| Version 41 (modified by lvpeng, 13 years ago) (diff) |
|---|
Welcome to HAVEN Project
High availability (HA) refers to a system and associated service implementation that is continuously operational for a long period of time. With respect to the clients, an ideal system never stops working, which also means the system will always respond to the clients’ requests. Whole-system replication is a conventional way to increase the system availability: once the primary machine fails, the running applications will be taken over by the backup machine. However, there are several limitations that make this method unattractive for deployment: it needs specialized hardware and software, which are usually expensive. The final system also requires complex customized configurations, which makes it hard to manage efficiently.
As virtualization becomes more and more prevalent, we can overcome these limitations in the virtual world. All the applications are running in the VM, so now it’s possible to implement the whole-system replication in an easy and efficient way — by saving the copy of the whole VM running on the system. As VMs are totally hardware-independent, the cost is much lower compared to the hardware expenses in traditional HA solutions. Besides, virtualization technology can facilitate the management of multiple VMs on a single physical machine. With virtual machine monitors (VMM), the service applications are separated from physical machines, thus provides increased flexibility and improved performance.
HAVEN means "High Availability in Virtualized Environment with Networking". It consists of several finished and ongoing projects which aim on addressing the availability and reliability challenges in virtualized system. HAVEN focus on providing transparent and comprehensive high availability (HA) to solo and multiple virtual machines (VM) running on The Xen Hypervisor. Most projects under HAVEN are based on Xen 3.4 VMM but they can easily be ported to more recent releases of Xen. HAVEN does not require any modification to the application and operating system (guest OS) inside the VMs, therefore although HAVEN is developed based on Xen, the ideas in HAVEN also benefit other VMMs with full virtualization.
HAVEN In Progress
- VDEchp -- Global Consistent Checkpoint for Virtual Distributed Environment
- FGBI -- Fine-Grained Block Identification
- LLM -- Lightweight Live Migration
Use HAVEN
Prerequisite
- Install the linux kernel -- Currently we use CentOS, but other OS like Fedora is also fine.
- Download and install Xen Hypervisor
- Install Remus for sub-projects LLM and FGBI -- Skip this if only want to try VDEchp
Start Using HAVEN
Documentation & Publications
Related Efforts
Some related and parallel projects with HAVEN are as following:
- The Xen Hypervisor -- Xen Open Source Industry Standard For Virtualization
- The Remus project -- Remus: Transparent High Availability For Xen
- The Kemari project -- A VM Synchronization Mechanism For KVM
- The VNsnap project -- Take A Snapshot For Entire Virtual Networked Environment
