Services

How IBM Spectrum Scale resembles my toddler twins

Share this post:

I’m a storage consultant in IBM Systems Lab Services and a working mother of two-and-a-half-year-old twins who were affectionately known as Flash and Elastic during my pregnancy because of the way they moved in my belly.

I usually spend my days onsite with IBM clients implementing and managing IBM Spectrum Scale clusters, but I also like to think that I have my own two-node cluster at home. In fact, I’ve realized that IBM Spectrum Scale and my twins have quite a few common characteristics.

Just to make sure everyone’s on the same page: IBM Spectrum Scale is a scalable, high-performance data and file management solution (based upon IBM General Parallel File System, or GPFS, technology) that’s being used across industries worldwide. IBM Spectrum Scale provides world-class storage management with extreme scalability, flash-accelerated performance and automatic policy-based storage tiering from flash through disk to tape and even to the cloud. It can reduce storage costs up to 90 percent while improving security and management efficiency in cloud, big data and analytics environments.

Big data processing

IBM Spectrum Scale provides simplified data management and integrated information lifecycle tools capable of managing petabytes of data and billions of files, in order to help organizations manage the growing cost of dealing with ever-increasing amounts of data.

Here’s where the similarities to my twins begin. For example, my kids are also capable of efficiently managing petabytes of data; they learn new things every day and have seemingly endless storage space.

Information lifecycle management

With IBM Spectrum Scale, using the automatic policy-based storage tiering for information lifecycle management (ILM), a storage administrator can set policies and rules to place data in the correct storage pool as well as migrate data between storage pools based on business needs and rules. With ILM, only the data that really needs high performance can land in the flash disks, while the remaining data can stay in a less expensive storage disk or even move to an external pool like tape. This can be accomplished by defining policies; for example, it could migrate files that haven’t been accessed for more than six months to second-tier storage or tape, or even delete them if no longer required for the business. Or, it could avoid writing a particular type of data to a file system, such as putting no MP3 files on a corporate file server.

At home, I also manage my twins with ILM. From Monday to Friday, I migrate the kids from bed to daycare. If their shoes or clothes don’t fit after three months, I migrate those to an external pool, which is my friend who has triplets (yes, life can be harder). ILM also helps me define rules to manage which cartoons they can watch. And if a toy hasn’t been accessed for more than six months, it gets deleted from home, by which I mean donated.

Easy management

The IBM Spectrum Scale management GUI provides an easy way to configure and manage various features that are available with the system, so it simplifies data management of petabytes of storage and all nodes from a cluster in a centralized way.

My two-node cluster is also easy to manage… well actually, not so much, so I’ll skip making a comparison on this one.

Active-active clustering

Another thought is the cluster itself. With Spectrum Scale, it’s a real active-active cluster. All data access is done in parallel through the nodes. If a node goes offline, access to the data is still available and functions are undertaken by the other nodes.

The same thing happens at home if I issue the “mmshutdown” command to one of my nodes, by which I mean put one of my kids to sleep. The awake node will remain active, playing and making all the mess that would’ve been done if both nodes were up.

Scalability

And last but not least, as the name says, IBM Spectrum Scale can scale. It supports up to 256 file systems of 18 PB each in a single cluster, and it can have up to 16,384 nodes connected per cluster.

When it comes to my home though, two kids are enough for me and my husband to manage, and we are not looking to scale up!

To learn more about IBM Spectrum Scale, check out the website. And if you’re looking for proven experience on designing and building storage and softwaredefined infrastructure systems, reach out to IBM Systems Lab Services Storage and Software Defined Infrastructure. We can help you efficiently capture, deliver, manage and protect your data with superior performance. Email us to learn more.

Storage Consultant, IBM Systems Lab Services Latin America

More Services stories

5 top takeaways from Think 2018

The first Think conference is in the rear-view mirror. There, visionary speakers and experts shared their solutions for some of the world’s most daunting challenges, and IBM revealed some of our big bets on infrastructure innovation in the coming years. Now that I’ve had some time to reflect on the conference, I’ve assembled my five […]

Continue reading

Cloud infrastructure designed for your business model

When we talk about cloud, one of the most important challenges for cloud service providers is changing the old thinking about protecting data. With all of the cyberattacks being launched on companies, there’s no doubt that security is extremely important. It’s even more important if we consider that data breaches can lead to the end […]

Continue reading

Taking the AI training wheels off: moving from PoC to production

In helping dozens of organizations build on-premises AI initiatives, we have seen three fundamental stages organizations go through on their journey to enterprise-scale AI. First, individual data scientists experiment on proof of concept projects which may be promising. These PoCs then often hit knowledge, data management and infrastructure performance obstacles that keep them from proceeding […]

Continue reading