How much data is stored on tape?

Tape has been used for data storage for decades, providing businesses and organizations with a reliable, cost-effective solution for long-term data retention and backup. But with the exponential growth of digital data in the modern era, many wonder – how much data can actually be stored on tape nowadays?

The History and Evolution of Tape Storage

Magnetic tape data storage emerged in the early 1950s, with IBM introducing their first commercial tape drive in 1952. Early tape drives used large open reels of tape that could hold a few megabytes of data. Tape technology continued advancing over the subsequent decades – tape widths got smaller, materials improved, and data densities increased dramatically. By the 1990s, cartridge and cassette tape formats like DLT and LTO emerged, making tape storage more practical and standardized.

Today, LTO (Linear Tape Open) remains the dominant tape format. LTO technology has gone through several generations, with each new generation roughly doubling the data capacity. The latest LTO-9 drives can hold 18 TB of uncompressed data per cartridge, a massive increase from LTO-1’s 200 GB per cartridge in 2000.

Tape Capacity Increases

Tape drive manufacturers continue to make major advances in tape capacity. Here’s a look at how much data various tape formats can hold:

Tape Format Native Capacity per Cartridge
LTO-1 100 GB
LTO-2 200 GB
LTO-3 400 GB
LTO-4 800 GB
LTO-5 1.5 TB
LTO-6 2.5 TB
LTO-7 6 TB
LTO-8 12 TB
LTO-9 18 TB

As the table shows, capacity increases rapidly with each LTO generation. And even greater capacities are on the horizon – the LTO roadmap outlines plans for 48 TB LTO-10 and 96 TB LTO-11 in the next few years.

Tape vs. Disk Storage

Tape has proven extremely scalable in terms of capacity, especially compared to hard disk drives (HDDs). Today’s highest-capacity HDDs top out at around 20 TB, similar to LTO-9 tape. But per-gigabyte costs are far lower with tape, making it more efficient for massive archives.

However, HDDs and solid-state drives (SSDs) offer faster random access to data. Tape works best as an offline archive or backup, not for live production systems. The sequential nature of tape drives makes them slower for accessing and updating individual files. But for rarely accessed cold data, tape provides enormous capacities offline at low cost.

How Much Data is Stored on Tape Today?

Estimating the total global volume of data stored on tape isn’t easy, as companies don’t publicly report their tape archives. But we can extrapolate some estimates based on tape sales and installed bases.

As of 2020, approximately 4 million LTO tape drives had been sold worldwide. Average LTO tape capacities are around 5-10 TB, meaning each tape drive could have 50-100 TB or more of data stored if fully loaded with tapes. This equates to around 200-400 exabytes of data stored on LTO tape worldwide.

Older and proprietary tape formats also hold vast amounts of data that have yet to be migrated to LTO. Overall, industry estimates peg the total amount of data stored on magnetic tape worldwide at around 400 exabytes. For context, this is approximately 80% of the total amount of data stored across hard disk drives!

Tape for Data Archiving

Tape remains highly popular for long-term data archiving. Its portability, longevity, and low cost make it ideal for storing large amounts of infrequently accessed data over extended time periods. Typical tape archive use cases include:

  • Regulatory compliance archives
  • Financial records
  • Healthcare patient records
  • Scientific data
  • Backups
  • Media libraries

Magnetic tape meets stringent requirements for data integrity over decades. And tape cartridges can be easily removed, transported, and stored in secure offsite facilities for data protection and retention.

Who Uses Tape Storage Today?

Tape is commonly found across industries and organizations that need massive data archives:

  • Research organizations – High energy physics, genome sequencing, astronomy, and climate modeling produce enormous datasets, much of which gets archived on tape.
  • Media companies – The entertainment industry archives large video and content libraries on tape.
  • Government agencies – Tape meets data retention requirements at low costs.
  • Financial services – Securities firms archive financial records and transactions on tape.
  • Hospitals – Patient medical records and imaging data is ideal for tape archiving.

Any organization with large amounts of inactive, “cold” data benefits from using tape for cost-effective long-term storage and retention.

Challenges and Limitations

While tape serves its archival purpose very well, it does come with some downsides:

  • Access latency – Retrieving data from tape introduces delays compared to disk or flash storage.
  • File management – Keeping track of data on thousands of tapes can be complex.
  • Durability – Tape media must be carefully stored and handled to ensure longevity.
  • Migrations – Transitioning to new formats requires migrating data to the latest tape tech.

These challenges can make it difficult to directly access and extract value from archived tape data. Solutions like digital tape libraries and analytics on tape-resident data are emerging to help overcome these limitations.

The Future of Tape Storage

Even with the rise of cloud storage, tape remains highly relevant in the digital era. Tape shipments continue growing year-over-year, and intense R&D continues on pushing tape capacities higher. While disks hold the edge for fast access, tape provides unmatched scalability on costs for less-active data.

One exciting innovation around tape is using it as an active storage tier integrated with cloud and disk systems. With the right infrastructure, even infrequently accessed data on tape can become available for analytics and intelligence. Tape’s unparalleled density will help it stay relevant well into the future.

Conclusion

In summary, current estimates indicate tape holds between 200-400 exabytes of data worldwide – equivalent to 80% of the total data stored on HDDs. Tape capacities and densities continue rapidly improving. LTO-9, today’s highest capacity tape format, can store 18 TB uncompressed on a single cartridge. Active R&D aims to push this to nearly 100 TB within the next decade.

Tape adoption remains strong for long-term data retention across numerous industries. While newer technologies have emerged, tape’s portability, longevity, and low cost make it ideal for massive archival storage. Even in the digital age, tape remains indispensable for any organization with large amounts of cold data to store cost-effectively over long time horizons.