Editing Hard disk drive (section)

=== Development ===
[[File:Full History Disk Areal Density Trend.png|thumb|Leading-edge hard disk drive [[Density (computer storage)|areal densities]] from 1956 through 2009 compared to [[Moore's law]]. By 2016, progress had slowed significantly below the extrapolated density trend.<ref name="Hayes 2016">{{cite web |url=http://bit-player.org/2016/wheres-my-petabyte-disk-drive |title= Where's My Petabyte Disk Drive? |first= Brian |last= Hayes|page= chart of historical data courtesy of Edward Grochowski  |date= March 27, 2016 |access-date= December 1, 2019 }}</ref>]]

The rate of areal density advancement was similar to [[Moore's law]] (doubling every two years) through 2010: 60% per year during 1988–1996, 100% during 1996–2003 and 30% during 2003–2010.<ref name="Byrne2015b">{{cite web |url=http://www.federalreserve.gov/econresdata/notes/feds-notes/2015/prices-for-data-storage-equipment-and-the-state-of-it-innovation-20150701.html#fn2 |title=Prices for Data Storage Equipment and the State of IT Innovation |publisher=The Federal Reserve Board FEDS Notes |first=David |last=Byrne |page=Table 2 |date=July 1, 2015 |access-date=July 5, 2015 |archive-url=https://web.archive.org/web/20150708124555/http://www.federalreserve.gov/econresdata/notes/feds-notes/2015/prices-for-data-storage-equipment-and-the-state-of-it-innovation-20150701.html#fn2 |archive-date=July 8, 2015 |url-status=live }}</ref> Speaking in 1997, [[Gordon Moore]] called the increase "flabbergasting",<ref name="Moore1997">{{cite news
 | url = https://www.pcmag.com/article2/0,2817,1172800,00.asp
 | title = Gallium Arsenide
 | work = PC Magazine
 | date = March 25, 1997
 | quote = Gordon Moore: ... the ability of the magnetic disk people to continue to increase the density is flabbergasting--that has moved at least as fast as the semiconductor complexity.
 | access-date = August 16, 2014
 | archive-url = https://web.archive.org/web/20140821103700/http://www.pcmag.com/article2/0,2817,1172800,00.asp
 | archive-date = August 21, 2014
 | url-status = live
 }}</ref> while observing later that growth cannot continue forever.<ref name="Moore2005">{{cite news |last=Dubash |first=Manek |url=http://www.techworld.com/news/operating-systems/moores-law-is-dead-says-gordon-moore-3576581/ |title=Moore's Law is dead, says Gordon Moore |work=techworld.com |date=April 13, 2005 |url-status=dead |archive-url=https://web.archive.org/web/20140706081110/http://news.techworld.com/operating-systems/3477/moores-law-is-dead-says-gordon-moore/ |archive-date=July 6, 2014 |access-date=March 18, 2022 |quote=It can't continue forever. The nature of exponentials is that you push them out and eventually disaster happens. }}</ref> Price improvement decelerated to −12% per year during 2010–2017,<ref name="McCallum">{{cite web |title=Disk Drive Prices (1955–2017) |url=http://www.jcmit.net/diskprice.htm |year=2017 |first=John C. |last=McCallum |access-date=July 15, 2017 |archive-url=https://web.archive.org/web/20170711202719/http://www.jcmit.net/diskprice.htm |archive-date=July 11, 2017 |url-status=live }}</ref> as the growth of areal density slowed. The rate of advancement for areal density slowed to 10% per year during 2010–2016,<ref name="IBM Fontana 2016">{{cite web |url=http://www.ibmsystemsmag.com/mainframe/storage/Support/cloud-trends-projections/?page=1 |title=A Look at Cloud Storage Component Technologies Trends and Future Projections |first1=Gary M. |last1=Decad |author2=Robert E. Fontana Jr. |website=ibmsystemsmag.com |date=July 6, 2017 |access-date=July 21, 2014 |page=Table 1 |archive-url=https://web.archive.org/web/20170729050933/http://ibmsystemsmag.com/mainframe/storage/support/cloud-trends-projections/?page=1 |archive-date=July 29, 2017 |url-status=dead }}</ref> and there was difficulty in migrating from perpendicular recording to newer technologies.<ref name="Mellor 2014-11-10">{{cite news |last=Mellor |first=Chris |url=https://www.theregister.co.uk/2014/11/10/kryders_law_of_ever_cheaper_storage_disproven/ |title=Kryder's law craps out: Race to UBER-CHEAP STORAGE is OVER |work=theregister.co.uk |location=UK |publisher=The Register |date=November 10, 2014 |access-date=November 12, 2014 |quote=The 2011 Thai floods almost doubled disk capacity cost/GB for a while. Rosenthal writes: 'The technical difficulties of migrating from PMR to HAMR, meant that already in 2010 the Kryder rate had slowed significantly and was not expected to return to its trend in the near future. The floods reinforced this.' |archive-url=https://web.archive.org/web/20141112004831/http://www.theregister.co.uk/2014/11/10/kryders_law_of_ever_cheaper_storage_disproven/ |archive-date=November 12, 2014 |url-status=live }}</ref>

As bit cell size decreases, more data can be put onto a single drive platter. In 2013, a production desktop 3&nbsp;TB HDD (with four platters) would have had an areal density of about 500&nbsp;Gbit/in<sup>2</sup> which would have amounted to a bit cell comprising about 18 magnetic grains (11 by 1.6 grains).<ref name="Anderson2013a" >{{cite web | url = https://www.dtc.umn.edu/resources/bd2013_anderson.pdf | title = HDD Opportunities & Challenges, Now to 2020 | year = 2013 | access-date = May 23, 2014 | quote = 'PMR CAGR slowing from historical 40+% down to ~8-12%' and 'HAMR CAGR = 20-40% for 2015–2020' | first = Dave | last = Anderson | publisher = Seagate | archive-url = https://web.archive.org/web/20140525232605/https://www.dtc.umn.edu/resources/bd2013_anderson.pdf | archive-date = May 25, 2014 | url-status = live }}</ref> Since the mid-2000s, areal density progress has been challenged by a [[Superparamagnetism#Effect on hard drives|superparamagnetic]] trilemma involving grain size, grain magnetic strength and ability of the head to write.<ref>{{cite journal
| title = New Paradigms in Magnetic Recording
| last = Plumer |display-authors=etal 
| first = Martin L.
| journal = Physics in Canada
| volume = 67
| issue = 1
| date = March 2011
| pages = 25–29
|arxiv = 1201.5543| bibcode = 2012arXiv1201.5543P }}</ref> In order to maintain acceptable signal-to-noise, smaller grains are required; smaller grains may self-reverse ([[electrothermal instability]]) unless their magnetic strength is increased, but known write head materials are unable to generate a strong enough magnetic field sufficient to write the medium in the increasingly smaller space taken by grains.

Magnetic storage technologies are being developed to address this trilemma, and compete with [[flash memory]]–based [[solid-state drive]]s (SSDs). In 2013, [[Seagate Technology|Seagate]] introduced [[shingled magnetic recording]] (SMR),<ref name="Seagate 2013-09-09">{{cite press release |url=http://www.seagate.com/about/newsroom/press-releases/shingled-magnetic-recording-milestone-pr-master/ |archive-url=https://web.archive.org/web/20141009135540/http://www.seagate.com/about/newsroom/press-releases/shingled-magnetic-recording-milestone-pr-master/ |title=Seagate Delivers On Technology Milestone: First to Ship Hard Drives Using Next-Generation Shingled Magnetic Recording |location=New York |publisher=[[Seagate Technology]] plc |date=September 9, 2013 |access-date=July 5, 2014 |archive-date=October 9, 2014 |quote=Shingled Magnetic Technology is the First Step to Reaching a 20 Terabyte Hard Drive by 2020}}</ref> intended as something of a "stopgap" technology between PMR and Seagate's intended successor [[heat-assisted magnetic recording]] (HAMR). SMR utilizes overlapping tracks for increased data density, at the cost of design complexity and lower data access speeds (particularly write speeds and [[random access]] 4k speeds).<ref>{{cite web
 | url = https://lwn.net/Articles/591782/
 | title = Support for shingled magnetic recording devices
 | date = March 26, 2014
 | access-date = January 7, 2015
 | first = Jake
 | last = Edge
 | publisher = [[LWN.net]]
 | archive-url = https://web.archive.org/web/20150202075938/http://lwn.net/Articles/591782/
 | archive-date = February 2, 2015
 | url-status = live
 }}</ref><ref>{{cite web
 | url = https://lwn.net/Articles/548116/
 | title = LSFMM: A storage technology update
 | date = April 23, 2013
 | access-date = January 7, 2015
 | first = Jonathan
 | last = Corbet
 | publisher = [[LWN.net]]
 | quote = A 'shingled magnetic recording' (SMR) drive is a rotating drive that packs its tracks so closely that one track cannot be overwritten without destroying the neighboring tracks as well. The result is that overwriting data requires rewriting the entire set of closely-spaced tracks; that is an expensive tradeoff, but the benefit—much higher storage density—is deemed to be worth the cost in some situations.
 | archive-url = https://web.archive.org/web/20150107075254/https://lwn.net/Articles/548116/
 | archive-date = January 7, 2015
 | url-status = live
 }}</ref>

By contrast, [[HGST]] (now part of [[Western Digital]]) focused on developing ways to seal [[helium]]-filled drives instead of the usual filtered air. Since [[turbulence]] and [[friction]] are reduced, higher areal densities can be achieved due to using a smaller track width, and the energy dissipated due to friction is lower as well, resulting in a lower power draw. Furthermore, more platters can be fit into the same enclosure space, although helium gas is notoriously difficult to prevent escaping.<ref>{{Cite web|date=2020|title=Brochure: HelioSeal Technology: Beyond Air. Helium Takes You Higher.|url=https://documents.westerndigital.com/content/dam/doc-library/en_us/assets/public/western-digital/collateral/brochure/brochure-helioseal-technology.pdf|website=Western Digital}}</ref> Thus, helium drives are completely sealed and do not have a breather port, unlike their air-filled counterparts.

Other recording technologies are either under research or have been commercially implemented to increase areal density, including Seagate's [[heat-assisted magnetic recording]] (HAMR). HAMR requires a different architecture with redesigned media and read/write heads, new lasers, and new near-field optical transducers.<ref name="Shilov_anandtech_b">{{cite news |url=http://www.anandtech.com/show/9866/hard-disk-drives-with-hamr-technology-set-to-arrive-in-2018 |title=Hard Disk Drives with HAMR Technology Set to Arrive in 2018 |first=Anton |last=Shilov |date=December 18, 2015 |access-date=January 2, 2016 |quote=Unfortunately, mass production of actual hard drives featuring HAMR has been delayed for a number of times already and now it turns out that the first HAMR-based HDDs are due in 2018. ... HAMR HDDs will feature a new architecture, require new media, completely redesigned read/write heads with a laser as well as a special near-field optical transducer (NFT) and a number of other components not used or mass produced today. |archive-url=https://web.archive.org/web/20160102200055/http://www.anandtech.com/show/9866/hard-disk-drives-with-hamr-technology-set-to-arrive-in-2018 |archive-date=January 2, 2016 |url-status=live }}</ref> HAMR is expected to ship commercially in late 2024,<!-- did it ship? --><ref>{{cite web |url= https://www.tomshardware.com/news/seagate-reveals-hamr-roadmap-32-tb-comes-first |title= Seagate Reveals HAMR HDD Roadmap: 32TB First, 40TB Follows |last= Shilov |first= Anton |date= June 8, 2023 |access-date= Oct 3, 2024 }}</ref> after technical issues delayed its introduction by more than a decade, from earlier projections as early as 2009.<ref name= "HAMR 2008 for 2009" >{{cite web |url= https://blog.dshr.org/2018/05/longer-talk-at-msst2018.html |title= Longer talk at MSST2018 |last= Rosenthal |first= David |date= May 16, 2018 |access-date= November 22, 2019 }}</ref><ref name= "HAMR 2014 for 2015" >{{cite web |url= https://www.kitguru.net/components/hard-drives/anton-shilov/tdk-hamr-technology-could-enable-15tb-hard-drives-already-in-2015/ |title= TDK: HAMR technology could enable 15TB HDDs already in 2015 |last= Shilov |first= Anton |date= October 15, 2014 |access-date= November 15, 2019 }}</ref><ref name= "HAMR 2013 for 2016" >{{cite web |url= http://www.tomsitpro.com/articles/wd-hamr-hdd-heat-assisted-magnetic-recording,1-1396.html |title= WD Demos Future HDD Storage Tech: 60TB Hard Drives |last= Oliver |first= Bill |work= Tom's IT Pro |quote= …Seagate expects to start selling HAMR drives in 2016. |date= November 18, 2013 |access-date= November 15, 2019 |archive-url= https://web.archive.org/web/20131121065015/http://www.tomsitpro.com/articles/wd-hamr-hdd-heat-assisted-magnetic-recording,1-1396.html |archive-date= November 21, 2013 }}</ref><ref name= "blocks HAMR 2019" >{{cite web |url= https://blocksandfiles.com/2019/08/28/nearline-disk-drives-ssd-attack/ |title= How long before SSDs replace nearline disk drives? |last= Mellor |first= Chris |quote= Seagate CTO Dr John Morris told analysts that Seagate has built 55,000 HAMR drives and aims to get disks ready for customer sampling by the end of 2020. |date= August 28, 2019 |access-date= November 15, 2019 }}</ref> HAMR's planned successor, [[bit-patterned recording]] (BPR),<ref name="AutoMK-22" /> has been removed from the roadmaps of Western Digital and Seagate.<ref name= "BPR roadmaps 2018" >{{cite web |url= https://blog.dshr.org/2018/05/longer-talk-at-msst2018.html |title= Longer talk at MSST2018 |last= Rosenthal |first= David |quote= The most recent Seagate roadmap pushes HAMR shipments into 2020, so they are now slipping faster than real-time. Western Digital has given up on HAMR and is promising that Microwave Assisted Magnetic Recording (MAMR) is only a year out. BPM has dropped off both companies' roadmaps. |date= May 16, 2018 |access-date= November 22, 2019 }}</ref> Western Digital's microwave-assisted magnetic recording (MAMR),<ref>{{cite journal |last=Mallary |display-authors=etal |first= Mike|date=July 2014 |title= Head and Media Challenges for 3 Tb/in<sup>2</sup> Microwave-Assisted Magnetic Recording|journal=IEEE Transactions on Magnetics |volume=50 |issue=7 |pages=1–8 |doi=10.1109/TMAG.2014.2305693|s2cid=22858444 |issn = 0018-9464 }}</ref><ref>{{cite journal|last1=Li|first1=Shaojing|last2=Livshitz|first2=Boris|last3=Bertram|first3=H. Neal|last4=Schabes|first4=Manfred|last5=Schrefl|first5=Thomas|last6=Fullerton|first6=Eric E.|last7=Lomakin|first7=Vitaliy|title=Microwave assisted magnetization reversal in composite media|journal=Applied Physics Letters|date=2009|volume=94|issue=20|page=202509|doi=10.1063/1.3133354|url=https://www.karlstechnology.com/hard-drives/JAP_2009_MAMR.pdf|bibcode=2009ApPhL..94t2509L|access-date=May 24, 2019|archive-url=https://web.archive.org/web/20190524225721/https://www.karlstechnology.com/hard-drives/JAP_2009_MAMR.pdf|archive-date=May 24, 2019|url-status=live}}</ref> also referred to as energy-assisted magnetic recording (EAMR), was sampled in 2020, with the first EAMR drive, the Ultrastar HC550, shipping in late 2020.<ref>{{Cite web|last=Shilov|first=Anton|title=Western Digital Reveals 18 TB DC HC550 'EAMR' Hard Drive|url=https://www.anandtech.com/show/14869/western-digital-announces-18-tb-eamr-hard-drive |date=September 18, 2019 |access-date=2021-10-11|website=AnandTech}}</ref><ref name="Blocks MAMR 2019">{{cite web |url= https://blocksandfiles.com/2019/09/03/western-digital-18tb-and-20tb-mamr-disk-drives/ |website=Blocks & Files |title= Western Digital debuts 18TB and 20TB MAMR disk drives |last= Mellor |first= Chris |quote= …microwave-assisted magnetic (MAMR) recording technology…sample shipments are due by the end of the year. |date= September 3, 2019 |access-date= November 23, 2019 }}</ref><ref>{{Cite web|last=Raevenlord |title=Western Digital Finally Launches Ultrastar DC HC550 18 TB Drives With EAMR for Enterprise|url=https://www.techpowerup.com/269562/western-digital-finally-launches-ultrastar-dc-hc550-18-tb-drives-with-eamr-for-enterprise|access-date=2021-10-11|website=TechPowerUp|date=July 8, 2020 |language=en}}</ref> [[Two-dimensional magnetic recording]] (TDMR)<ref name="Anderson2013a" /><ref name="Wood 2010">{{cite web |url=https://www.ewh.ieee.org/r6/scv/mag/MtgSum/Meeting2010_10_Presentation.pdf |title=Shingled Magnetic Recording and Two-Dimensional Magnetic Recording |last=Wood |first=Roger |work=[[IEEE]] |publisher=Hitachi GST |date=October 19, 2010 |access-date=August 4, 2014 |archive-url=https://web.archive.org/web/20140810161542/http://www.ewh.ieee.org/r6/scv/mag/MtgSum/Meeting2010_10_Presentation.pdf |archive-date=August 10, 2014 |url-status=live }}</ref> and "current perpendicular to plane" [[giant magnetoresistance]] (CPP/GMR) heads have appeared in research papers.<ref name="Coughlin" /><ref>{{Cite arXiv |title=All-Heusler giant-magnetoresistance junctions with matched energy bands and Fermi surfaces |eprint = 1301.6106|last1 = Bai|first1 = Zhaoqiang|last2 = Cai|first2 = Yongqing|last3 = Shen|first3 = Lei|last4 = Han|first4 = Guchang|last5 = Feng|first5 = Yuanping|year = 2013|class = cond-mat.mes-hall}}</ref><ref>{{cite web|url=http://www1.hgst.com/hdd/research/recording_head/pr/PerpendicularAnimation.html|title=Perpendicular Magnetic Recording Explained - Animation|date=December 21, 2001 |access-date=July 27, 2014|archive-url=https://web.archive.org/web/20181006062214/http://www1.hgst.com/hdd/research/recording_head/pr/PerpendicularAnimation.html|archive-date=October 6, 2018|url-status=live}}</ref>

Some drives have adopted dual independent actuator arms to increase read/write speeds and compete with SSDs.<ref>{{cite web |url=https://www.anandtech.com/show/13935/seagate-hdd-plans-2019 |title= State of the Union: Seagate's HAMR Hard Drives, Dual-Actuator Mach2, and 24 TB HDDs on Track |work=Anandtech.com |access-date=February 20, 2019 |archive-url=https://web.archive.org/web/20190220002907/https://www.anandtech.com/show/13935/seagate-hdd-plans-2019 |archive-date=February 20, 2019 |url-status=live }}</ref>
A 3D-actuated vacuum drive (3DHD) concept<ref name= "3DHD blog" >{{Cite web |url= https://blog.dshr.org/2019/09/promising-new-hard-disk-technology.html |title= Promising New Hard Disk Technology |access-date= December 1, 2019 }}</ref><!--3DHD is developed by L2 drive--> and 3D magnetic recording have been proposed.<ref>{{Cite web|url=https://www.extremetech.com/extreme/168619-3d-magnetic-storage-breakthrough-enables-100tb-hard-drives|title=3D magnetic storage breakthrough enables 100TB+ hard drives &#124; Extremetech|date=October 15, 2013 }}</ref>

Depending upon assumptions on feasibility and timing of these technologies, Seagate forecasts that areal density will grow 20% per year during 2020–2034.<ref name= "blocks WWrevenue August2019"/>