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

Jul 16, 2014 by Larry Hardesty

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 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 and (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.

Explore further: Researchers unveil experimental 36-core chip

More information: Fastpass: fastpass.mit.edu

add to favorites email to friend print save as pdf

Related Stories

Researchers unveil experimental 36-core chip

Jun 23, 2014

The more cores—or processing units—a computer chip has, the bigger the problem of communication between cores becomes. For years, Li-Shiuan Peh, the Singapore Research Professor of Electrical Engineering ...

Chips as mini Internets

Apr 10, 2012

Computer chips have stopped getting faster. In order to keep increasing chips’ computational power at the rate to which we’ve grown accustomed, chipmakers are instead giving them additional “cores,” or ...

Recommended for you

Microsoft unveils Xbox in China as it faces probe

9 hours ago

Microsoft on Wednesday unveiled its Xbox game console in China, the first to enter the market after an official ban 14 years ago, even as it faces a Chinese government probe over business practices.

Teens love vacation selfies; adults, not so much

10 hours ago

(AP)—Jacquie Whitt's trip to the Galapagos with a group of teenagers was memorable not just for the scenery and wildlife, but also for the way the kids preserved their memories. It was, said Whitt, a "selfie ...

Tiny UAVs and hummingbirds are put to test

10 hours ago

Hummingbirds in nature exhibit expert engineering skills, the only birds capable of sustained hovering. A team from the US, British Columbia, and the Netherlands have completed tests to learn more about the ...

US spy agency patents car seat for kids

13 hours ago

Electronic eavesdropping is the National Security Agency's forte, but it seems it also has a special interest in children's car seats, Foreign Policy magazine reported Wednesday.

User comments : 2

Adjust slider to filter visible comments by rank

Display comments: newest first

NIS_0
5 / 5 (1) Jul 16, 2014
Take out the arbiter, then what?
Jimee
not rated yet Jul 16, 2014
Plenty of backups needed, I would assume.