Toward dependency-aware live virtual machine migration

The most powerful characteristic of any machine virtualization technology is its ability to adapt to both its underlying infrastructure and the applications it supports. Possibly the most dynamic feature of machine virtualization is the ability to migrate live virtual machines between physical hosts in order to optimize performance or avoid catastrophic events. Unfortunately, the need for live migration increases during times when resources are most scarce. For example, load-balancing is only necessary when load is significantly unbalanced and impending downtime often causes many virtual machines to seek new hosts simultaneously. It is imperative that live migration mechanisms be as fast and efficient as possible in order for virtualization to provide dynamic load balancing, zero-downtime scheduled maintenance, and automatic failover during unscheduled downtime.

This paper proposes a novel dependency-aware approach to live virtual machine migration and presents the results of the initial investigation into its ability to reduce migration latency and overhead. The approach uses a tainting mechanism originally developed as an intrusion detection mechanism. Dependency information is used to distinguish processes that create direct or indirect external dependencies during live migration. It is shown that the live migration process can be significantly streamlined by selectively applying a more efficient protocol when migrating processes that do not create external dependencies during migration.