Please consider a donation to the Higher Intellect project. See https://preterhuman.net/donate.php or the Donate to Higher Intellect page for more info.

Driving the Digitized World

From Higher Intellect Vintage Wiki
Revision as of 02:03, 8 October 2020 by Netfreak (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Introduction

The rapid transformation of our world into a digitized world — one in which vast amounts of alphanumeric, audio, and video information are stored in digital, rather than analog form, — has impacted today’s home and work environments. Digital information can be manipulated by computer users, transmitted over networks, and randomly accessed and retrieved. Behind the scenes, helping to move this information revolution from pipedream to widespread reality, is today’s faster, reliable and economical hard disk drives.

Most desktop computers include 3.5-inch drives that provide the storage needed to create graphics or presentations, play multimedia-based computer games, or download information after “surfing the net.” These drives must provide increased capacities at lower costs in order to accommodate the delivery of digitized applications to end users.

High-end drives, which offer even higher capacities and more performance features than their desktop counterparts, are an enabling technology for high-end digitized applications: professional video and audio production, video-on-demand, E-mail, medical imaging and satellite communications.

In order to meet the needs of these particularly storage-intensive applications, hard disk drives must be able to provide:

  • Ever-increasing capacities
  • High random throughput
  • High sequential throughput
  • Uninterrupted data streams
  • High reliability

Unlimited Capacities

The capacity rule today is “you can never have too much.” Today’s high-end 3.5-inch drives, such as the Quantum Atlas™ II and Quantum Empire™ II drives offer as much as nine gigabytes (GB). Depending on the compression method used, half an hour of audio requires about 30 megabytes (MB) and one hour of video requires approximately 2GB of storage space. With these demands, it is easy to see why high capacities in digitized applications are a necessity — not a luxury.

Drive capacity is typically increased by altering the mechanical design or improving areal density (capacity per disk). The first method involves simply adding more disks and heads. Though this is a common and widely accepted practice, it does add expense and complicates manufacturing.

Increasing the drive’s areal density also results in increased storage capacity. Commonly measured in bits per square inch, areal density has been doubling every 18 months over the last three years. The most advanced drives accomplish this feat by incorporating new Partial Response Maximum Likelihood (PRML) read channels, new magnetoresisitive (MR) heads, or a combination of the two technologies. PRML read channels and MR heads will eventually replace the peak detect read channels and inductive head technology used since the introduction of the first hard disk drives.

The fact that 3.5-inch drives now offer 9GB versus 4GB just one year ago, demonstrates the ability of drive vendors to improve areal density at amazing rates. But consider the Internet or video-on-demand, both of which can easily consume terabytes (1,000 gigabytes) of storage space. To achieve these desired capacities, servers today may feature 60 or more drives housed in a single cabinet. Thus, today’s Internet and video servers add a whole new meaning to the term “capacity requirements.”

High Random Throughput

Superior random throughput is required of high-end drives in the digitized world — especially when used in server environments. Video servers, for example, allow multiple viewers to access and watch the same movie — with each viewer able to pause, rewind and fast forward, as if they were using their own personal VCR. These and other digitized applications such as E-mail, voicemail, the Internet and other on-line database services are highly dependent on rapid random throughput.

Random throughput can be increased by reducing a drive’s command overhead time, head seek and settle time, and rotational latency (which occurs when the head arrives at the appointed track, but then must wait for the requested data to rotate under it). Command overhead, for example, is reduced by executing SCSI commands in hardware rather than firmware. Average rotational latency is also improved with drive spin speeds as high as 7,200 RPM.

Random throughput can be improved by adding intelligence to the drive design. Quantum drives, for example, now incorporate the built-in processing power of a 386 chip to control the inner workings of the drives. This increased intelligence is used to add new features including advanced reordering algorithms. Quantum’s Optimized Reordering Command Algorithm (ORCA™) feature reduces average latency by 20 percent by reordering and optimizing commands, looking for the shortest total seek plus latency times.

High Sequential Throughput

High sequential throughput is essential for such applications as video editing, medical imaging and satellite communications — applications in which the data stream flows in realtime. Sequential throughput can be improved by incorporating faster read channel electronics (such as PRML) into the drive. PRML read channels enable both higher areal densities and higher internal data rates because they permit more and more bits to be packed onto a disk’s surface. The Quantum Atlas II and Quantum Empire II drives provide industry-leading internal data rates of 110 and 90 megabits per second, respectively. These internal data rates, in turn, have led to the fast sequential throughput required by digitized applications. The sequential throughput of hard disk drives has improved by about 30 percent per year over the last few years.

High sequential throughput is essential for such applications as video editing, medical imaging and satellite communications — applications in which the data stream flows in realtime. Sequential throughput can be improved by incorporating faster read channel electronics (such as PRML) into the drive. PRML read channels enable both higher areal densities and higher internal data rates because they permit more and more bits to be packed onto a disk’s surface. The Quantum Atlas II and Quantum Empire II drives provide industry-leading internal data rates of 110 and 90 megabits per second, respectively. These internal data rates, in turn, have led to the fast sequential throughput required by digitized applications. The sequential throughput of hard disk drives has improved by about 30 percent per year over the last few years.

Uninterrupted Throughput

In addition to providing fast sequential throughput, the drive system must also ensure that the transmission is free of interruptions. Even a slight interruption can have large consequences on sequential operations. For example, a medical imaging device, such as a CAT scan machine, spews out data to a buffer and from there to a disk drive. If the drive is not fast enough, the buffer can overflow, and data will be lost. A satellite transmission also requires uninterrupted data flow. If part of the signal is lost, the entire dataset must be resent, with prohibitively expensive results.

Today, there are two primary causes of momentary pauses in the data stream: thermal recalibrations (TCALs) and time-consuming error correction schemes. Quantum and recently, other drive vendors have eliminated TCALs by implementing an advanced embedded servo (head positioning) scheme. Embedded servo schemes eliminate head misalignments that require off-line and often time consuming TCALs to ensure data integrity.

Interruptions can also be eliminated by correcting errors on-the-fly, rather than shifting into separate and lengthy firmware error recovery routines. Quantum’s current generation of drives can correct errors of up to 73 bits in length in realtime. This capability better ensures continuous transmission of video, audio and other data streams.

High Reliability

Hard drive reliability is crucial for servers handling mission-critical data. Drive reliability has improved with higher levels of ASIC integration, fewer moving parts within the drive and through power reduction. Quantum high-end drives use just one single-sided printed circuit board (PCB) as compared to early high-end drives that had as many as four interconnected PCBs. And now, five disks achieve the 4GB capacity point that required ten disks just one year ago.

Drive reliability is further improved through rigorous environment testing. For example, the PCBs of Quantum drives are tested over a broader range of temperatures (-40°C to 100°C). This and other types of stress testing provides valuable information to Quantum engineers who can design more robust drives.

A terabyte “site” for a virtual world’s fair

The new role of high-capacity 3.5-inch drives in the digitized world is exemplified by the Internet 1996 World Exposition, a virtual world’s fair for the information age, conceived of by Carl Malamud, founder of the Internet Multicasting Society. As an official organizer of the event, Quantum is donating more than a terabyte worth of storage space in the form of 250 drives that will be distributed to content providers around the globe. The drives will constitute one of the largest collections of data storage ever assembled.

Preliminary plans include storage solutions for everything from a Global Schoolhouse to an online exhibit of Thai food. Washington’s Kennedy Center will host performances in cyberspace, and one exhibit will feature a virtual Huis Ten Bosch, a city near Nagasaki that has become a model for environmental activism.

As a virtual event, the Exposition’s size is measured not in acres, but in gigabytes. As Malamud has noted, “Our Eiffel Tower is 1.2 terabytes of disk space.” For this event, and for future applications of the digitized world, the disk drive is the stuff that 21st century dreams are made of.

See Also[edit]