Full Redundancy

Full Network Failover Redundancy

Our cloud infrastructure (network, hypervisor and SAN storage) is clustered and fully redundant down to every router and switch. Our entire cloud infrastructure is powered by Intel, Cisco, and Dell™ equipment.

We have failover routers configured at each layer to ensure your website and applications are accessible at all times, even in the event of a single router failure. The first layer of failover routers is setup with a direct connection to the Internet and the second layer failover routers is dedicated to the cloud, the hypervisor, and the SAN storages. We use Open-E storage systems with built-in redundancy to withstand entire system, network, drive, or power failures with zero downtime.

Live Migration

With Live Migration, scheduled downtime will be history. Live Migration allows us to move VMO instances between hardware nodes in the same cloud zone without service interruption. Thus, hardware maintenance and upgrades are virtually unnoticeable for end users and website visitors.

Full Server Hardware Failover Redundancy (HA)

Redundancy and fault tolerance ensures that service is always available even in the event of a failure. Redundancy is basically extra hardware that is used as backup in the event the main hardware fails. High redundancy is achieved by automatic failover, and more so when the backup device is completely separate from the primary device. This way, the backup device automatically takes over until the failed primary device is back up and running.
The DevHost cloud setup is a multi-hypervisor cloud system and is configured and connected to your control panel. Each VM in your cloud is hosted by a hypervisor. It is from the hypervisor that the VM receives CPU time, RAM, network and other hardware and system resources.
In the event of a hardware component failure, VMs stored in the failed hypervisor will be automatically recreated in available, active hypervisors. Because your data is not stored on the VM, but rather on the SAN storage, your data would not lost in the event of a hardware failure. The recreated VMs would simply retrieve your data from the SAN storage systems through the use of optic fiber connections. This ensures highly efficient use of available hardware and complete isolation of virtual server processes, thus ensuring availability at all times.

Full Storage Failover Redundancy (MPIO* and Real-time Replication)

A storage area network (SAN) is a dedicated network that provides access to consolidated data storage devices. When hosting with DevHost, your data is stored on the DevHost SAN, separate from your VMs.
Our SAN is made up of two duplicated storage arrays: primary and secondary.

This allows real-time data replication and storage on two separate arrays. Should the primary SAN fail, the hypervisors will re-route data from the secondary SAN via the MPIO* methodology.
* MPIO stands for multipath I/O, which is a fault-tolerance and performance enhancement technique that establishes multiple parallel paths between devices. This allows the avoidance of a particular path in an interrupted stream and load balancing over available resources.