Light Reading
Facebook's load balancing is designed to keep its servers running at a moderate speed -- not too slow.

Facebook Slashes Data Center Power Consumption

Mitch Wagner
8/8/2014
50%
50%

Facebook is developing a new traffic management technology called Autoscale to optimize energy consumption by 10-15% at its data centers.

Facebook currently uses a traditional round-robin approach to load balancing, but found that was less than optimal, because servers running low-level loads use power more inefficiently than idle servers or servers running at moderate or greater loads, writes Qiang Wu, Facebook infrastructure software engineer, on the Facebook Code Engineering Blog.

Autoscale is designed to optimize workloads so that servers are either idling, or running at medium capacity. It tries to avoid assigning workloads in a way that results in servers running at low capacity, Wu writes.

An idle server consumes about 60 watts. It takes a big power hit, to 130 watts, when it jumps to low-level CPU utilization, for a small number of requests per second. But it only takes a small power hit, to 150 watts, when it goes from low-level to medium-level CPU utilization, Wu writes.

Therefore, from a power-efficiency perspective, we should try to avoid running a server at low RPS and instead try to run at medium RPS.

To tackle this problem and utilize power more efficiently, we changed the way that load is distributed to the different web servers in a cluster. The basic idea of Autoscale is that instead of a purely round-robin approach, the load balancer will concentrate workload to a server until it has at least a medium-level workload. If the overall workload is low (like at around midnight), the load balancer will use only a subset of servers. Other servers can be left running idle or be used for batch-processing workloads.

Though the idea sounds simple, it is a challenging task to implement effectively and robustly for a large-scale system.

Autoscale dynamically adjusts the size of the server pool in use, so that each active server will get at least a medium-level CPU load. Servers not in the active pool don't receive traffic.


Power up your data center knowledge on Light Reading's data center infrastructure channel


Optimizing both performance and power consumption was key in developing decision logic for traffic management: "On one hand, we want to maximize the energy-saving opportunity. On the other, we don't want to over-concentrate the traffic in a way that could affect site performance."

Results have been promising:

Autoscale led to a 27% power savings around midnight (and, as expected, the power saving was 0% around peak hours). The average power saving over a 24-hour cycle is about 10-15% for different web clusters.

Normalized power consumption for a production web cluster with and without Autoscale. Source: Facebook.
Normalized power consumption for a production web cluster with and without Autoscale. Source: Facebook.

Facebook is driving open source data center hardware design with its own Open Compute project. The project is self-serving -- Facebook runs among the most massive data centers in the world, and data center cost savings improves Facebook's bottom line. Facebook says it has saved $1.2 billion over three years using the Open Compute hardware designs it champions. (See Open Compute Project Takes on Networking.)

Earlier this week, Facebook bought PrivateCore, a security software company, to beef up its server security. (See Facebook Buys PrivateCore for Server Security.)

— Mitch Wagner, Circle me on Google+Follow me on TwitterVisit my LinkedIn profileFollow me on Facebook, West Coast Bureau Chief, Light Reading. Got a tip about SDN or NFV? Send it to wagner@lightreading.com.

(9)  | 
Comment  | 
Print  | 
Newest First  |  Oldest First  |  Threaded View
SachinEE
50%
50%
SachinEE,
User Rank: Light Sabre
8/12/2014 | 2:23:27 PM
Re: good news for Facebook
With the millions of users that Facebook has bagged over he years, it is good to know that they have found a way to improve their data centers. Facebook is used world wide and they make a lot of profit but this new occurrence will no doubt help them to cut costs and probably boost their earnings by a great percentage. It is a wonder that they did not do this sooner.
brooks7
50%
50%
brooks7,
User Rank: Light Sabre
8/11/2014 | 11:44:17 AM
Re: Not been done before ?
Dennis,

Note, that the applications that people like Amazon and Google do are diverse.  It may not be as easy to eliminate compute power in that environment.  Scaling computing and storage in those environments might have very different curves.

seven

 
mendyk
50%
50%
mendyk,
User Rank: Light Sabre
8/11/2014 | 11:39:05 AM
Re: Not been done before ?
Maybe they have but choose not to crow about it. Or maybe they haven't. The point of the story was to highlight what FB is doing to improve its efficiency and margins.
Whatdoyouwant
50%
50%
Whatdoyouwant,
User Rank: Light Beer
8/11/2014 | 11:31:47 AM
Re: Not been done before ?
I meant by the industry in general.  Google, Yahoo, Amazon, etc..   none of these guys have figured this out ?
mendyk
50%
50%
mendyk,
User Rank: Light Sabre
8/11/2014 | 10:36:51 AM
Re: Not been done before ?
When your growth is in triple digits, you don't worry so much about sweating down costs. That comes with maturity. Now that Facebook is a public company, it has to focus more on stuff like margins.
Whatdoyouwant
50%
50%
Whatdoyouwant,
User Rank: Light Beer
8/11/2014 | 9:46:42 AM
Not been done before ?
Is it me or does this seem like something that would have been done a long time ago ?
danielcawrey
50%
50%
danielcawrey,
User Rank: Light Sabre
8/9/2014 | 6:31:59 PM
Re: Something good from Facebook
I did not realize that the optimum power consumption for a server instance was at medium level capacity. This is really useful - something that hardware designers and cloud service providers should usel to optimize machines and cut costs.

More and more services are being powered through the cloud - which means there is huge opportunity to slash operating expenses. 
thebulk
50%
50%
thebulk,
User Rank: Light Sabre
8/9/2014 | 11:36:47 AM
Re: Something good from Facebook
Just think of the cost they are cutting with this! It really is impressive. 
mendyk
50%
50%
mendyk,
User Rank: Light Sabre
8/9/2014 | 9:01:31 AM
Something good from Facebook
Congratulations to Facebook for figuring out how to make its data centers more efficient. Do you think there's a similar potential for energy cost savings for network operators that deploy virtualization?
Educational Resources
sponsor supplied content
Educational Resources Archive
Flash Poll
From The Founder
It's clear to me that the communications industry is divided into two types of people, and only one is living in the real world.
LRTV Custom TV
Using Service Quality to Drive WiFi Monetization

10|22|14   |   6:51   |   (0) comments


Live from the SCTE conference: Heavy Reading's Alan Breznick explores the forces shaping the WiFi opportunity in an interview with CableLabs' Justin Colwell and Amdocs' Ken Roulier.
LRTV Custom TV
Distributed Access Architectures – 2

10|21|14   |   8:51:00 AM   |   (0) comments


ARRIS CTO Network Solutions Tom Cloonan discusses why many if not most MSOs will continue with integrated CCAP, while addressing why some are also looking at two futuristic, distributed access architectures: Remote PHY and Remote CCAP.
LRTV Custom TV
Distributed Access Architectures – 1

10|21|14   |   9:01   |   (0) comments


SCTE Sr. Director of Engineering Dean Stoneback discusses the pros and cons of distributed access architecture (DAA) and its various forms, which range from basic Remote PHY to full CMTS functionality in the node.
LRTV Custom TV
The WiFi Road to Riches – 2

10|21|14   |   3:58   |   (0) comments


ARRIS Senior Solution Architect Eli Baruch talks about how MSOs can enable public and community WiFi through 1) outdoor access points, 2) businesses seeking to offer WiFi to customers, and 3) residential WiFi gateway extensions.
LRTV Custom TV
The WiFi Road to Riches – 1

10|21|14   |   10:15   |   (0) comments


SCTE Director of Advanced Technologies Steve Harris discusses WiFi deployments, drivers, challenges and advances, including 802.11ac, carrier-grade WiFi, community WiFi, Hotspot 2.0, Passpoint, WiFi-First and voice-over-WiFi.
LRTV Custom TV
Advantech Accelerates 100G Traffic Handling

10|17|14   |   7:56   |   (0) comments


Paul Stevens from Advantech explains why handling 100GbE needs a whole new platform design approach and how Advantech is addressing the needs of equipment providers and carriers to give them the flexibility and performance they will need for SDN and NFV deployment.
LRTV Huawei Video Resource Center
Holland's Imtech Traffic & Infra Discusses Huawei's ICT Solution and Services

10|16|14   |   4:49   |   (0) comments


Dimitry Theebe is from the business unit at Imtech Traffic & Infra which delivers communications solutions for transportations. His partnershp with Huawei began about a years ago. In this video, Theebe speaks more about this partnership and what he hopes to accomplish with Huawei.
LRTV Huawei Video Resource Center
Huawei's Comprehensive Storage Solutions Vital for SVR

10|16|14   |   6:16   |   (0) comments


SVR Information Technology provides cloud services for academic and special sectors. With Huawei's support, SVR and Yildiz Technical University has established Turkey's largest and most advanced High Performance Computing system. CSO Ismail Cem Aslan talks about what he hopes Huawei's OceanStor storage system will bring for him.
LRTV Huawei Video Resource Center
Mexico's Servitron's Impression of Huawei at CCW 2014

10|16|14   |   6:35   |   (0) comments


Servitron is a network operator in Mexico that has been in the trunking industry for the past 20 years. Its COO, Ing. Ragnar Trillo O., explains at Critical Communications World 2014 that his company has been interested in the long-term evolution of LTE technology and its adoption for TETRA.
LRTV Huawei Video Resource Center
Building a Better Dubai

10|16|14   |   2:06   |   (0) comments


Abdulla Ahmed Al Falasi is the director of commercial affairs, a telecommunications coordinator for the government of Dubai. Their areas of service span across multiple industries, including police, safety, shopping malls and more. In this video, Abdulla talks about his department's work with Huawei.
LRTV Huawei Video Resource Center
Huawei Lights Up Malaysia Partner Maju Nusa

10|16|14   |   1:59   |   (0) comments


Malaysia's Maju Nusa is an enterprise partner to Huawei in networking, route switches and telco equipment. At this year's Critical Communications World in Singapore, CTO Pushpender Singh talks about what Huawei's eLTE solutions mean to his company and for Malaysia.
LRTV Custom TV
Evolving From HFC to FTTH Networks

10|15|14   |   2:19   |   (0) comments


Cisco's Todd McCrum delves into the future of cable's HFC plant, examining how DOCSIS 3.1 and advanced video compression will extend its life and how the IP video transition will usher in GPON and EPON over FTTH.
Upcoming Live Events
October 29, 2014, New York City
November 6, 2014, Santa Clara
November 11, 2014, Atlanta, GA
December 2, 2014, New York City
December 3, 2014, New York City
December 9-10, 2014, Reykjavik, Iceland
February 10, 2015, Atlanta, GA
June 9-10, 2015, Chicago, IL
Infographics
WhoIsHostingThis.com presents six of the world's most extreme WiFi hotspots, enabling the most epic selfies you can imagine.
Hot Topics
Analysts Warn of Major NFV Gaps
Carol Wilson, Editor-at-large, 10/22/2014
Google: Carriers & Cloud Providers Need to Cooperate
Mitch Wagner, West Coast Bureau Chief, Light Reading, 10/16/2014
iPad Air 2 Lets Users Switch Carriers Any Time
Mitch Wagner, West Coast Bureau Chief, Light Reading, 10/17/2014
Is Health the Killer App for the IoT?
Jason Meyers, Senior Editor, Gigabit Cities/IoT, 10/22/2014
NYC Subway Wireless No Cure for Ebola Fears
Dan Jones, Mobile Editor, 10/16/2014
Like Us on Facebook
Twitter Feed
Upcoming Webinars
Webinar Archive