Method and device for adaptive switching of openstack control node to computing node
An adaptive switching and computing node technology, applied in the transmission system, electrical components, etc., can solve the problems of complex deployment, low timeliness, and slow service speed, and achieve the effect of high deployment efficiency and high availability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] A method for adaptively switching an OpenStack control node to a computing node. OpenStack is a topology structure composed of a control node group and a computing node group, such as figure 1 , the method includes:
[0044] S1: Divide the control node group into a switchable control node group and a non-switchable control node group, and elect a to-be-switched control node from the switchable control node group through an election algorithm;
[0045] S2: Trigger monitoring on a periodic basis. If it is found that there is a node failure in the computing node group or the total load is too high, the adaptive upgrade process is triggered, otherwise the process ends;
[0046] The self-adaptive upgrade process is specifically: switching the control node to be switched to the computing node and joining the computing node group described in step S2 through an automated management tool in combination with the container technology.
[0047] The election algorithm selects a no...
Embodiment 2
[0064] In this implementation, the total load of the computing node group is calculated and obtained through the prediction algorithm. Others are the same as those in the first embodiment, and the prediction algorithm is specifically:
[0065] Based on the historical monitoring data of the computing nodes, the prediction is made through a multi-input single-output neural network linear regression model. The neural network linear regression model is:
[0066] Z=WX+B
[0067] Where Z is the predicted value of the computing node load, X={x 1 ,x 2 ,…,x N } is the input sample, the sample includes time, number of virtual machines and number of tenants, W={w 1 ,w 2 ,…,w N } is the weight matrix, B={b 1 } is the offset matrix, the mean square error function is used as the cost function, W and B are calculated through forward calculation and backward conduction, and the total load of the calculation node group is obtained according to the load prediction value Z of each calculat...
Embodiment 3
[0069] A device for adaptively switching an OpenStack control node to a computing node corresponding to the first embodiment. OpenStack includes a control node group and a computing node group, and the device includes:
[0070] A fault monitoring module, configured to detect whether a node failure occurs in the computing node group by sending a heartbeat packet to each computing node in the computing node group;
[0071] The load detection module is used to collect the load information elements of each computing node in the computing node group, calculate the total load of the computing node group according to the collected load information, or predict the total load of the computing node group according to the historical load information, and set the load threshold according to the load threshold. Determine whether the computing node group is overloaded;
[0072] The node processing module is used to divide the control node group into a switchable control node group and a non...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


