Remus: High Availability via Asynchronous Virtual Machine Replication. (Best Paper)
By Brendan Cully, Geoffrey Lefebvre, Dutch T. Meyer, M. Feeley, N. Hutchinson, A. Warfield. Symposium on Networked Systems Design and Implementation, 2008
686 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/881061ab139a89fe629f5663c6da2db43c186493
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Andreas Haeberlen
- Byung-Gon Chun
- Paarijaat Aditya
- Rodrigo Seromenho Miragaia Rodrigues
- Peter Druschel
- Petros Maniatis
- Andrew Colin Rice
- Mohammad Shahrad
Citations in the corpus
- Survey (2016, background): “Lock stepping [Bressoud et al. 1996; Scales et al. 2010], checkpointing replication [Cully et al. 2008], and COLO (COarse-grained LOck-stepping virtual machine) [Dong et al. 2013] are the main fault tolerance approaches for memory synchronization.”
- Post-copy based live virtual machine migration using adaptive pre-paging and dynamic self-ballooning (2009, background): “Recently, in a different context (4), similar mechanisms have been successfully used to provide high availability.”
- Post-copy live migration of virtual machines (2009, unknown): “Recently, in a different context [4], simi-”
- Accountable Virtual Machines (2010, background): “However, snapshotting techniques have become very efficient; recent work on VM replication has shown that incremental snapshots can be taken up to 40 times per second [11] and with only brief interruptions of the VM, on the order of a few milliseconds.”
- Augmented Smartphone Applications Through Clone Cloud Execution (2009, background): “The primary performs speculative execution , which has been used in local and distributed file systems and virtual machine replication for high availability [14,24,25] while invoking augmented execution.”
- Availability Knob: Flexible User-Defined Availability in the Cloud (2016, background): “Each diagonal distribution in the plot corresponds to users with the same fraction of their VMs being paused at the end of a period, and in particular, dots on the bisector correspond to the case where all VMs of a user experienced DDT.”
- Predicting the Performance of Virtual Machine Migration (2010, background): “The Remus project provides a high degree of fault tolerance using asynchronous virtual machine replication [23].”