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 Secure networks for the Internet of the future
25.08.2016 | Julius-Maximilians-Universität Würzburg

nachricht New microchip demonstrates efficiency and scalable design
23.08.2016 | Princeton University, Engineering School

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Streamlining accelerated computing for industry

PyFR code combines high accuracy with flexibility to resolve unsteady turbulence problems

Scientists and engineers striving to create the next machine-age marvel--whether it be a more aerodynamic rocket, a faster race car, or a higher-efficiency jet...

Im Focus: X-ray optics on a chip

Waveguides are widely used for filtering, confining, guiding, coupling or splitting beams of visible light. However, creating waveguides that could do the same for X-rays has posed tremendous challenges in fabrication, so they are still only in an early stage of development.

In the latest issue of Acta Crystallographica Section A: Foundations and Advances , Sarah Hoffmann-Urlaub and Tim Salditt report the fabrication and testing of...

Im Focus: Piggyback battery for microchips: TU Graz researchers develop new battery concept

Electrochemists at TU Graz have managed to use monocrystalline semiconductor silicon as an active storage electrode in lithium batteries. This enables an integrated power supply to be made for microchips with a rechargeable battery.

Small electrical gadgets, such as mobile phones, tablets or notebooks, are indispensable accompaniments of everyday life. Integrated circuits in the interiors...

Im Focus: UCI physicists confirm possible discovery of fifth force of nature

Light particle could be key to understanding dark matter in universe

Recent findings indicating the possible discovery of a previously unknown subatomic particle may be evidence of a fifth fundamental force of nature, according...

Im Focus: Wi-fi from lasers

White light from lasers demonstrates data speeds of up to 2 GB/s

A nanocrystalline material that rapidly makes white light out of blue light has been developed by KAUST researchers.

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

The energy transition is not possible without Geotechnics

25.08.2016 | Event News

New Ideas for the Shipping Industry

24.08.2016 | Event News

A week of excellence: 22 of the world’s best computer scientists and mathematicians in Heidelberg

12.08.2016 | Event News

 
Latest News

Environmental DNA uncovers biodiversity in rivers

30.08.2016 | Ecology, The Environment and Conservation

Solar houses scientifically evaluated

30.08.2016 | Power and Electrical Engineering

Amazon forests: Biodiversity can help mitigate climate risks

30.08.2016 | Life Sciences

VideoLinks
B2B-VideoLinks
More VideoLinks >>>