Flash is undoubtedly considered a superhero within the world of storage. However, it is unlikely to save the day all on its own. Whilst playing an important role, flash is just one of multiple solutions required to address the most common storage pain points in the data centre.
Just like any superhero, it needs to work as part of a team in order to save the world or at least save you time. And in that respect, there is an underlying problem (or villain) that needs to be fought off. After all, without villains, there would be no need for superheroes in the first place.
The danger here stems from the shift of physical to virtualised workloads. Over the past decade, the percentage of virtualised workloads has jumped from 2 per cent to 75 per cent; but organisations continue to use storage that was originally built for physical workloads. This speedy adoption of virtualisation has created a mismatch in the data centre, with physical storage becoming the reason for rapidly increasing costs and even higher levels of frustration, as IT admins battle bottlenecks on a daily basis.
- Virtualisation: a major pain point
A survey of 1,000 data centre professionals conducted recently found that the two most cited storage pain points were performance (50 per cent of respondents) and manageability (41 per cent of respondents).
Given that increasing numbers of virtual workloads are generating far more random I/O patterns that are bound to choke disk-centric storage, that’s hardly surprising. To try and improve performance, storage admins shuffle virtual machines from one storage LUN or volume to another: this presents them with a number of manageability shortcomings in the process.
- Buying time doesn’t solve the problem
One way to try and overcome performance pain is to use flash because it is low latency and can handle random I/O (it’s also much faster). A single commodity SSD (Solid State Drive) is 400 times quicker than a hard disk drive (HDD). To put that in context, the speed of sound is "only" 250 times faster than walking – quite a comparison!
However, flash’s powerful speed can only buy admins time. It doesn’t have the ability to deal with the root cause of storage pain –the disconnect between virtual workloads and physical-world storage: it only addresses the symptoms.
Over time, data centre professionals are likely to add more virtualised workloads as they expand their footprint from virtualised desktops to servers to private cloud. To keep up with the added strain on their infrastructure, they are forced to buy more and more (high cost) flash. Not only is that bad for their budget, worse still, it won’t resolve the disconnect.
- How to match your storage with your virtualised environments
Deploying storage specifically built for the world of virtualised workloads, storage that is VM-aware, is the best way to solve the root cause of storage pain.
VM-aware storage has none of the LUNs, volumes or other management constructs found in conventional, physical-first storage. Without those outdated constructs, VM-aware storage performs all actions and analytics at the virtual machine-level.
Conventional storage groups virtual machines into LUN or volume and applies policies at that aggregated level — assigning an amount of performance to be shared by all the virtual machines inside the LUN or volume. A rogue virtual machine in the LUN will consume performance that could or should be better used by its neighbours.
VM-aware storage gives admins x-ray visibility to see latency for an individual VM across compute, network and storage. It can even set minimum performance for mission critical VMs or set performance caps on potentially rogue VMs. This enables admins to guarantee every VM will get the exact performance it needs.
- Manageability is key
A vital part of the equation is undoubtedly managebility. Most storage admins and/or virtualisation admins have to maintain a large spreadsheet to map all VMs to their respective LUN or volume. As the VMs are shuffled around, the spreadsheet must be meticulously maintained. VM-aware storage makes the spreadsheet obsolete with its x-ray like powers.
Admins can log in and see every individual VM, drill in for full analytics or set a policy (replication, cloning, etc.) at the VM level. And, without LUNs or volumes, VM-aware storage introduces a common language (VMs) that works across the entire data centre.
- Getting your money’s worth with the right solution
For storage admins, the only way to improve performance in the long term is with VM level visibility and control. A VM-aware brain can ensure that flash brawn is effectively applied to the VMs with the greatest needs. And it can provide VM level analytics, both real-time and predictive to help the organisation understand how its storage footprint (and its requirements) are changing.
With the arrival of VM-aware all-flash on the market, organisations have choice. This choice involves enhancing their hybrid storage strategy of mixing flash and spinning disk or adopting an all-flash approach where it is required.
In other words, customers are able to decide which workloads benefit from an all-flash or hybrid-flash approach. VM-aware storage can guide them on how best to balance workloads across storage platforms to make the best use of their time and money.
Although flash may not be able to rescue an organisation's data centre single-handedly, it plays a vital role in helping VM-aware storage to save the day.
Kieran Harty, CTO & co-founder of Tintri