Mission-Critical Readiness
Application Storage Awareness
Simple Installation
Use Existing Storage
VMware Integration with VASA
Integrating The Cloud
Integrating The Cloud

Mission-Critical Readiness

DataSphere proactively prevents failure and information loss, and provides the ability to recover when faults do occur. These capabilities provide enterprise reliability, accessibility and serviceability without impact to ongoing I/O.

DataSphere is architected to provide fail overs and backups of its metadata. The metadata is synchronously copied between DataSphere pairs to protect against component failures. In the event that a DataSphere node fails, operation automatically failsover within seconds to a paired DataSphere to ensure there is no disruption to applications I/O. It is important to note that with DataSphere out of the data path, no in-flight data requests are impacted when a failover event occurs. Resiliency is built into the communication protocols between DataSphere and the clients to ensure no metadata requests are lost during the fail over process.

This ability allows non-disruptive software updates as each DataSphere node is updated in an orchestrated (rolling cluster update) sequence that is transparent to clients. Further, the metadata is backed up and can be restored to protect against the most extreme failure events.

The overall DataSphere architecture ensures a higher level of operational performance by eliminating all single points of failure through redundancy, and non-disruptive maintenance during normal operations.

Give Your Applications Intelligent Storage Awareness

Applications and storage have long been blind to each other’s capabilities and needs. The majority (if not nearly all) of today’s enterprise applications do not know the attributes of the storage where its data resides. Applications cannot tell if the storage is fast or slow, premium or low cost.

Conversely, storage does not know what data is the most important to an application. It only knows what was recently accessed, and uses that information to place data in caching tiers, which will increase performance if that same data happens to be accessed again. However, caching tiers do not have the intelligence needed to protect capacity for mission-critical applications, which can cause serious performance inconsistency or require more cache.

DataSphere gathers metadata intelligence in real-time to understand how applications experience storage (for example latency, IOPS and bandwidth). It also collects telemetry on the data that applications access, such as which files are open, closed, with modified dates and times, as well as any other metadata.

Open standard data and I/O access-based protocol stacks in the client make this possible. The recent release of NFS 4.2 includes enhancements to the Parallel Network File System (pNFS) Flex File layout that allow clients to provide statistics on how data is being used, and the performance provided by the storage resources serving the data. These advanced features are already being rapidly adopted, as the most recent release of Red Hat Enterprise Linux 7.3 features Flex Files support to simplify management of Parallel NFS (pNFS) clusters. DataSphere DSX enables the same capabilities with legacy protocols such as NFS v3, SMB 2.1 and SMB 3.x.

Products | Primary Data

With the ability to collect analytics from individual clients on single data objects, DataSphere can analyze application workloads, priority, historical trending, and available storage resources, comparing real-time activity against business objectives defined by IT and application administrators. DataSphere then automates data management for NFS, SMB, VMware ESXi clients across datacenter and cloud based resources, moving data to the most appropriate resource without application interruption.

Simple Installation and Data Assimilation

DataSphere integrates easily into existing customer environments, enabling customers to be up and running within minutes of completing the DataSphere installation. With no required software changes on the client, or configuration changes on the storage, DataSphere installation and configuration completes in minutes. The only client configuration required is the NFS server IP; the shares are then mounted from DataSphere (or DSX depending on protocol) instead of the NAS storage. Data access can continue to be direct to the storage for modern Linux clients.

For existing NAS environments, DataSphere can assimilate the storage, or more specifically, assimilate the metadata of the data. The DataSphere in-place data assimilation process is non-disruptive for clients, as the metadata is collected on-demand as well as a background process.

Use Existing Storage

Enterprises don’t have to purchase any new storage to use DataSphere. As a metadata engine, DataSphere can integrate existing storage without moving any data. This makes it easy to start managing large amounts of data with DataSphere by integrating existing storage into the global namespace with minimal disruption.

DataSphere’s assimilation feature extracts metadata from existing NAS exports without the need to touch or move the actual data. DataSphere can take several exports from different vendors and then create a single new global namespace that can be shared as a single or many exports. Objectives can be applied to deliver performance and archive to the cloud in a single, uniform namespace.

Connecting different resources to the global namespace with DataSphere makes it possible to ensure all your storage investments are being used to serve data with the capabilities they deliver best, whether those attributes are peak performance, enterprise-grade protection, or low-cost capacity.

vSphere integration with VASA

DataSphere supports VMware VASA 2.0 APIs to enable VMware VVol support for VM granular management with offload snapshots and clones. Unlike other VVol solutions, DataSphere uses objectives to manage data, and non-disruptively moves virtual disks between storage tiers based on activity. This intelligence allows active VMs to be moved to fast storage to maintain compliance, while cold VMs move to lower cost storage to reduce costs.

DataSphere makes it simple to deploy Virtual Volumes with existing storage devices. Storage can include NAS, Block or Object/Cloud, with each providing differing performance and protection capabilities to create a datastore that can meet a wide range of SLOs.

Using vCenter workflows, admins create VM Storage policies to define the performance and protection needs of their VMs, and DataSphere will then automatically maintain compliance. DataSphere also integrates with vCenter to offload VM snapshots and clones, which enables rapid VM provisioning and better VM backup solutions.

DataSphere greatly simplifies VM and datastore management, automatically ensures VM compliance, reduces cost and increases business agility.

Integrating the Cloud on Your Horizon

DataSphere seamlessly integrates cloud-based storage with your datacenter infrastructure. With support for the ubiquitous Amazon S3 API, adding cloud end-points to your storage pool is non-disruptive and simple. You can add cloud storage (buckets) from any number of vendors (including on-premise object storage), with full control over what data goes to what cloud provider, whether it be for active archiving, or selective backups.

Additionally, WAN optimization is already built into DataSphere, as all data that is sent to the cloud is automatically de-duplicated and compressed. During transfer, a secure link is used to ensure that data remains safe.

Data mobility between the cloud and on-premise storage is automatic and transparent to the user. Files that require performance when opened are automatically transferred back to ensure application needs are met.

Finally, your data is not stuck in one cloud. Mobility between clouds is as simple as a single click and the data transfer is initiated, with data reduction automatically applied along the way.

Products | Primary Data

Enterprise Resource Management

Manage Over a Billion Files from a Single UI

DataSphere enables enterprises to serve and manage data at scale. The dashboard provides visibility of data activity and summarizes key performance metrics for files hosted across different tiers of on-premises storage and the cloud.

See Your Data in Motion

Products | Primary Data

DataSphere’s intuitive interface gives clear visibility into where and why data is moving, the data’s historical activity and why data was moved to maintain objectives.

Put Out All Your Fires

Poor visibility into application needs and storage usage can create unexpected problems and loss of business. The intelligence DataSphere provides helps IT avoid hot spots at storage, client and application levels:

Storage Hot Spots

Products | Primary Data

When too much data is trying to move through a single storage resource, the system becomes overloaded and performs poorly, while other storage tiers or arrays sit idle with free resources. DataSphere understands the real-time performance of each storage resource and dynamically balances I/O across storage tiers to meet data performance objectives.

Client Hot Spots

Mounting clients to dedicated storage means that IT cannot easily adapt to changing application and business priorities. Enterprises often overspend by over-provisioning, or risk client performance issues. DataSphere solves this by providing parallel data access across multiple storage devices and non-disruptively moving data when needed to meet changing performance needs. This eliminates the need to overprovision, while maintaining business Service Level Objectives and accelerating performance.

Application Hot Spots

In traditional architectures, mission critical applications can be starved by less important applications that are overloading shared storage resources. Enterprises typically overspend to manage this problem, and overprovision dedicated storage to meet Service Level Agreements. Managing by objectives with DataSphere protects mission critical applications by ensuring they are on the right storage at the right time, maximizing the efficiency of shared resources.

Storage Planning Made Simple

Products | Primary Data

With predictive analysis based on actual data activity, DataSphere automatically rebalances data across storage tiers to eliminate the cost of oversubscription. Alerts and notifications ensure admins know when they need to deploy more storage of a given type, and can recommend changes to objectives for better load balancing. When more performance or capacity is needed, IT can deploy new resources from any vendor in minutes instead of days or weeks. Once IT no longer has to worry about having to overprovision to deliver application performance, they can achieve significant savings that can easily run into the millions for petabyte-scale enterprises.

Contact Form

Channel Partner