Hello, everyone! Today I will share with you QoS in FusionCompute.
FusionSphere provides support for setting an upper limit for VM resources, such as CPUs, memory, networks, and disk input/output per second (IOPS), preventing non-critical applications or malicious users from preempting shared resources.
CPU QoS
The solution supports configuration of CPU Quota, CPU Reserved (MHz), and CPU Limit (MHz).
CPU Quota
Specifies the proportion of CPU resources a VM can obtain in resource contention.
The quota defines the relative priority or importance of a VM. For example, three VMs (A, B, C) each with one vCPU run on a single-core physical server with 2.8 GHz frequency. The quotas of VMs A, B, and C are 1000, 2000, and 4000, respectively. When the CPU workloads of the VMs are heavy, the system allocates compute resources to the VMs based on the CPU quotas. VM A with 1000 CPU quota can obtain a computing capability of 400 MHz. VM B with 2000 CPU quota can obtain a computing capability of 800 MHz. VM C with 4000 CPU quota can obtain a computing capability of 1600 MHz.
CPU Reserved (MHz)
Specifies the minimum compute resources to be allocated to each VM when multiple VMs compete for physical CPU resources.
If the computing capability calculated based on the CPU quota of a VM is less than the CPU reservation value, the system allocates the computing capability to the VM according to the CPU reservation value. The offset between the computing capability calculated based on the CPU quota and the CPU reservation value is deducted from computing capabilities of other VMs based on their CPU quotas and is added to the VM.
If the computing capability calculated based on the CPU quota of a VM is greater than the CPU reservation value, the system allocates the computing capability to the VM according to the CPU quota.
CPU Limit (MHz)
Specifies the upper limit of physical CPUs used by a VM.
For example, if a VM with two vCPUs has a CPU limit of 3 GHz, each vCPU of the VM can obtain a maximum of 1.5 GHz compute resources.
Memory QoS
VM memory can be intelligently reused, which depends on the preset percentage of reserved memory. Memory overcommitment technologies, such as memory ballooning, are used to provide more virtual memory resources, thereby increasing memory utilization. In this case, memory QoS is used to reserve the minimum memory for reliable running of VMs and thereby ensures optimal use of memory. The memory resource quota and reserved memory resource can be configured.
Network QoS
The network QoS policy provides the bandwidth configuration control capability. Each member port in a port group is provided with controlling capability for traffic shaping and bandwidth priority. Average bandwidth, peak bandwidth, and burst size can be configured for transmission and reception.
Network QoS does not support the limitation of traffic between two VMs on the same host.
Storage QoS
The virtualization platform supports storage QoS, that is, setting the data read and write I/O upper limit for a VM disk. Any I/O operation from the backend storage device on the VM cannot exceed the configured I/O limit.
This is what I want to share with you today, thank you!
