What is our primary use case?
At Secure-24, we have been a long time customer of Pure Storage. We started with Pure Storage approximately four years ago. We use it as the primary mechanism for block storage in our environment.
We specialize at comprehensive managed services of business-critical applications. We run a hosting environment and the full gamut of applications, infrastructure, security, compliance, and governance. Using that model, Pure Storage is a key part of being able to deliver the performance, encrypted storage, and reliability for mission-critical applications.
How has it helped my organization?
The biggest impact changing to Pure is we saw an influx of tickets from customers because they thought their BI applications were broken because they were running too quickly.
Operationally, we find that we are not having storage problems anymore on performance. Historically, there might be various storage performance issues when you have DBAs involved utilizing network and storage resources, since it's very operationally intensive to gather multiple teams together and do comprehensive troubleshooting of problems. We found these issues have simply gone away since we have migrated to Pure Storage. It's been fairly significant change in how we manage and deploy applications.
It's helped us because we've changed fundamentally what we talk about. We don't talk about storage and different tiers of storage anymore nor do we talk about servers. We talk now about applications and how applications impact the business and end users.
You don't have to worry about the different tiers of storage. They are always fast and reliable with consistent performance.
What is most valuable?
Based on the various types of workloads and environments we run, we have looked at Pure Storage as being one of the largest infrastructure-based changes we have seen in our environment in the last 10 years of infrastructure hosting.
What has changed is you now have databases and applications where you can make an infrastructure change and it directly impacts the end user experience. You generally don't see that with other infrastructure changes. If I change from storage A to storage B, maybe there is a small or minor performance increase.
With Pure Storage, there was a dramatic performance increase which we saw across various different applications. Going from a legacy vendor to Pure Storage, we saw reductions in MRP reports previously running at six hours going to 30 minutes.
What needs improvement?
With Pure Storage, we would like to continue seeing price reductions with flash storage. I don't think we're any different than anybody else when we continue to look to the industry for price reductions of both NVMe and traditional SSD storage. We would like to see these prices continue to decline and erode, even displacing large spinning disks.
Ideally, in a perfect world, you would have all-flash arrays being able to displace even your traditional "cheap and deep" type storage frames. We are more excited from the industry perspective when this type of transition can happen from a cost perspective.
Also, I want to see Pure Storage not only be for fast storage, but I want to see it be for the entire data center.
For how long have I used the solution?
Three to five years.
What do I think about the stability of the solution?
With mission-critical, business-critical environments, stability is of the utmost importance. Pure Storage has impressed us in this area. We have gone through multiple software upgrades, as well as completely non-disruptive hardware upgrades. Upgrading from an FA450, which is one of the arrays from more than four years ago, to an M70, then to the X70s. We have gone through that, the full controller and full storage upgrades, non-disruptively to any of our customers. This has been a big change from what we've seen historically in the storage industry, where you had to do an upgrade or when you had to do a large new purchase, and there would be a significant amount of time, planning, and organization which would go along with it. There would be intangible costs that would generally come along with legacy providers.
What do I think about the scalability of the solution?
The way that we have looked at scalability is from a linear scalability perspective with multiple storage frames. We like having the capability of scaling wide with multiple storage frames as opposed to trying to scale too large with any one individual frame. However, we also have an X90R2 with two petabytes of NVMe in it which fits in about six rack units of space. This has been transformational, as well. From there, we scale out linearly with multiple of X90R2s, as opposed to trying to somehow cluster them or make them larger.
Which solution did I use previously and why did I switch?
Over the last four years, we have displaced the majority of other storage solutions in our data centers with Pure Storage.
What about the implementation team?
The engineers and architects on our team were the ones directly doing the setup and implementation.
What was our ROI?
We have absolutely seen a reduction in total cost of ownership (TCO), specifically around the operational overhead of running a storage array. Now, we have our Pure Storage arrays managed by VMware resources. Therefore, we don't have a specific role for storage management where one used to exist. So, the VMware team is able to manage, deploy, and configure the arrays. The simplicity of drives allows for this consolidation.
There are a lot of intangible costs, such as gathering teams together in war rooms to troubleshoot performance issues, simplicity of managing the array, growing the array, and going through upgrades. When you look at all the intangible operational expenses, in many cases, these will offset the capital investment of going to an all-flash array.
What other advice do I have?
To say, "Pure Storage has simplified storage," is a bit of an understatement. The array has gone from having a PhD in working with it to effectively having a high school diploma. Anyone who understands anything about IT can run a Pure Storage array. It's incredibly easy to use and greatly simplified our ability to both deploy and manage our storage subsystems.
With the traditional Pure Storage array, you had very consistent low latency, but you still were in one to three milliseconds. Now, with the all NVMe arrays, it's a whole new paradigm of fast. You're actually measuring everything in less than a millisecond. So, with the I/O responses, your high bar is one millisecond. This is something you haven't seen in most traditional storage frames or even all-flash storage frames.
We generally always advise people to make the choice to go with Pure Storage because they won't regret it. We can evidence that a lot through our experiences of running massive databases and systems on Pure Storage today and prior experiences that we've had with it.