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.
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
Andrew Carleen | Eurek Alert!
Navigating the unknown
09.10.2015 | The Agency for Science, Technology and Research (A*STAR)
Theoretical computer science provides answers to data privacy problem
08.10.2015 | National Science Foundation
Nondestructive material testing (NDT) is a fast and effective way to analyze the quality of a product during the manufacturing process. Because defective materials can lead to malfunctioning finished products, NDT is an essential quality assurance measure, especially in the manufacture of safety-critical components such as automotive B-pillars. NDT examines the quality without damaging the component or modifying the surface of the material. At this year's Blechexpo trade fair in Stuttgart, Fraunhofer IZFP will have an exhibit that demonstrates the nondestructive testing of high-strength automotive body parts using 3MA. The measurement results are available in a matter of seconds.
To minimize vehicle weight and fuel consumption while providing the highest level of crash safety, automotive bodies are reinforced with elements made from...
The MICADO camera, a first light instrument for the European Extremely Large Telescope (E-ELT), has entered a new phase in the project: by agreeing to a Memorandum of Understanding, the partners in Germany, France, the Netherlands, Austria, and Italy, have all confirmed their participation. Following this milestone, the project's transition into its preliminary design phase was approved at a kick-off meeting held in Vienna. Two weeks earlier, on September 18, the consortium and the European Southern Observatory (ESO), which is building the telescope, have signed the corresponding collaboration agreement.
As the first dedicated camera for the E-ELT, MICADO will equip the giant telescope with a capability for diffraction-limited imaging at near-infrared...
Self-driving cars will be on our streets in the foreseeable future. In Graz, research is currently dedicated to an innovative driver assistance system that takes over control if there is a danger of collision. It was nature that inspired Dr Manfred Hartbauer from the Institute of Zoology at the University of Graz: in dangerous traffic situations, migratory locusts react around ten times faster than humans. Working together with an interdisciplinary team, Hartbauer is investigating an affordable collision detector that is equipped with artificial locust eyes and can recognise potential crashes in time, during both day and night.
Inspired by insects
An interdisciplinary team of researchers has built the first prototype of a miniature particle accelerator that uses terahertz radiation instead of radio...
At present, tiny magnetic whirls – so called skyrmions – are discussed as promising candidates for bits in future robust and compact data storage devices. At...
01.10.2015 | Event News
30.09.2015 | Event News
17.09.2015 | Event News
09.10.2015 | Earth Sciences
09.10.2015 | Life Sciences
09.10.2015 | Life Sciences