Open main menu
Home
Random
Recent changes
Special pages
Community portal
Preferences
About Wikipedia
Disclaimers
Incubator escapee wiki
Search
User menu
Talk
Dark mode
Contributions
Create account
Log in
Editing
Server farm
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
{{Short description|Collection of computer servers}} [[File:Wikimedia-servers-Sept04.jpg|thumb|right|170px|A row of racks in a server farm]] [[File:JTF-Guantanamo server farm.jpg|thumb|right|170px|This server farm supports the various computer networks of the [[Joint Task Force Guantanamo]]]] A '''server farm''' or '''server cluster''' is a collection of [[Server (computing)|computer servers]], usually maintained by an [[organization]] to supply server functionality far beyond the capability of a single machine. They often consist of thousands of computers which require a large amount of power to run and to keep cool. At the optimum performance level, a server farm has enormous financial and environmental costs.<ref> {{cite journal|last= Mitrani|first= Isa|title= Managing performance and power consumption in a server farm |journal= Annals of Operations Research |date= January 2013|volume= 202|issue= 1 |pages= 121β122 |doi= 10.1007/s10479-011-0932-1 |s2cid= 12276102}} </ref> They often include backup servers that can take over the functions of primary servers that may fail. Server farms are typically collocated with the [[network switch]]es and/or [[router (computing)|router]]s that enable communication between different parts of the cluster and the cluster's users. Server "farmers" typically mount computers, routers, power supplies and related electronics on [[19-inch rack]]s in a [[server room]] or [[data center]]. ==Applications== Server farms are commonly used for [[cluster computing]]. Many modern [[supercomputer]]s comprise giant server farms of high-speed [[Processor (computing)|processors]] connected by either [[Ethernet]] or custom interconnects such as [[Infiniband]] or [[Myrinet]]. [[Web hosting]] is a common use of a server farm; such a system is sometimes collectively referred to as a ''web farm''. Other uses of server farms include scientific simulations (such as [[computational fluid dynamics]]) and the rendering of [[3D rendering|3D computer generated imagery]] (see [[render farm]]).<ref>{{Cite news|url=https://garagefarm.net/blog/the-benefits-of-using-a-render-farm|title=What is a render farm|date=2021-06-11|work=GarageFarm|access-date=2021-06-11|language=en-US}}</ref> Server farms are increasingly being used instead of or in addition to [[mainframe computer]]s by large enterprises. In large server farms, the failure of an individual machine is a commonplace event: large server farms provide [[Redundancy (engineering)|redundancy]], automatic [[failover]], and rapid reconfiguration of the server cluster. ==Performance== The performance of the largest [[Server (computing)|server]] farms (thousands of processors and up) is typically limited by the performance of the data center's [[Computer cooling|cooling]] systems and the total electricity cost rather than by the processors' performance.<ref>{{cite journal|url=http://www.barroso.org/ |title=Luiz AndrΓ© Barroso |doi=10.2200/S00193ED1V01Y200905CAC006 |publisher=Barroso.org |access-date=2012-09-20|doi-access=free |url-access=subscription }}</ref> Computers in server farms run 24/7 and consume large amounts of electricity. For this reason, the critical design parameter for both large and continuous systems tends to be [[performance per watt]] rather than cost of peak performance or (peak performance / (unit * initial cost)). Also, for [[high availability]] systems that must run 24/7 (unlike supercomputers that can be power-cycled to demand, and also tend to run at much higher utilizations), there is more attention to power-saving features such as variable [[clock rate|clock-speed]] and the ability to turn off both computer parts, processor parts, and entire computers ([[Wake-on-lan|WoL]] and [[platform virtualization|virtualization]]) according to demand without bringing down services. The network connecting the servers in a server farm is also an essential factor in overall performance, especially when running applications that process massive volumes of data.<ref>{{cite journal|last1=Noormohammadpour|first1=Mohammad|last2=Raghavendra|first2=Cauligi|title=Datacenter Traffic Control: Understanding Techniques and Tradeoffs|journal=IEEE Communications Surveys & Tutorials|date=16 July 2018|volume=20|issue=2|pages=1492β1525|url=https://www.researchgate.net/publication/321744877|arxiv=1712.03530|doi=10.1109/COMST.2017.2782753|s2cid=28143006 }}</ref> ===Performance per watt=== The [[EEMBC]] EnergyBench, [[SPECpower]], and the [[Transaction Processing Performance Council]] TPC-Energy are benchmarks designed to predict performance per watt in a server farm.<ref>{{cite web |url=http://itknowledgeexchange.techtarget.com/server-farm/tpc-describes-upcoming-server-power-efficiency-benchmark |title=TPC describes upcoming server power efficiency benchmark β Server Farming |publisher=Itknowledgeexchange.techtarget.com |date=2009-02-19 |access-date=2012-09-20 |archive-date=2012-02-20 |archive-url=https://web.archive.org/web/20120220051246/http://itknowledgeexchange.techtarget.com/server-farm/tpc-describes-upcoming-server-power-efficiency-benchmark/ |url-status=dead }}</ref><ref>{{cite web |url=http://searchdatacenter.techtarget.com/news/article/0,289142,sid80_gci1338006,00.html |title=TPC eyes energy consumption and virtualization benchmarks |publisher=Searchdatacenter.techtarget.com |date=2008-11-06 |access-date=2012-09-20 |archive-date=2009-09-30 |archive-url=https://web.archive.org/web/20090930234143/http://searchdatacenter.techtarget.com/news/article/0,289142,sid80_gci1338006,00.html |url-status=dead }}</ref> The power used by each rack of equipment can be measured at the [[power distribution unit]]. Some servers include power tracking hardware so the people running the server farm can measure the power used by each server.<ref>{{cite web|author=Rich MillerApril 1st, 2009 |url=http://www.datacenterknowledge.com/archives/2009/04/01/efficient-ups-aids-googles-extreme-pue/ |title=Efficient UPS Aids Google's Extreme PUE |publisher=Data Center Knowledge |date=2009-04-01 |access-date=2012-09-20}}</ref> The power used by the entire server farm may be reported in terms of [[power usage effectiveness]] or [[data center infrastructure efficiency]]. According to some estimates, for every 100 watts spent on running the servers, roughly another 50 watts is needed to cool them.<ref name="BBCnews">{{cite news | url=http://news.bbc.co.uk/2/hi/programmes/click_online/8297237.stm | title=Iceland looks to serve the world | work = BBC News | date=2009-10-09 | access-date=2009-10-15}}</ref> For this reason, the siting of a server farm can be as important as processor selection in achieving power efficiency. [[Iceland]], which has a cold climate all year as well as cheap and [[carbon-neutral]] [[geothermal electricity]] supply, is building its first major server farm hosting site.<ref name="BBCnews" /> Fibre optic cables are being laid from Iceland to [[North America]] and [[Europe]] to enable companies there to locate their servers in Iceland. Other countries with favorable conditions, such as Canada,<ref name="Channelbuzz.ca">{{cite web|url=http://www.channelbuzz.ca/2010/12/cold-front-can-canada-play-a-leading-role-in-the-cloud-846/ |title=Cold front: Can Canada play a leading role in the cloud? |publisher=ChannelBuzz.ca |date=2010-12-08 |access-date=2012-09-20}}</ref> Finland,<ref>{{cite web|url=http://datacenter-siting.weebly.com/ |title=Finland β First Choice for Siting Your Cloud Computing Data Center |publisher=Fincloud.freehostingcloud.com |date=2010-12-08 |access-date=2012-09-20}}</ref> Sweden<ref>[http://www.stockholmbusinessregion.se/templates/page____41724.aspx?epslanguage=EN] {{webarchive|url=https://web.archive.org/web/20100819190918/http://www.stockholmbusinessregion.se/templates/page____41724.aspx?epslanguage=EN|date=August 19, 2010}}</ref> and Switzerland,<ref>{{cite web|last=Wheeland |first=Matthew |url=http://www.greenbiz.com/news/2010/06/30/swiss-carbon-neutral-servers-hit-cloud |title=Swiss Carbon-Neutral Servers Hit the Cloud |publisher=GreenBiz.com |date=2010-06-30 |access-date=2012-09-20}}</ref> are trying to attract cloud computing data centers. In these countries, heat from the servers can be cheaply vented or used to help heat buildings, thus reducing the energy consumption of conventional heaters.<ref name="Channelbuzz.ca"/> ==See also== {{cmn| * [[Blade server]] * [[Compile farm]] * [[Data center]] * [[Geoplexing]] * [[Green computing]] * [[Link farm]] * [[PS3 cluster]] * [[Render farm]] }} ==References== {{Reflist}} {{DEFAULTSORT:Server Farm}} [[Category:Cluster computing]] [[Category:Server hardware]] [[Category:Servers (computing)]] [[Category:Fault-tolerant computer systems]]
Edit summary
(Briefly describe your changes)
By publishing changes, you agree to the
Terms of Use
, and you irrevocably agree to release your contribution under the
CC BY-SA 4.0 License
and the
GFDL
. You agree that a hyperlink or URL is sufficient attribution under the Creative Commons license.
Cancel
Editing help
(opens in new window)
Pages transcluded onto the current version of this page
(
help
)
:
Template:Cite journal
(
edit
)
Template:Cite news
(
edit
)
Template:Cite web
(
edit
)
Template:Cmn
(
edit
)
Template:Reflist
(
edit
)
Template:Short description
(
edit
)
Template:Webarchive
(
edit
)