Unikernel-based cloud Android operating environment construction method

Abstract

The invention discloses a Unikernel-based cloud Android operating environment construction method, and belongs to the technical field of cloud computing virtualization. The method comprises the stepsthat firstly, an Android subsystem assembly which must be supported for achieving the minimum Android operating environment cloud under the Android code unloading scene is analyzed and obtained at first; then, an Android essential subsystem and a Bionic and Dalvik virtual machine are transplanted into a library operating system; then, an Android application code is compiled, and a related dependence package is extracted from the library operating system for generating a Unikernel virtual machine mirror image; finally, the Unikerel is started on a KVM, an XEN and other Hypervisor, and the Android code is operated. The essential Android environment support is added to the library operating system, the Android application code is compiled to the Unikernel, the characteristics that the Unikernel mirror image is large in size, low in cost, rapid in starting, high in isolation performance and the like are utilized, the cloud resource cost can be effectively lowered, the number of virtual machine instances provided by the cloud is increased, meanwhile, the delay of cloud and terminal communication is greatly lowered, and the user experience of terminal applications is improved.

Description

technical field [0001] The invention belongs to the technical field of cloud computing virtualization, and more specifically relates to a method for constructing a Unikernel-based cloud Android operating environment. Background technique [0002] In recent years, the mobile application market has developed rapidly, and the application functions have become more and more sophisticated. More and more mobile applications try to complete more complex logic functions, such as the emergence of large-scale games and virtual reality (Virtual Reality) functions. Processor performance presents challenges. In addition, the improvement of terminal battery life is very slow, and the use time is limited. [0003] In order to solve the above problems, Mobile Cloud Computing (MCC) emerged as the times require, using the nearly unlimited resources and high performance of cloud computing to expand the limited hardware performance of mobile devices. By handing over complex calculations, even...

AI Technical Summary

Problems solved by technology

However, the cloud generally uses a virtual machine-based approach to serve terminals. Since a complete operating system runs in the virtual machine, this virtualization solution has a very large resource overhead and slow startup, usually taking more than ten seconds to several Ten seconds, it is difficult to guarantee the real-time performance of terminal requests, so it is not advisable

Another lightweight solution based on container technology, using the characteristics of the container and the host operating system to share the kernel, greatly reduces the overhead of the cloud. At the same time, the container starts quickly, which greatly reduces the terminal request. The response is delayed, but it is still not fast enough, not streamlined enough, and the isolation and security of containers are far less good than virtual machines

Images