Cloud Based Services

Unified Storage

Technology Bridge offers a block-based interface to Virtual Machines while using object-based storage as Tier 2. It creates a unified, single pane of glass on the storage and abstracts the storage specific behavior from the hypervisor. For the hypervisor it looks like it is using shared storage such as a NAS. This means that high availability features such as vMotion (VMware) or Live Migration (KVM) are supported out of the box. Open vStorage offers each host in the cluster a shared Virtual File System but other interfaces like iSCSI are also possible.

Leverage Server side Flash Acceleration

Technology Bridge uses SSD devices and PCIe flash cards inside the host as Tier 1 storage. Due to this aggressive caching on the host where the Virtual Machine is running, the performance is unmatched in the storage industry. To maximize the amount of data in the cache, a deduplicated read cache is used. As Virtual Machine writes are performed on low latency flash, it results in fast acknowledgements of writes to the Virtual Machine file system and a high capacity throughput. When data is no longer required inside the Tier 1 storage, it gets pushed to the Tier 2 storage at a slower pace to make space for new data.

Turn Object Storage into block-based VM storage

Technology Bridge is today the standard to build scale-out storage. But due to technical hurdles such as eventual consistency and performance it is impossible to run Virtual Machines directly on top of an Object Store. Technology Bridge is the answer to turn these object-based storage solutions into a block-based, high performance, distributed, VM-centric storage platform. Technology Bridge supports almost any object storage solution as Tier 2 storage. Out of the box it supports S3 compatible object stores such as Ceph, Swift, Cloudian, etc but even the new and upcoming ethernet disks, such as the Seagate Kinetic drive, are supported. When data is no longer required in the Tier 1 storage, it is pushed to the object-based Tier 2 storage. There it can be encrypted and compressed. Technology Bridge also supports Forward Error Correction technology to spread data across multiple disks in the object store. This allows to save about 50% on hardware costs compared to 3-way replication and ensures at the same time a higher protections against dataloss.

Distributed Transaction Logs

Technology Bridge uses a Distributed Transaction Log to make sure no data is lost when a host goes down. When a Virtual Machine writes data to the cache, the write is synchronously to another host in the cluster by means of a Distributed Transaction Log. In case the host running the VM goes down, the Virtual Machine is restarted on another hosts using the data from the Tier 2 storage and the latest data in the Distributed Transaction Log.

Asymmetric Scale Out Architecture

Technology Bridge is build to be hyperscale. It even allows to scale CPU, storage capacity and storage performance independently. This allows for asymmetric scale-out of your cluster. To increase the CPU and RAM for the Virtual Machines, add more hosts. To increase the Tier 1 storage performance, add more SSDs or PCIe flash to the mix. Storage capacity can also be seamlessly increased by adding more storage nodes or disks to the Tier 2 storage. With Technology Bridge any size of environment can be addressed whether it is small or datacenter wide.

Virtual Machine Centric

Gone are the days where Storage administrators where diving into LUNs and iSCSI targets. These storage paradigms are something of the past as they are too complex to manage. The new way of storage management brings the management to a higher level in the stack: the VM-level. With VM-centric storage management, you are no longer managing the underlying disks or hardware but are managing the snapshots at VM-level. You can easily set a snapshot policy and retention period per Virtual Machine or even per Virtual Disks. The Replication becomes for example something you set for a single VM and not for a complete LUN. This higher level of management brings down the management overhead and accompanying storage cost.

Multiple Hypervisors

Single hypervisor environments are more and more becoming something of the past. There are various reasons (license costs, hypervisor specif functionality, …) to have a mix of hypervisors in your environment. That is why Open vStorage is designed to support all major hypervisors.

Apache 2.0 Open Source License

We are firm believers in the approach taken by hyperconverged appliances where software running on a cluster of machines provides you a reliable storage pool and where the storage intelligence is moved closer to the compute layer. However, we believe this is too important a piece of the virtualization stack for a proprietary solution that is either hypervisor specific, hardware specific, management stack specific and storage back-end specific. Our goal behind Open vStorage is not only build something open and non-proprietary but something modular enough which allows developers to innovate on top of Open vStorage. We believe with contributors from the open source community Open vStorage can become a far superior software compared to proprietary offerings.