An Insider's Look at HPE SimpliVity: USS-POSCO Industries

[JanetRunberg]

USS-POSCO Industries is a joint venture steel finishing facility that produces hot rolled, cold rolled, galvanized, and tin plate used for construction, formed products, and containers. Joshua Goodall, automation engineer, has been with the company for nearly 20 years and has experienced multiple equipment failures in the aging data center.  IT downtime brought operations to a standstill on more than one occasion, but their limited budget did not seem like it would support a complete data center overhaul.

Here's the automation engineer’s story.

The challenge

We had two or three major failures of servers and IT infrastructure over the last few years that caused a massive ripple effect across the entire facility. One caused 30 hours of downtime. To address the situation, we initially planned to add a secondary disaster recovery site built on traditional three-tier architecture (separate compute, storage, and networking), but that proved to be absurdly expensive.

Searching for alternative highly available solutions, we zeroed in on hyperconverged infrastructure (HCI). The more I learned about it, the more I understood that HCI meant simplicity. It meant avoiding excessive overhead, because we wouldn’t have to manage all the ancillary products and processes: site recovery software, separate storage arrays, replication between sites, compatibility issues, not to mention backup management and licensing costs.

Why HPE SimpliVity?

We chose HPE SimpliVity because it’s a total package. It’s something that you bring into your organization and you reduce the complexity of your stack, the man-hours associated with managing that stack, and data center footprint. When you combine all those components and data services into one system, it’s so much simpler. And the lower TCO is a massive benefit.

But what really excited me was learning that HPE SimpliVity supported two-node clusters set up in a “stretched cluster.” What that means is two nodes can be separated to set up resilient disaster recovery on a single site. We have the nodes about a mile apart on our campus. If there’s a problem at our data center, everything fails over automatically to the secondary node – there’s no management involved. It’s all native, built-in functionality, leveraging VMware and HPE SimpliVity architecture.

Any surprises?

It was even simpler – and faster – than promised. And every bit as resilient. We had our first test of redundancy and built-in backup/restore in 2018 when a Windows update caused problems. I had to go back four weeks in HPE SimpliVity to restore the VM. The entire process took less than five minutes. That's restoring from the VM environment, booting, logging in, and rejoining the domain—all in less than five minutes. Later, we ran into a similar situation where we had to replace our legacy core switches. We failed the system over to one side of our facility and left all the VMs up on the other side. We changed the core switch and then brought everything back up. The process couldn’t have been simpler.

Tips for customers considering HCI

I have 3 suggestions.

1. Evaluate cost based on your goals. To be sure, HCI is not one-size-fits-all solution. Before you investigate hyperconvergence solutions:
   • Take a hard look at your applications. Identify your use case scenarios and what you want to accomplish.
   • Make sure you understand your data footprint, including backup storage and how you expect to store data in the new infrastructure.
   • Roll the cost of that functionality into your calculations to get the total cost of ownership, not just one function or feature. That’s really where you get the value of the HPE SimpliVity product.
2. Read the tech blogs. I found a couple really good articles on LinkedIn about HPE SimpliVity data architecture. One blog on VM management was an actual dive into the underlying structure, allowing me to understand how the product works. It ought to be handed out to every prospective and new customer.
3. Join HPE SimpliVity Insiders. If you go with HPE SimpliVity, the Insiders community is awesome. I probably learned more there than I did from any single blog post or engineer. I’ve personally met 4-5 people in the community, and we all keep in touch. It’s an amazing experience because it gives me a direct interface with other customers and use cases, not just to challenge what I do in my organization but to show me opportunities where I can expand the product portfolio to address other challenges.

A bright and shiny future for the steel company’s IT organization

We are just now moving forward with our final 2-node cluster, which is going to get us off of our traditional equipment. When we’re done, we’ll have three 2-node stretched clusters, all part of the same federation. For our virtual environment we’ll be fully HPE SimpliVity – ready for whatever comes.

Read more about USS-POSCO’s story or watch the video.

To learn more about HPE SimpliVity architecture and capabilities, including stretched clusters, download the technical whitepaper: HPE SimpliVity hyperconverged infrastructure for VMware vSphere

Janet

Janet Runberg
Hewlett Packard Enterprise

twitter.com/JanetRunberg
twitter.com/HPE_SimpliVity
hpe.com/simplivity

HPE SimpliVity Insiders is a user community for current hyperconverged technology customers. Users share tips, and are eligible for HPE rewards and exclusive access to the extended HPE SimpliVity team. If you’d like to be invited to join the community, contact jennifer.insiders@hpe.com