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!
'Magic' sphere for information transfer
24.08.2015 | Lomonosov Moscow State University
Fraunhofer IPA develops prototype of intelligent care cart
20.08.2015 | Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA
A University of Oklahoma astrophysicist and his Chinese collaborator have found two supermassive black holes in Markarian 231, the nearest quasar to Earth, using observations from NASA's Hubble Space Telescope.
The discovery of two supermassive black holes--one larger one and a second, smaller one--are evidence of a binary black hole and suggests that supermassive...
A team of European researchers have developed a model to simulate the impact of tsunamis generated by earthquakes and applied it to the Eastern Mediterranean. The results show how tsunami waves could hit and inundate coastal areas in southern Italy and Greece. The study is published today (27 August) in Ocean Science, an open access journal of the European Geosciences Union (EGU).
Though not as frequent as in the Pacific and Indian oceans, tsunamis also occur in the Mediterranean, mainly due to earthquakes generated when the African...
In mountainous regions earthquakes often cause strong landslides, which can be exacerbated by heavy rain. However, after an initial increase, the frequency of these mass wasting events, often enormous and dangerous, declines, in fact independently of meteorological events and aftershocks.
These new findings are presented by a German-Franco-Japanese team of geoscientists in the current issue of the journal Geology, under the lead of the GFZ...
Bacteria do not cease to amaze us with their survival strategies. A research team from the University of Basel's Biozentrum has now discovered how bacteria enter a sleep mode using a so-called FIC toxin. In the current issue of “Cell Reports”, the scientists describe the mechanism of action and also explain why their discovery provides new insights into the evolution of pathogens.
For many poisons there are antidotes which neutralize their toxic effect. Toxin-antitoxin systems in bacteria work in a similar manner: As long as a cell...
It comes when called, bringing care utensils with it and recording how they are used: Fraunhofer IPA is developing an intelligent care cart that provides care staff with physical and informational support in their day-to-day work. The scientists at Fraunhofer IPA have now completed a first prototype. In doing so, they are continuing in their efforts to improve working conditions in the care sector and are developing solutions designed to address the challenges of demographic change.
Technical assistance systems can improve the difficult working conditions in residential nursing homes and hospitals by helping the staff in their work and...
20.08.2015 | Event News
20.08.2015 | Event News
19.08.2015 | Event News
28.08.2015 | Physics and Astronomy
28.08.2015 | Health and Medicine
28.08.2015 | Life Sciences