The spectacular success of server virtualization begs the big question: What comes next? Can the same practice on servers be applied to the rest of the datacenter? This is what gives rise to the concept of software-defined datacenter (SDDC) infrastructure — a datacenter with infrastructure fundamentally more flexible, automated, and cost-effective; infrastructures that understand application workloads and can automatically and efficiently allocate pooled resources to match application demands.
While servers, and to a lesser extent networking, started down the SDDC path a few years ago, little has changed in the world of traditional storage that was designed for physical environments. As datacenters become more virtualized, there is a growing gap due to the complete mismatch between how storage systems were designed and the demands of virtual environments. It’s a bit like a human language barrier — storage speaks LUNs and volumes; servers speak VMs. As a result, they don’t understand each other very well. Storage allocation, management, and performance troubleshooting for virtualized infrastructure are difficult — if not impossible — with traditional storage, which is fundamentally ill-equipped to deal with the random IO demands of virtualized applications. Companies have tried to work around this obstacle by overprovisioning storage, but that approach is very expensive and increases complexity.
The time is right for a new generation of storage – smart application-aware storage that’s simple to manage, agile like the cloud, responsive to the needs of applications, and delivers performance that puts plain old disks to shame.
This is exactly what Tintri set out to do. Founded by Dr. Kieran Harty, who led development at VMware, we aim to complete the virtualization story by bringing the same kind of efficiency and simplicity to storage that VMware brought to computing.
We built smart application-aware storage that sees, learns, and adapts to help IT organizations focus on virtualized applications, instead of managing storage infrastructure. After all, applications drive the business and infrastructure exists to support the apps. This means it’s far more important for the IT teams to focus on performance, QoS, speed to deployment, and scalability of apps – instead of just managing the storage infrastructure.
Tintri smart storage is able to see how applications behave at the virtualization layer, and then presents the information in a way that’s useful to storage and virtualization professionals. Equally important, every step in the Tintri experience is designed to be profoundly simple.
Starting from a clean sheet of paper and unencumbered by traditional storage concepts, Tintri developed FlashFirst™ architecture that natively understands and integrates with the virtual infrastructure. The primary objects of management within a Tintri system are VMs and virtual disks, the same objects that the hypervisor manages. Focusing exclusively on VMs enables Tintri to eliminate unnecessary levels of mapping and complexity required by traditional storage and improves storage efficiency. Tintri VMstore uses flash efficiently and reliably while leveraging key technologies, including deduplication, compression, and automatic data placement to deliver 99 percent of IO from flash. The underlying storage system natively understands and supports storage management operations such as performance and capacity monitoring, snapshots, quality of service (QoS) management, and replication at the VM level.
Storage that Sees: The only application-aware storage in the industry with VM-level visibility and control across the entire infrastructure.
Tintri storage brings visibility to the previously hidden world of data in virtualized environments. Unlike all other storage platforms, that are blind even to the concept of a virtual machine, Tintri is application-aware, seeing into the software environment to reveal and even call attention to issues. Tintri VMstore automatically surfaces information on VM behavior and yields insights about performance – including IO, storage growth, and utilization – for individual VMs. This enables IT to make and support quick, knowledge-based decisions with new confidence, impact, and ease.
Imagine if you could see across your hosts, network, and storage and be able to identify performance problems in minutes? Inconceivable you say? Only if you have never heard of Tintri.
Storage That Learns: The only hypervisor-agnostic storage in the industry with VM-level management self-learning, making it easy to deploy and manage, and providing a profoundly simple and smooth experience.
The primary objects of management within a Tintri system are VMs and virtual disks – the same objects that the hypervisor manages. Focusing exclusively on VMs enables Tintri to eliminate the unnecessary levels of mapping and complexity required by traditional storage and improves storage efficiency. The underlying storage system natively understands and supports storage management operations, such as performance and capacity monitoring, snapshots, quality of service (QoS) management, and replication at the VM level. This enables Tintri storage to achieve much higher levels of automation and optimization for general-purpose storage systems. Tasks that previously took IT days or weeks to complete, can now be done in minutes.
Imagine you never had to worry about RAID levels, RAID groups, LUN masking, volume layout, queue depth settings, profiles, SSD/HDD capacity, or drive types ever again. Imagine spending less than one hour each month managing 20,000 VMs in a single 42U rack with sub-millisecond latencies. With Tintri, there will be no more spreadsheet hell and mind-numbing drudgery. No pain, no pain.
Storage that Adapts: No knobs, no tuning, no special configurations. Agile services that scale to the demand of the apps.
Tintri hypervisor-agnostic smart storage systems are designed to support mixed workloads—server, VDI, and development and testing—concurrently with VM-level quality of service (QoS). Tintri VMstore ensures there is never any impact from ‘noisy neighbors’ on the same system. With VM-level QoS functionality, storage performance is equitable and predictable. Different types of VMs, such as IO-intensive OLTP workloads and latency-sensitive end-user desktops, can reside on the same Tintri VMstore. Tintri VMstore automatically aligns all VMs as they are migrated, deployed, cloned, or created, with zero downtime.
Tintri’s adaptive capabilities also make scaling, especially hyper-scaling, a breeze. With traditional storage, administrators are forced to plan far in advance how they want their storage environments to map to the different groups of VMs they will be creating. Many IT managers still use extensive spreadsheets for storage LUN or volume-to-VM mapping. This practice can overwhelm IT administrators, as they manually track the assignments of virtual servers and VMs to storage arrays and volumes. This is an incredibly time-consuming, inefficient, and error-prone way to manage storage and also extremely difficult to predict how scaling will affect existing virtualized workloads. The problem is further exacerbated in the cases when environments with related VMs are forced to span multiple storage systems for performance reasons.