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

Method for constructing large-scale high-availability cluster operating system

An operating system and large-scale technology, applied in the field of computer systems, can solve problems such as complex implementation, difficulty in ensuring software reliability, and protocol complexity, and achieve high availability and good scalability

Inactive Publication Date: 2008-10-29
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Hierarchical distributed control has the problem of very complex protocols, and the actual implementation will be very complicated, making it difficult to guarantee the reliability of the software

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 constructing large-scale high-availability cluster operating system
  • Method for constructing large-scale high-availability cluster operating system
  • Method for constructing large-scale high-availability cluster operating system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] deploy:

[0032] Such as Figure 5 As shown, each node of the cluster is equipped with a local detection process device, and each physical partition of the cluster has a management process device. The partition management process device is responsible for managing the partition node status and network connectivity, and the management process device Managed by distributed control. Figure 5 The GSD (Group Service Daemon) is the management process device (referred to as the management process device) of the nodes and network connection status in each physical partition. WD (watch Daemon) is a local monitoring process device installed on each node (referred to as a local monitoring process device).

[0033] Figure 6 It is a structural diagram of a local detection process device. Its software modules include heartbeat sending and command receiving modules, and its hardware includes multiple sets of physical networks, memory, and CPU.

[0034] Figure 7 It is a structu...

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 is a method for constructing a large-scale high practicability armada operation system. The method divides the system into several physical areas, a managing process device is set in each area, and a local detection process device is set on each joint. The detection process device sends heat beat to managing process device in the area through the network, the managing process device acquires the network state and joint running state according to the received heat beat, thus carries on central monitoring and uniform management to the area. There uses distributed structure between the managing process devices in each area, then are equal in logic, cooperates, and maintains the uniform view for the running state and network state of all joints.

Description

technical field [0001] The invention relates to the technical field of computer systems, in particular to a method for constructing a large-scale high-availability cluster operating system. technical background [0002] Since its inception, the cluster has quickly become the mainstream architecture of high-performance computing due to its good scalability and competitive performance / price ratio, and has also been widely used in commercial fields such as Internet services and database services. [0003] The cluster operating system is based on the node operating system and provides a single system image support for ordinary users, software developers and system administrators. It is the most basic system software set in the cluster. [0004] High availability is an important requirement of the cluster system. A highly available cluster operating system requires itself to be highly reliable and must be able to detect and repair failures in time when the cluster system fails. ...

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): G06F11/30
Inventor 詹剑锋王磊黄伟孟丹
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI