• Corpus ID: 2705898

Live migration of virtual machines

@inproceedings{Clark2005LiveMO,
  title={Live migration of virtual machines},
  author={Christopher Clark and Keir Fraser and Steven Hand and Jacob Gorm Hansen and Eric Jul and Christian Limpach and Ian Pratt and Andrew Warfield},
  booktitle={NSDI},
  year={2005}
}
Migrating operating system instances across distinct physical hosts is a useful tool for administrators of data centers and clusters: It allows a clean separation between hard-ware and software, and facilitates fault management, load balancing, and low-level system maintenance. By carrying out the majority of migration while OSes continue to run, we achieve impressive performance with minimal service downtimes; we demonstrate the migration of entire OS instances on a commodity cluster… 
Performance Study of Live Virtual Machine Migration using KVM Hypervisor
TLDR
In this report performance evaluation of post-copy live migration is presented along with proper mathematical modeling and this model can be used to estimate the Downtime, Resume Time and Total Migration Time of a VM being transferred using post- copy live migration.
Efficient Live Migration of Linux Containers
TLDR
This paper proposes a novel approach for live migration of containers to address this issue by utilizing a recently published CRIU feature, the so-called “image cache/proxy”, which allows for better total migration time and down time of the container applications that are migrated by avoiding the use of secondary storage.
A quantitative study of virtual machine live migration
TLDR
An automated testing framework is developed that measures important performance characteristics of live migration, including total migration time, the time a VM is unresponsive during migration, and the amount of data transferred over the network during migration.
Dependable Estimation of Downtime for Virtual Machine Live Migration
TLDR
A new model for estimating the worst-case values of migration time and downtime in live migration is presented, based on a small set of input parameters characterizing the application load and the behavior of the host, which shows that total migration time as well as downtime are influenced by the memory utilization pattern inside the virtualized system.
Live Virtual Machine Migration via Asynchronous Replication and State Synchronization
TLDR
Experimental results show that the CR/TR-Motion approach can drastically reduce migration overheads compared with memory-to-memory approach in a LAN, and for a variety of workloads migrated across WANs, the migration downtime is less than 300 milliseconds.
Nomad: migrating OS-bypass networks in virtual machines
TLDR
Nad, a design for migrating modern interconnects with intelligent NICs pose significantly more challenges as they have additional features including hardware level reliable services and direct I/O accesses, is presented, focusing on cluster environments running VMs.
Cost of Virtual Machine Live Migration in Clouds: A Performance Evaluation
TLDR
The effects of live migration of virtual machines on the performance of applications running inside Xen VMs are evaluated and it is shown that, in most cases, migration overhead is acceptable but cannot be disregarded.
Efficient live migration of virtual machines using shared storage
TLDR
This work presents a technique to reduce the total time required to migrate a running VM from one host to another while keeping the downtime to a minimum and has implemented the approach into the Xen hypervisor and ran a series of experiments with Linux HVM guests.
Heterogeneous Live Migration of Virtual Machines
TLDR
This paper proposes Vagrant, a live migration framework which bridges the heterogeneity among diverse VMM abstractions and implementations, and implements a prototype, that supports live VM migration between the Xen VMM and KVM.
Live migration of virtual machine based on full system trace and replay
TLDR
The design and implementation of a novel approach CR/TR-Motion is described that adopts checkpointing/recovery and trace/replay technology to provide fast, transparent VM migration and can greatly reduce the migration downtime and network bandwidth consumption.
...
...

References

SHOWING 1-10 OF 36 REFERENCES
The design and implementation of Zap: a system for migrating computing environments
TLDR
The paper demonstrates that the Linux Zap prototype can provide general-purpose process migration functionality with low overhead and results for migrating pods show that these kinds of pods can be migrated with subsecond checkpoint and restart latencies.
Self-migration of operating systems
TLDR
This paper presents two prototypes that allow migration not only of an application but also of the operating system running the application, and includes a novel approach, self-migration, to operating system migration.
Optimizing the migration of virtual computers
TLDR
This paper shows how to quickly move the state of a running computer across a network, including the state in its disks, memory, CPU registers, and I/O devices, and calls this state a capsule, and suggests that efficient capsule migration can improve user mobility and system management.
Attacking the process migration bottleneck
TLDR
Copy-on-reference shipment is shown to successfully attack the bottleneck in process migration in the Accent distributed computing environment, and the number of bytes exchanged between machines as a result of migration and remote execution drops, and message-handling costs are cut.
Constructing Services with Interposable Virtual Hardware
TLDR
The design, implementation, and evaluation of µDenali are presented, an extensible and programmable virtual machine monitor that has the ability to run modern operating systems and an application-level API that simplifies writing extensions is presented.
Process migration
TLDR
This survey reviews the field of process migration by summarizing the key concepts and giving an overview of the most important implementations, and then revisited for each of the case studies described.
Preemptable remote execution facilities for the V-system
TLDR
It is argued that preemptable remote execution allows idle workstations to be used a a "pool of processors" without interfering with use by their owners and without significant overhead for the normal execution of programs.
Transparent process migration: Design alternatives and the sprite implementation
TLDR
The Sprite operating system is used to offload work onto idle machines, and also to evict migrated processes when idle workstations are reclaimed by their owners, providing a high degree of transparency both for migrated processes and for users.
The Sprite network operating system
TLDR
The discussion covers: the application interface: the basic kernel structure; management of the file name space and file data, virtual memory; and process migration.
...
...