Live migration is typically defined as the migration of virtual machines (VMs) from one host to another with as minimal interruption as possible. This is done to ensure that businesses are constantly able to run on a physical host that is reliable and has sufficient resources.
In what is today known as the era of cloudification, live migration of virtual machines is a hot technology that has attracted widespread attention. As one of the core technologies of cloud computing, Sangfor has deeply researched virtual machine live migration in search of ways to accelerate and improve the process.
As more and more users deploy core services on the cloud platform, business applications require higher Service Level Agreement guarantees, which also means the highest standard available of the services provided. Live migration is not exempt from this. There is a need for the length of disruption experienced during migrations to decrease, going as far as organizations requiring zero downtime. The scenarios that may lead to downtime include:
- Maintenance of physical hosts, such as hardware replacement and service maintenance.
- Cloud platform upgrade that requires immediate upgrade of physical hosts in the cluster.
- The need for better resource utilization efficiency by the cloud platform.
- A server overload that requires migration to an underloaded server.
Oracle’s virtual machines carry 1000 concurrent users, making use of Sangfor HCI as the host of their business services. During migration, Oracle’s performance jitters for a mere 6 seconds, and the service interruption time is only 1 second. This means the upper-layer service can get a smooth migration experience with almost zero interruption. When compared to the test results of other hyper-converged products in the industry, the advantages of Sangfor HCI are evidently superior. So, how does Sangfor HCI achieve this?
The Innovation behind Sangfor HCI
Sangfor HCI is derived from the advantages of multiple underlying core technologies. One of these key technologies is the CPU throttling algorithm, the basic principle of which is as follows:
- In the initial stage of migration, the source host starts an identical virtual machine on the destination host through the negotiation mechanism and puts it into a quiesced state.
- After the source host QEMU records all the memory data of the virtual machine, it is transmitted to the destination host through the network. However, since the running business will read and write memory data during the transmission process, the newly generated memory data will be re-recorded after the first round of transmission is completed. It will transmit it to the destination host in the same way, and iterate in turn until the last recorded memory data meets a threshold, the source host will stop running- that is, only 1 second of service interruption duration.
- QEMU transfers the remaining memory data to the destination host at one time, then the destination host starts running, and the source host shuts down.
In this process, it may happen that the sequential iterations fail to converge, which will reduce the CPU utilization of the virtual machine and reduce the throughput of the business.
Furthermore, during the final downtime of the live migration, the ping network interruption time does not exceed 2 seconds (the best test result is 0 seconds).
The key manner in which Sangfor HCI optimizes is by designing a new algorithm, taking into account multiple indicators, such as the migration time and the time that the business is affected by throttling. Sangfor HCI ultimately reduces both of these factors.
The implementation of this technology enables the aforementioned use cases for migration to be completed successfully and with new ease.
In addition to the CPU throttling algorithm, Sangfor HCI has optimized the QEMU live migration compression algorithm, BITMAP data block granularity adjustment, RAM dirty data delay migration mechanism, RAM live migration time slice dynamic adjustment mechanism, and IO QoS dynamic adjustment mechanism.
Sangfor HCI’s efficiency is undeniable and unlike any other. It is certainly worth considering by organizations looking to speed up and smoothen their migration processes.
What are the Benefits of VMs and Migration?
- The most evident benefit -particularly emphasized by Sangfor- is the increased uptime. We understand the importance of minimizing downtime to avoid even the slightest halt in system processes, which is why we have continued to find ways to decrease interruption and avoid failure
- VMs allow organizations to easily upgrade their software and hardware
- Virtual machines are environmentally friendly. Virtualization reduces hardware and space requirements
- Cost savings. In the long run, opting for VMs is cost-effective
- Quick resource provisioning- Virtualized environments can be resolved quickly where disasters would affect physical servers indefinitely
- Better security and data protect
What is QEMU?
QEMU (Quick EMUlator) is a virtualization software that enables the running of programs on devices that would otherwise be incompatible; such as running a Windows program on OS or Linux.
What is required in order for live migration to take place?
A stable source that will not be damaged or altered by the outgoing migration is necessary, as well as a virtual machine that can be suspended and resumed without causing even the slightest failure
What might cause failure during migration?
- The hardware or software at the destination host is not compatible with that of the source host
- Slow network connection
- The destination machine has not been configured to receive migrations
While there are many other possible diagnoses, and they may even differ across platforms being used for migration, these are a few of the common issues.
What is Sangfor HCI – Hyper Converged Infrastructure?
Sangfor HCI (Hyper-Converged Infrastructure) is the new generation of cloud IT architecture that is built on the innovative 3rd generation, hyper-converged infrastructure platform. By converging compute, storage, networking and security on a single software stack, Sangfor HCI provides a 1-stop software-defined data centre solution which is extremely simplified in architecture, ultimately reliable for business-critical applications and dramatically easy to use in management.