pub:projects:parallel_vm_migration
Differences
This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
| pub:projects:parallel_vm_migration [2013/03/04 11:08] – created classicsong | pub:projects:parallel_vm_migration [2013/03/16 10:36] (current) – [Publications] root | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | Live VMmigration | + | ======Parallelizing |
| - | virtualized cloud platforms. | + | |
| - | a comprehensive analysis on the parallelization opportunities | + | Live VM migration |
| - | live VM migration on two popular open-source VMMs (i.e., Xen | + | virtualized cloud platforms. |
| - | and KVM). By leveraging abundant resources like CPU cores and | + | resources configured to a single |
| + | time-consuming, causing notable disruption to the running services. | ||
| + | In this project, we investigate how this process could be parallelized | ||
| + | on commodity multicore platforms. | ||
| + | |||
| + | === Faculty === | ||
| + | |||
| + | * [[pub: | ||
| + | |||
| + | === Students === | ||
| + | |||
| + | * [[pub: | ||
| + | |||
| + | |||
| + | =====Approaches===== | ||
| + | By leveraging abundant resources like CPU cores and | ||
| NICs in contemporary server platforms, we design and implement | NICs in contemporary server platforms, we design and implement | ||
| a system called PMigrate that leverages data parallelism and | a system called PMigrate that leverages data parallelism and | ||
| - | pipeline parallelism to parallelize the operation. | + | pipeline parallelism to parallelize the operation. |
| + | |||
| + | As the parallelization | ||
| + | framework requires intensive mmap/munmap operations that | ||
| + | tax the address space management system in an operating system, | ||
| + | we further propose an abstraction called range lock, which improves | ||
| + | scalability of concurrent mutation to the address space of | ||
| + | an operating system (i.e., Linux) by selectively replacing the perprocess | ||
| + | address space lock inside kernel with dynamic and fine grained | ||
| + | range locks that exclude costly operations on the requesting | ||
| + | address range from using the per-process lock. | ||
| + | |||
| + | =====Result===== | ||
| + | |||
| + | Evaluation with our | ||
| + | working prototype on Xen and KVM shows that PMigrate accelerates | ||
| + | the live VM migration ranging from 2.49X to 9.88X, and decreases | ||
| + | the downtime ranging from 1.9X to 279.89X. | ||
| + | |||
| + | |||
| + | =====Availability===== | ||
| + | |||
| + | The source code of this project includes three parts (each source code | ||
| + | includes a README file to show how to play with PMigrate): | ||
| + | - PMigrate for KVM: https:// | ||
| + | - PMigrate for Xen: https:// | ||
| + | - Range Lock Linux: https:// | ||
| + | |||
| + | ======Publications====== | ||
| + | * Xiang Song, Jicheng Shi, Ran Liu, Jian Yang, Haibo Chen. Parallelizing Live Migration of Virtual Machines. In Proceedings of 2013 ACM International Conference on Virtual Execution Environments (**VEE 2013**), March, 2013. [{{: | ||
| + | |||
| + | ======Acknowledgement====== | ||
| + | This research was funded by NetApp Faculty Fellowship. | ||
pub/projects/parallel_vm_migration.1362366527.txt.gz · Last modified: by classicsong