Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

No-wait data centers

17.07.2014

New system could reduce data-transmission delays across server farms by 99.6 percent

Big websites usually maintain their own "data centers," banks of tens or even hundreds of thousands of servers, all passing data back and forth to field users' requests. Like any big, decentralized network, data centers are prone to congestion:

Packets of data arriving at the same router at the same time are put in a queue, and if the queues get too long, packets can be delayed.

At the annual conference of the ACM Special Interest Group on Data Communication, in August, MIT researchers will present a new network-management system that, in experiments, reduced the average queue length of routers in a Facebook data center by 99.6 percent — virtually doing away with queues.

When network traffic was heavy, the average latency — the delay between the request for an item of information and its arrival — shrank nearly as much, from 3.56 microseconds to 0.23 microseconds.

Like the Internet, most data centers use decentralized communication protocols: Each node in the network decides, based on its own limited observations, how rapidly to send data and which adjacent node to send it to. Decentralized protocols have the advantage of an ability to handle communication over large networks with little administrative oversight.

The MIT system, dubbed Fastpass, instead relies on a central server called an "arbiter" to decide which nodes in the network may send data to which others during which periods of time. "It's not obvious that this is a good idea," says Hari Balakrishnan, the Fujitsu Professor in Electrical Engineering and Computer Science and one of the paper's coauthors.

With Fastpass, a node that wishes to transmit data first issues a request to the arbiter and receives a routing assignment in return. "If you have to pay these maybe 40 microseconds to go to the arbiter, can you really gain much from the whole scheme?" says Jonathan Perry, a graduate student in electrical engineering and computer science (EECS) and another of the paper's authors. "Surprisingly, you can."

Division of labor

Balakrishnan and Perry are joined on the paper by Amy Ousterhout, another graduate student in EECS; Devavrat Shah, the Jamieson Associate Professor of Electrical Engineering and Computer Science; and Hans Fugal of Facebook.

The researchers' experiments indicate that an arbiter with eight cores, or processing units, can keep up with a network transmitting 2.2 terabits of data per second. That's the equivalent of a 2,000-server data center with gigabit-per-second connections transmitting at full bore all the time.

"This paper is not intended to show that you can build this in the world's largest data centers today," Balakrishnan says. "But the question as to whether a more scalable centralized system can be built, we think the answer is yes."

Moreover, "the fact that it's two terabits per second on an eight-core machine is remarkable," Balakrishnan says. "That could have been 200 gigabits per second without the cleverness of the engineering."

The key to Fastpass's efficiency is a technique for splitting up the task of assigning transmission times so that it can be performed in parallel on separate cores. The problem, Balakrishnan says, is one of matching source and destination servers for each time slot.

"If you were asked to parallelize the problem of constructing these matchings," he says, "you would normally try to divide the source-destination pairs into different groups and put this group on one core, this group on another core, and come up with these iterative rounds. This system doesn't do any of that."

Instead, Fastpass assigns each core its own time slot, and the core with the first slot scrolls through the complete list of pending transmission requests. Each time it comes across a pair of servers, neither of which has received an assignment, it schedules them for its slot. All other requests involving either the source or the destination are simply passed on to the next core, which repeats the process with the next time slot. Each core thus receives a slightly attenuated version of the list the previous core analyzed.

Bottom line

Today, to avoid latencies in their networks, most data center operators simply sink more money into them. Fastpass "would reduce the administrative cost and equipment costs and pain and suffering to provide good service to the users," Balakrishnan says. "That allows you to satisfy many more users with the money you would have spent otherwise."

Networks are typically evaluated according to two measures: latency, or the time a single packet of data takes to traverse the network, and throughput, or the total amount of data that can pass through the network in a given interval.

###

Written by Larry Hardesty, MIT News Office

Additional background

Fastpass: http://fastpass.mit.edu 

Andrew Carleen | Eurek Alert!
Further information:
http://www.mit.edu

Further reports about: Data Centers Facebook MIT electrical engineering microseconds networks

More articles from Information Technology:

nachricht NASA CubeSat to test miniaturized weather satellite technology
10.11.2017 | NASA/Goddard Space Flight Center

nachricht New approach uses light instead of robots to assemble electronic components
08.11.2017 | The Optical Society

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Nanoparticles help with malaria diagnosis – new rapid test in development

The WHO reports an estimated 429,000 malaria deaths each year. The disease mostly affects tropical and subtropical regions and in particular the African continent. The Fraunhofer Institute for Silicate Research ISC teamed up with the Fraunhofer Institute for Molecular Biology and Applied Ecology IME and the Institute of Tropical Medicine at the University of Tübingen for a new test method to detect malaria parasites in blood. The idea of the research project “NanoFRET” is to develop a highly sensitive and reliable rapid diagnostic test so that patient treatment can begin as early as possible.

Malaria is caused by parasites transmitted by mosquito bite. The most dangerous form of malaria is malaria tropica. Left untreated, it is fatal in most cases....

Im Focus: A “cosmic snake” reveals the structure of remote galaxies

The formation of stars in distant galaxies is still largely unexplored. For the first time, astron-omers at the University of Geneva have now been able to closely observe a star system six billion light-years away. In doing so, they are confirming earlier simulations made by the University of Zurich. One special effect is made possible by the multiple reflections of images that run through the cosmos like a snake.

Today, astronomers have a pretty accurate idea of how stars were formed in the recent cosmic past. But do these laws also apply to older galaxies? For around a...

Im Focus: Visual intelligence is not the same as IQ

Just because someone is smart and well-motivated doesn't mean he or she can learn the visual skills needed to excel at tasks like matching fingerprints, interpreting medical X-rays, keeping track of aircraft on radar displays or forensic face matching.

That is the implication of a new study which shows for the first time that there is a broad range of differences in people's visual ability and that these...

Im Focus: Novel Nano-CT device creates high-resolution 3D-X-rays of tiny velvet worm legs

Computer Tomography (CT) is a standard procedure in hospitals, but so far, the technology has not been suitable for imaging extremely small objects. In PNAS, a team from the Technical University of Munich (TUM) describes a Nano-CT device that creates three-dimensional x-ray images at resolutions up to 100 nanometers. The first test application: Together with colleagues from the University of Kassel and Helmholtz-Zentrum Geesthacht the researchers analyzed the locomotory system of a velvet worm.

During a CT analysis, the object under investigation is x-rayed and a detector measures the respective amount of radiation absorbed from various angles....

Im Focus: Researchers Develop Data Bus for Quantum Computer

The quantum world is fragile; error correction codes are needed to protect the information stored in a quantum object from the deteriorating effects of noise. Quantum physicists in Innsbruck have developed a protocol to pass quantum information between differently encoded building blocks of a future quantum computer, such as processors and memories. Scientists may use this protocol in the future to build a data bus for quantum computers. The researchers have published their work in the journal Nature Communications.

Future quantum computers will be able to solve problems where conventional computers fail today. We are still far away from any large-scale implementation,...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

Ecology Across Borders: International conference brings together 1,500 ecologists

15.11.2017 | Event News

Road into laboratory: Users discuss biaxial fatigue-testing for car and truck wheel

15.11.2017 | Event News

#Berlin5GWeek: The right network for Industry 4.0

30.10.2017 | Event News

 
Latest News

From Hannover around the world and to the Mars: LZH delivers laser for ExoMars 2020

21.11.2017 | Physics and Astronomy

Borophene shines alone as 2-D plasmonic material

21.11.2017 | Materials Sciences

Penn study identifies new malaria parasites in wild bonobos

21.11.2017 | Health and Medicine

VideoLinks
B2B-VideoLinks
More VideoLinks >>>