Tintri VM Scale-out Storage
Scale-out storage made simple
Overview:
Scale out your storage as easily as your compute
No more manual effort. Tintri treats up to 64 systems as a federated pool of storage, and underlying offload tech leverages Tintri replication to move VMs of any size or quantity in minutes. Plus, machine learning optimizes VM placement, so all you need to do is hit “execute.” Start with one 17 TB array and scale up to 40 PB with ease.
Forget conventional storage scale-up and scale-out solutions. Those are expensive and hardware-dependent, and require a team of storage PhDs to manage them. What if you could scale-out your storage the same way you scale-out compute in your enterprise cloud and virtualized environment: by just adding another server and letting the hypervisor manager optimize VMs across the pool? Now you can with Tintri Enterprise Cloud.
FIGURE 1: VM Scale-out recommends actions that will optimize the placement of applications across your storage pool.
5 THINGS YOU WILL LOVE ABOUT VM SCALE-OUT
- VM Scale-out optimizes your VMs based on a complete picture of their storage capacity and performance needs.
- Gives you least-cost recommendations, saving you time, bandwidth and capacity, to maintain optimal VM distribution.
- You can review and edit the recommendations, and see the outcome before committing.
- VM Scale-out learns every time you edit its recommendations and allows you to opt certain VMs out of migration.
- Allows you to start small, with as few as 17TB and a couple hundred VMs, all the way to 480,000 or more with the same storage team you have today
Features:
Deep workload analysis
Tintri VM Scale-Out software always works in the background, analyzing up to one million statistics about your applications every ten seconds. It looks back 30 days to capture performance peaks, not just averages, to better inform its recommendations and your decisions.
Optimize workload placement
Machine learning algorithms recommend the optimal placement of each of your applications, considering snapshots, clones, thin provisioning and storage activity to minimize impact on capacity and performance. Plus, array offloaded data transfer for storage live migration reduces migration time from hours to minutes. Just hit "execute" and Tintri does the rest.
Attach policies to applications like glue
And as your applications are moved around your virtual footprint, the data protection and QoS policies you’ve set for them will follow—as do snapshots and clones—without any manual intervention. So the policies you set when you have 500 applications remain intact as you grow past 5,000 applications.
VM Scale-out Differentiation
- Identify issues
Based on 30 days of historical data, VM Scale-out looks forward a week, looking for ways to optimize VM distribution within a pool of VMstores. - Recommend actions
VM Scale-out finds the best location for every individual virtual machine, factoring in time, data movement, and capacity utilization. Edit the recommendations and VM Scale-out learns. - Predict outcomes
If you accept the recommendation, VM Scale-out tells you what the result will be and how long it will take to execute. With storage live migration offload, you can execute the recommendation in a matter of minutes instead of hours.
Conventional storage scale-out was not designed for today’s cloud and virtualized applications. TIntri was designed to simplify workload scaling—with our CONNECT architecture and VM Scale-out technology you can manage up to 480,000 VMs from one central console:
- Federated pool of storage: Treat multiple systems as a pool of storage, simplifying management, planning and resource allocation.
- Scalability and performance: Scale to more than one million VMs, with separation of control flow from data flow that ensures low latency and high scalability.
- Compatability: Scale from small to very large with new and existing systems, whether they’re all flash or hybrid, or partially or fully populated systems.
- VM and software-based: Deliver consistent performance for virtualized and cloud applications, instead of inflexible hardware solutions requiring proprietary interconnects and specialized vendor training.
- Scale compute and storage independently: Loose coupling of storage and compute provides customers with the maximum flexibility to scale these elements independently.
Documentation:
Download the Tintri VM Scale-out Datasheet (PDF).