technologies have not considered and designed in this regard.

Contents of the invention

In order to solve the shortcomings and deficiencies in the prior art, the present invention proposes an OSGi-based migration method for computing tasks near data sources, which implements OSGi componentization of computing tasks, and finds the most suitable computing task under the premise of fully utilizing OSGi context management. The best near data source for the task, and migrate the computing task to the best near data source for calculation.

Technical scheme of the present invention is:

An OSGi-based migration method for computing tasks near data sources, based on a computing task decision module, a computing task detection module and a computing task migration module, comprising the following steps:

Step (1), obtain computing task information according to the context of OSGi, and the computing task detection module checks in real time whether there is a computing task that can be migrated;

Step (2), when a task that can be migrated is detected, the calculation task decision module makes a decision whether to migrate it;

Step (3), if no task migration is performed, obtain the data required by the computing task, then execute the computing task locally, and return the calculation result; if it is decided to transfer the computing task, then the task decision module selects the best near data source according to the context;

Step (4), the task decision module calls the task migration module to migrate the calculation task to the best near data source of the target in the form of OSGi components, and the calculation task is calculated at the target near data source;

Step (5), return the calculation result.

Optionally, the OSGi-based computing task migration method near the data source of the present invention further includes an exception handling module, which handles the exceptions caught in the whole process.

Beneficial effects of the present invention:

(1) By migrating computing tasks to near data sources for calculation, the transmission of source data is avoided, and the computing efficiency is effectively improved;

(2) Make it have the advantages of OSGi's highly modular, flexible, hot-swappable, etc.;

(3) The consumption of computing resources of the original computing body, such as power, bandwidth, and memory, is saved.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is the system structural diagram of the near data source migration method of computing tasks based on OSGi in the present invention;

FIG. 2 is a flow chart of the method for migrating computing tasks near data sources based on OSGi in the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

As shown in FIG. 1 , the system structure of the OSGi-based computing task near data source migration method of the present invention includes four modules: a computing task detection module, a computing task decision module, a computing task migration module and an exception handling module.

The specific flow of the OSGi-based computing task migration method near the data source will be described in detail below in combination with Figure 1 and Figure 2:

In step (1), computing task information is obtained according to the OSGi context, and the computing task detection module checks in real time whether there is a computing task that can be migrated.

Step (2), when a task that can be migrated is detected, the calculation task decision module decides whether to migrate it.

Step (3), if the task migration is not performed, obtain the data required by the computing task, then execute the computing task locally, and return the calculation result; if it decides to transfer the computing task, then the computing task decision module estimates the task execution resource consumption, according to the context Select the best near data source, where the best near data source refers to the data source near the computing subject that can be used to perform computing tasks to achieve the minimum resource consumption.

In step (4), the task decision module calls the task migration module to migrate the calculation task to the best near data source in the form of an OSGi component, and the calculation task is calculated at the target near data source.

Step (5), return the calculation result, and perform related processing.

Preferably, during the whole process, the exception handling module handles the exceptions caught in the whole process, including task detection exception, calculation task component acquisition exception, calculation task component transmission exception, and calculation task component remote execution exception.

The OSGi-based calculation task near data source migration method of the present invention avoids the transmission of source data by migrating the calculation task to the near data source for calculation, and effectively improves the calculation efficiency; moreover, it has the high degree of modularization of OSGi , flexible, hot-swappable and other advantages; it saves the consumption of computing resources of the original computing body, such as power, bandwidth, memory, etc.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of the present invention. within the scope of protection.

Claims (2)

1. An OSGi-based calculation task near data source migration method is characterized in that, based on a calculation task decision module, a calculation task detection module and a calculation task migration module, comprising the following steps: Step (1), obtain computing task information according to the context of OSGi, and the computing task detection module checks in real time whether there is a computing task that can be migrated; Step (2), when a task that can be migrated is detected, the calculation task decision module makes a decision whether to migrate it; Step (3), if the task migration is not performed, obtain the data required by the computing task, then execute the computing task locally, and return the calculation result; if it is decided to transfer the computing task, then the computing task decision module estimates the resource consumption of the task execution, and the task decision The module selects the best near data source according to the context, where the best near data source refers to the data source that is used to perform computing tasks to achieve the minimum resource consumption of the adjacent computing subject; Step (4), the task decision module calls the task migration module to migrate the calculation task to the best near data source of the target in the form of OSGi components, and the calculation task is calculated at the target near data source; Step (5), return the calculation result. 2. The OSGi-based method for migrating computing tasks near data sources according to claim 1, further comprising an exception handling module, which handles the exceptions captured during the whole process.