Google uses large data center facilities to provide their services, which combine large drives, computer nodes organized in aisles of racks, internal and external networking, environmental controls (mainly cooling and humidification control), and operations software (especially as concerns load balancing and fault tolerance).
There is no official data on how many servers are in Google data centers, but Gartner estimated in a July 2016 report that Google at the time had 2.5 million servers. This number is changing as the company expands capacity and refreshes its hardware.
Locations The locations of Google's various data centers by continent are as follows: +ContinentLocationGeoProducts LocationCloud LocationTimelineDescriptionNorth AmericaArcola (VA), USALoudoun CountyN. Virginia (us-east4)2017 - announcedNorth AmericaAtlanta (GA), USADouglas County -2003 - launched350 employeesSouth AmericaCerrillos, Santiago, Chile -Santiago (southamerica-west1)2020 - announced 2021 - launchedAsiaChanghua County, TaiwanChanghua CountyTaiwan
(asia-east1)2011 - announced 2013 - launched60 employeesNorth AmericaClarksville (TN), USAMontgomery County -2015 - announcedNorth AmericaColumbus (OH), USA -Columbus (us-east5)2022 - launchedNorth AmericaCouncil Bluffs (IA), USACouncil Bluffs2007 - announced
2009 - completed first phase completed
2012 and 2015 - expanded130 employeesNorth AmericaCouncil Bluffs (IA), USAIowa (us-central1)AsiaDelhi, India -Delhi (asia-south2)2020 - announced 2021 - launchedMiddle EastDoha, Qatar -Doha (me-central1)2023 - launchedEuropeDublin, IrelandDublin -2011 - announced 2012 - launched150 employeesEuropeEemshaven, NetherlandsEemshavenNetherlands (europe-west4)2014 - announced 2016 - launched
2018, 2019 - expansion200 employeesEuropeFrankfurt, Germany -Frankfurt (europe-west3)2022 - expandedEuropeFredericia, DenmarkFredericia -2018 - announced 2020 - launched€600M building costsEuropeGhlin, Hainaut, BelgiumSaint-GhislainBelgium (europe-west1)2007 - announced 2010 - launched12 employeesEuropeHamina, FinlandHaminaFinland
(europe-north1)2009 - announced 2011 - first phase completed
2022 - expansion6 buildings, 400 employees North AmericaHenderson (NV), USAHendersonLas Vegas (us-west4)2019 - announced
2020 - launched64-acres; $1.2B building costsAsiaHong Kong, Hong Kong -Hong Kong (asia-east2)2017 - announced 2018 - launchedAsiaInzai, JapanInzai -2023 - launchedAsiaJakarta, Indonesia -Jakarta (asia-southeast2)2020 - launchedAsiaKoto-Ku, Tokyo, Japan -Tokyo
(asia-northeast1)2016 - launchedNorth AmericaLeesburg (VA), USALoudoun CountyN. Virginia (us-east4)2017 - announcedNorth AmericaLenoir (NC), USALenoir -2007 - announced
2009 - launchedover 110 employeesAsiaLok Yang Way, Pioneer, SingaporeSingaporeSingapore (asia-southeast1)2022 - launchedEuropeLondon, UK -London
(europe-west2)2017 - launchedNorth AmericaLos Angeles (CA), USA -Los Angeles (us-west2)EuropeMadrid, Spain -Madrid (europe-southwest1)2022 - launchedPacificMelbourne, Australia -Melbourne
(australia-southeast2)2021 - launchedEuropeMiddenmeer, Noord-Holland, The NetherlandsMiddenmeerNetherlands (europe-west4)2019 - announcedNorth AmericaMidlothian (TX), USAMidlothianDallas (us-south1)2019 - announced 2022 - launched375-acres; $600M building costsEuropeMilan, Italy -Milan (europe-west8)2022 - launchedNorth AmericaMoncks Corner (SC), USABerkeley CountySouth Carolina (us-east1)2007 - launched
2013 - expanded150 employeesNorth AmericaMontreal, Quebec, Canada -Montréal (northamerica-northeast1)2018 - launched62.4-hectares; $600M building costsAsiaMumbai, India -Mumbai (asia-south1)2017 - launchedNorth AmericaNew Albany (OH), USANew Albany -2019 - announced400-acres; $600M building costsAsiaOsaka, Japan -Osaka
(asia-northeast2)2019 - launchedSouth AmericaOsasco, São Paulo, Brazil -São Paulo (southamerica-east1)2017 - launchedNorth AmericaPapillion (NE), USAPapillion -2019 - announced275-acres; $600M building costsEuropeParis, France -Paris (europe-west9)2022 - launchedNorth AmericaPryor Creek (OK), USAMayes County -2007 - announced
2012 - expanded over 400 employees, land at MidAmerica Industrial Park South AmericaQuilicura, Santiago, ChileQuilicura -2012 - announced 2015 - launchedup to 20 employees expected. A million dollar investment plan to increase capacity at Quilicura was announced in 2018.North AmericaReno (NV), USAStorey County -2017 - 1,210 acres of land bought in the Tahoe Reno Industrial Center
2018 - announced
2018 November - project approved by the state of NevadaNorth AmericaSalt Lake City (UT), USA -Salt Lake City (us-west3)2020 - launchedAsiaSeoul, South Korea -Seoul
(asia-northeast3)2020 - launchedPacificSydney, Australia -Sydney
(australia-southeast1)2017 - launchedMiddle EastTel Aviv, Israel -Tel Aviv (me-west1)2022 - launchedNorth AmericaThe Dalles (OR), USAThe DallesOregon (us-west1)2006 - launched80 full-time employeesNorth AmericaToronto, Canada -Toronto (northamerica-northeast2)2021 - launchedEuropeTurin, Italy -Turin (europe-west12)2023 - launchedSouth AmericaVinhedo, São Paulo, BrazilSão Paulo (southamerica-east1)EuropeWarsaw, Poland -Warsaw (europe-central2)2019 - announced 2021 - launchedAsiaWenya, Jurong West, SingaporeSingaporeSingapore (asia-southeast1)2011 - announced 2013 - launched
2015 - expandedNorth AmericaWidows Creek (Bridgeport) (AL), USA Jackson County -2018 - broke groundEuropeZürich, Switzerland -Zurich (europe-west6)2018 - announced 2019 - launchedEuropeKronstorf,AustriaStart of Building 2026EuropeBerlin, GermanyBerlin (europe-west10)2021 - announced 2023 August - launched Middle EastDammam, Saudi Arabia2021 - announcedEuropeAthens, Greece2022 - announcedNorth AmericaKansas City, Missouri2019 - announcedMiddle EastKuwait2023 - announcedAsiaMalaysia2022 - announcedPacificAuckland, New Zealand2022 - announcedEuropeOslo, Norway2022 - announcedNorth AmericaQuerétaro, Mexico2022 - announcedAfricaJohannesburg, South AfricaJohannesburg (africa-south1)2022 - announced 2024 - launchedEuropeSweden2022 - announcedAsiaTainan City, Taiwan -Taiwan
(asia-east1)2019 September - announcedAsiaThailand2022 - announcedAsiaYunlin County, Taiwan -Taiwan (asia-east1)2020 September - announcedNorth AmericaMesa (AZ), USAPhoenix (us-west8)2023 - construction startedEuropeWaltham Cross, Hertfordshire, UK2024 January - announcedSouth AmericaCanelones, Uruguay2024 - construction started 2026 - inauguration expectedAsiaVisakhapatnam, Andhra Pradesh, IndiaAnnounced July 2025.Google plans to invest US$15 billion to build a 1 GW data center campus in Visakhapatnam, including US$2 billion for renewable energy infrastructure. It is expected to be the company’s largest data center project in Asia.North AmericaFort Wayne, Indiana, USAIndiana—October 2023: Introduced as “Project Zodiac”January 2024: Google Announced Connection to ProjectApril 26, 2024: GroundbreakingDecember 2025: Operational (First-phase)August 2026: Construction Ongoing728 acres
Hardware
Original hardware
The original hardware (circa 1998) that was used by Google when it was located at Stanford University included:. Stanford University (provided by Internet Archive). Retrieved on July 10, 2006.
Sun Microsystems Ultra II with dual 200 MHz processors, and 256 MB of RAM. This was the main machine for the original Backrub system. 2 × 300 MHz dual Pentium II servers donated by Intel, they included 512 MB of RAM and 10 × 9 GB hard drives between the two. It was on these that the main search ran. F50 IBM RS/6000 donated by IBM, included 4 processors, 512 MB of memory and 8 × 9 GB hard disk drives. Two additional boxes included 3 × 9 GB hard drives and 6 x 4 GB hard disk drives respectively (the original storage for Backrub). These were attached to the Sun Ultra II. SSD disk expansion box with another 8 × 9 GB hard disk drives donated by IBM. Homemade disk box which contained 10 × 9 GB SCSI hard disk drives.
Google Cluster The state of Google infrastructure in 2003 was described in a report by Luiz André Barroso, Jeff Dean, and Urs Hölzle as a "reliable computing infrastructure from clusters of unreliable commodity PCs".
At the time, on average, a single search query read ~100 MB of data, and consumed CPU cycles. During peak time, Google served ~1000 queries per second. To handle this peak load, they built a compute cluster with ~15,000 commodity-class PCs instead of expensive supercomputer hardware to save money. To make up for the lower hardware reliability, they wrote fault tolerant software.
The structure of the cluster consists of five parts. Central Google Web servers (GWS) face the public Internet. Upon receiving a user request, the Google Web server communicates with a spell checker, an advertisement server, many index servers, many document servers. Each of the four parts responds to a part of the request, and the GWS assembles their responses and serves the final response to the user.
The raw documents were ~100 TB, and the index files were ~10 TB. The index files are sharded, and each shard is served by a "pool" of index servers. Similarly, the raw documents are also sharded. Each query to the index file results in a list of document IDs, which are then sent to the document servers to retrieve the title and the keyword-in-context snippets.
There were several CPU generations in use, ranging from single-processor 533 MHz Intel-Celeron-based servers to dual 1.4 GHz Intel Pentium III. Each server contained one or more hard drives, 80 GB each. Index servers have less disk space than document servers. Each rack had two Ethernet switches, one per side. The servers on each side interconnected via a 100-Mbps. Each switch had a ~250 MB/sec uplink to a central switch that connected to all racks.
The design objectives include:
Use low-reliability consumer hardware and make up for it with fault-tolerant software. Maximize parallelism, such as by splitting a single document match lookup in a large index into a MapReduce over many small indices. Partition index data and computation to minimize communication and evenly balance the load across servers, because the cluster is a large shared-memory machine. Minimize system management overheads by developing all software in-house. Pick hardware that maximizes performance/price, not absolute performance. Pick hardware that has high thoroughput over high latency. This is because queries are served with massive parallelism, with very few dependent steps and minimal communication between servers, so high latency does not matter.
Due to the massive parallelism, scaling up hardware scales up the thoroughput linearly, i.e. doubling the compute cluster doubles the number of queries servable per second.
The cluster is made of server racks at 2 configurations: 40 x 1u per side with 2 sides, or 20 x 2u per side with 2 sides. The power consumption is 10 kW per rack, at a density of 400 W/ft^2, consuming 10 MWh per month, costing $1,500 per month.
Production hardware As of 2014, Google has used a heavily customized version of Debian Linux. They migrated from a Red Hat-based system incrementally in 2013.