Hello, everyone!
This post will show you the DVS.
1. What is DVS?
FusionCompute supports DVSs running on computing nodes. Complete virtual switching is implemented on server CPUs. A virtual port is assigned to a virtual NIC of a VM for virtual switching, and physical NICs of a server function as virtual switching uplink ports.
A DVS has the following features:
High performance in internal server communication. A DVS can implement layer 2 forwarding of packets among VMs on a server using software.
Moderate performance in cross-server communication. For a server CPU, the cross-server communication requests must be forwarded by a physical switch. Therefore, the virtual switching performance is inferior to a physical switch.
Flexible scalability. Unlike physical switches that use layer 3 chips, servers use only software to implement virtual switching, which provides flexible and rapid scalability to better extend cloud computing networks.
Large size of server memory. The layer 2 switching capability and access control list (ACL) capability of a server is much greater than those of a physical switch.
In addition, FusionCompute supports virtual switching capability provided by single-root I/O virtualization (SR-IOV) NICs.
A DVS provides virtual network security capability, preventing VM IP address spoofing.
2. Current status of virtual switching
Virtual switching modes are classified as server-based virtual switching, which is called layer 2 virtual switchings, and switch-based virtual switching.
Server-based virtual switching can be implemented using a CPU or NIC.
In summary, virtual switching can be implemented on a server CPU, server NIC, and physical switch.
CPU-based Virtual Switching
The CUP-based virtual switching is a mature and well-commercialized technical plan. Full virtual switching is implemented on a server CPU. A virtual port is assigned to a virtual NIC of a VM for virtual switching and physical NICs of a server function as virtual switching uplink ports.
The packet forwarding mechanism of a VM is as follows: A DVS receives Ethernet packets from the source virtual or physical port, queries the layer 2 forwarding table for the destination port based on the MAC address and VLAN of the VM, and forwards the packet to the VM through the destination virtual or physical port.
The characteristics of this plan are as follows:
1. High performance and low delay in packet forwarding between VMs on the same server
2. High performance in layer 2 software forwarding among VMs powered by the DVS
3. Moderate performance in cross-server communication. For a server CPU, the cross-server communication requests must be forwarded by a physical switch. Therefore, the virtual switching performance of the CPU is inferior to a physical switch.
4. Flexible scalability. Unlike physical switches that use layer 3 chips, servers use only software to implement virtual switching, which provides flexible and rapid scalability to better extend cloud computing networks.
5. Large size of server memory. The layer 2 switching capability and access control list (ACL) capability of a server is much greater than those of a physical switch.
Physical NIC-based Virtual Switching
The physical NIC-based virtual switching function is designed to enable an intelligent network interface card () to implement virtual switching. In addition, when NIC performance is improved, a DVS uses less CPU resources so that VM performance is improved. With the help of the passthrough function of physical NICs, the virtual switching performance is enhanced.
Traditional Single-Root I/O Virtualization (SR-IOV) NICs for commercial use can also support virtual switching functions. However, due to its design limitation and no interaction with the hypervisor, SR-IOV NICs can hardly support live migration and other virtualization features.
Figure 1 SR-IOV-based virtual switching mechanism
Physical NIC-based virtual switching has the following characteristics:
Compared with DVSs that use Virtual Ethernet Bridge (VEB) for data exchange, NIC-based virtual switching reduces CPU usage because NICs are directly used for virtual switching and no CPU is required for virtual switching.
When the passthrough function is enabled for a physical NIC, the delay of packet forwarding from a VM to the physical NIC is dramatically reduced. This is because the passthrough function enables a VM to connect to a PCI Express (PCIe) device.
Traditional physical NICs for commercial use do not support live migration or flexible security isolation, and are difficult to implement function extension.
3. Huawei Distributed Virtual Switches Solution
A Huawei DVS consists of centralized DVS management modules. The centralized management modules provide a unified portal for configuration, thereby simplifying user management.
Figure 2 Virtual switching scenario
The DVS on each physical server provides VMs with capabilities, such as layer 2 communication, isolation, and quality of service (QoS).
The DVS model has the following characteristics:
Multiple DVSs can be configured, and each DVS can serve multiple CNA nodes in a cluster.
A DVS provides several virtual switch ports (VSPs) with their own attributes, such as the rate, statistics. The ports with the same attributes are assigned to a port group for management. The port groups with the same attributes use the same VLAN.
Different physical ports can be configured for the management plane, storage plane, and service plane. An uplink port or an uplink port aggregation group can be configured for each DVS to enable external communication of VMs served by the DVS. An uplink aggregation group comprises multiple physical NICs working based on load balancing policies.
Each VM provides multiple vNIC ports, each of which can connect to a unique VSP.
Administrators or users can specify a server, which allows layer 2 migration in a cluster, to create a virtual layer 2 network based on service requirements and configure the subnet and VLAN used by this network.
Figure 3 DVS model
Table 1 Parameters required for virtual switching
Name | Description | Remarks |
Port Group | Specifies a port group that consists of multiple ports with the same attributes. | Setting port group attributes, including bandwidth QoS, layer 2 security attributes, and VLAN ID, facilitates VM port group attributes setting. The port group attributes setting has no impact on the proper running of VMs. |
Uplink Port | Specifies an uplink that connects to the host and the DVS. | Administrators can query information about an uplink, including its name, traffic rate, mode, and status. |
Uplink Aggregation | Specifies a subfunction that allows multiple physical ports on a server to be bound as one port to connect to VMs. | Administrators can set the bound ports to loading balancing mode or active/standby mode. |
That's all, thanks!