ServerPrimer

Understandingthecurrentstateofthe
industry
GolisanoInstituteforSustainability
DATE:10/10/2012

2012

GolisanoInstituteforSustainability
RochesterInstituteofTechnology
111LombMemorialDrive
Rochester,NY14623
www.sustainability.rit.edu

2 ServerPrimer

Acknowledgements
The primary authors of this report are Brian Hilton, Senior Research Engineer,
andMichaelWelch,MastersStudent,GolisanoInstituteforSustainability(GIS)
atRochester InstituteofTechnology(RIT).Questions,comments andfeedback
onthisreportshouldbedirectedto:
BrianHilton,Sr.ResearchEngineer
GolisanoInstituteforSustainability
RochesterInstituteofTechnology
133LombMemorialDrive,Building78,Room1220
Rochester,NewYork146235608
Tel:5854755379
Email:[email protected]

We gratefully acknowledge and thank the primary sponsor, the International

Sustainable Development Foundation, for providing the resources and support
tomakethisreportpossible.Wewouldalsoliketoacknowledgethefacultyand
staffattheGolisanoInstituteforSustainabilityforprovidingresearchdataand
advice on the report focus and content. Additionally, we would also like to
acknowledgetheU.S.EnvironmentalProtectionAgencyforprovidingtheinitial
ecolabel comparison document Server ecolabel comparison 8 15 2011.xls
whichwasusedasthefoundationforthecompaniondocumentforthisreport
MasterlistofserverstandardsJune2012.xlsx.Wealsosendaspecialthank
you to Pamela BrodyHeine and Patty Dillon who served as an advisors and
reviewersofthisreport.
We believe this report provides useful data, information, findings and
recommendations for positioning the industry for the future, including key
considerationsonenergy,environmentandsustainability.

RochesterInstituteofTechnology
October10,2012

3 ServerPrimer

Table of Contents
Acknowledgements...............................................................................................2
1.

Introduction...................................................................................................5

2.

BackgroundandPurposeoftheStudy..........................................................6

3.

ServerIntroduction........................................................................................7
3.1.

ServerHardware....................................................................................7

3.1.1.

BladeServerHardware................................................................11

3.2.

ServerPriceandPerformance.............................................................12

3.3.

ServerMarket&Sales..........................................................................12

3.4. ENERGYSTARandExclusionofServerswithMorethanFourProcessor
Sockets.............................................................................................................15
4.

ServerIndustryTrends.................................................................................16
4.1.

HighDensityComputing......................................................................16

4.2.

ServerInternalWasteHeatManagement...........................................18

4.3.

ServerUtilizationandConnectivity.....................................................20

4.3.1.

ServerVirtualization....................................................................21

4.3.2.

ServerConsolidation....................................................................22

4.3.3.

CloudComputing.........................................................................23

5.

ServerImpactonOverallDataCenterEnergyUse......................................24

6.

ServerEnvironmentalAssessments.............................................................27

7.

6.1.

CarbonFootprintofaTypicalDellRackServer...................................27

6.2.

CarbonFootprintofFujitsuPrimergyRXandTX300S5Servers.........29

6.3.

CaseStudyofanIBMRackmountedServer.......................................30

ServerStandardScopeTopics.....................................................................31
7.1.

ServerMaterialSelection.....................................................................31

7.1.1.

ServerDemanufacturing:GIS.......................................................31

7.1.2.

ServerDemanufacturing:Cascade...............................................33

7.2.

EnvironmentallySensitiveMaterials...................................................34

7.2.1.

RoHSDirective.............................................................................35

7.3.

ProductLongevity................................................................................36

7.4.

DesignforEndofLife...........................................................................37

7.5.

EndofLifeManagement......................................................................37

7.5.1.

ServerEndofLife........................................................................37

7.5.2.

EndofLifeManagement..............................................................40

RochesterInstituteofTechnology
October10,2012

4 ServerPrimer

7.6.

7.6.1.

PSUEfficiencyStandards.............................................................43

7.6.2.

ProcessorEnergyUse...................................................................44

7.7.
8.

EnergyConservation............................................................................42

Packaging.............................................................................................46

ServerEnvironmentalStandardsandLabels...............................................47
8.1.

KeyAcronyms......................................................................................50

RochesterInstituteofTechnology
October10,2012

5 ServerPrimer

1. Introduction
The computer server industry is in the midst of major change stimulated by
increasingdemandfordataprocessingandstorageasaresultofoureconomys
shiftfrompaperbasedtodigitalinformationmanagement.
The Golisano Institute for Sustainability (GIS) at Rochester Institute of
Technology (RIT), was commissioned by the International Sustainable
DevelopmentFoundation(ISDF)tobetterunderstandthestateofthecomputer
serverindustryandtowhatextenttheindustryhasfacedorisfacingchallenges
associatedwithenergy,environmentandsustainability.
A threemonth research effort was conducted to collect, identify, assess, and
understand the industry trends and environmental impacts associated with
computerservers.ResearchconductedbyRITsoughttobalancetheacquisition
ofdataandinformationthroughquantitativeandqualitativeresearchmethods
tosupporttheserverstandarddevelopmentworkby:

Assessingandunderstandingenvironmentalimpactsonalifecyclebasis
Assessingandunderstandingenergyuseinthecomputerserver
industry
Reviewingcurrentenvironmentalpurchasingstandardsforcomputer
serversandothercomputerequipment
Broadlyunderstandingthebusiness,technology,regulatoryandmarket
challengesofthecomputerserverindustry
DistillingthecommentsanddataprovidedbytheTechnicalCommittee

Theremainderofthisreportpresentsdataandinformationknownatthetime
ofpublicationontheenvironmentalimpactoftheserverindustry.Thepurpose
is to document the current state of the industry to inform the Technical
Committee charged with drafting a framework of environmental performance
criteriaforthedevelopmentofaproductstandardforservers.Accordingtothe
IEEEProjectAuthorizationRequest,1theproductstandardisintendedtodefine
a measure of environmental leadership in: the design and manufacture of
servers;thedeliveryofspecifiedservicesthatareassociatedwiththesaleofthe
product;andassociatedcorporateperformancecharacteristics.Thisstandardis
defined with the intention that the criteria are technically feasible to achieve,
but that only products demonstrating the leading environmental performance
currently available in the marketplace would meet them at the time of their
adoption.

P1680.4StandardforEnvironmentalAssessmentofServers,ProjectAuthorization
Request(PAR),https://development.standards.ieee.org/get
file/P1680.4.pdf?t=11051900003

RochesterInstituteofTechnology
October10,2012

6 ServerPrimer

2. Background and Purpose of the Study

The International Sustainable Development Foundation (ISDF) requested the
GolisanoInstituteforSustainability(GIS)toconductbackgroundresearchonthe
technical and sustainability issues surrounding the development of computer
server hardware (server). Research results are intended to inform a Technical
Committee established by the ISDF which will help draft a framework for the
developmentofaproductstandardforservers.
Thisstudyprovidesaliteraturereviewoftechnicalandscientificstudies,aswell
as publicly available lifecycle assessments performed on servers. This work is
compiledandsummarizedandisintendedtoprovideacommonfoundationand
reference materials for participants in the Technical Committee and Working
Group.

Golisano Institute for

Sustainability new
75,000 sqft academic
research building
including a research
data center for
sustainable
computing is opening
fall of 2012.

This report includes background information on servers such as description of

servers, server functions, server components, typical server performance
characteristics, analysis of market and market size and key players, and key
market and performance trends. The report also highlights data within
environmental performance categories of material selection, environmentally
sensitive materials, product longevity, design for end of life, end of life
management,energyconservation,corporateperformanceandpackaging.
This study was conducted with financial support from ISDF and data support
fromGIS.

AbouttheGolisanoInstituteforSustainability
The Golisano Institute for Sustainability is a multidisciplinary academic and
appliedresearchunitofRochesterInstituteofTechnology,Rochester,NY,USA.
ThemissionofGISistoundertakeworldclasseducationandresearchmissions
insustainability.
GIS academic and research programs focus on sustainable production,
sustainable energy, sustainable mobility, and ecologically friendly information
technology systems. These programs are led by a multidisciplinary team of
faculty and researchers who collaborate with organizations locally, nationally,
andinternationallytocreateimplementablesolutionstocomplexsustainability
problems.
TheacademiccomponentofGISwasfoundedin2007witha$10Mgrantfrom
B. Thomas Golisano. The GIS Ph.D. program started in 2008 offering the
world's first doctorate in sustainable production. An M.S. Program in
Sustainable Systems was approved and begun in 2010. The first GIS graduates
receivedtheirdiplomasin2011.
Thisacademicprogramisbuilt,inpart,uponthestrongtrackrecordofthefive
(5) applied research centers within GIS that address problems facing industry,
government, and nongovernmental partners as they regulate, design, deploy,
maintain, and recycle products. The Center for Remanufacturing, Reuse, and

RochesterInstituteofTechnology
October10,2012

7 ServerPrimer

Resource Recovery (C3R), established in 1992, has played a major role in this
regard, as will the New York State Pollution Prevention Institute (NYSP2I). The
applied research centers missions are accomplished through a dynamic
collaboration of nearly 100 fulltime inhouse technical experts, support
professionals, faculty, and students. The Centers 170,000 squarefoot facility
supports research and development through applied technology laboratories
and a stateoftheart education center. Additional information on GIS can be
foundat:http://www.rit.edu/gis/about/

3. Server Introduction
Acomputerserverisahardwaredeviceconnectedtoanetworkwhosepurpose
is to manage networked resources. The term server can also refer to the
software used to manage the networked resources; however, this report only
addressestheenvironmentalimpactoftheserverhardware.

Servers and data

centers consumed an
estimated 238 billion
kWh worldwide in
2010, or 1.3% of the
worldwide electricity
consumption.

Computerserverhardwarehashistoricallybeendedicatedtomanagingasingle
functional purpose; therefore, the server hardware can range widely in size,
performance, cost, capability, and environmental impact. Dedicated server
functions include: application servers, file servers, game servers, mail servers,
printservers,databaseservers,andmanymore.
Severalserversaretypicallyrequiredtoenableacomputertoproperlyinteract
withothernetworkclientsduetothisdedicatednatureofaserver.Acollection
ofserversisreferredtoasaserverfarmorserverclusterandthefacilityusedto
house the server farm and associated components is referred to as a data
center. Data centers have increased in popularity over the past decade as the
number of servers required by businesses has increased to compensate for
increasedinternettrafficinallfacetsoflife.Tokeeppacewithincreasedserver
space, the traditional data center has evolved to include cooling equipment,
networkequipment,andstorageequipment.
The following subsections discuss both the server hardware and the server
market.

3.1.

Server Hardware

A server, as referenced in this document, is computer hardware that provides

services and manages networked resources for client devices. Servers range
widely in size and performance; however, generally, they will contain similar
hardware components. One server model, the IBM System x3650 M4 (X3650),
was therefore chosen to illustrate the hardware components that are in a
server.
TheX3650serverperformance(Table1)iswithinthelikelytargetmarketforthe
proposed purchasing standard as its scope is within what is described by
ENERGYSTAR(describedinmoredetailinSection3.4).

RochesterInstituteofTechnology
October10,2012

8 ServerPrimer

Figure1:IBMSystemX3650M4Server
Source:[IBM2012]

IBM has published images and specification for the IBM System x3650 M4
server.2 These images and specifications are reproduced here to describe in
generalserverhardwarecomponents.TheX3650suggestedusesare:database,
virtualization, enterprise applications, collaboration/email, streaming media,
web,andcloudapplications.
The IBM System X3650 M4 server supports two processors in a scalable 2U
package. Rack servers such as the X3650 are designed to mount in steel racks
thatare19incheswide.Rackserversarethereforedescribedwithaformfactor
thatindicatestheserverheightinmultiplesofrackunits(U),whichisaheightof
1.75 inches. The IBM X3650 is 3.4 inches high, thus 2U. Note that a standard
serverrackis42Uhigh.
Typically,servercomponentsinclude:anexternalenclosure,centralprocessing
unit(CPU),14CPUsockets,mainmotherboard,memory,storage(harddrives,
solidstatedrive(SSD)),Input/Outputadaptors,fans,powersupplies,andmay
includeasmallscreen.3Figure2andFigure3showtheX3650serverfrontand
backviewrespectivelywhichshowmanyavailableconnections.Figure4shows
theinternalcomponents.Notethatmanyofthecomponentsareredundantand
hotswappable4 including fans, disks and power supplies making it easy to
replacefailureswithouttakingthesystemdown.

[IBM2012]IBMSystemx3650M4IBMRedbooksProductGuide,
http://www.redbooks.ibm.com/technotes/tips0850.pdf
3
Source:ServerTechnicalCommitteemeeting,Houston,Texas,July31,2012.
4

Componentsarehotswappableiftheycanbeinstalledorremovedwithoutpoweringdownthe
system.

RochesterInstituteofTechnology
October10,2012

9 ServerPrimer

Figure2:IBMSystemX3650FrontView
Source:[IBM2012]

Figure3:IBMSystemX3650M4BackView
Source:[IBM2012]

RochesterInstituteofTechnology
October10,2012

10 ServerPrimer

Figure4:IBMSystemX3650M4InternalComponents
Source:[IBM2012]

Table1:IBMSystemX3650M4ProductSpecifications
Source:[IBM2012]
Components
Specification
Formfactor
2URack.
UptotwoIntelXeonprocessorE52600productfamilyCPUswitheightcores
(upto2.9GHz)orsixcores(upto2.9GHz)orquadcores(upto3.3GHz).Two
Processor
QPIlinksupto8.0GT/seach.Upto1600MHzmemoryspeed.Upto20MBL3
cache.
Chipset
IntelC602J
Upto24DIMMsockets(12DIMMsperprocessor).RDIMMs,UDIMMs,
Memory
HyperCloudDIMMs,andLRDIMMs(LoadReducedDIMMs)supported,but
memorytypescannotbeintermixed.Memoryspeedupto1600MHz.
WithRDIMMs:Upto384GBwith24x16GBRDIMMsandtwoprocessors
WithUDIMMs:Upto64GBwith16x4GBUDIMMsandtwoprocessors
Memory
WithHyperCloudDIMMs:Upto768GBwith24x32GBHyperCloudDIMMsand
maximums
twoprocessors
WithLRDIMMs:Upto768GBwith24x32GBLRDIMMsandtwoprocessors
Memory
ECC,Chipkill,memorymirroring,andmemoryranksparing.
protection
Upto321.8"SSDbays,or162.5"hotswapSAS/SATAbays,oruptosix3.5"
Diskdrive
hotswapSAS/SATAbays,oruptoeight2.5"SimpleSwapSATAbays,orupto
bays
six3.5"SimpleSwapSATAbays.
Maximum
Upto14.4TBwith900GB2.5"SASHDDs,upto16TBwith1TB2.5"NL
internal
SAS/SATAHDDs,orupto18TBwith3TB3.5"NLSAS/SATAHDDs.Intermixof
storage
SAS/SATAissupported.
RAID0,1,10withintegratedServeRAIDM5110e;optionalupgradestoRAID5,
RAIDsupport
50areavailable(zerocache;512MBbatterybackedcache;512MBor1GB
flashbackedcache).OptionalupgradetoRAID6,60isavailablefor512MBor1

RochesterInstituteofTechnology
October10,2012

11 ServerPrimer

Components
Opticaldrive
bays
Tapedrive
bays
Network
interfaces
PCIExpansion
slots
Ports

Cooling
Powersupply
Video
Hotswap
parts
Limited
warranty
Dimensions
Weight

Specification
GBcache.
OnebayforoptionalDVDROMorMultiburnerdrive.
OptionalTapeEnablementKitisavailabletosupportoneDDS5,DDS6,orRDX
internalUSBtapedrive.
FourintegratedGigabitEthernet1000BASETports(RJ45);twoembedded10
GbEthernetports(10GBASETRJ45or10GBASESRSFP+based)onoptional10
GbEthernetmezzaninecard(doesnotconsumePCIeslot).
Uptosixslotsdependingontherisercardsinstalled.Optionalrisercards
availablewithPCIex8orPCIex16orPCIXslots.
TwoUSB2.0andoneDB15videoonfront.FourUSB2.0,oneDB15video,one
DB9serial,oneRJ45systemsmanagement,fourRJ45GbEnetworkports,two
optionalRJ45orSFP+10GbEnetworkportsonrear.TwointernalUSBports
IBMCalibratedVectoredCoolingwithuptofourredundanthotswapfans
(threestandard,additionalfanwithsecondprocessor);twofanzoneswithN+1
fandesign;eachfanhastwomotors.
Uptotworedundanthotswap550Wacor750Wacor900Wacpower
supplies(all80PLUSPlatinumcertification)
MatroxG200eR2with16MBmemoryintegratedintotheIMM2.Maximum
resolutionis1600x1200at75Hzwith16Mcolors.
Harddrives,powersupplies,andfans.
Threeyearcustomerreplaceableunitandonsitelimitedwarrantywith9x5
nextbusinessday(NBD).
Height:86mm(3.4in),width:445mm(17.5in),depth:746mm(29.4in)
Minimumconfiguration:25kg(55lb),maximum:30kg(65lb)

3.1.1. Blade Server Hardware

Abladeservercanbeconsideredastrippeddownrackmountedserver.Blade
servers have a modular design and do not include many components typically
found in traditional rack servers to save space, and minimize power
consumption. The removed components are found in the blade enclosure,
which can hold multiple blade servers and provides services such as power,
cooling, and various interconnects and management. Different blade server
manufacturers include different components in the blade itself. Blade servers
arediscussedfurtherinSection4.1.
Typically,bladeservercomponentsinclude:anexternalenclosure,CPU,14CPU
sockets, main mother board, memory, storage (hard drives, solid state drive
(SSD). Other components such as input / output adaptors, fans, and power
suppliescanbesharedresources.5IBMhaspublishedimagesandspecification
for the IBM BladeCenter HS22 server.6 An image is reproduced here to
demonstrateageneralbladeserverhardwareconfiguration.SeeFigure5.

Source:ServerTechnicalCommitteemeeting,Houston,Texas,July31,2012.

[IBM2011]IBMBladeCenterHS22TechnicalIntroduction,
http://www.redbooks.ibm.com/redpapers/pdfs/redp4538.pdf,REDP453803wascreatedor
updatedonMay12,2011.

RochesterInstituteofTechnology
October10,2012

12 ServerPrimer

Figure5:IBMBladeCenterHS22Server(servicecoverremoved)
Source:[IBM2011]

3.2.

Server Price and Performance

InternationalDataCorporation(IDC)isaproviderofmarketintelligenceforthe
information technology (IT), telecommunications and consumer technology
markets.IDChasmapped11pricebandswithintheservermarketintothree(3)
price ranges: volume servers, midrange servers and highend servers. By IDCs
definition, volume servers cost less than $25,000 per server, midrange servers
cost $25,000$250,000, and highend servers cost more than $250,000. These
three price ranges are commonly used to define market trends and are used
throughoutthisreport.

3.3.

Server Market & Sales

Volume servers are currently the most common type of server with 4Q 2011
factoryrevenueof$8.8billion.Forthesametimeframe,midrangeservershad
factoryrevenueof$1.8billion,andhighendservershadfactoryrevenueof$3.7
billion.7
TheIDCreportedthattheserverindustrygenerated$52.3billioninrevenueand
shipped 8.3 million servers worldwide during 2011. Despite these strong sales
the market growth was reported to be decelerating in 3Q11 as demand
stabilizedformanysystemcategories8.Thispredictionwasaccurateasallthree
price bands showed a decrease in revenue during 4Q11. This trend continued

Morgan,T.P.WhereDidtheMidrangeGo?ITJungle,12Mar2012.Web.12Jun2012.
http://www.itjungle.com/tfh/tfh031212story03.html

IDCPressRelease.WorldwideServerMarketRevenuesIncrease4.2%inThirdQuarteras
MarketStabilizes,AccordingtoIDC.Nov2011.Web.June12,2012.
http://www.idc.com/getdoc.jsp?containerId=prUS23179011

RochesterInstituteofTechnology
October10,2012

13 ServerPrimer

into 1Q12 for midrange and highend servers as both experienced over 10%
yearoveryear revenue declines; however, volume servers experienced 2%
yearoveryeargrowth.MattEastwood,anIDCanalyst,statesthatTheserver
market worked through a transitional period in the first quarter of 2012 as
suppliers prepared to introduce numerous critically important x86 server
offerings,andthatlowerrevenueintheAsia/Pacificregioncriticallyaffectsthe
marketbecauseChinaisoneofonlythreecountriesthatregularlyspendmore
than$1billionquarterlyonservers.9
PublicallyavailabledatafromtheIDCpressreleaseswascollectedtogenerate
thefollowingrevenuestreamforthepastdecade.Notethatthenumberslisted
include revenue from server peripherals such as the frame or cabinet and all
cables, processors, memory, communications boards, operating system
software, other bundled software and initial internal and external disk
shipments,andsoarenotpurelyindicativeoftheservermarketitself.
10
9

50

8
7

40
30

6
5

20

4
3

10
0

Revenue($B)

Year
2004 2005 2006 2007 2008 2009 2010 2011

Shipmnets(M)

RevenueEstimate($B)

60

2
1
0

49.5 51.8 52.8 55.1 53.3 43.22 48.77 52.27

Shipments(M) 6.712 7.565 8.233 8.84 9.07 7.56 8.89 9.52

Figure6AnnualServerMarketRevenue(IDC&GartnerEstimates)

Information from this section was combined from a number of different

sources.10,11,12,13,14,15,16,17,18,19

IDC Press Release. Worldwide Server Market Revenues Decline 2.4% in First Quarter as
Market Growth Slows in Face of Market Transitions, According to IDC, 30 May 2012,
http://www.idc.com/getdoc.jsp?containerId=prUS23513412
10

Koomey,J.EstimatingTotalPowerConsumptionbyServersintheU.S.andtheWorld.2007.
http://sites.amd.com/us/Documents/svrpwrusecompletefinal.pdf

11

2006PressReleases.GartnerSaysWorldwideServerShipmentsExperienceDoubleDigit
Growth,WhileIndustryRevenuePostsSingleDigitIncreasein2005.Gartner,Feb2006.Web.12
Jun2012.http://www.gartner.com/it/page.jsp?id=492245

12

GartnerNewsroom.GartnerSaysWorldwideServerShipmentsExperience9PercentGrowth,
WhileIndustryRevenuePosteda2PercentIncreasein2006.Gartner,Feb2007.Web.12Jun2012.
http://www.gartner.com/it/page.jsp?id=501405

RochesterInstituteofTechnology
October10,2012

14 ServerPrimer

Itisexpectedthatservershipmentswillcontinuetoincreaseinthenearfuture
as the world becomes more dependent on the IT sector. In 10 years, the
numberofInternetusershasmorethanquadrupledfrom0.5billionin2001to
2.0billionin2010andthistrendisexpectedtocontinue.
Hewlett Packard (HP) held the number one position in the worldwide server
marketwith29.3%factoryrevenuemarketshareforthefirstquarterof2012.
Additionalworldwidesalesleadersarelistedinthetablebelow.
Table2:WorldwideServerFactoryRevenue(inMillionsofUSdollars)20
Vendor

1Q12

1Q12

1Q11

1Q11

Revenue

Market

Revenue

Market

11

Share

Revenue

Share

1Q12/1Q

Growth
1. HP

$3,460

29.3%

$3,838

31.7%

2. IBM

$3,223

27.3%

$3,477

28.8%

-9.8%
-7.3%

3. Dell

$1,842

15.6%

$1,879

15.5%

-2.0%
-7.3%

4. Oracle

$718

6.1%

$775

6.4%

5. Fujitsu

$614

5.2%

$573

4.7%

7.3%

$1,950

16.5%

$1,551

12.8%

25.8%

$11,808

100%

$12,093

100%

-2.4%

Others
All Vendors

13

GartnerNewsroom.GartnerSaysWorldwideServerShipmentsExperienced7PercentGrowth,
WhileIndustryRevenuePosteda4PercentIncreasein2007.Gartner,Feb2008.Web.12Jun2012.
http://www.gartner.com/it/page.jsp?id=608710

14

GartnerNewsroom.GartnerSaysWorldwideServerShipmentsandRevenueExperience
DoubleDigitDeclinesinFourthQuarterof2008.Gartner,Mar2009.
http://www.gartner.com/it/page.jsp?id=905914

15

GartnerNewsroom.GartnerSays2010WorldwideServerMarketReturnedtoGrowthwith
ShipmentsUp17PercentandRevenue13Percent.Gartner,Feb2011.Web.4Jun2012.
http://www.gartner.com/it/page.jsp?id=1561014

16

GartnerNewsroom.GartnerSaysWorldwideServerRevenueGrew7.9PercentandShipments
Increased7Percentin2011.Gartner,Feb2012.Web.4Jun2012.
http://www.gartner.com/it/page.jsp?id=1935717

17

IDCPressRelease.WorldwideServerMarketAcceleratesSharplyinFourthQuarteras
DemandforHeterogeneousPlatformsLeadstheWay,AccordingtoIDC.IDC,Feb2011.Web4Jun
2012.http://www.idc.com/about/viewpressrelease.jsp?containerId=prUS22716111

18

IDCPressRelease.Despitea7.2%DeclineinFourthQuarterRevenue,WorldwideServer
MarketRevenuesIncrease5.8%in2011,AccordingtoIDC.IDC,Feb2012.Web4Jun2012.
http://www.idc.com/getdoc.jsp?containerId=prUS23347812

19

Short,J.Bohn,R.,Chaitanya,B.HowMuchInformation?2010ReportonEnterpriseServer
Information.2011.http://hmi.ucsd.edu/pdf/HMI_2010_EnterpriseReport_Jan_2011.pdf

20

IDCPressRelease.WorldwideServerMarketRevenuesDecline2.4%inFirstQuarteras
MarketGrowthSlowsinFaceofMarketTransitions,AccordingtoIDC,30May2012,
http://www.idc.com/getdoc.jsp?containerId=prUS23513412

RochesterInstituteofTechnology
October10,2012

15 ServerPrimer

HPwasalsothenumberonemanufacturerofbladeserverswith47.4%market
share. Additional sales leaders were: IBM (21.5%), Cisco (11.0%) and Dell
(8.7%).21

3.4.

ENERGY STAR and Exclusion of Servers with More

than Four Processor Sockets

In1992the EPAintroducedENERGYSTARasavoluntarylabelingprogramto
identifyandpromoteenergyefficientproductsandtherebyreducegreenhouse
gas emissions.22 Now a joint program between the U.S. Environmental
ProtectionAgencyandtheU.S.DepartmentofEnergy,theENERGYSTARlabelis
on major appliances, office equipment, lighting, home electronics, computer
serversandmore.
Asseenbythemarketdata,serversrangewidelyinsizeandperformance.The
US Environmental Protection Agency (EPA) has therefore created a limiting
definitionofserverstoboundtheenergyspecification.WhilethelatestENERGY
STAR standard revision for servers is currently under review, its current
definition(Draft3,Version2.0)forcomputerserverisreproducedbelow:
Acomputerthatprovidesservicesandmanagesnetworkedresourcesfor
clientdevices(e.g.,desktopcomputers,notebookcomputers,thinclients,
wireless devices, PDAs, IP telephones, other computer servers, or other
network devices). A computer server is sold through enterprise channels
for use in data centers and office/corporate environments. A computer
server is primarily accessed via network connections, versus directly
connecteduserinputdevicessuchasakeyboardormouse.Forpurposes
of this specification, a computer server must meet all of the following
criteria:
1) Ismarketedandsoldasacomputerserver;
2) Is designed for and listed as supporting one or more computer
serveroperatingsystems(OS)and/orhypervisors,andistargeted
torunuserinstalledenterpriseapplications;
3) Provides support for errorcorrecting code (ECC) and/or buffered
memory (including both buffered DIMMs and buffered on board
(BOB)configurations).
4) Is packaged and sold with one or more ACDC or DCDC power
supplies;and
5) Isdesignedsuchthatallprocessorshaveaccesstosharedsystem
memory and are independently visible to a single OS or
hypervisor23.

21

ibid

22

HistoryofENERGYSTAR,http://www.energystar.gov/index.cfm?c=about.ab_history

23

[ENERGYSTAR2012]EnergyStarProgramRequirementsProductSpecificationsforComputer
ServersEligibilityCriteriaDraft3Version2.0.USEPA.2012.

RochesterInstituteofTechnology
October10,2012

16 ServerPrimer

Additionally, the ENERGY STAR scope states that a product must meet the
definition of a Computer Server provided in Section 1 of this document [as
reproduced above] to be eligible for ENERGY STAR qualification under this
specification. Eligibility under Draft 3 Version 2.0, is limited to blade, rack
mounted, or pedestal form factor computer servers with no more than four
processor sockets.24 This scope restricts the servers that are covered by the
ENERGYSTARstandardbytheirabilitytosupportadditionalprocessors;thisin
turnlimitstheserversenergyuseaswellasotherenvironmentalcriteria.
Accordingtomanyservermanufacturers,98%ofserverunitssoldare4sockets
or less. The remainder of the market is highend servers, which are typically
custombuilds/configurations.25

4. Server Industry Trends

Over the past decade, server manufacturers and others within industry have
developedprogramstocreatefasterandbetterservers.Serverdevelopmentis
beingdriven,inpart,byMooresLaw,aprinciplenamedafterIntelcofounder
Gordon E. Moore, and based on his observation in 1965 that the number of
transistors that can be placed inexpensively on an integrated circuit doubles
roughlyeverytwoyears,thusenhancingtheperformanceofsucceedingcircuit
generations. After nearly half a century the trend toward progressively higher
performance still continues. The following subsections discuss some of these
performanceimprovingtrendsandassociatedissues.

4.1.

High Density Computing

Amajortechnologytrendintheserverindustryistowardsmallerformfactors
to accommodate IT expansion within confined floor spaces. Modular form
factorsdrovetheservermarketinthefirstquarterof2012,withbladeservers
increasing 7.3% annually and density optimized servers increasing 38.8%
annually. Density optimized servers, as defined by IDC26, are servers that have
beendesignedforlargescaledatacenterswithstreamlinedsystemdesignsthat
focus on performance, energy efficiency, and density. Blade servers now
account for 16.6% of all server revenue, while density optimized accounts for
4.5%. In the first quarter of 2012, several vendors announced converged
solutionsforbladeplatforms;IDCexpectsthesetoenterthemarketstartingin

http://www.energystar.gov/ia/partners/prod_development/revisions/downloads/computer_serv
ers/Servers_V2_Draft_3_Specification.pdf
24
25

ibid

Source:ServerTechnicalCommitteemeeting,Houston,Texas,July31,2012.

26

IIDCPressRelease.Despitea7.2%DeclineinFourthQuarterRevenue,WorldwideServer
MarketRevenuesIncrease5.8%in2011,AccordingtoIDC.IDC,Feb2012.Web4Jun2012.
http://www.idc.com/getdoc.jsp?containerId=prUS23347812

RochesterInstituteofTechnology
October10,2012

17 ServerPrimer

thesecondquarterof2012,deliveringanintegratedsystemforserver,storage,
andnetwork.27
IDC estimates that server system density has increased by 15% annually over
thelast10yearsascompaniesshiftedfrompedestalserverstorackoptimized
systemsandmainstreamadoptionofbladeserversbegan.28In1996,companies
deployedanaverageof7serversperrack.In2006,theaveragehadincreasedto
14 servers per rack. During 2008 HP revealed the potential to have up to 256
halfheight blade servers in a single 42U rack, with support for up to 1024
processors.29
The ENERGY STAR Program Requirements for Computer Servers draft 2 of
Version2.0definesabladeserverasahighdensitydevicethatfunctionsasan
independent computer server and includes at least one processor and system
memory, but is dependent upon shared blade chassis resources (e.g., power
supplies,cooling)foroperation.30
Inordertobeconsideredequivalenttoatraditionalrackserver,abladeserver
must be installed within a Blade Chassis with access to Blade Storage. The
ENERGYSTARComputerServerVersion2draftdefinesthesetwosystemsas:
Blade Chassis: An enclosure that contains shared resources for the
operationof bladeservers,bladestorage,andotherbladeformfactor
devices. Shared resources provided by a chassis may include power
supplies,datastorage,andhardwareforDCpowerdistribution,thermal
managementsystemmanagement,andnetworkservices.
Blade Storage: A storage device that is designed for use in a blade
chassis.Abladestoragedeviceisdependentuponsharedbladechassis
resources(e.g.powersupplies,cooling)foroperation.
The blade server, blade chassis, and blade storage combined form a
BladeSystem.
Theindustrymovetohighdensitycomputingmayprovidesignificantlifecycle
financial and environmental benefits. Scaramella and Perry studied eight
companiesthathadreplaced19100%oftheirserverinfrastructurewithblade
serversandreportedseveralbenefitsincluding:31

27

IDCPressRelease.WorldwideServerMarketRevenuesDecline2.4%inFirstQuarterasMarket
GrowthSlowsinFaceofMarketTransitions,AccordingtoIDC.IDC,May2012.Web.12Jun2012.
http://www.idc.com/getdoc.jsp?containerId=prUS23513412

28

Scaramella,J.WorldwideServerPowerandCoolingExpense20062010Forecast.IDC.2006.
http://www.mm4m.net/library/IDCPowerCoolingForecast.pdf

29

Branscombe,M.HPPuts1000CoresinaSingleRack.TomsHardware,Jun2008.Web.11Jun
2012.http://www.tomshardware.com/reviews/hpserverweb,1943.html

30

[ENERGYSTAR2012]

31

Scaramella,J.,Perry,R.BusinessValueofBlade.HP.2011.
http://h17007.www1.hp.com/docs/proliantgen8/IDCWhitePaperBusinessValueofBlades.pdf

RochesterInstituteofTechnology
October10,2012

18 ServerPrimer

Powercostswerereducedby$17peruserperyear
IT Infrastructure costs were reduced by $55 per user per year; an
additional 17.1% savings was reported by companies that utilized
virtualization(refertoSection4.3.1foradiscussionofvirtualization)
Anestimatedreturnoninvestmentof250%overathreeyearperiod

The move to highdensity computing is also likely to increase the pressure on

systemlevel power and cooling management. Additionally, increased power
drawandhotspotsarelikelytodecreaseserverreliability,thusincreasingfailure
rates.Powerandcoolingchallengescausedbydensificationisthereforelikelyto
requirenovelcoolingsolutions,bothincoolingsystemsandthe matingserver
hardware.

4.2.

Server Internal Waste Heat Management

Notethattheissueofwasteheatmanagementisaddressedbothinternaltothe
server through design and externally in the data center. The following section
focuses on the issues internal to the server, and the data center is discussed
moreinSection5.

Nearly 99% of the

electricity used to
power a server is
converted to heat.

AccordingtotheAPCWhitePaper57,typicallymorethan99%oftheelectricity
usedtopoweraserverisconvertedintoheat.32Theheatenergyincreasesthe
internal temperature of components which will eventually lead to equipment
failure. Servers are therefore designed to remove the heat energy, usually
through forced convection cooling by directing cool air over the hot
components. Note however that server cooling is becoming a more difficult
challenge as the amount of heat generated by a server increases with the
increaseinenergyuseassociatedwiththeincreaseinserverperformance.
Traditional rack servers have internal fans that move cool room air into the
serverandacrossthecomponentsandexpelthegeneratedheatbackintothe
room. For blade server systems, fans provide similar functionality; however,
they are resident in the blade server chassis and therefore not server
components. Computer room air conditioners (CRAC) provide recurrent heat
exchange accepting the heat energy expelled by the server and other
equipment,coolingit,andreturningthecooledairbacktoroom.Thecooledair
istypicallycontrolledwithinaspecifiedtemperaturerangetosatisfythecooling
demands of IT equipment with the current ASHRAE specification is 64.4F
80.6F.33 The cooling effectiveness is therefore limited by the incoming air

32

Evans,T.APCWhitePaper#57:FundamentalPrinciplesofAirConditionersforInformation
Technology.APC.Rev20042.http://www.apcdistributors.com/whitepapers/Cooling/WP57
FundamentalPrinciplesofAirConditionersforInformationTechnology.pdf
33

2008ASHRAEEnvironmentalGuidelinesforDatacomEquipmentExpandingthe
RecommendedEnvironmentalEnvelope.AmericanSocietyofHeating,RefrigeratingandAir
ConditioningEngineers,2008.http://tc99.ashraetcs.org/documents/
ASHRAE_Extended_Environmental_Envelope_Final_Aug_1_2008.pdf

RochesterInstituteofTechnology
October10,2012

19 ServerPrimer

temperature,themaximumoperatingtemperatureofthecomponents,andthe
speedoftheairmovingoverthecomponentsurfaces.

34

Figure7DiagramofInternalServerComponents

Theamountofheatbeingreleasedtotheroomenvironmentiscompoundedby
theincreasingdensityofservers.TheAPCWhitePapernotesthatasingleblade
serverchassiscanreleasefourkilowattsofheatenergyintotheITroomordata
center, with approximately 50% of the heat energy released by servers
originatinginthemicroprocessoritself.HewlettPackardoffersadditioninsight,
statingthatatraditionalracktypeserversetupwith14serverswillrequire8kW
of heat exchange, 26 servers will require 15kW, and 42 servers will require
24.2kW.35
Datacentersarehavingdifficultyadjustingtotheeffectofhighdensityrackson
power and cooling resources and alternate cooling technologies are being
developed.Severalcompaniesareconsideringliquidcoolingasanalternativeto
traditional air cooling as a means to promote energy and cost efficiency. A
commonmethodofliquidcoolingistousewaterasthecoolingmediumsince
water has 3500 times the thermal capacity of air.36 In order to utilize water

34

TheProblemofPowerConsumptioninServers.Intel,2009.
http://www.intel.com/intelpress/articles/The_Problem_of_Power_Consumption_in_Servers.pdf

35

Miller,R.DataCenterKnowledge.TooHotforHumans,butGoogleServerskeepHumming.
March2012.Web.4Jun2012.http://www.datacenterknowledge.com/archives/2012/03/23/too
hotforhumansbutgoogleserverskeephumming/

36

HPModularCoolingSystem:watercoolingtechnologyforhighdensityserverinstallations.
HP.2007.
http://h20000.www2.hp.com/bc/docs/support/SupportManual/c00600082/c00600082.pdf

RochesterInstituteofTechnology
October10,2012

20 ServerPrimer

cooling,awaterblockmustbefixedtotheheatgeneratingcomponentsinplace
ofthetraditionalaircoolingheatsinkandfan.Astheprocessorsgenerateheat
it is transferred to the water which is run through a cooling system that
dissipates the generated heat and chills the water. A benefit of watercooled
systemsistheirmodularity;theycanoperateonaserverbyserverbasisorfor
anentirerackwhileeffectivelydissipatingheat.Thisoffersseveraladvantages
overtraditionalaircoolingsincetheenergyuseissubstantiallyreduced.Water
cooledsystemscanalsobeoverclocked,aprocessthatincreasestheprocessor
speed and allows for increased performance in exchange for increased heat
generation.IBMsAquasarsupercomputer,builtin2010,useswatercoolingto
maintainthesystemstemperature.Duetowatersthermalcapacity,itcarriesa
majorityoftheheatgeneratedawayfromthesystematover60C;thewateris
thenusedasaheatsourcefornearbybuildings.Thishasresultedinanenergy
savingsof40%andareductionofCO2emissionsbyupto85%.37
Other liquid cooling strategies exist. For example, Green Revolution Cooling, a
smallTexasbasedcompany,usesamodifiedmineralwatercalledGreenDefasa
dielectric medium to cool servers. Because of the dielectric properties of their
solution, servers can be submerged in the liquid after waterproofing; this
involves removing the fans and encapsulating the hard drives. GreenDef has
1200timesthethermalcapacityofair,allowingforthecustomserverracktobe
densely packed; this property enables server processors to overclocked
successfully,creatingevenhigheroutput.Thesystemisattachedtoapumpand
heatexchanger.Somesetupsfeatureexportingthehotwaterasaheatsource
tonearbyfacilities.Inaregular100kWinstallation,thecostofinstallandenergy
requirementsperyearwashalfthatofthesamesizedaircooledsystem.38

4.3.

Server Utilization and Connectivity

As previously stated, a server is typically dedicated to a single function and

therefore the amount of time an average server is actually being used, or the
server utilization, is only around 1022%.39 This means that a data centers
processing capacity as a whole is significantly underutilized. Some estimates
statethat15%oftheserversindatacentersareneverutilized.40Thefollowing

37

"IBMResearchZurich."Zeroemissiondatacenter.IBM,Jul2010.Web.4Jun2012.
http://www.zurich.ibm.com/st/server/zeroemission.html

38

TheCarnotJetSystem.GreenRevolutionCooling.http://www.grcooling.com/docs/Green
RevolutionCoolingCarnotJetSystemPamphlet.pdf

39

Koomey,J.,Belady,C.,Wong,H.,Snevely,R.,Nordman,B.,Hunter,E.,Lange,K.,Tipley,R.,
Darnell,G.,Accapadi,M.,Rumsey,P.,Kelley,B.,Tschudi,B.,Moss,D.,Greco,R.,BrillK.Server
EnergyMeasurementProtocol.(2006).
http://www.energystar.gov/ia/products/downloads/Finalserverenergyprotocolv1.pdf

40

[Microsoft2011]Aggar,M.TheITEnergyEfficiencyImperative.Microsoft.2011.
http://download.microsoft.com/download/7/5/A/75AB83E82487409FAC6C
4C3D22B72139/ITEI_Paper_5.27.11.pdf

RochesterInstituteofTechnology
October10,2012

21 ServerPrimer

subsectionsdiscusssomeoftrendstoboostutilization,reduceenergycosts,and
saveequipmentandspace.
4.3.1. Server Virtualization
Virtualization is a softwarebased solution to server underutilization. By using
speciallydesignedsoftware,onephysicalserver,orhost,canbeconvertedinto
multiple virtual machines, or guests. Each virtual server acts like a unique
physicaldevice,capableofrunningitsownoperatingsystem(OS).
This allows the one application per server motif to be reworked into one
applicationpervirtualmachine.Usingvirtualization,atypicalsmalldatacenter
with one domain name server, one mail server, and one web server could be
compacted to a single machine running the base processor and two virtual
machines. Following a survey of the IT industry, Healy, Humphreys, and
Andersonsuggestedthat virtualizationcanreduce hardwarecostsby20%and
generate a savings of 23%.41 Despite these potential benefits, twothirds of
organizationshavevirtualizationenabledonlessthanhalfoftheirservers.42
Virtualization not only provides hardware reduction benefits, but it also saves
energy.Figure6showsatypicalserverenergyprofile,whereatlowutilization
thepowerconsumedisabouthalfofthepowernecessaryatfullutilization.Two
of the same servers operating at 20% utilization each would require more
energythanasingleserveroperatingat40%utilization.

Figure8RelationshipbetweenServerUtilizationandPowerConsumption43

41

Healy,M.,Humphreys,J.,Anderson,C.IBMVirtualizationServices.IBM.2008.http://www
935.ibm.com/services/us/its/pdf/idc_white_paper_for_ibm_on_virtualization_srvcsv2.pdf

42

[Microsoft2011]

43

ibid
RochesterInstituteofTechnology
October10,2012

22 ServerPrimer

4.3.2. Server Consolidation

Like virtualization, consolidation is a method to reduce the number of servers
within a data center. However, unlike the softwarebased virtualization,
consolidation is hardware based. Instead of grouping different applications or
functions onto one server, consolidation replaces multiple servers, each with
low utilization and serving the same function, with a single higherutilized
server.44Aswithvirtualizationthismethodcanhelplowercostsandsavespace
byeliminatingexcessequipment.Carrstatesthatby2005,largedatacenters
are becoming increasingly common as smaller data centers consolidate.45 As
notedinFigure6,servershavehighpowerrequirementsatlowutilization;thus
consolidating two servers into one is less energy intensive than running two
independentservers.Figure7depictssixfirmsoperatingindividualmailservers
andasecondscenariowheretheyshareacloudbasedserviceinstead,enabling
anetreductionoftwoservers.Acloudcomputingcentercanbeconsideredto
bealargedatacenterconsolidatedfromseveralsmallerones.Thishighlightsa
basic economy of scale: the larger the data center, the more efficient it is
comparedtoasetofsmallerdatacentersservingthesamepurpose.46

44

Iams,T.,Consolidationandvirtualization:Thesame,butdifferent.
http://searchdatacenter.techtarget.com/tip/ConsolidationandvirtualizationThesamebut
different

45

Carr,NicholasG.TheEndofCorporateComputing.MITSloanManagementReview.vol.46,
no.3,pp.6773.2005.http://sloanreview.mit.edu/themagazine/2005spring/46313/theendof
corporatecomputing/

46

GooglesGreenComputing:EfficiencyatScale.Google.2011.
http://static.googleusercontent.com/external_content/untrusted_dlcp/www.google.com/en/us/g
reen/pdfs/googlegreencomputing.pdf

RochesterInstituteofTechnology
October10,2012

23 ServerPrimer

Figure9EffectsofConsoldation/CloudComputing

In February 2010, the U.S. government launched the Federal Data Center
Consolidation Initiative (FDCCI) and issued guidance for Federal Chief
InformationOfficers(CIO)Councilagencies.Theguidancecalledforagenciesto
inventorytheirdatacenterassets,developconsolidationplansthroughoutfiscal
year 2010, and integrate those plans into agency fiscal year 2012 budget
submissions.
The Consolidation Initiative is intended to reduce the number of data centers
across the government and assist agencies in applying best practices from the
public and private sector, with goals to: reduce the overall energy and real
estate footprint of government data centers, reduce the cost of data center
hardware,software,andoperations,increasetheoverallITsecuritypostureof
thegovernment,andshiftITinvestmentstomoreefficientcomputingplatforms
andtechnologies.
TheConsolidationInitiativeplanistoshutdownatleast1,200ofthe3,133data
centers the government owns and operates. To date, 250 data centers have
beenshutdownandthereareplanstocloseatotalof479bytheendoffiscal
year2012.47
4.3.3. Cloud Computing
TheNationalInstituteofStandardsandTechnologydefinescloudcomputingas
amodelforenablingubiquitous,convenient,ondemandnetworkaccesstoa
shared pool of configurable computing resources (e.g., networks, servers,
storage,applications,andservices)thatcanberapidlyprovisionedandreleased
withminimalmanagementeffortorserviceproviderinteraction.
Figure 7 illustrates how consolidation using a cloudcomputing data center is
moreefficient.AGooglecasestudyanalyzedtheeffectsoflocallyhostedemail
service compared to cloudhosted email service. The study methodology was
based on businesses with 50 (small business), 500 (medium business), and
10,000+(largebusiness)employees,andcomparedthedatacentersrequiredby
these businesses to a cloud computing datacenter operated by Google. The
resultsindicatethatasthenumberofusersincrease,peruserrequirementsfor
power and the corresponding emissions decrease exponentially following a
basic economy of scales argument. Some results from this study are outlined
below:48

47

Federal Chief Information Officers Council, Maximizing ROI: Consolidating Federal IT

Infrastructurehttps://cio.gov/maximizingroi/,accessed10/8/12

48

[Google.2011]
RochesterInstituteofTechnology
October10,2012

24 ServerPrimer

Business
emailservice
Small

Medium

Large
Google

ServerRequirements
Asingle,midrangemulticore
serverwithlocaldiskthatcan
serve300usersanddraws200
Watts.
Asingle,large,manycoreserver
withcombinationsoflocaland
networkstorage,whichcanhost
1,000usersandwhichdraws450
Watts
Several,large,manycoreservers
withcombinationsoflocaland
networkstoragewhichcanhost
1,000usersanddraws450Watts.
Cloudbasedservices

Annual
EnergyPer
User

AnnualCO2
emissionsPer
User

175kWh

103kg

28.4kWh

16.7kg

7.6kWh

4.1kg

<2.2kWh

<1.23kg

Data center design

is improving with
a PUE average
value of 1.91. This
means that over
47% of the power
used in a data
center is used to
support the
infrastructure,
including cooling.

Accenture,aresearchfirm,derivedsimilarresultsusingcompanysizesof100,
1000, 10,000 and comparing individual data center emissions to those from a
single Microsoft cloud data center.49 The analysis suggests that typical carbon
emission reductions by deployment size are more than 90 percent for small
deployments of about 100 users, 60 to 90 percent for mediumsized
deployments of about 1,000 users, 30 to 60 percent for large deployments of
about10,000users.

5. Server Impact on Overall Data Center Energy Use

Asignificantportionoftheenergyrequiredtouseaserverisdirectedintothe
infrastructure used to support the server. The server design can not only
influencetheenergyusedbytheserveritself,butalsotheenergyusedbythe
infrastructure.
Power Usage Effectiveness (PUE) is a frequently used measure of the
effectivenessofdatacenterinfrastructureandoperation.PUEistheratioofthe
total data center power input, to the power directly consumed by the IT
equipment.Assumingthatallpowersourceshavebeenproperlyaccountedfor,
the theoretically ideal PUE for a data center is 1.0, meaning that there is no
additional energy required to operate the data center beyond the power
directlyconsumedby theequipment. While1.0 is notpracticallyachievable,a
number of companies and organizations are reporting PUE numbers for their
newstateoftheartdatacenterswhichareapproaching1.0,withanumberof

49

CloudComputingandSustainability.Accenture.2010.
http://download.microsoft.com/download/A/F/F/AFFEB671FA2745CF9373
0655247751CF/Cloud%20Computing%20and%20Sustainability%20%20Whitepaper%20
%20Nov%202010.pdf

RochesterInstituteofTechnology
October10,2012

25 ServerPrimer

facilitiesreportingapproximately1.10.50Astudyconductedin2009bytheU.S.
EPAENERGYSTARprogramlookedatPUEforabroadrangeof100datacenters,
thisstudyshowedarangeofPUEvaluesbetween1.253.75,withanaverage
valueof1.91.51Electricalpowermanagement,equipmentutilizationlevels,and
HVAC are major areas for energy consumption within data centers. In
conventionally cooled data centers, the air conditioning loads are one of the
largestdriversofenergyconsumptionaftertheITequipment.
Heatrecoveryandreuse(forexampleinabsorptivecoolingsystems),wateror
refrigerant based cooling, and free air cooling52 are all strategies for reducing
theenergycostofdatacentercooling.However,thesecanbeverydifficultor
expensivetoimplementasaretrofittoexistingdesigns.
Expanding the allowable environmental operating range (temperature and
humidity) of IT equipment can result in lower HVAC related energy
consumption.In2008,ASHRAEexpandeditsclassesfordatacenterequipment
environmental specifications; four classes are defined 14, with each higher
number class having a wider environmental range.53 The classes define
recommended and allowable (wider) operational ranges for drybulb
temperature and humidity (RH and wetbulb), as well as ranges for non
operating equipment. In the 2011 whitepaper referenced, the recommended
andallowablerangesarerefinedrelativetothe2008standard,andclasses(A1
A4)aredefined;theoperationalrangesforA3andA4areexpandedrelativeto
the 2008 standard. In the model R270 server technical documentation, Dell
provides environmental specifications that allow for continuous operation at
the A2 level, and transient operation at A3 and A4 (less than 10% of annual
operatinghours,lessthan1%ofannualoperatinghours).54Thistypeofproduct
information can be helpful to the data center designer/operator in setting

50

M.K.Patterson,"Metricsoverviewandupdate,"Powerpointpresentation,presentedatthe
Proceedingsofthe2011workshoponEnergyEfficiency:HPCSystemandDatacenters,Seattle,
Washington,USA,2011.
http://dl.acm.org/citation.cfm?id=2159350&CFID=170830100&CFTOKEN=87344492

51

Sullivan,A.,ENERGYSTARforDataCenters,USEPA,ENERGYSTARPowerPointPresentation,
Feb4,2010,
http://www.energystar.gov/ia/partners/prod_development/new_specs/downloads/uninterruptib
le_power_supplies/ENERGY_STAR_Buildings_Team_Metering_Presentation.pdf,lastaccessed
October8,2012.

52

Pendelberry,S.,Thurston,M.,et.al.,CasestudyThemakingofaGreenDataCenter.
Proceedingsofthe2012IEEEInternationalSymposiumonSustainableSystemsandTechnology,
Boston,MA,May1618,2012.
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6228001

53

ASHRAETC9.9,2011ThermalGuidelinesforDataProcessingEnvironmentsExpandedData
CenterClassesandUsageGuidance,ASHRAE,2011,http://www.eni.com/greendata
center/it_IT/static/pdf/ASHRAE_1.pdf,lastaccessedOctober8,2012.

54

PowerEdgeR720andR720XDTechnicalGuide,Rev1.1,March2012.
http://i.dell.com/sites/content/sharedcontent/datasheets/en/Documents/dellpoweredger720
r720xdtechnicalguide.pdf,lastaccessedOctober8,2012.

RochesterInstituteofTechnology
October10,2012

26 ServerPrimer

environmental controls criteria that minimize HVAC related energy

consumption, and could be added to the ENERGY STAR Power and
PerformanceDataSheet.55

55

ENERGYSTARPowerandPerformanceDataSheet,DellPowerEdgeR720XDfeaturingtheDell
Smart1100WPSUandIntelE52640.
http://www.dell.com/downloads/global/products/pedge/en/DellPowerEdgeR720XD1100W
E52640FamilyDataSheet.pdf,lastaccessedOctober8,2012.

RochesterInstituteofTechnology
October10,2012

27 ServerPrimer

6. Server Environmental Assessments

Environmental impacts of a product occur throughout the product life cycle.
Someexamplesinwhichaproductwillimpacttheenvironmentarethroughthe
depletion of natural resources (fuel / energy, material, water), the impact on
the ecosystem health (terrestrial and aquatic ecotoxicity, acidification,
eutriophication, land use), and the impact on human health (human toxicity,
stratosphericozonedepletion,ionizingradiation,andclimatechange).

A LCA showed the

Dell PowerEdge
R710 was
responsible for
approx. 6360 kg
CO2e over a 4yr
lifetime. 90% of
the CO2e emissions
were from use.

Lifecycleassessment(LCA)isatoolusedtoquantifytheenvironmentalimpacts
of a product, holistically, throughout the entire life cycle; from material
extraction, manufacturing, transportation, use, and end of life. The impacts
associatedwiththeproductareassessedbycompilinganinventoryofrelevant
energyandmaterialinputsandenvironmentalreleases,evaluatingthepotential
environmental impacts associated with the identified inputs and releases, and
interpreting the results to help make more informed decisions. These studies
arealsoveryusefulinidentifyingifenvironmentalburdensareshiftedfromone
product life cycle phase (for example: material extraction) to another product
lifecyclephase(forexample:productendoflife).
Effort was exerted to identify full life cycle studies for computer servers. In
additiontoliteraturesearchesandinquiriesthroughRITindustrycontacts,the
manufacturersontheTechnicalCommitteewereaskedtoidentifyanyknowfull
LCA on servers. At the time of this writing, no full LCA studies using multiple
environmentalimpactshavebeenidentified.
Carbonfootprintingstudiesofcomputerservers,however,wereidentified,and
the following subsections highlight some of these studies that have
investigated the life cycle global warming potential of a server. It should be
notedthatcarbonfootprintingisasimplifiedformofLCAfocusedononlyone
environmental impact, and that computer servers have additional known
environmental impacts such as resource depletion, human toxicity, and
environmental toxicity that are not reported by these studies. Complementing
the carbon footprinting studies with full life cycle assessments would avoid
burdenshiftingfromGHGtootherrelevantenvironmentalareasofconcern.

6.1.

Carbon Footprint of a Typical Dell Rack Server

Dellconductedastudyin2011todeterminethecarbonfootprint(greenhouse
gas (GHG) emissions contribution to global warming potential (GWP) in kg of
carbon dioxide equivalents (CO2e)) of the Dell PowerEdge R710 server. 56 This
analysis was performed following the ISO 1404057 and ISO 1404458 standard

56

Stutz,M.,O'Connell,S.,&Pfluefer,J.Carbonfootprintofatypicaldellrackserver.
InternationalSymposiumonSustainableSystemsandTechnology.May2012.Boston,MA.
57

ISO14040:2006EnvironmentalmanagementLifecycleassessmentPrinciplesandframework

58
ISO 14044:2006 Environmental management Life cycle assessment Requirements and
guidelines

RochesterInstituteofTechnology
October10,2012

28 ServerPrimer

frameworkonthePowerEdgeR710serverwithtwoIntelXeonprocessors,12Gb
ofRAM,4x146GBharddrives(HDD),twohighoutputpowersupplies,oneDVD
drive,andfourfans.
TheDellpaperstatesthatthetotalcarbonfootprintofaDellPowerEdgeR710is
approximately6360kgCO2e.Thiswascalculatedovera4yearlifetimerunning
24hoursaday,7daysaweekassumingoperating50%ofthetimeat148Widle
workload,and50%ofthetimeat285Wfullworkload.TheaverageUSgridmix
wasusedforthiscalculation.
Results show that over 90 percent of the total lifecycle GHG emissions was
from the use phase (5960 kg CO2e). See Figure 10. Only 7 percent of the GHG
emissions was from manufacturing, which included raw material extraction,
subassembly manufacturing, transportation of subassemblies, and final
assembly.

DellPowerEdgeR710
GHGEmissions(kgCO2e)

7000
6000
5000
4000

Use

5960

3000

Manufacturing

2000

Transport

1000
0
1000

Recycling
15

471
86

GHGEmissions

Figure10TotalProductCarbonFootprintoftheDellPowerEdgeR710intheUS

Dell ran two additional model scenarios. The first was to model the server at
100 percent utilization, and the second was to run the server at 100 percent
idle. At full utilization the unit produced 8240 kg CO2e, or 30% more carbon
emissions, and at idle it produced 4470 kg CO2e, or 30% less emissions (see
Figure11).
Dell stated that these results were a powerful message for eliminating
underutilized server through virtualization. Using the above report numbers,
onecanseethattwoserversrunningat50percentutilization(nominalcaseat
2x 6360 = 12720 kg CO2e) would produce 54 percent more carbon emissions
than one server running at 100 percent utilization (8240 kg CO2e) reinforcing
theirsupportforvirtualization.

RochesterInstituteofTechnology
October10,2012

29 ServerPrimer

GHGEmissions(kgCO2e)

DellPowerEdgeR710
9000
8000
7000
6000
5000
4000
3000
2000
1000
0
1000

Use
Manufacturing
Transport
Recycling

Full
Nominal
Utilization

FullIdle

Figure11TotalCarbonFootprint(kgCO2e)oftheDellPowerEdgeR710server

6.2.

Carbon Footprint of Fujitsu Primergy RX and TX

300 S5 Servers

Fujitsu published a study in 2010 called Life Cycle Assessment and Product
Carbon Footprint PRIMERGY TX 300 S5 and PRIMERGY RX 300 S5 Server.59
Thoughthetitleimpliesthatafulllifecycleassessmenthasbeencompleted,the
whitepaperonlypublishedresultsofthecarbonfootprint.Thepaperhowever
states that greenhouse effect, cumulative energy demand, acidification,
terrestrialandaquaticeutrophication,photochemicaloxidantformation,human
toxicity,andecotoxicitywerestudied.TheserversincludedoneIntelXeon2.26
GHz 8MB processor, one 4GB DDR31066 PC38500 ECC memory, one 146GB
harddrive,RAIDcontroller,DVDRW,andrackmountkitserver.
TheFujitsupaperstatesthatthetotalcarbonfootprintofthePRIMERGYTX300
S5 is approximately 3750 kg CO2e. This was calculated over a 5year lifetime
operating at a 30% workload. The average German grid mix was used for this
calculation. Results show that over 85 percent of the total lifecycle GHG
emissionswasfromtheusephase.SeeFigure12.Theimpactoftheusephase
oncarbonfootprintwasverysimilartotheDellresults.
Though limited data is contained in the white paper, a few other interesting
results were presented. One result highlighted how source power generation
impactsthecarbonfootprint.ThesameanalysisasaboveruninFrance,where
thereisahighlevelofnuclearpower,insteadofGermany,wherethereishigh
coal use, reduced the carbon footprint from 3750 kg CO2e to 980 kg CO2e.

59

WhitePaper:LifeCycleAssessmentandProduceCarbonFootprintServerPRIMERGYTX/RX
300S5.Fujitsu.2010.http://fujitsu.fleishmaneurope.de/wpcontent/uploads/2010/12/LCA_PCF
WhitepaperPRIMERGYTXRX300S5.pdf

RochesterInstituteofTechnology
October10,2012

30 ServerPrimer

Additionally,oneofthereportlessonslearnedwastoavoidfocusingsolelyon
energy efficiency of servers. Though the use phase plays a big role in the
greenhouse effect, raw materials are key factors for several other impact
categories. This is an important statement, though no supporting data was
provided.

Figure12RespectiveShareoftheTotalProductCarbonFootprint(Fujitsu)

6.3.

Case Study of an IBM Rackmounted Server

Weber looked at the uncertainty and variability in the carbon footprinting

methodology using an IBM rackmounted server. The specific server model
numberandcomponentsarenotidentified;however,theserverisidentifiedas
an IBM circa 2008 model. The server life was modeled as a triangular
distribution with a most likely value of 6 years and minimum and maximum
valuesof3and10years.Theusephasemeanwas6238kgCO2erepresenting
around 94 percent of the servers total carbon footprint (88% 97% with
uncertainty).
The analysis also highlighted the contribution of the various components
without including the dominant use phase. The analysis showed that the
manufacture of the Integrated Circuits (ICs) and printed wiring boards (PWBs)
are responsible for a combined 45% of the remaining carbon emissions not
includingtheusephase.Thebreakdownofindividualproductcarbonfootprint
contributionsfromthecomponentsisshowninthefigurebelow.60

60

Weber,C.L.UncertaintyandVariabilityinProductCarbonFootprinting.JournalofIndustrial
Ecology,16(2),203211.2012.doi:10.1111/j.15309290.2011.00407.x

http://onlinelibrary.wiley.com/doi/10.1111/j.15309290.2011.00407.x/full

RochesterInstituteofTechnology
October10,2012

ProductCarbonFootprint
(withoutuse)(kgCO2e)

31 ServerPrimer

400

Logistics

350

Packaging

300

BulkMaterials

250

PowerSupplies

200

DVDROM

150

HardDrive

100

Components

50

RawPWB

0
Server

IC

Figure13MeanResultsforServerCarbonFootprintbySubgroupwithoutUsePhase61

7. Server Standard Scope Topics

The following subsections highlight industry current practices and current
requirements of various environmental impact areas of concern. The sub
sectiontopicsarealignedwiththetopicsintheIEEE1680familyofstandards.

7.1.

Server Material Selection

All materials used in products impact the environment in some manner either
through their production, their use in products, or in the disposal of those
products. Minimizing the impact that a product has on the environment
requirestheselectionofmaterialsthatare,ingeneral,lesstoxic,arelessenergy
intensive to make (which may include containing recycled content), are from
renewablesources,andareeasiertoreuseorrecycle.
Thecurrentmaterialsusedinserversareestimatedinthefollowingsubsections.
Thesematerialsweredeterminedthroughadisassemblyanalysisperformedat
GIS,andamaterialanalysisprovidedbyCascadeAssetManagement.Notethat
a significant percentage of materials used in servers are steel and aluminum,
withalowpercentageofplasticcontent.
7.1.1. Server Demanufacturing: GIS
In2010,graduatestudentsleadbyGISfaculty,Dr.CallieBabbitandDr.Michael
Thurston,researchedtheeffectsthatelectronicwastehasonspecificmaterial
flows. This study62 included various endoflife scenarios, including reuse and
recycling, for components of common IT products. The study included

61

ibid

62

RIT internal report, Analysis of EWaste Material Flows, and Opportunities for
Improved Material Recovery March, 2010, Confidential, some data reproduced here
withpermission.

RochesterInstituteofTechnology
October10,2012

32 ServerPrimer

completingafulldisassemblyanalysisdowntotheindividualmateriallevelwith
materials identified by using various material analysis laboratory techniques.
One of the products studied was a Dell PowerEdge R710 server. This server
modelwasconsideredrepresentativeofvolumeservers.Thoughthemainstudy
scholarshipremainsconfidential,someofthegeneralfindingsofthisstudyare
reproducedbelowwithpermission.
Amajorstudyfocusareaappliedmaterialflowanalysis(MFA)methodologyto
servers.TheMFAinvestigatedeachmaterialfortheirtotalvolumes,value,and
percent of total waste and then this data was used to estimate the current
breakdownandvolumesinwhichproductsandcomponentsarerecoveredfor
refurbishment and reuse, remanufactured, recycled, or disposed. The Dell
PowerEdgecomponentsandassemblieswereseparatedintoindividualmaterial
types. In some cases, for simple geometries, material breakdown was
determined by means of simple volume/density calculations. Plastic
components were identified by their material codes. For those plastics
components without material codes, the material was assigned to an
Undefined Plastic category. A variety of methods were used to assign metal
components to a material category such as: inspection (observed density and
stiffness), level of magnetism, and Energy Dispersive Xray Spectroscopy was
alsousedonsomecomponentsthatwerenotobviousbyinspection.Finally,for
Lithium Ion batteries and for printed circuit boards, previous compositional
studiesfromtheliteraturewereusedtoestimatethematerialcompositionby
weightpercentage.
The material analysis results indicate that the majority of a Dell PowerEdge
servers weight is composed of ferrous steel (62.7%), aluminum (15.9%),
halogenated epoxy (9.6%) and plastics, (4.8%). Detailed estimates of material
compositioncanbefoundinthetablebelow.
Table3TotalMaterialCompositionoftheDellPowerEdgeR710byweight

TotalWeight

Weight
(grams)
24680

Steel/Ferrous

15480

62.70%

Ferrites/Magnets

456

1.80%

Aluminum

3934

15.90%

Copper

863

3.50%

Tin

123

0.50%

Brass

1.8

0.00%

Mercury

0.00%

Carbon

0.36

0.00%

Lithium

0.21

0.00%

Cobalt

0.6

0.00%

Nickel

32.1

0.10%

Silver

10.6

0.00%

Material

RochesterInstituteofTechnology
October10,2012

Percentage

33 ServerPrimer

Gold

Weight
(grams)
0.68

0.00%

Palladium

0.17

0.00%

TotalPlastic

1179

4.80%

Plastic(various)

701

2.80%

PC+ABSFR

23.8

0.10%

PC+ABSFR(40)

299.7

1.20%

PBTGF30FR(17)

154.9

0.60%

PVC

0.00%

Rubber(includingfoams)

5.3

0.00%

Paper

15.3

0.10%

Epoxy

11.5

0.00%

CapacitorElectrolyte(EthyleneGlycolorButyrolactone)

30

0.10%

HDGlass/CeramicDisk

176.3

0.70%

HalogenatedEpoxy+GlassReinf

2359.4

9.60%

LiIonElectrolyte
NonAqueousLiIonSolvent(propylenecarbonate,1.3
dioxolane,Dimethoxyethane)

0.03

0.00%

0.14

0.00%

Material

Percentage

7.1.2. Server Demanufacturing: Cascade

Neil PetersMichaud, Owner and CEO Cascade Asset Management (Cascade),
provided a rack server demanufacturing study performed in August 2012.
Cascadeanalyzedthematerialfractionsin1972lbsofserversthatwerebeing
processed at end of life. The study results are reproduced in Figure 14 with
permission.

RochesterInstituteofTechnology
October10,2012

34 ServerPrimer

DemanufacturedFractions Servers
TotalWeight 1972lbs
ScrapFerrousMetal(1251lbs)
PreciousCircuitBoards(202lbs)
CopperHeatsinksw/Aluminum(58lbs)
AluminumBreakage(24lbs)
ComputerCables(10lbs)
UniversalWaste:NiCad/NiMHBatteries(1lbs)

12.8%

PowerSupplies(249lbs)
ShreddedHardDrives(104lbs)
MixedPlastic(25lbs)
Copper(18lbs)
LowValueBoards(3lbs)
UniversalWaste:LithiumBatteries(1lbs)

10.4%

1.2%

0.9%

5.3%
7.2%
64.3%

0.5%

1.3%

0.2%
0.1%

3.0%
0.1%

Figure14CascadeDemanufacturedMaterialFractionsofServers(August2012)

7.2.

Environmentally Sensitive Materials

No information was found in the literature search concerning the specific

chemical makeup of substances used in servers. However, servers contain
componentssimilartootherelectronicsdevicesandthatdataisreportedhere
asaproxy.Thereport,InformationonChemicalsinElectronicProducts63,states
that analysis of chemicals present in electronic products is not easy. For
example, computers and mobile phones can contain over one thousand
differentsubstances.Thereportalsostatesthatthemainhazardoussubstances
found in electronic products are: lead, mercury, cadmium, zinc, yttrium,
chromium, beryllium, nickel, brominated flame retardants, antimony trioxide,
halogenatedflameretardants,polyvinylchloride(PVC),andphthalates.
The report also provided some examples of material use in electronic
equipment. Batteries can contain heavy metals such as lead, mercury, and
cadmium.Soldercancontainlead,tin,andothermetals.Internalandexternal
wiringisoftencoatedwithPVCwhichcancontainadditionalsubstancessuchas
phthalates. Semiconductors can be encapsulated by plastics containing
brominated flame retardants. Finally, printed circuit boards can contain

63

Nimpuno,N&CScruggs(2011).InformationonChemicalsinElectronicProducts.Copenhagen:
NordicCouncilofMinisters.ISBN9789289322188
http://www.norden.org/en/publications/publikationer/2011524

RochesterInstituteofTechnology
October10,2012

35 ServerPrimer

brominatedflameretardants,antimonytrioxide,andotherhazardousmaterials
suchaschromium,lead,mercury,beryllium,zincandnickel.
Limited data was found on the active use of alternative materials. Server
operatingconditionsandperformancedemandsofhighreliability,highenergy
use, and high temperature operation to name a few require performance
materialsthatarenoteasilyreplacedwithgreenalternatives.
Some information was found on the use of leadfree solders. Dell64 advertises
thatsincelate2007,theyhavebeenlaunchingleadfreeserverssuchastheDell
R900andR905.Inearly2008,Delllaunchedtheirfirstleadfreebladeservers,
the PowerEdge M600 and M605. Since then, they claim that all new basic
configurationPowerEdgeservershavebeenleadfree.
7.2.1. RoHS Directive
A few hazardous materials in electronic equipment are governed by the
European Directive 2002/95/EC on the Restriction of the Use of Certain
Hazardous Substances in Electrical and Electronic Equipment (commonly
referredtoastheRoHSDirective).TheDirectivewasadoptedinFebruary2003
by the European Union (EU) and took effect in July of 2006 and is required to
become law in each member state of the European Union. This directive
restrictstheuseofsixhazardousmaterials(lead,mercury,cadmium,hexavalent
chromium,polybrominatedbiphenyls(PBB)orpolybrominateddiphenylethers
(PBDE))inthemanufactureofelectricalequipmentsoldintheEU.ThisDirective
has been adopted by many server manufacturers worldwide due to the global
nature of IT equipment sales. Additionally, some states in the U.S. such as
California65 have adopted RoHS legislation based on the EU directive. On May
14, 2009, H.R. 2420, the Environmental Design of Electrical Equipment Act
(EDEE) Act, was introduced as a Bill in the US House of Representatives with
similarrequirementsastheEURoHS;however,thisbilldiedincommittee.
The EU Directive has an exemption specific to servers for lead in solders for
servers, storage and storage array systems, network infrastructure equipment
for switching, signaling, transmission as well as network management for
telecommunications. The primary reason for this exemption is that solder
jointsaresubjectedtosignificantstressduetothermalcycling,andsolderswith
leadhavehistoricallybeenmoretolerantandhavehigherreliabilitythanlead
freesolders.

64

Design.Smartermaterialchoices:what'sinsideourproductsandwhat'snot.Dell,2012.Web.
12Jun2012.http://content.dell.com/us/en/corp/d/corpcomm/earthgreenerproductsmaterials

65

CaliforniaDepartmentofToxicSubstancesControl.RestrictionsontheuseofCertain
HazardousSubstances(RoHS)inElectronicDevices.StateofCalifornia,2010.Web.12Jun2012.
http://dtsc.ca.gov/HazardousWaste/rohs.cfm

RochesterInstituteofTechnology
October10,2012

36 ServerPrimer

7.3.

Product Longevity

Server equipment has historically been replaced when it no longer meets the
performance needs of the market, not necessarily by the functional life of the
equipmentitself.AsurveyoftheITmarketfromtheIDCnotesthattheoptimal
time to replace a server is after three years of operation, at which time the
returnoninvestment(ROI)topurchasenewcomparedtocontinualoperationof
current equipment will be less than one year66. These product refreshes have
the benefit of increased efficiency and better power utilization, as noted by
Dell67. Data from Dell supports this replacement timeframe noting that their
PowerEdgeserversusuallyoperateforabout4yearsbeforetheyareremoved
fromthemarket.HewlettPackardsuggestsatypicallifetimeisapproximately3
4years.
Oneofthe mainreasonsgivenforreplacingserversbeforecompletefailureis
thatmanyexperienceadecreaseinserverreliabilitywhichincreasesoperating
costs. The survey of the IT market mentioned above questioned over 50
participantsintheservermarkettodiscovertheeffectthataginghadonserver
equipment.Notetheincreaseinfailureratesanddowntimeastheequipment
ages.(Figure15)

20%
18%
16%
14%
12%
10%
8%
6%
4%
2%
0%

8
7
6
5
4
3
2
1

Downtime(hrsperyear)

FailureRate

EffectofTimeonServerReliability

FailureRate
Downtime

0
1

ServerAge(years)

66

Figure15EffectofTimeonServerReliability

66

Perry,R.,Pucciarelli,J.,Bozman,J.,Scaramella,J.TheCostofRetainingAgingIT
Infrastructure.HP.2012.http://h18006.www1.hp.com/storage/pdfs/4AA39351ENW.pdf

67

Stutz,M.,O'Connell,S.,&Pfluefer,J.Carbonfootprintingofatypicaldellrackserver.
InternationalSymposiumonSustainableSystemsandTechnology.May2012.Boston,MA.

RochesterInstituteofTechnology
October10,2012

37 ServerPrimer

7.4.

Design for End of Life

A significant mass of electronic equipment reaches the end of life and is

discarded every year. A 2005 paper estimated that global electronic waste
generationwasonthescaleof2050milliontonsperyear68withapproximately
40thousandtonsofthiswastefromendoflifeservers.Thisvalueisprojected
to continue to increase as more servers reach the end of life through both
failureandobsolescenceduetorapidtechnologyadvancements.
Servers have traditionally been designed for rapid repair and easy upgrade to
ensure minimal downtime. Many of the components are therefore hot
swappable, or able to be removed and changed while the server continues to
run. The traditional repairable and modular design provides the secondary
benefit of simple separation at the servers end of life. Servers are therefore
easily separated into recyclable material streams, or are easily upgraded to
extend the product life. The challenges associated with upgrade are further
detailedinsection7.5.2.
This ability to disassembly the server to the component level was also seen in
the GIS demanufacturing analysis covered in section 7.1.1. The Dell server
studied in this analysis had a very modular design, with many of the major
componentsretainedbyquickreleaseattachments.Thisdesignallowsforquick
and cost effective servicing of components with little or no down time during
the use phase, and complete removal of all major components at the endof
life. In the study, the total disassembly time was only 8.2 minutes. The quick
releaselatcheshadeitherlightblueororangecoloredtabs,whichincreasedthe
easeoflocatingandidentifyingtheselatches.Wireharnesseswerealsoclearly
labeledforeasyidentificationwithquickreleaseconnectorsthatdidnotrequire
the use of tools to remove. The motherboard was mounted to a large steel
framewhichwaseasilyremovedbyremovingafewT15Torxscrews.
The modular design of both components and the use of quick release clips
insteadofthreadedfastenersfacilitatedmanualdisassemblyasanoptionprior
to mechanical separation. This separation of components with highvalue
materialscanpotentiallymaximizethevaluerecovered.

7.5.

End of Life Management

7.5.1. Server EndofLife

The European Union (EU) has implemented legislation (the WEEE Waste
ElectricalandElectronicEquipmentdirective)tocontrolthedispositionofend
oflife electronics. The WEEE directive requires manufacturer to report the
material content of products and support environmentally sound endoflife
processing.WithintheUnitedStates,thereisalsoamovetowardslegislationto

68

EnvironmentalAlertBulletin:Ewaste,thehiddensideofITequipmentsmanufacturingand
use.UnitedNationsEnvironmentProgramme.Jan,2005.
http://www.grid.unep.ch/products/3_Reports/ew_ewaste.en.pdf

RochesterInstituteofTechnology
October10,2012

38 ServerPrimer

prevent dumping endoflife electronics into municipal waste streams, and

many companies are taking proactive steps to provide for collection and
processing of endoflife products. In the recent past, some endoflife
electronics have been shipped from developed countries to developing
countries that do not have stringent environmental requirements; publicity
around these practices has raised worldwide concern resulting in increased
monitoringbyNGOsandincreasedoversightbywesterngovernments.
The increased legislation, oversight, and public and corporate sensitivities are
resulting in improvements in the environmental impact of endoflife
electronics;however,therearetechnical,logistic,andeconomiclimitationson
theeffectivenessofendoflifeprocessingpractices.
Thereareavarietyofsourcesofbestpracticetypeinformationonelectronics
design to decrease the endoflife environmental impacts through
remanufacturing,recycling,andrecovery.
There is a significant body of literature in the area of product, and more
specificallyelectronicproduct,recyclingandmaterialrecovery;thisresearchcan
be grouped into several areas. One area describes the state of the art in
recyclingprocesses;thisincludesbroadreviewsaswellasdetailedevaluations
of particular processes.69,70,71,72 A second group of literature looks at the
economicand/orenvironmentalaspectsofrecycling,thisisofparticularinterest
asfreemarketrecyclingwillnotsurviveifnoteconomicallyviable.73,74,75,76,77,78A

69

Cui,J.,Forssberg,E.,Mechanicalrecyclingofwasteelectricandelectronicequipment:a
review,JournalofHazardousMaterials,Vol.99,No.3,pp243263,May2003.
http://www.sciencedirect.com/science/article/pii/S030438940300061X

70

Kang,H.Y.,andSchoenung,J.M.,Electronicwasterecycling:AreviewofU.S.infrastructure
andtechnologyoptions,Vol.45,No.4,Dec2005,pp.368400.
http://aix.meng.auth.gr/pruwe/dhmosieuseis/weee_usa.pdf

71

Hageluken,C.,RecyclingofelectronicscrapatUmicoresintegratedmetalssmelterand
refinery,ProceedingsofEMC,Vol.1,p.307,2005.
http://www.preciousmetals.umicore.com/PMR/Media/e
scrap/show_recyclingOfEscrapAtUPMR.pdf

72

Li,J.,et.al.,PrintedCircuitBoardRecycling:AStateoftheArtSurvey,IEEETransactionson
ElectronicsPackagingManufacturing,Vol.27,No.1,pp3342,Jan.2004.
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1331573&userType=&tag=1

73

Boon,J.E.,Isaacs,J.E.,andGupta,S.M.,EconomicsofPCRecycling,ProceedingsoftheSPIE
InternationalConferenceonEnvironmentallyConsciousManufacturing,Boston,MA,Nov.58,pp.
2935,2000.http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=927163

74

Sodhi,M.S.,andReimer,B.,Modelsforrecyclingelectronicsendoflifeproducts,OR
Spectrum,Vol23,No.1,Feb,2001.
http://aix.meng.auth.gr/helcare/ScareEng/Papers/%D7%D1%C7%D3%C9%CC%CF%20
%20Models%20for%20recycling%20electronics.pdf

75

Kang,H.Y.,andSchoenung,J.M.,Estimationoffutureoutflowsandinfrastructureneededto
recyclepersonalcomputersystemsinCalifornia,JournalofHazardousMaterials,Vol.137,Issue
2,pp.11651174,Sept2006.
http://www.sciencedirect.com/science/article/pii/S0304389406003360

RochesterInstituteofTechnology
October10,2012

39 ServerPrimer

third group of literature attempts to evaluate the suitability for recycling of a

particulardesign.79,80ThesereferencesfromVillalbaetal.,provideametricfor
materialrecyclabilitythattakesintoaccountthepostrecycledmaterialvalueas
comparedtotheoriginalvalue;asecondindexthattakesintoaccountthecost
ofdisassemblyprovidesanoverallrecyclabilitymetric.Thisapproachdoesnot
allowvisibilityintothedesignfactorsthataffectdisassemblycost.
In general, most of the components of ewaste have some economic value as
part of the recovery or recycling process; however, the costs associated with
transportation, disassembly, and separation can very quickly exceed the
potential material recovery value.81 In addition to proper material selection,
designfordisassemblyiscriticaltocosteffectiverecyclingofelectronics.
Thereisrobustliteratureintheareaofdesignfordisassemblyanddisassembly
planning for remanufacturing that is also applicable to recycling. Bras and
McIntosh (1999)82 provide an overview of the early research in this field. The
work includes models that can be used to optimize assembly or disassembly
processes for a particular design; these models can also be used for design
optimization. This continues to be an area of significant research interest, and
recent work has begun to apply some of these techniques to recycling
applications.83,84,85,86

76

Gregory,J.R.,andKirchain,R.E.,AFrameworkforEvaluatingtheEconomicPerformanceof
RecyclingSystems:ACaseStudyofNorthAmericanElectronicsRecyclingSystems,Environmental
ScienceandTechnology,42(18),pp.68006808,2008.
http://pubs.acs.org/doi/abs/10.1021/es702666v

77

Choi,B.C.,et.al.,LifeCycleAssessmentofaPersonalComputeranditsEffectiveRecycling
Rate,TheInternationalJournalofLifeCycleAssessment,Vol.11,No.2,March,2006.
http://psp.sisa.my/elibrary/attachments/441_11LifecycleAssessment.pdf

78

Schmidt,M.,Aproductiontheorybasedframeworkforanalysingrecyclingsystemsinthee
wastesector,EnvironmentalImpactAssessmentReview,Vol.25,Issue5,pp.505524,July2005.
http://www.sciencedirect.com/science/article/pii/S0195925505000545

79

Villalba,G.,et.al.,Aproposalforquantifyingtherecyclabilityofmaterials,Resources,
Conservation,andRecycling,Vol.37,no.1,pp.3953,2002.
http://www.sciencedirect.com/science/article/pii/S0921344902000563

80

Villalba,G.,et.al.,Usingtherecyclabilityindexofmaterialsasatoolfordesignfor
disassembly,EcologicalEconomics,Vol.50,Issues34,pp195200,Oct.2004.
http://www.sciencedirect.com/science/article/B6VDY4DBSX38
1/2/9e10b1f37aa9be4a8dede9eb647374f2

81

PersonalcommunicationswithMikeWhyte,PresidentofRegionalComputerRecyclingand
Recovery,Rochester,NY,Aug28,2009.

82

Bras,B.,andMcIntosh,M.W.,Product,process,andorganizationaldesignforremanufacture
anoverviewofresearch,RoboticsandComputerIntegratedManufacturing,Vol.15,Issue3,pp.
167178,June1999.http://www.sciencedirect.com/science/article/pii/S0736584599000216

83

Tang,Y.,et.al.,DisassemblyModeling,Planning,andApplication,JournalofManufacturing
Systems,Vol.21,Issue3,pp.200217,2002.
http://www.sciencedirect.com/science/article/pii/S0278612502801625

RochesterInstituteofTechnology
October10,2012

40 ServerPrimer

Product or component reuse or remanufacturing recover the greatest amount

ofenergyembeddedintheoriginalproduct.However,forelectronicproducts,
the rapid change in performance or features, coupled with a high level of
integration or changes in product architectures, limit 3rd party reuse and
remanufacturing. Material selection, tight coupling of dissimilar materials, the
presence of hazardous materials, and the cost of disassembly create technical
andeconomicchallengesthatlimitmaterialrecovery/recyclingoptions.
7.5.2. End of Life Management
In order to combat the ewaste stream from servers and other electronic
products, manufacturers have created both recycling and remanufacturing
programs. Dell87, HP88, and IBM89 have set up recycling programs for their
equipment.
Littleoperationaldataispublicallyavailable;however,HewlettPackarddetailed
theirewastehandlingprocessina2008testimonybeforeaHouseCommittee90
andthistestimonyisreproducedbelowasanexampleprogram.
The equipment returned to HP is managed through a network of
partners and service providers who perform the recycling of the
equipment. HP formerly partnered with a large electronics recycling
company to operate two recycling centers in the US; our partner now
operates these facilities with the assistance of HP. HP invested in the
development of those recycling centers in order to directly participate
and lead the development of the types of technology and processes
necessary to recycle used electronics to the environmental and data

84

Veerakamolmal,P.,andGupta,S.,Acasebasedreasoningapproachforautomating
disassemblyprocessplanning,JournalofIntelligentManufacturing,Vol.13,No.1,pp.4760,Feb,
2002.DOI:10.1023/A:1013629013031.
http://www.springerlink.com/content/u173h5g4604h1836/

85

Campbell,M.I.,andHasan,A.,DesignEvaluationMethodfortheDisassemblyofElectronic
Equipment,ProceedingsoftheInternationalConferenceonEngineeringDesign,Stockholm,Aug
1921,2003.http://www.me.utexas.edu/~campbell/pubs/conf/ICED2003abstract_dfd.htm

86

Rios,P.J.,andStuart,J.A.,SchedulingSelectiveDisassemblyforPlasticsRecoveryinan
ElectronicsRecyclingCenter,IEEETransactionsonElectronicsPackagingManufacturing,Vol.27,
Issue3,pp187197,July,2004.http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=01393074

87

Design:DesignforRecyclability.Dell,2012.Web.12Jun2012.
http://content.dell.com/us/en/corp/d/corpcomm/designinggreenrecycling.aspx

88

HPRenewProgramNorthAmerica.HP,2012.Web.12Jun2012.
http://www.hp.com/unitedstates/renew/

89

IBMProductTakeBackforRecycling.IBM,2012.Web.12Jun2012.
http://www.ibm.com/ibm/recycle/us/index.shtml

90

TestimonyofHewlettPackardCompanyBeforetheHouseCommitteeonScienceand
TechnologyFortheHearingonElectronicWaste:CantheNationManageModernRefuseinthe
DigitalAge?,April30,2008.
http://www.hp.com/hpinfo/abouthp/government/us/pdf/Sciencecommitteetestimony.pdf

RochesterInstituteofTechnology
October10,2012

41 ServerPrimer

security standards we require. Over time, an infrastructure has started

toemergewhichhascreatedanabilityforHPtoreduceourfocusonthe
actual recycling operation and to renew our focus on the design of
products which are easier to recycle and can include recyclable
commodities in their manufacture as well as the development of
recyclingservicesforourcustomers.
Anyreusableequipmentissegregated.Fromthere,anycustomerdatais
destroyed and the equipment is then reused either in whole or in part.
Equipmentwithoutareusechannelissentforremovalofanyhazardous
components (typically CRT glass, batteries or other elements). After
removalofanyhazardouscomponentstheequipmentiseithermanually
or mechanically separated into a variety of basic commodities: various
types of precious and base metals, plastics and other constituent
materials. These materials are processed in the separation process to
createvaluablecommoditystreamswhicharethensoldforreuseintoa
variety of industrial processes. These include the manufacture of new
partsandproductsforanumberofindustries,including,insomecases,
theelectronicsindustry.
One major concern is that end of life materials are handled and recycled
responsibly. A few standards and initiatives exist to help guide and direct
responsible recycling. These standards relate to material recyclers and as such
are outside the scope of this report, but are briefly mentioned here for
informationalpurposes.
Currently two accredited certification standards are widely recognized: the
Responsible Recycling Practices (R2)91 and the eStewards92 standards. These
standards assess an electronics recyclers environmental, worker health and
safetyandsecuritypractices.Manyorganizationsencouragetheuseofcertified
recyclerstoassurethataproductishandledresponsiblyatitsendoflife.
HP93 and IBM both have active remanufacturing operations to modernize old
equipment.ThefollowingisfromarecentIBMpressrelease94:
ARMONK, N.Y. 29 Feb 2012: IBM (NYSE: IBM) today announced the
opening of the firstever server remanufacturing center in China. The
newcenter,locatedinShenzhen,willhelpreducetheimpactofewaste
on the environment by extending the life of older IT equipment that
otherwise would go into landfills. IBM will also buy back select IBM
PowerSystemsfromclientsastheyupgradetonewIBMequipment.

91

http://www.r2solutions.org/

92

http://estewards.org/

93

HPRenewProgramNorthAmerica.HP,2012.Web.12Jun2012.
http://www.hp.com/unitedstates/renew/

94

IBMNewsRoom.IBMOpenstheFirstServerRemanufacturingCenterinChina.IBM,Feb2012.
Web.4Jun2012.http://www03.ibm.com/press/us/en/pressrelease/36976.wss

RochesterInstituteofTechnology
October10,2012

42 ServerPrimer

The new facility expands IBM's global remanufacturing and

refurbishmentoperationsinAustralia,Singapore,Japan,Brazil,Canada,
France, Germany and the United States. The Shenzhen facility will
initially remanufacture hundreds of midrange IBM Power Systems,
which are reconditioned, tested and certified using rigorous processes
and original manufacturing standards, or rebuilt to meet specific
customer requirements. The facility will rapidly expand to
remanufacture 100,000 PCs and lowend and midrange IBM and non
IBMserversperyearby2014.

The combination of
increased
performance and
cost yields a 36%
increase per year in
a servers
performance per
watt.

Brill claims that such remanufacturing, or tuning up, is very lowrisk and can
promote a 20% improvement in efficiency for relatively little capital
investment.95 Some next generation processor and component improvements
are incompatible with prior equipment limiting the potential for
remanufacturing. Though the carbon footprint improvement due to improved
energy efficiency is well documented (see section 6), there is limited life cycle
dataonthebenefitsofmaterialsavingsandendoflifematerialrecoverdueto
remanufacturing. Further study of this topic could provide useful information
concerningmultipleenvironmentaltradeoffs.

7.6.

Energy Conservation

Energyconsumptionbytheworldsserversanddatacentersissignificant.The
EPAreportedtoCongressthatserversanddatacentersconsumedanestimated
61 billion kilowatthours (kWh) in 2006, or 1.5% of the total U.S. electricity
consumption. This was more than double the energy consumption of servers
and data centers just six years prior.96 The economic downturn in 20082009,
the effort by industry to improve efficiency, and the increased prevalence of
virtualization has slowed the rate of increase of energy consumption by data
centers.However,accordingtoKoomey201197,theU.S.andworlddatacenter
electricity use grew by about 36% and 56%, respectively, from 2005 to 2010.
Therefore,itisestimatedthatdatacentersconsumedabout1.3%oftheworld
electricity use (238 billion kWh) and 2% of the U.S. electricity use (76.3 billion
kWh)in2010.
One caveat to the increased power consumption, however, is that servers are
also increasing performance. A modern server, when compared to an older
model, was observed to have 45% better performance at the cost of only 9%
greater power consumption. The combination of increased performance and

95

Brill,KennethG.2007.DataCenterEnergyEfficiencyandProductivity.SantaFe,NM:The
UptimeInstitute.www.uptimeinstitute.org/symp_pdf/(TUI3004C)DataCenterEnergyEfficiency.pdf.
96

ReporttoCongressonServerandDataCenterEfficiency,PublicLaw109431.USEPA.2007.
http://www.energystar.gov/index.cfm?c=prod_development.server_efficiency_study
97

Jonathan Koomey. 2011. Growth in data center electricity use 2005 to 2010. Oakland, CA:
Analytics Press. July. http://www.analyticspress.com/datacenters.html The midpoint data
betweentheLowandHighcasesshowninTables2and3ispresentedhere.

RochesterInstituteofTechnology
October10,2012

43 ServerPrimer

cost yields an annual 36% increase in a servers performance per watt.98 In

additiontothelargegainsincomputationalperformanceperwatt,othertrends
have emerged in recent years that are helping reduce server energy usage. A
typicalbreakdownofenergyusageisshowninFigure16.

Figure16ServerPowerConsumption
Source:TheProblemofPowerConsumptioninServers.Intel,200999

7.6.1. PSU Efficiency Standards

Asignificant contributortotheserverpowerconsumptionistheserverpower
supply unit, or PSU. A server uses a PSU to convert a data centers AC or DC
electricity input to a lowvoltage output so the servers internal components
mayoperateattheirratedvoltage,usually5VDC.100Bythisdefinition,PSUsare
miniaturetransformers(theytransformthevoltagefromoneleveltoanother)
andalsoregulators(theymaytakeanACinputandregulateittoaDCoutputby
usingswitches).Bothtransformersandregulatorsareinherentlyinefficientand
shed energy in the form of heat. The magnitude of PSU efficiency loss is also
illustratedinFigure16.
InordertobetterunderstandinefficiencyofserverPSUs,ECOSConsultingand
theElectricPowerResearchInstitute(EPRI)testedavarietyofcommonservers
ataninputof230VACandtooktheindividualresultsandextrapolatedthemto
the data centerlevel for comparison purposes. The results of their study

98

Koomey,J.,Belady,C.,Patterson,M.,Santos,A.,&Lange,K.AssessingTrendsOverTimeIn
Performance,Costs,AndEnergyUseForServers.MicrosoftCorp.andIntelCorp.2009.
http://www.intel.com/assets/pdf/general/servertrendsreleasecompletev25.pdf

99

TheProblemofPowerConsumptioninServers.Intel,2009.
http://www.intel.com/intelpress/articles/The_Problem_of_Power_Consumption_in_Servers.pdf

100

Meisner,D.,Gold,B.,Wenisch,T.PowerNap:EliminatingServerIdlePower.ASPLOS.March
2009.WashingtonDC.
http://web.eecs.umich.edu/~meisner/David_Max_Meisner/Home_files/asplos09.pdf

RochesterInstituteofTechnology
October10,2012

44 ServerPrimer

detailed the inherent inefficiencies present in the server market. The two
organizations used these results to establish the 80 PLUS Standard, which
outlines basic efficiency and power factor requirements a PSU must meet to
qualify.Thebasicqualificationis80%efficiencyatallloadlevels;higherratings
(bronze, silver, gold, etc.) are achievable for higher efficiency ratings. A
minimum expected power factor is also incorporated into the standard to
indicate the amount of real power that the PSU supplies. At the time of this
studysreleaseonlythreeofthesampledPSUsmettheBronzerating;todaya
much larger number of servers qualify for it, and some models qualify for the
newlyestablishedPlatinumandTitaniumratings.101
Theratinglevelsforthe80PLUSstandardareoutlinedbelow:102
Efficiency
LoadLevel

PowerFactor

10% 20% 50% 100% 10% 20% 50% 100%

80PLUS

80% 80%

80%

0.9

80PLUSBronze

81% 85%

81%

0.9

0.9

80PLUSSilver

85% 89%

85%

0.9

0.9

80PLUSGold

88% 92%

88%

0.9

0.9

80PLUSPlatinum

90% 94%

91%

0.95

0.95

90% 94% 96%

91%

0.95 0.95

0.95

80PLUSTitanium

7.6.2. Processor Energy Use

Afterelectricityenterstheserver,overhalfofitisusedbytheprocessor(s)and
attached onboard memory (SDRAM). The processor will step through various
stagesofutilization,ametricbasedonthepercentageofSDRAMbeingusedat
any point in time. When a processor has 0% utilization, it is considered to be
idle; at 100% utilization, it is being fully used. A processors energyuse profile
scales from its idle power draw to its maximum power draw. Most processors
average1022%utilizationduringregularuse.103
The energy use of the latest Intel processors was provided by Intel during the
TechnicalCommitteemeeting.(Figure17)

101

EfficientPowerSuppliesforDataCenterandEnterpriseServers.ECOSandEPRI.Feb2008.
http://www.etccca.com/images/stories/pdf/ETCC_Report_467.pdf

102

80PLUSCertifiedPowerSuppliersandManufacturers.PlugLoadSolutions,May2012.Web.
29May2012.http://www.plugloadsolutions.com/80PlusPowerSupplies.aspx

103

Koomey,J.,Belady,C.,Wong,H.,Snevely,R.,Nordman,B.,Hunter,E.,Lange,K.,Tipley,R.,
Darnell,G.,Accapadi,M.,Rumsey,P.,Kelley,B.,Tschudi,B.,Moss,D.,Greco,R.,BrillK.Server
EnergyMeasurementProtocol.2006.
http://www.energystar.gov/ia/products/downloads/Finalserverenergyprotocolv1.pdf

RochesterInstituteofTechnology
October10,2012

45 ServerPrimer

Figure17IntelProcessorPerformanceprovidedbyHenryWong,ServerTechnicalCommittee
Meeting,Houston,Texas,July31,2012.

TherehasbeenincreasinginterestinCPUvoltageandfrequencyscaling(DVFS),
atechnologythatallowstheclockspeedofaservertodecreaseinproportionto
itsloadlevel.AstudybyFan,Weber,andBarrososuggeststhatsuchtechnology
could offer substantial energy savings at both low and high loads. Their study
evaluatedaDVFSprotocolthatscaledtheCPUspoweroutputfromidleto5%,
20%, and 50% load levels, representing a passive, active, and aggressive DVS
setup,respectively.Usingthepassive5%cutoffforscaling,a10%reductionin
peak power can be realized, while an aggressive 50% cutoff could realize a
reductionof18%.Thesevaluescorrelatetoenergysavingsofgreaterthan12%
and22%,respectively.104
ThisstudyalsoinvestigatedtheeffectsofDVFSonaserverwhenitisidleand
assumedthatidlepowerdrawwouldbereducedtoabout10%ofpeakpower.
This would create a total reduction of 30% in the realized peak power and a
reductionof50%intherequiredenergy.Atthetimeofwriting,severalserver

104

Fan,X.,Weber,W.,Barroso,L.PowerProvisioningforaWarehousesizedComputer.ISCA.
June2007.SanDiego,CA.doi:10.1145/1273440.1250665.
http://reference.kfupm.edu.sa/content/p/o/power_provisioning_for_a_warehouse_sized_83189.
pdf

RochesterInstituteofTechnology
October10,2012

46 ServerPrimer

manufacturers use processors with this technology, in contrast, in 2007, only

about10%ofservershadtheabilitytouseDVFS.105

7.7.

Packaging

Publically available information concerning packaging of servers is very sparse

and varies from product to product and by the number and configuration of
servers ordered by the client. Many servers are also shipped to value added
resellers (VARs) which, after providing some service, may be repackaged and
shippedtotheclient.
This topic was discussed in the Server Technical Committee, Houston, Texas,
July31,2012meetingandgeneralinformationwasprovidedbymembersofthe
committee. Members generally agreed that single server units are shipped in
corrugatedboxeswith padding,whichcould befoamorcorner bracing.These
boxes are then generally stacked on reusable pallets to be shipped to the
customer.Analternateconfigurationwouldbetopreinstalltheserversintothe
racks,andthenbuildcustomcratestoprotecttherackandserverassembly.
Typically packaging is not returned to the manufacturer. One manufacturer
notedthatmanyoftheserversarebuiltinChinaanditwouldbeuneconomical
to return the packaging back to the manufacturing site. Due to the travel
distance, the question was asked whether it would be better to reuse the
packagingortorecyclethepackaging.Nocommitteememberknewtheanswer
andfurtherstudywouldberequired.

105

ReporttoCongressonServerandDataCenterEfficiency,PublicLaw109431.USEPA.2007.
http://www.energystar.gov/ia/partners/prod_development/downloads/EPA_Datacenter_Report_
Congress_Final1.pdf

RochesterInstituteofTechnology
October10,2012

47 ServerPrimer

8. Server Environmental Standards and Labels

Environmental labels are often used by manufacturers to communicate to
customers that their products meet certain environmental standards. These
standardscanbedevelopedbyprivateentities,bypublicagencies,orjointlyby
stakeholdersandexpertsfromthepublicandprivatesectors.Theycanvaryin
numberofrequiredcriteria,datadetailandreportingrequirements.
Very few environmental standards address servers directly, and therefore the
search for environmental standards was expanded to include other similar IT
equipment.Thefollowingtablecontainsenvironmentalstandardsthatapplyto
computers,servers,anddatacenters.Thisisasummarytablefromthisreports
companion document, Master list of server standards June 2012.xlsx. The
Master List was built upon the foundational document Server ecolabel
comparison8152011.xlsprovidedbyHollyElwoodoftheU.S.EPA.
The Master list document also contains details on the various criteria per
environmentalstandard.

EUEcolabel

COMMISSIONDECISION,
June2011,establishingthe
ecologicalcriteriaforthe
awardoftheEUEcolabelfor
personalcomputers
N
(2011/337/EU),Application
formandguidance
documentfornotebook
computersVersion1.0,2012

BlueAngel

RALUZ161Energy
ConsciousDataCenters,July Y L N http://www.blauerengel.de/
2011

BlueAngel

RALUZ78aPersonal
Computers(Desktop
Computers,Integrated
DesktopComputers,
Workstations,thinClients,
January2012

http://ec.europa.eu/environmen
t/ecolabel/

Y http://www.blauerengel.de/

RochesterInstituteofTechnology
October10,2012

LCA

Noise

8)Packaging

7)Corporate

6)EOLManagement

5)EnergyConservation

4)Longevity

3)DesignforEOL

Y Y http://www.geca.org.au/

2)MaterialSelection

Website

1)SensitiveMaterials

Servers

GECA242008The
Good
AustralianEcolabel
Environmental Program,Good
Choice
EnvironmentalChoice
Australia
AustraliaStandard
Computers

Standard/
Label

Computers

Standard/Document

DataCenter

6)EOLManagement

7)Corporate

5)EnergyConservation

2)MaterialSelection

http://www.greencouncil.org/en
g/index.asp

Japaneco
mark

EcoMarkProductCategory
No.119,Personal
ComputersVersion2.7,
October2011

Y http://www.ecomark.jp/english/

TheNewZealand
Environmental
EcolabellingTrust
ChoiceNew
N
LicenceCriteriaforPersonal
Zealand
ComputersEC2705

http://www.enviro
choice.org.nz/

http://www.svanen.se/en/Nordi
cEcolabel/

NordicEcolabellingof
Computers:Version6.18
June200930June2012

GREENCHOICEPHILIPPINES
GreenChoice
NELPGCP20080022
Philippines
DESKTOPCOMPUTER

Y http://www.pcepsdi.org.ph/

TCO
TCOCertifiedDesktops3.0,
Development March2010

GES/CO/2011
Global
InternationalSustainability
Environmental
andEnvironmentalProduct
Standard
Standard,Computers

http://www.tcodevelopment.co
m/

Y Y

http://www.globalenvstandard.o
rg

IEEEStd1680.12009
IEEEStandardfor
EnvironmentalAssessment N
ofPersonalComputer
Products,9December2009

http://www.epeat.net/resources
/criteriaverification/

TheEco
Declaration
(TED)

StandardECMA370:4th
Edition/June2009TheEco
Declaration

EnergyStar

ENERGYSTARProgram
Requirementsfor
Computers
N
Version5.0(effectivedate
July1,2009)

ENERGYSTARProgram
RequirementsforComputer
N
ServersDraft2Version2.0
(20100412)

http://www.energystar.gov/ia/p
artners/prod_development/revis
Y N ions/downloads/computer_serv
ers/Servers_Draft_2_v2_Specific
ation.pdf?04f6df81

EnergyStar

Noise

LCA

8)Packaging

HongKong
GreenLabel

GL006001HongKong
GreenLabelScheme
ProductEnvironmental
CriteriaforPersonal
Computers(excluding
monitor)

4)Longevity

Website

3)DesignforEOL

Servers

Computers

DataCenter

Standard/Document

EPEAT

Standard/
Label

NordicSwan

1)SensitiveMaterials

48 ServerPrimer

www.ecma
international.org/publications/st
andards/Ecma370.htm

http://www.energystar.gov/ia/p
artners/prod_development/revis
Y
ions/downloads/computer/Versi
on5.0_Computer_Spec.pdf

RochesterInstituteofTechnology
October10,2012

http://www.greenpeace.org/inte
rnational/Global/international/p
ublications/climate/2011/Cool%
N
20IT/greenerguidenov
2011/Guide%20Ranking%20Crite
ria.pdf?id=

Noise

LCA

8)Packaging

5)EnergyConservation

4)Longevity

7)Corporate

GuidetoGreener
Electronics
N N
RankingCriteriaExplained
August2011,v.17onwards

http://www.eicc.info/documents
/EICCCodeofConductEnglish.pdf

3)DesignforEOL

Y Y

6)EOLManagement

Greenpeace
Guideto
Greener
Electronics

2)MaterialSelection

EICCCodeof EICCCodeofConduct,
Conduct
Version4.0(2012)

http://www.ul.com/global/eng/
pages/corporate/aboutul/public
Y N
ations/newsletters/hightech/vol
2issue3/4par/

Website

1)SensitiveMaterials

UL2640

Servers

PAR4

Standard/Document

Computers

Standard/
Label

DataCenter

49 ServerPrimer

RochesterInstituteofTechnology
October10,2012

50 ServerPrimer

8.1.
AC

Key Acronyms
Alternatingcurrent

ASHRAE American Society of Heating, Refrigerating and AirConditioning

Engineers
BFRs

Brominatedflameretardants

CRAC

Computerroomairconditioner

CPU

Centralprocessingunit

DC

Directcurrent

DIMM

Dualinlinememorymodule

DVFS

Dynamicvoltageandfrequencyscaling

ECC

Errorcorrectingcode

Gb

gigabyte

GHG

Greenhousegas

GRI

GlobalReportingInitiative

HDD

Harddiskdrive

IEEE

InstituteofElectricalandElectronicsEngineers,Inc.

IDC

InternationalDataCorporation

ISO

InternationalOrganizationforStandardization

IT

Informationtechnology

LCA

Lifecycleassessment

LED

Lightemittingdiode

OS

Operatingsystem

PCF

productcarbonfootprint

PCI

Peripheralcomponentinterconnect

PSU

Powersupplyunit

REACH European Union Regulation (EC) No 1907/2006: Registration,

Evaluation,AuthorizationandRestrictionofChemicals
RoHS

European Union, European Council former Directive 2002/95/EC as

amended by 2005/618/EC and 2011/65/EU of the European
ParliamentandoftheCouncilontherestrictionoftheuseofcertain
hazardoussubstancesinelectricalandelectronicequipment

ROI

Returnoninvestment

SDRAM Synchronousdynamicrandomaccessmemory

RochesterInstituteofTechnology
October10,2012

51 ServerPrimer

SSD

Solidstatedrive

SVHC

Substancesofveryhighconcern

TRI

U.S.EPAToxicsReleaseInventory

rackunitheight(1.75inches)

USB

Universalserialbus

U.S.EPA UnitedStatesEnvironmentalProtectionAgency
WEEE

Wasteelectricalandelectronicequipment

RochesterInstituteofTechnology
October10,2012