The Boom of Data, The Power of Scale

DEC 15, 2020

By: John Lukavsky, Engagement Architect, Trace3

In 2016 after about four decades of global Internet use, a trillion gigabytes of collective data officially became the first Zettabyte and launched a new era of storage. In four short years, and one pandemic later, the Zettabyte is no longer the largest approved standard size of storage. This is because a Zettabyte takes only days to create enough data to fill— about six if we were to look at the number of Zettabytes expected this year. According to the International Data Corporation (IDC) in 2020 alone, the Global DataSphere is likely to hit 59 Zettabytes, and by 2025 they are projecting the amount of global data will grow to 175 Zettabytes, of which will be unstructured data.

What does this all mean? The ‘Boom of Data’ hasn’t even hit us yet, and the ability to store and protect your data is increasingly more important. You need the right technology that can take these challenges on, and scale to meet data demands. Below are the Top-Ten ways the Dell EMC PowerScale can help you tackle any amount of data headed our way.

  1. Cost

The Dell EMC PowerScale is a massively scalable single name space NAS platform that serves data on almost any protocol – NFS, SMB, HDFS, and S3 at the same time. One key feature that enables you to manage costs is the ability to add one node at a time if you want, which allows you to predict future costs and makes budgeting simple. You also have the option of putting hot data on faster nodes/drives and tiering down cold data to less expensive nodes or the cloud, which allows you to get ‘the most bang for your buck’.

  1. Storage Efficiency

OneFS delivers up to 80 percent storage utilization. The PowerScale uses erasure coding to break up the files and add protection (like how RAID works) and efficiency improves with the more nodes that you have.

SmartDedupe data deduplication can further reduce storage requirements by up to 30 percent. The F200, F600, F810 all-flash, and the H5600 hybrid platforms deliver high-speed in-line data compression and deduplication to improve storage utilization depending on the dataset.

  1. Storage Tiering

There are many models of PowerScale that allow you to pick what best fits your needs with SmartPools. SmartPools allow you to define policies that are based on metrics that you choose – whether it’s a file path, access time, modify time, and more to move data to the tier that you choose. You can also tier to the cloud or Dell EMC ECS as another optional tier using CloudPools.

  1. Access Zones

Access Zones in PowerScale serve multiple purposes. Since PowerScale is a single namespace file system you can use multiple Access Zones to segregate data from organizations if you’re a managed service provider or if you have separate authentication providers for different sets of data within your same organization. You can also grant administrators rights to just manage their own Access Zones if you want as well and not to the entire cluster.

  1. Performance

The back-end and front-end networking ranges from 10Gb to 100Gb NICs on each node. Since these clusters can grow to be so massive another great option is having the ability to just let certain nodes have management connectivity. This allows the slower nodes that may not be used for client connectivity don’t waste additional network connectivity.

  1. SmartQuotas

Just because you have a huge pool of data capacity doesn’t necessarily mean you want to allow users to use it all. You can implement SmartQuotas to limit usage by assigning quotas at the cluster, directory, subdirectory, user, and group levels. They can be configured as hard, soft, or advisory limits with additional options for alerting users and actions.

  1. Data Intelligence

CloudIQ monitors your cluster(s) and allows for issue identification, expedition of problem resolution, and data growth patterns for expansion needs for all your clusters in the same interface.

DataIQ provides information about your data, for example, data type, size, age, and modification date. This allows you to plan your tiering strategy thoughtfully while remaining the most cost-effective by moving hotter data towards flash and colder data towards the cloud.

  1. SnapshotIQ and SyncIQ

By now snapshots and replication are a basic requirement of any storage platform. SnapshotIQ allows for on-demand snapshots, snapshots on a schedule, up to 1024 snapshots per-directory, and changes to files are saved in the snapshot at the block level. SyncIQ allows for a high-performance replication using as many nodes as you choose to have participated in replication responsibilities. You can configure replication for the entire cluster at your base level directory or make multiple replication policies at different directory levels. Replication works at the block level as well so that only changed blocks are transferred to the target cluster, which any cluster can be actively serving data as well as serving as a SyncIQ target.

  1. Additional features

There are many more features of PowerScale, such as SmartLock, which allows you to protect your data from being altered either for your company policy or SEC compliance. SmartConnect is what wraps all the networking together and allows you to have multiple IP Pools, subnets, allows for seamless client failover, and more.

  1. 3rd Party Integration

Superna offers many different products with their base product Superna Eyeglass DR edition helping you to automate failover to a second cluster. Automated, not automatic, it won’t automatically failover your cluster if a network outage occurs, for example, you still have to manually tell it you want to fail over. You could, if you want, create your script to make it automatic though, but that has other implications that need to be considered as well. An add-on product to Superna Eyeglass is Ransomware Defender which monitors your cluster(s) in real-time and can lockout users if a ransomware threat is detected, as well as potentially provide an ‘AirGap’ solution between your clusters as well. Superna also has many other add-on products such as Easy Auditor, Search and Recover, Golden Copy, Performance Auditor, and Cluster Storage Monitor to help you manage your clusters and data.

As you can see in this basic introduction to Dell EMC PowerScale it is a feature rich enterprise class NAS storage platform that I have barely scratched the surface on the potential of it.

Leave a Reply

Your email address will not be published. Required fields are marked *