On the ground, people fill brick-and-mortar storage facilities with all kinds of items, whether they’re downsizing homes, stashing personal keepsakes, or heading overseas with nothing but their suitcases in hand. But in the cloud, people are investing in storage facilities and solutions designed to hold vast amounts of another kind of personal asset: data.
In fact, the requirement for global data storage capacity is increasing exponentially each year. According to Statista, people create 328.77 million terabytes of data each day, equating to approximately 120 zettabytes of data per year. These mountains of data have only grown since 2010, with experts estimating that 90% of all global data available today was generated in the last two years alone.
Since the two measly zettabytes of 2010, the global stockpile of data has increased more than 60 times over. If projections hold true, the 120 zettabytes generated by the end of 2023 will balloon by over 150% in 2025, reaching a new high of 181 zettabytes.
Just like people stashing furniture, boxes, and boats in earth-bound storage containers, people using cloud storage do so for a wide range of reasons. Ceph is one of these storage facilities in the ether, and the company’s 2022 user survey sheds light on who is using Ceph’s cloud-based storage and why.
What is Ceph?
Before digging into the survey’s results, it’s helpful to paint a broad picture of just what Ceph offers. In a nutshell, this open-source software-defined storage solution aims to address the block, file, and object storage needs of today’s businesses. The name of the game in this space is providing affordable storage that is highly reliable and scalable.
Sage Weil envisioned Ceph during his doctoral program at the University of California, Santa Cruz. His project began as a file system prototype before blossoming into an open-source storage platform with wide-ranging capabilities.
Today, those capabilities include decoupling data from hardware with software abstraction layers and offering interfaces for multiple storage types within a single storage space. This enables people to stash large volumes of data without multiple storage solutions or specialized hardware.
Who is using Ceph?
According to the latest user survey, industries in 44 countries rely on Ceph as a data storage solution. Of its total user base, 39.37% have been storing data with Ceph for over five years and 25.98% for between two and five years.
Possibly the most revealing question of the survey asked users to report their industry. Surprisingly, 57.48% of 127 respondents to Ceph’s most recent user survey indicated that their needs arise from the commercial sector.
“You tend to expect Ceph’s clientele to fall in the realm of academia,” says Martin Verges, founder and CEO of croit. “However, the numbers don’t lie — only 22.83% of Ceph’s users are in that space.”
The remaining participants of the survey form a small slice of Ceph’s user base, with those using the storage for personal reasons making up only 13.39% of the company’s user base. The nonprofit, government, miscellaneous other, and military sectors ranked at 9.45%, 8.66%, 6.3%, and 2.36% respectively.
How people are using Ceph data storage
The survey of Ceph users reveals that almost all respondents use the software for block storage, with a significant shift toward the software’s RADOS Block Device. “There could be a number of reasons for this,” speculates Verges, “but I tend to think it relates to more people using OpenStack and Kubernetes platforms that pair nicely with Ceph’s RBD.”
Another notable shift is the 10% increase in survey respondents who reported using Ceph to provide multiple kinds of storage services in 2022 than in 2021. “It appears that the global market is favoring collaboration systems that can work well across hybrid storage implementations,” observes Verges.
According to the survey, respondents use Ceph as a data storage solution for five main reasons. The fact that the software is open source ranks highest with 91.34% of users.
Ceph users also appreciate scalability, with 78.74% of survey respondents ranking this reason as the highest. In the survey, some users report storing over 50 petabytes of data on Ceph, not including replication or erasure coding.
It’s inevitable that one reason for choosing a data storage solution would ensure the durability, reliability, and integrity of the data. In the survey, 77.95% of Ceph users ranked this reason as their highest priority.
“When human error is taken out of the equation, Ceph doesn’t lose data,” Verges says. “The designers build redundancy into every system. They go into it assuming everything will fail, even whole data centers, then design safeguards to protect data in each and every scenario.”
The final priority Ceph users seem to value is affordability, ranking highest among 52.76% of survey respondents. This is due to the fact that Ceph costs nearly 10% less per GB for primary storage than other data storage solutions.
As the amount of global data increases, surveys such as this provide invaluable information. Only by learning who is storing data and why can people hope to stay ahead of the world’s growing storage needs.
