[FAQ] Does the Huawei FC Support FT?

hello,
High availability (HA) is the ability to shorten the unplanned shutdown time due to hardware faults to improve the system and application availability. Different from the fault tolerance (FT) technology that does not interrupt services, HA is regarded in the industry as the most effective measure to prevent core computer systems from shutting down due to hardware faults.
The Huawei FusionSphere virtualization solution supports HA for VMs within a cluster.

Thanks

Hello, dear!

FT is supported in POC but cannot be put into commercial use.

FT needs configuration of twice resources, and service zero interruption is required in few scenarios. Huawei's virtualization technology already supports HA, and service interruption duration equals to that of restarting the VM. Therefore, basic requirements can be met.

l   FT requires the primary and secondary VMs run at the same time. The two VMs always occupy resources, featuring high cost.

l   FT has restrictions on the number of VM cores and is not applicable to all VMs. Therefore, it is not practical for customers. (The maximum number of fault-tolerant VMs supported by a VMware host is 4, and that of vCPUs for all fault-tolerant VMs across hosts is 8.)

l   FT has high network requirements. It is recommended that the FT dedicated network be used, increasing the network complexity.

l   The hardware CPU models on the primary and secondary VMs must be consistent. The deployment becomes difficult.

l   All mainstream virtualization vendors provide the HA mechanism to ensure high availability of virtual servers.

Any further questions, let us know!

hy
Latency is a key performance indicator for carrier-class applications. Telecom applications are typically composed of multiple virtual machines that communicate frequently with one another. Compared with dedicated physical hardware, typical enterprise-class virtualization adversely affects the communication performance of applications. Based on innovative technologies, FusionSphere hypervisor improves the communication performance of VMs by 1.5 to 3 times, greatly reducing the latency, and enabling traditional carrier-class applications to be smoothly migrated to the cloud platform.
FusionSphere’s cloud resource scheduling engine has been optimized for telecom applications, allocating virtualized resources according to "affinity" between network elements, thus achieving high performance  and high reliability, allowing network elements to migrate from specialized hardware to standard x86 servers.

When deploying telecommunication network elements in the cloud, each virtual machine can be located based on "performancepriority". A logical network element contains multiple VMs working together to provide a complete service function. Using the "performance priority” policy, FusionSphere will ensure that all the VMs for that logical network element stay close physically in the network topology to guarantee optimized latency and throughput between VMs. To meet the requirements of IT and communication applications, FusionSphere provides reliability mechanisms independent of applications, such as high availability (HA) and lightweight fault tolerance (FT). High performance, high reliability, and low latency enable a better user experience in the environment of network function virtualization (NFV)

Great info :)