5 Trends in Data Center Storage


Time of issue:2022-10-25

Views:

Data Center Storage Data center storage is a fascinating area. On the one hand, there are compliance requirements about storing certain materials and never deleting them. There are also retention policies for how long the data is kept and discarded after that.

 

But the value of the data should also be considered. It turns out that most data is looked at once and then ignored. There are many factors to consider with data center storage.

Here are some key trends in the data center storage market:

 

1. Artificial intelligence, hot and cold storage

When you see people taking high-definition videos and photos with smartphones at concerts, sporting events or parades, most of the footage will be sent to cloud data centers and never be accessed again.

The good news is that cloud storage providers are getting smarter at identifying these types of data-heavy, rarely accessed content, using artificial intelligence (AI) for IT operations (AIOps) and quickly routing them to cold storage .

Cold storage is being used for rarely accessed archival data, said Steve Carlini, vice president of innovation and data centers at Schneider Electric.

It's cost-effective, but it takes longer for users to access it if needed.

On the other hand, hot storage refers to fast, easily accessible data storage. Thermal storage technology is moving from spinning hard disk drive (HDD) technology to static solid state drives (SSD). SSDs are smaller, faster, and use a fraction of the energy of HDDs.

 

2. The need for speed

Data-intensive workloads supporting database and analytics applications increasingly require more compute and NVMeSSD storage resources, said Seth Bobroff, director of product marketing at Pliops.

"A new class of data processors has emerged in data center architectures to address performance and storage management efficiency challenges once addressed by adding more CPUs that overcome the use of traditional RAID technology in SSD deployments," said Bobroff. , ushered in the revival of RAID.”

 

3. Storage efficiency

With IT being asked to do more with less, storage systems will no longer be judged on their ability to deliver high performance or high capacity.

Instead, they are being evaluated on how they can meet those requirements in the most efficient way. Standard enterprise-class flash drives are available in capacities up to 200K per drive. Current storage systems require dozens of these drives to deliver hundreds of thousands of IOPS. At the same time, most vendors shy away from cost-effective high-density (20TB) hard drives due to the longer recovery time in the event of a drive failure.

"Modern storage solutions need to unlock the full performance potential of flash drives by handling I/O more efficiently, reducing the need for flash drives to as few as six drives, and it should also intelligently Flash is combined with hard drives to reduce costs while providing consistent performance between the two tiers.”

​​

4. Reduce data movement and copying

Another strategy for improving efficiency is to minimize the amount of data movement and copying. Organizations spend too much money, time and resources moving files and object data. This ties into the trend of taking stored data and moving and copying it to any application that needs it. This raises data capacity, management and security challenges. "Workflows can be designed to execute in real-time on remote, distributed datasets," said Steve Wallo, CTO of Vcinity. "Dynamic and agile application movement can now be accomplished while data remains in place, giving applications full access and performance without the penalty of network latency."

 

5. Data Decentralization

Data locations are no longer just servers. A decade ago, on average, companies kept data in about five places at most. Companies are now using more data sources than ever before: not just on-premises, but across multiple public cloud locations, including dozens of SaaS applications.

According to Simon Taylor, founder and CEO of HYCU, each siloed data source creates, on average, more than 150 locations for medium-sized businesses, and even higher for larger businesses.​​

"The wide range of data locations presents challenges for data protection and backup and recovery, and as companies adopt new data locations, they need to eliminate sprawl, reduce the number of silos, and protect data in a unified and holistic manner, while processing Emerging and new threats such as the stealthy rise of ransomware and the growing threat of cyberattacks.”