We all know that there is a lot of wasted space in most VM storage repositories due to duplicate data. (Or we should.) But what isn’t as well known is the way the disk storage is configured can introduce a lot of delays in its throughput. This is because most storage arrays aren’t aware of the peculiarities of how VMs have to store their data on the specific blocks of their arrays, and the array can waste time seeking and retrieving information from its VMs.

A way around this is to re-align your VMs to make sure their information is stored properly on the array, but until now this has been a fairly complex process. Tintri is attempting to resolve this and other VM storage issues with its second-generation VMstore hardware storage appliance. Most of its storage input/output comes from its built-in flash memory and the new version has dual storage controllers for added redundancy.

The VMstore comes with the ability to do auto-alignment, to boost performance by anywhere from 10 to 20 percent. VMware is currently supported and other hypervisors are planned for the near future. Here is a description of the underlying issue.

The array has some additional features, including the ability to have visual and quantitative (real-time and historical) “end-to-end latency” from the application all the way down to the block storage level. You can now tell where your storage bottlenecks are, and be able to determine if you have throughput or application layer issues. Dashboard can either be run from a browser, as you see here, or fit inside a tab on vSphere’s vCenter.

Product Range

Tintri VMstore™ is the first storage solution designed exclusively for virtual machines (VMs). Traditional shared storage solutions require complex configuration, specialized knowledge and are cost-prohibitive to deploy in virtual environments. With Tintri VMstore, VM admins get simple, fast storage and can focus on managing VMs, not LUNs or volumes.

VMstore T445 VMstore T540
CHASSIS 4U, single controller 3U, dual-controller
9 x 160GB, hot-plug RAID6
15 x 1TB, hot-plug RAID6
8 x 300GB, hot-plug RAID6
8 x 3TB, hot-plug RAID6
Dual Gigabit Ethernet (RJ-45/Cat-5)
Dual-port 10Gb (fibre, SFP+ or copper)
2x Dual Gigabit Ethernet (RJ-45/Cat-5)
2x Dual-port 10Gb (fibre, SFP+ or copper)
POWER SUPPLIES Hot-plug redundant , 500W typical Hot-plug redundant, 500W typical
VMware vSphere™ 4.x and 5.x via NFS
Microsoft® Internet Explorer® 8.x or later; Mozilla Firefox™ 3.6 or later
VMware vSphere™ 4.x and 5.x via NFS
Microsoft® Internet Explorer® 8.x or laterMozilla Firefox™ 3.6 or later
Download Datasheet Download Datasheet


Manage VMs directly

Manage virtual machines directly using Tintri VMStoreSpend less time managing and troubleshooting VM and storage interactions.Tintri VMstore™ is VM-aware and eliminates complexity by relating the storage infrastructure directly to the VMs and business applications. There are no LUNs or volumes, tiers, RAID groups or other traditional storage objects that create complexity in a virtualized environment. Provisioning storage for VMs is simpler and faster. VMware™ administrators will feel right at home: The VM objects in VMstore are the same ones used in VMware vCenter™, and the VMs and vDisks will be familiar to VMware vSphere™ users.


Instant VM bottleneck visualization

Instant storage bottleneck visualization

Diagnose VM performance issues instantly. VM administrators dread troubleshooting performance bottlenecks. It is one of the most tedious VM management tasks. Triage meetings are often described as “pin the blame meetings.” Is it the host, network, storage or something else? With Tintri VMstore, administrators now have easy, instant visibility — from the guest OS layer to the storage layer. They can see per-VM or per-vDisk latency at any infrastructure layer, identify the source of performance issues, and take immediate action. VMstore also maintains historical latency data automatically, giving administrators a graphical seven-day view of performance.

Interchangeable datastores

VM-aware storage diagramGet the right quality of service for all your VMs. Tintri VMstore offers interchangeable storage resources — just like the CPU, memory and networking resources on your host servers. A hybrid flash/disk architecture allows VMs the right level of resources when they need it — without the complexity or cost of managing traditional shared storage. Virtualization-resistant applications can now easily be virtualized. Unlike other storage solutions with a read-only flash cache, Tintri VMstore is designed from the ground-up as an integrated flash/disk architecture that can both read and write to flash, making full use of its potential to deliver the appropriate quality of service for each VM.


Intuitive performance fuel gauge

Intuitive performance gauge for all datastoresManaging performance is as easy as managing capacity. With Tintri VMstore, eliminate worries about VM storage performance. A unique “fuel gauge” gives you immediate visibility to both the available storage capacity and performance headroom on any Tintri VMstore appliance. For the first time, this gives you predictable storage performance with a single, easy-to-use metric. Two aggregate indicators with drilldown capability let you keep tabs on your VMs.
View storage performance changes in real-time



Change dashboard

Detect problems before they begin. Tintri VMstore’s dashboard view quickly identifies VMs with the most changes in performance or capacity requirements in the past seven days. You don’t need to understand how VMs map to the storage components — all you need to know is the name of the VM — Tintri VMstore manages the details for you.


VM auto-alignment

Auto-align virtual machines with Tintri VMStoreImprove VM performance by up to 30 percent. Misaligned guest file systems and underlying storage degrades performance, amplifying IO requirements. Re-aligning them is difficult and time-consuming — and administrators rarely have the luxury to address it. For conventional storage arrays, re-alignment means manually remapping the guest file system. Fortunately, Tintri VMstore automatically aligns VMs, strengthening performance. It adapts the storage layer to the guest file system without user interaction or service impact. Learn more about how alignment affects VMs, and how Tintri VMstore helps.




VM pinning

Assure performance for specific VMs. Tintri VMstore can isolate VMs and even individual vDisks that demand guaranteed performance by pinning them to flash. This assures performance for mission-critical applications or time-sensitive workloads, such as software builds.

VM pinning for increased performance

VM-level visibility into pinning


Scalable nodes

Scale-out storage in easy-to-add increments. Tintri VMstore integrates software and hardware capability in to a field-servicable storage appliance, built from the ground-up to run VMs. It plugs into your existing environment as an NFS appliance — each device is a single datastore with 13.5 TB of usable storage. A file system designed to take full advantage of flash, multicore CPUs and 10 GbE delivers the performance you need for your VMs.

Learn more: download the datasheet

Scalable nodes for better storage performance

Easy to set-up and manage

Easy set-up for Tintri VMStoreStorage that’s as simple to manage as your hypervisor servers. Tintri VMstore can be set up and configured in minutes. No complex storage configuration required. Once the appliance is powered on, it’s as simple as connecting it to your VMware vCenter Server™ and migrating VMs to the VMstore. Each node is a single datastore, making it easy to map to your VMware vSphere™ hosts. What’s more, when you add new VMs, you won’t need to worry about configuring new LUNs, volumes, RAID groups or any other complex storage objects — since there are none.



Array-side snapshots

Take snapshots of VMs, not LUNs or volumes. Tintri VMstore lets you snapshot individual VMs at the storage level without any performance impact. No need to take snapshots of entire LUNs or volumes just to capture a few VMs. Tintri VMstore also creates crash-consistent snapshots without quiescing VMs, letting you run maintenance operations without disruption.

Array-side snapshots in one location


Truly Hypervisor aware File System

The storage objects we manage are VMs and vDisks not LUNs or Volumes. We can provide visibility and performance metrics on individual VMs, vDisks and Swap files including latency, IOPS and throughput. We can also show the latency characteristics from the host to network to storage subsystem.

Hybrid File System

We make intelligent use of SSDs so that all data is loaded into flash and only evicted once the flash fills up and we do this at a very granular 8k block size. We also use inline duplication and compression technologies to boost efficiency of flash usage. This allows us to deliver a 97% hit rate for reads and writes with incredibly low latency. Traditional storage arrays typically load all data to spinning disks and then promote hot data to flash and invariably this is for read only operations. The traditional approach yields a range of between 30-60% of IO from flash, but to reiterate this is generally only for reads not writes.

Single 8.5TB or 13.5 TB data store

VM admins want fewer data stores that can be self-provisioned. With traditional approaches data stores are provisioned in 500GB or 1TB sizes and require interaction with the storage admin. This yields a 17:1 up to a 27:1 management overhead when compared to Tintri, and the Tintri approach is provisioned by the VM admin with no requirement to learn the complexities of storage. This can dramatically lower operational cost and speed up time to deployment.

200 x Server VMs per Tintri appliance or 400 x Virtual Desktops

This allows us to provide a very low cost per VM again whilst lowering administrative costs and simplifying troubleshooting.


An Introduction to Tintri from Dr. Kieran Harty, CEO and co-founder

A brief look at Tintri by Kieran Harty, Co-Founder and CEO

 Tintri VMstore Overview

 Tintri Performance Troubleshooting Demo

Tintri VM Snapshots and Cloning

Request Quote

First Name (Required)

Surname (Required)

Email (Required)

Company (Required)

Contact Number (Required)

Optional: Ethernet Top of Rack Data Center Switch

Optional: Extend Maintenance and Support
(One Year Standard (8x5) Support Included)

Optional: Do you need to match another quote specification?
Please cut/paste specification or upload document

Optional: If you have any specifications in the form of a document
Please attach (pdf|txt|doc|docx|xls|xlsx|csv)

Optional: Additional sizing information

Verification: captcha