By Guest Blogger, Dr. Shawn O. Brume Sc. D., IBM Tape Evangelist and Strategist
According to a study by McKinsey, the average lifespan of companies listed in Standard & Poor’s is less than 18 years! That means that tape technology is already in business almost 4 times longer than the average S&P will survive. Tape technology celebrated 70 years young on May 21st. Tape has been and continues to be the most transforming data storage technology in history.
In the 50’s it was the only viable technology for storing data generated by the few computers in existence. In the 60’s tape took the world to the moon and preserved the data for usage nearly 40 years later when it was retrieved to assist in modern space explorations. By the 70’s Tape was dominating storage, transforming the financial industry by providing the ability to access data on accounts with minimal human intervention. The 80’s and 90’s continued the transformation of data availability by performing transactional data storage for ATMs, but also was key in the investigation of the space shuttle Challenger disaster; an investigation enhanced as a result of the durability of tape even when submerged in saltwater.
Today tape lives in the data center, preserving Zettabytes of data. Data being preserved and utilized across nearly every industry, examples:
Healthcare – Data preserved on tape is being utilized to develop new predictive health services. Digital medical records can be retained for the life of patients and shared across organizations.
Financial – Online transaction retention ensures customers valuable financial data is protected in the eventuality of a cyber-attack. Mortgage loans are preserved without fear of tampering.
Cloud – Data stored in public clouds are growing at a 30% faster rate than traditional storage. Cloud providers rely on tape to provide data durability and low-cost storage subscriptions.
Tape’s popularity has often been driven by the low cost of storage, modern data storage requires so much more including cyber-resiliency, data durability and low carbon footprints that enable sustainable IT.
Cyber Resiliency – Tape is the only true airgap data storage solution available.
Data Durability – Tape has a native single copy durability of 11- Nines. This means the likelihood of a single bit failure is 1 in 100 Petabytes.
Sustainability – At scale tape technology is 96% lower carbon footprint than highly dense HDD storage (when comparing OCP Bryce canyon and IBM tape technology with 27PB of data).
If preserving data, in a cyber-resilient solution, at low cost, with relatively low carbon impact meets your business outcomes, then why wait? Clearly tape is here to stay and surging in usage across nearly every business use case.
Happy 70-years to an amazing technology!
For more information about technology since tape’s introduction, check out this post from my colleague Mike Doran.
The Tape Storage Council, (TSC), released a new report “Tape to Play Critical Roles as the Zettabyte Era Takes Off,” which highlights the current trends, usages and technology innovations occurring within the tape storage industry. The zettabyte era is in full swing generating unprecedented capacity demand as many businesses move closer to Exascale storage requirements.
According to the LTO Program, 148 Exabytes (EB) of total tape capacity (compressed) shipped in 2021, marking an impressive record year. With a growth rate of 40%, this strong performance in shipments continues following the previous record-breaking 110 EB capacity shipped in 2019 and 105 EB of capacity shipped in the pandemic affected year of 2020.
The ever-increasing thirst for IT services has pushed energy usage, carbon emissions, and reducing the storage industry’s growing impact on global climate change to center stage. Plus, ransomware and cybercrime protection requirements are driving increased focus on air gap protection measures.
As a result of these trends, among others, the TSC expects tape to play an even broader role in the IT ecosystem going forward as the number of exabyte-sized environments grow. Key trends include:
Data-intensive applications and workflows fuel new tape growth.
Data accessibility. Tape performance improves access times and throughput.
Tape should be included in every green data center strategy.
Storage optimization receives a big boost from an active archive which provides dynamic optimization and fast data access for archival storage systems.
Organizations continue to invest in LTO tape technology thanks to its high capacity, reliability, low cost, low power consumption and strong data protection features, especially as threats to cybersecurity soar.
I had the opportunity to present at AFCOM’s Data Center World (DCW) exhibit and conference in Austin, Texas yesterday. The first thing I have to share about this experience is how surreal it was to get back on an airplane! It was my first trip since COVID started two years ago with many zoom presentations and virtual conferences since then. But not much has changed about air travel. The seating is still cramped, the flight was packed full, and my dog gets more snacks in a four hour period than I did on my four hour flight!
Committed to Sustainability Sustainability is a hot topic these days and was one of the main themes of this year’s DCW. It was also the topic I presented on, specifically “How to Avoid CO2 Emissions in Long Term Storage with Modern Data Tape Technology.” The good news is that the DCW attendees that I met and listened to in other sessions are genuinely concerned about the environment and worried about what kind of planet we will be leaving behind for our kids and grandchildren. They recognize the opportunity to improve sustainability in data center operations and are committed to it.
Key Questions about Storage At the outset of my presentation, I asked for a show of hands for those directly involved in data storage. I was not surprised to confirm my suspicion that there would be few if any attendees to raise a hand, since AFCOM’s DCW is more about facilities management than storage management. But I was also glad to see this because we need everyone to be advocates for any possible sustainability improvements in IT operations. So I asked my audience to lean on their colleagues in storage and pose two simple questions to them: “If data has gone cold and is infrequently accessed, why are we keeping it on energy intensive tiers of storage like constantly spinning and heat producing HDD arrays? Why not move it to eco-friendly tape?” The attendees in my session admitted they can feel the power drain and heat being produced by endless disk arrays in their data centers.
Climate Change and Global Warming I began my presentation by setting the stage on global warming from the forest fires in 2020, to the Texas deep freeze in early 2021, to the fact that July of 2021 was the hottest month ever on earth. Add to this the dire reports from the U.N. in late 2021 and early 2022. All this has led to changing consumer sentiment demanding that governments do more. Thankfully they are. Corporate attitudes are also changing from resistance to action on climate and we will be seeing more CSOs (Chief Sustainability Officers) being appointed and implementing change top down. Even Wall Street and the SEC are getting in on the act, demanding reporting and disclosures on corporate sustainability initiatives.
Energy Intensive IT Industry Next, I confirmed what we all know, that the IT industry is energy intensive and its demand for energy is rapidly increasing. The demand curve for energy looks similar to the demand curve for data storage. Driven by digital transformation, IDC expects persistent data that needs to be stored to grow from 2.0 ZB in 2016 to more than 11.0 ZB in 2025, a CAGR of 27%. Suffice it to say no one in the audience really understood what a zettabyte was or that just one zettabyte was equal to the capacity of 55 million LTO-9 data cartridges or 55 million 18.0 TB HDDs. That’s a lot of storage requirement for one zettabyte, let alone 11.0 zettabytes in 2025. We are going to need a lot of flash, disk and tape to handle that kind of volume!
Renewable Energy plus Conservation Next came the conversation about renewables and how Greenpeace has done a great job advocating for more use of renewables in data centers, especially the cloud hyperscalers. But from the looks of progress being made on this front, renewable sources of energy likely can’t come on line fast enough or cheaply enough, or in sufficient volume to satisfy the energy needs of the massive data center industry. While Fujifilm is a big fan of renewables (we use it ourselves for our LTO plant in Boston) what’s really needed is a combination of renewables and energy conservation. How about turning off those lights and HDDs before leaving the office each night!
The Data Life Cycle When it comes to conserving energy in data storage, one needs to understand a few simple principles related to the “data lifecycle.” Data quickly goes cold and access frequency drops off dramatically after 30, 60 or 90 days. At the same time, data retention periods are getting longer, sometimes reaching indefinite time periods. This is where data tiering saves the day as cold data can move from expensive, energy intensive tiers of storage to economy, eco-friendly tiers like modern data tape.
Advantages of Eco-Friendly Tape I then shared the research findings from Brad Johns Consulting in his two white papers where tape consumes 87% less energy and produces 87% less CO2 than equivalent amounts of HDD storage. When analyzed over the total product lifecycle from procurement of raw materials to production to distribution to usage and finally disposal, tape produces 95% less CO2 than HDD and produces 80% less e-waste. I also shared the results of an IDC study that shows migrating more cold data from tape to HDD could result in an avoidance of 664 million metric tons of CO2 on a global basis by 2030. That’s the CO2 equivalent of 144 million automobiles being taken off the road for a full year! I also referenced research by IBM showing a side by side compare of TS4500 tape library and Bryce Canyon HDD where the IBM gear produced 80% less CO2 over a ten year period than the Bryce Canyon system. To round things out, I shared the end user perspective from an executive roundtable where Microsoft Azure stated:
“When you take the material savings and power savings, tape actually does offer quite a bit of advantage compared to other technologies that are on the market today.”
Tape remains the lowest cost storage media on a $/GB basis
Tape storage supports air gap ransomware
Tape can reliably store data for long periods with an excellent bit error rate
Tape technology has room to grow in areal density and therefore capacity, and has a well-defined roadmap
I concluded by saying that data growth is here to stay and the volumes of valuable data are getting enormous. What the industry needs to do in support of strategic data storage management and sustainability objectives is this:
“Get the right data, in the right place, at the right time, at the right cost, and…at the right energy consumption level.”
I think the attendees got the message and now see modern tape storage as part of the carbon reduction answer for the data centers of today and tomorrow. It was well worth the snack deprived four hour flight!
In early August of this year, a United Nations panel called the “Intergovernmental Panel on Climate Change (IPCC)” issued a new report, the Sixth Assessment Report, on climate change and global warming. You can explore the lengthy and technical full report here. But in short, a few key headline statements from the report include:
It is unequivocal that human influence has warmed the atmosphere, ocean, and land. Widespread and rapid changes in the atmosphere have occurred.
Global warming of 1.5 degrees C and 2.0 degrees C will be exceeded during the 21st century unless deep reductions in carbon dioxide (CO2) and other greenhouse gas emissions occur in the coming decades.
Many changes in the climate system become larger in direct relation to increasing global warming. They include increases in the frequency and intensity of hot extremes, marine heatwaves, and heavy precipitation, agricultural and ecological droughts in some regions, and intense tropical cyclones as well as reductions in Arctic sea ice, snow cover, and permafrost.
Many changes due to past and future greenhouse gas emissions are irreversible for centuries to millennia, especially changes in the ocean, ice sheets, and global sea level.
The U.N. report is pretty scary, especially that last bullet. But think about the severe weather events we experienced in 2020 only to be outdone by recent calamities in 2021 like the Texas deep freeze, the record heat in the Pacific Northwest, torrential floods in Europe, China and the U.S., extreme storms, not to mention the worsening forest fires.
A Time for IT to Take Action on Climate Change
We as a society, as individuals and as commercial organizations and governments need to take action. No effort is too small, even turning off a single light switch when not needed is worthwhile. Collectively we can make a difference.
The IT industry is no exception and needs to take action. Data centers are major consumers of energy amidst rapid and widespread digital transformation initiatives resulting in exponential data growth. While the IT industry has made significant strides in ramping up renewable sources of energy, it can’t come online fast enough or cheaply enough to make a big difference. What is also needed is energy conservation and storage is a good place to start.
Assessing the Eco-Friendly Advantages of Tape
Back in November of 2020 industry expert and consultant Brad Johns published a whitepaper on the energy advantage of today’s modern and highly advanced data tape systems. That paper, entitled “Reducing Data Center Energy Consumption and Carbon Emissions with Modern Tape” showed:
Tape systems consume 87% less energy and therefore reduce CO2 emissions by 87% compared to equivalent capacities of HDD storage.
What’s more, the lower energy consumption of tape contributes to an 86% reduction in TCO.
More recently, Brad Johns did an even deeper dive into the energy advantage of tape in a second whitepaper on the subject entitled: “Improving Information Technology Sustainability with Modern Tape Storage.” This time, instead of just looking at energy consumption during the operational usage phase of tape vs. HDD, Brad decided to look at the energy consumption and environmental impact of tape vs. HDD from “cradle to grave.” That is to say, from sourcing of raw materials to manufacturing, to distribution, to usage, and disposal at end of life. Here are the key findings:
Tape produces 95% less CO2 than HDD during its lifecycle from manufacturing to disposal.
Electronic waste (e-waste) at the time of disposal is reduced by 80% for tape compared to HDD.
Ten-year TCO in this paper shows a 73% reduction for tape compared to HDD.
Brad also did a “what if” scenario as follows: what if industry best practices were truly observed and 60% of HDD data was moved to tape systems?
72 million tons of CO2 would be avoided, a 57% reduction compared to keeping all the data on HDD!
To download this whitepaper for complete details, click here.
While simply using more tape for cold and inactive data won’t solve climate change or make scary U.N. reports go away, it certainly is a positive contribution to the global effort. We all need to do whatever we can so that collectively we can make a difference.
There is increasing pressure around the world to reduce emissions and lower mankind’s carbon footprint. It is up to the IT sector to do its part, and that means considerably lowering power usage. But that is easier said than done when you consider the statistics.
IDC predicts we will arrive at the mind-boggling figure of 175 zettabytes of data in the digital universe within 4 years. 175 ZB? Consider how long it takes most users to fill a one TB drive. Well, 175 ZB equates to approximately 175 billion TB drives.
The problem is this: how do you reduce IT’s overall power draw in the face of a massive and continual upsurge in data storage? Once 175 ZB of data exists, there is no possibility of containing electrical usage if the vast majority of storage is sitting on hard disk drives (HDDs). The only solution is to cure the industry’s addiction to disk.
Here are the numbers. Data centers alone account for close to 2% of all power consumed in the U.S., about 73 billion kilowatt hours (kWh) in 2020. That is enough to set off the alarm bells. Yet tremendous progress has been made over the past two decades in terms of data center efficiency. When power consumption in data centers soared by 90% between 2000 and 2005 period, the industry acted forcefully. The rate of growth slowed to 24% between 2005 and 2010 and then fell to less than 5% for the entire decade between 2010 and 2020. That’s miraculous when you consider that it was achieved during a period that represented the largest surge in storage growth in history. Smartphones, streaming video, texting, multi-core processors, analytics, the Internet of Things (IoT), cloud storage, big data, and other IT innovations demanded the retention of more and more data.
Big strides were made in Power Usage Effectiveness (PUE – the ratio of data center power consumption divided by the power usage). Data centers have largely done a good job in improving the efficiency of their operations. But the one area lagging badly behind is storage efficiency.
By Rich Gadomski, Fujifilm, and Paul Lupino and Tom Trela, Iron Mountain
If there was ever a time for industries and governments around the world to come together and finally take steps to mitigate climate change, now would seem to be it. The return of the United States to the Paris Climate Agreement and the recent U.S. – China talks on climate change are all positive signs when it comes to moving the needle forward on sustainability initiatives. While fighting COVID-19 took center stage in 2020 and early 2021, our future depends on what we do collectively to reduce our environmental impact now and in the immediate years ahead.
It’s Hard to Deny Global Warming and Climate Change
According to an article that appeared in the Wall Street Journal earlier this year, NASA has ranked 2020 as tied with 2016 for the warmest year since record-keeping began in 1880. In a separate assessment, NOAA (National Oceanic and Atmospheric Administration), which relies on slightly different temperature records and methods, calculated that the global average temperature last year was the second highest to date – just 0.04 degrees Fahrenheit shy of tying the record set in 2016.
On top of the record number of hurricanes and the wildfires out west, the recent Texas deep freeze, which caused widespread power outages and other weather-related tragedies and calamities, seems to be just one more example of climate change. Weather patterns are becoming more unpredictable, which can result in extreme heat, cold and increased intensity of natural disasters.
It is widely acknowledged that global temperatures have been rising especially in the north polar region where we have seen a dramatic shrinking of the polar ice cap. When Arctic air warms, it sets off an atmospheric phenomenon that weakens the polar vortex (the normal jet stream of wind that keeps frigid air to the north) and allows cold air to fall…as far as Texas.
Data Center Energy Consumption and the Advantage of Modern Tape Technology
The key to mitigating the worst impacts of climate change is a reduction in the amount of greenhouse gases produced by humans. Producing energy is extremely resource-intensive, so reducing the amount of energy we consume in all aspects of our lives is of critical importance.
Data centers are significant consumers of energy accounting for as much as 2% of global demand and rising to 8% by some estimates. Data centers can do their part to reduce energy consumption in many ways by becoming more energy-efficient, including simply migrating the vast amounts of still valuable, but rarely accessed, “cold data”.
The changing landscape of the data protection industry has evolved from primarily backing up data in order to recover from hardware, software, network failures and human errors, to fighting a mounting wave of cybercrime. Over the years, hardware and software have significantly improved their reliability and resiliency levels but security is a people problem, and people are committing the cybercrimes.
Cybercrime has now become the biggest threat to data protection and the stakes are getting higher as anonymous individuals seek to profit from other’s valuable digital data. With a cease-fire in the cybercrime war highly unlikely, we are witnessing a rapid convergence of data protection and cybersecurity to counter rapidly growing and costly cybercrime threats, including ransomware. The growing cybercrime wave has positioned air-gapped storage solutions as a key component of digital data protection – they simply can’t be hacked.
Traditional backup and archival data can be stored locally or in cloud environments. In contrast, a cyber-resilient copy of data must meet additional more stringent requirements. This is where “air gapping” and tape technology are gaining momentum. The rise of cybercrime officially makes the offline copy of data stored on tape more valuable and takes advantage of what is referred to as the tape air gap. The tape air gap is an electronically disconnected or isolated copy of data in a robotic library or tape rack that prevents cybercriminals from attacking a backup, archive or any other data.
Tape cartridges in a robotic tape library or manually accessed tape cartridges in tape racks, are currently the only data center class air-gapped storage solution available.
Organizations across all industries are concerned about global warming and are actively looking for ways to reduce carbon emissions. As a result, many companies have decided they must incorporate carbon reductions into their strategies and have announced green initiatives.
Fortunately for IT organizations, there is a significant opportunity to achieve meaningful carbon emissions reductions while lowering operational and capital expenses by changing the way they store their data. Researchers estimate that data centers consume 1.8% of all electricity in the United States. Within the data centers, data storage is a significant portion of total energy usage and disk systems are the primary driver of storage energy consumption.
It is estimated that up to 60% of stored information is seldom accessed, meaning that the expectation of access diminishes after 30 days. By identifying this “cold data” and moving it to modern tape storage, organizations can dramatically reduce energy consumption and associated carbon emissions while also lowering data center capital and operational expenses.
Part 3: THE VALUE OF TAPE RISES RAPIDLY AS HYPERSCALE DATA CENTERS GROW
In Part 2 of this series, we looked at some of the key characteristics of hyperscale data centers. Now, we’ll explore how tape plays a role.
Today HSDCs are leveraging the many advantages of tape technology solutions to manage massive data growth and long-term retention challenges. Keep in mind most digital data doesn’t need to be immediately accessible and can optimally and indefinitely reside on tape subsystems. Some data requires secure, long-term storage solutions for regulatory reasons or due to the potential value that the data can provide through content analysis at a later date. Advanced tape architectures allow HSDCs to achieve business objectives by providing data protection for critical assets, backup, recovery, archive, easy capacity scaling, the lowest TCO, highest reliability, the fastest throughput, and cybersecurity protection via the air gap. These benefits are expected to increase for tape in the future.
Fighting the cybercrime epidemic has become a major problem for most data centers and HSDCs are no exception. Tape can play a key role in its prevention and provides WORM (Write-Once-Read-Many) and encryption capabilities providing a secure storage medium for compliance, legal and any valuable files. Tape, as an “Air Gap” solution, has gained momentum providing an electronically disconnected copy of data that prevents cybercrime disasters from attacking data stored on tape. Disk systems remaining online 7×24 are the primary target as they are always vulnerable to a cybercrime attack.
HSDCs are taking advantage of tiered storage by integrating high-performance SSDs, HDD arrays and automated tape libraries. Even though HSDCs are struggling with the exploding growth of disk farms which are devouring IT budgets and overcrowding data centers, many continue to maintain expensive disks often half full of data which often has little or no activity for several years. Obviously, few data centers can afford to sustain this degree of inefficiency. The greatest benefits of tiered storage are achieved when tape is used as its scalability, lower price and lower TCO plays an increasing role as the size of the storage environment increases. For the hyperscale world “adding disk is tactical – adding tape is strategic.”
Part 2: CHARACTERISTICS OF THE HYPERSCALE DATA CENTER
In Part 1 of this series, we looked explored the definition of hyperscale data centers. Now, we’ll take a look at some of the key characteristics.
HSDCs don’t publicly share an abundance of information about their infrastructure. For companies who will operate HSDCs, the cost may be the major barrier to entry, but ultimately it isn’t the biggest issue – automation is. HSDCs must focus heavily on automating and self-healing environments by using AI and ML whenever possible to overcome inevitable and unexpected failures and delays. Unlike many enterprise data centers, which rely on a large full-time staff across a range of disciplines, HSDCs employ fewer tech experts because they have used technology to automate so much of the overall management process. HSDC characteristics include:
Small footprint, dense racks–HSDCs squeeze servers, SSDs (Solid State Disks) and HDDs (Hard Disk Drives) directly into the rack itself, as opposed to separate SANs or DAS to achieve the smallest possible footprint (heavy use of racks). HSDC racks are typically larger than standard 19” racks.
Automation–Hyperscale storage tends to be software- defined and is benefitting from AI delivering a higher degree of automation and self-healing minimizing direct human involvement. AI will support automated data migration between tiers to further optimize storage assets.
Users–The HSDC typically serves millions of users with only a few applications, whereas in a conventional enterprise there are fewer users but many more applications.
Virtualization–The facilities also implement very high degrees of virtualization, with as many operating system images running on each physical server as possible.
Tape storage adoption–Automated tape libraries are on the rise to complement SSDs and HDDs to easily scale capacity, manage and contain out of control data growth, store archival and unstructured data, significantly lower infrastructure and energy costs, and provide hacker-proof cybercrime security via the tape air gap.
Fast scaling bulk storage–HSDCs require fast, easy scaling storage capacity. One petabyte using 15 TB disk drives requires 67 drives and one exabyte requires 66,700 15 TB drives. Tape easily scales capacity by adding media, disk scales by adding drives.
Minimal feature set–Hyperscale storage has a minimal, stripped-down feature set and may even lack redundancy as the goal is to maximize storage space and minimize cost.
Energy challenges–High power consumption and increasing carbon emissions has forced HSDCs to develop new energy sources to reduce and more effectively manage energy expenses.
In Part 3 of this series, we’ll take a look at the how the value of tape is rapidly rising as hyperscale data centers grow. For more information on this topic, download our white paper: The Ascent to Hyperscale.
Usage of Cookies