Cluster distributed resource scheduling method, apparatus and device, and storage medium

A cluster distributed resource scheduling device, comprising:

• a memory, configured to store a computer program;
• and
• a processor, configured to execute the computer program to:
• respectively acquire host CPU utilization rates of hosts in a cluster and virtual CPU (vCPU) utilization rates of virtual machines in the hosts;
• respectively perform a quantization operation on the host CPU utilization rates and the vCPU utilization rates, to obtain host quantized pressure values and virtual machine quantized pressure values;
• acquire historical host pressure values respectively corresponding to the hosts, and historical virtual machine pressure values respectively corresponding to the virtual machines;
• calculate target CPU pressure values respectively corresponding to the hosts according to the host quantified pressure values and historical host pressure values respectively corresponding to the hosts, and virtual machine quantified pressure values and historical virtual machine pressure values respectively corresponding to the virtual machines in the hosts;
• and
• perform a live migration operation on the virtual machines in the hosts according to the target CPU pressure values;
• wherein the processor is further configured to:
• respectively acquire vCPU utilization rates respectively corresponding to vCPUs in the virtual machines and the host CPU utilization rates;
• and
• respectively perform a quantization operation on the host CPU utilization rates and the vCPU utilization rates includes:
• determine whether there is a virtual machine having a full load vCPU,
• when there is a virtual machine having a full-load vCPU, determine the virtual machine having a full load vCPU as a target virtual machine;
• perform a first quantization operation on a target vCPU utilization rate corresponding to the target virtual machine according to a first preset pressure interval;
• select, from a target host where the target virtual machine is located, a preset number of vCPUs and add same to the target virtual machine, and perform a second quantization operation on the target vCPU utilization rate according to a second preset pressure interval;
• determine whether a preset vCPU addition stopping trigger condition is reached;
• when the preset vCPU addition stopping trigger condition is not reached, repeatedly execute the step of performing a first quantization operation on a target vCPU utilization rate corresponding to the target virtual machine according to a first preset pressure interval;
• and
• when the preset vCPU addition stopping trigger condition is reached, perform a quantization operation on a target host CPU utilization rate corresponding to the target host according to a third preset pressure interval when the preset vCPU addition stopping trigger condition reached is that a resource utilization rate of the target host reaches a preset threshold.

A non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, cause the processor to:

• respectively acquire host CPU utilization rates of hosts in a cluster and virtual CPU (vCPU) utilization rates of virtual machines in the hosts;
• respectively perform a quantization operation on the host CPU utilization rates and the vCPU utilization rates, to obtain host quantized pressure values and virtual machine quantized pressure values;
• acquire historical host pressure values respectively corresponding to the hosts, and historical virtual machine pressure values respectively corresponding to the virtual machines;
• calculate target CPU pressure values respectively corresponding to the hosts according to the host quantified pressure values and historical host pressure values respectively corresponding to the hosts, and virtual machine quantified pressure values and historical virtual machine pressure values respectively corresponding to the virtual machines in the hosts;
• and
• perform a live migration operation on the virtual machines in the hosts according to the target CPU pressure values;
• when the computer program is executed by the processor cause the processor further to:
• respectively acquire vCPU utilization rates respectively corresponding to vCPUs in the virtual machines and the host CPU utilization rates;
• and
• respectively perform a quantization operation on the host CPU utilization rates and the vCPU utilization rates includes:
• determine whether there is a virtual machine having a full-load vCPU;
• when there is a virtual machine having a full-load vCPU, determine the virtual machine having a full-load vCPU as a target virtual machine;
• perform a first quantization operation on a target vCPU utilization rate corresponding to the target virtual machine according to a first preset pressure interval;
• select, from a target host where the target virtual machine is located, a preset number of vCPUs and add same to the target virtual machine, and perform a second quantization operation on the target vCPU utilization rate according to a second preset pressure interval;
• determine whether a preset vCPU addition stopping trigger condition is reached;
• when the preset vCPU addition stopping trigger condition is not reached, repeatedly execute the step of performing a first quantization operation on a target vCPU utilization rate corresponding to the target virtual machine according to a first preset pressure interval;
• and
• when the preset vCPU addition stopping trigger condition is reached, perform a quantization operation on a target host CPU utilization rate corresponding to the target host according to a third preset pressure interval when the preset vCPU addition stopping trigger condition reached is that a resource utilization rate of the target host reaches preset threshold.