As the XXXI Olympic games came to a close, we were again reminded of the dedication required to compete at extraordinary levels. Athletes such as Usain Bolt, Michael Phelps, and Simone Biles clearly separated themselves from the rest of the pack to be the fastest and the most consistent. They have what it takes to succeed and have won gold medals consistently.
For example, Usain Bolt has won nine gold medals at the last three Olympics, all while only spending a couple of minutes on the track. To achieve this goal, he trained for over 15 years. He did so by pushing himself to get to the gym every day and has a regime that is second to none. His motivation is derived from not wanting to be in second place, enabling him to reach a top speed of 27 mph. We have a similar mantra at Nutanix: we don’t want to be in second place!
We do this through the collective efforts of our broad set of employees with various backgrounds that come to win every day. Nutanix uses consistent innovation and adoption of game-changing technologies such as NVMe, Persistent Memory, and container, file and block services, to push past the norm.
Data continues to expand at exponential rates, and these technologies become paramount in making sense of the massive amounts of data being collected. To fully realize the benefits of these technologies, compute resources must sit near storage resources. This can massively reduce CPU wait times while delivering consistently low latency access to data.
As these technologies mature and become mainstream, choosing the right platform becomes paramount. The Nutanix enterprise cloud platform is built to adapt and take advantage of newer technologies, putting your business ahead of the competition
Sprint the Globe
Sprinting versus running, what’s the difference? A runner maintains an average speed for a longer period, typically not having a great top speed or ever reaching it during a race. However, a sprinter, like Usain Bolt, will accelerate to a top speed in a matter of seconds and will maintain that speed for the entire race. Now imagine if you could utilize the sprinting methodology for the way an application accesses data, but at the duration of a runner. That would be revolutionary!
To understand what these technologies – NVMe and Persistent Memory - can produce, we have to look at where it started. Rotational media, such as Hard Disk Drives (HDD) have been around for a long time. HDDs provided adequate performance for single workloads at very low costs, but as additional workloads are added HDD performance suffers.
HDDs are significantly constrained in performance especially with mixed workloads on the same infrastructure, and for applications like OLTP and OLAP. HDDs have remained stagnant in terms of performance capabilities, and in fact, the I/O density (IOPS/GB) has continued to precipitously decline with each step-up in HDD capacity (e.g. HDD capacities are 6x to 10x higher than they were a few years back, but IOPS have remained at about 75).
HDDs can be viewed as the long distance runner that doesn’t have a high top speed (IOPS). At the same time, flash costs continue to fall as densities increase resulting in Solid State Drives (SSDs) moving into many enterprise datacenters, replacing the long distance runners - HDDs. However, SDDs were built using the same interfaces as HDDs, and can’t reap the true performance flash offers.
As newer solid state and persistent memory technologies are developed, new interfaces must be designed to take advantage of these performance characteristics.
NVMe is the new access standard for PCI express SSDs. NVMe takes advantage of SSDs by being able to read or write lots of data simultaneously, parallelizing access. As an example, 3D-XPoint technology, with the right interface, has made waves on the performance it will offer. Intel and Micron have summarized the benefits of the technology in a document they wrote (included a small excerpt below).
“In the time it takes an HDD to sprint the length of a basketball court, NAND could finish a marathon, and 3D-XPoint technology could nearly circle the globe.”
Looking at today’s options for high-performance workloads, NAND and DRAM are the two storage/memory media that come to mind. Today’s NAND technologies provide low costs and are non-volatility, and DRAM provides superior performance.
If you take the best of these two technologies and combine them, you get persistent memory technology. It is memory-class speeds which are cheaper than DRAM, faster than NAND, and non-volatile like NAND. We believe as this technology makes inroads into the datacenter, you will start seeing it in SSD type form factors.
The culmination of the two technologies enables applications to have unparalleled access to data without bottlenecks. The only way to truly harness these technologies is to converge compute, flash storage and virtualization on the same platform.
Nutanix keeps the server close to the data. In contrast, legacy three-tier architectures separate applications from storage by networks and storage controllers incurring additional latencies. In these legacy architectures, networks will quickly become saturated as these technologies surface.
Multiple Parallel Lanes
Consider a scenario where you can leverage many Usain Bolt type sprinters in a widened lane, each holding a piece of data. They would be able to get data between two different points at blazing fast speeds. Applying this to applications accessing data increases the amount of I/O between the application and SSD. Applications would just scream with performance, minimizing the amount of time your users wait for access.
Flash performance is steadily increasing as demand for faster systems continues to rise. Today’s SSDs can deliver over 100,000 IOPS and with a few of them aggregated, they can quickly saturate storage controllers. If a single array holds 10-20 SSDs on average, then you are probably not getting the full potential of the SSDs.
The same situation applies when looking at the network where bandwidth becomes a concern. A typical enterprise SSD using AHCI (Advanced Host Controller Interface) interfaces can deliver on average 500MB/s read and 450MB/s write performance, again saturating common network infrastructure. SATA drives with AHCI interfaces typically have a single queue and can handle 32 commands.
AHCI was designed to handle slow read/write operations and not designed for SSDs that can handle large amounts of I/Os. NVMe, on the other hand can handle parallel operations, up to 64,000 queues with 64,000 commands per queue, enabling simultaneous disk I/Os.
Keep Pushing the Norm
The modern hyperconverged architectures not only shorten the path (direct PCIe access) but also enable a significant increase in parallelization, which can allow massive amounts of data to be processed in real time.
As you look for a next-generation platform to push mixed application workloads and drive higher business value, consider a solution that can take advantage of newer NVMe and SSDs options as these technologies become mainstream.
Come See Us at Microsoft Ignite 2016
Nutanix is proud to be a Platinum Sponsor at Microsoft Ignite 2016 at the Georgia World Congress Center in Atlanta, September 26 – September 30, 2016. Visit us at our booth and hear how our customers are deploying large-scale environments with Nutanix all-flash solutions.
If you like what you see on the show floor and want to have a more in-depth discussion about our solutions, we would love to talk to you. Visit the Nutanix booth to schedule a meeting with our engineering, product management, or product marketing team.
Let’s Get Social!
You can stay connected with Nutanix throughout the entire Ignite 2016 event by following @Nutanix on Twitter, and connecting with us on the Next community forms (next.nutanix.com)
We look forward to meeting you at our booth #1310 at Ignite in Atlanta where we will show you how to deliver mission-critical business applications securely and reliably, all while reducing your TCO at scale. Your IT organization will truly be elevated to focus on delivering core business value and innovation by making your infrastructure invisible with the Nutanix enterprise cloud platform.
This post is authored by Rohit Goyal, Product Marketing Manager at Nutanix
Disclaimer: This blog contains links to external websites that are not part of Nutanix.com. Nutanix does not control these sites, and disclaims all responsibility for the content or accuracy of any external site. Our decision to link to an external site should not be considered an endorsement of any content on such site.