Backup and recovery is a bit like snowboarding. When the time comes to speed down the mountainside or keep your business running in the event of a disaster, a little bit of preparation will make the difference between a smooth landing or ending up face-first in a snowdrift. Here are four ways to avoid an epic fail.
Backup and recovery is a bit like snowboarding. When the time comes to speed down the mountainside or keep your business running in the event of a disaster, a little bit of preparation will make the difference between a smooth landing or ending up face-first in a snowdrift. Here are four ways to avoid an epic fail.
Epic Fail #1: Faulty Gear
How do you spot a newbie on the slopes? How about the snowboarder who has an expensive, stylish ski jacket but thin gloves and non-waterproof paints? Or the guy who forgot to make sure his bindings were in good working order and loses his board halfway down the mountain? After all, you can’t shred the hill unless your gear works.
Similarly, you can’t recover from a disaster if your backup isn’t in place before the data loss occurs. It’s critical to ensure that your technology is working as it should, and has a feature set robust enough for your business, well before a disaster strikes. You’ll want an implementation where backups are automatic and reliable, the integrity of your data is upheld through inline and offline validation, recovery testing is automated via recovery assurance software, and backups are copied successfully to a secondary location or the cloud. In simple terms, make sure your data is actually being backed up and copied offsite. Sounds simplistic, but it’s important to confirm that your business can keep running even if your on-premise servers go down.
Epic Fail #2: Ignoring the Trail Map
You wouldn’t get on a ski lift without checking to see if it’s going to the green slopes or a black diamond. Nor would you take an unplanned turn off-trail and snowboard through the trees, as you’d most likely find yourself hitting dirt or something worse, like falling into a crevice or canyon. Before you head up the mountain, you need to plan your descent. You also need to check the signs along the way to make sure you’re still on course.
Just as you need a trail map for your snowboarding adventure, you also need a written plan for a successful disaster recovery. This means you need to create a document that is broad in scope and includes step-by-step guidelines. This should be done with three unique areas in mind:
- People: Identify key operational personnel and plan a way for them to work remotely or at a secondary location when a disaster strikes. This means giving them direct access—regardless of their location—to the recovery systems, data, and other resources they need to maintain business operations. It’s also important to set up an alternate form of communication (e.g., employees’ cell phones) in the event that your organization’s primary communications infrastructure goes down (e.g., corporate email or phone systems).
- Infrastructure: Identify key operational infrastructure—those parts of your infrastructure that your business can’t operate without—and make sure those are protected. Remember that the reason that you want your IT infrastructure to successfully survive a disaster is so that your most important asset, your staff, has the tools they need to continue to drive revenue and profitability for the business.
- Processes: Identify key operational processes—step-by-step guidelines that outlines who does what in the event of a disruption—and make sure team members are aware of and have practiced their role. Consider every process that is critical to the daily operations of the business and don’t just focus on IT processes.
Your DR plan, as well as your data protection solutions, should also meet your company’s Recovery Point Objectives (RPOs), or the maximum amount of data (in terms of time) that you can afford to lose, as well as your Recovery Time Objectives (RTOs), which is the maximum amount of time that you can afford to be without your data and systems. The best DR plans are based on how much data is being recovered and how quickly that information needs to be brought online.
Epic Fail #3: Neglecting to Practice
If your first trip down the mountain is on a double-black-diamond trail, you’re guaranteed to fall on your face. You can’t just buy the gear and study the trail map and magically know how to snowboard without ever setting foot on the snow. Practicing your technique, building your physical fitness, and honing your instincts are key to making your ride down the mountain a success.
Continuing your business during a disaster and recovering lost data is a black-diamond level event. If you’ve never tested your DR strategy, you’re likely to wipe out. It’s not uncommon for IT administrators to install a backup solution and rarely (or never) getting around to testing an actual recovery. Further, and when it comes to testing, one or two are not enough. The swift pace of today’s digital transformation and IT evolution means your infrastructure is changing quickly too. The best DR test is iterative and done on a consistent schedule, so you can make sure your backup is protecting the current state of your company’s infrastructure. The change rate of your data is a good benchmark to determine how frequently to test your disaster recovery plan. A few backup vendors offer automated DR testing, which can save you a ton of time and hassle.
You also need to consider various disaster scenarios and evaluate how DR processes may change as a result. For example, does your strategy require a team member to drive to a secondary location to rotate media? What if a large scale natural disaster like flooding or blizzard prevents travel? Backup in the cloud is a good solution for overcoming physical and site-based limitations, but you also need to plan for how fast you need your data back from the cloud. Hyperscale clouds can provide cheap storage but may take days to restore your data over the WAN. If you don’t have a secondary site that’s geographically separated from your primary site (an expensive proposition for many businesses), DR as a service can deliver affordable spin-up and business continuity in the cloud. Whatever you choose, educate yourself on the vendor’s SLA, know your RPOs and RTOs, and of course, test.
Epic Fail #4: Assuming all Snow is the Same
It would be great if the powder was always fresh and the trails were never crowded, but let’s face it sometimes you’ll be struggling through the slush or avoiding the tourists on spring break. Seasoned boarders also know that you tend to have the most fun snowboarding if you build the skills to tackle diverse terrain and different snow parks. Even if you spend most of your time on your favorite slope, the trails will vary day-to-day and season-to-season. If you assume all snow is the same, you’re find yourself in trouble on your way down the hill.
With your IT infrastructure, you can’t assume homogeneity. Maybe you prefer as much virtualization as possible, but your organization requires some physical servers. It’s important to maintain flexibility so that your IT team remains responsive and agile to the changing needs of users and the evolving technology landscape.
To take the most common example, avoiding single vendor lock-in is critical to both the technical and financial success of modern IT. DR failures often occur because administrators support only a single technology in their DR planning. For example, they’ll support storage technologies such as SAN or NAS, but ignore direct attached storage; embrace virtualization, but ignore physical servers; or support physical appliances, but fail to consider the need to restore between different models and generations of servers. Create and test a backup and DR plan that encompasses the range of technology your business needs to keep running.
If you’re new to snowboarding, one of the first things to know is that you will fall. It’s the same with IT infrastructures—data loss will occur, whether by a minor deletion by a user, a disruptive malware invasion, or a full-scale natural disaster that takes down an entire site. Whatever the magnitude, you can be ready. Avoid epic fails by ensuring your gear is functioning, completing your plan, testing your DR, and maintaining flexibility in your strategy. In doing so, you’ll be shredding those slopes in no time.
About the Author
Brooke Bullman, is a Product Marketing Manager at Unitrends, a leader in enterprise-level cloud-empowered business continuity solutions. For more information contact the author at [email protected] or visit www.unitrends.com
Sign up for the StorageReview newsletter
