- Relationship between latency and throughput
A common concern in the development or procurement of a telecommunications system is a simple question: "will my data arrive fast enough?". This question in fact contains many subtle parts, based on the interplay of several factors. The perceived 'fastness' (speed being a scientific quantity related to propagation and so is not used in this context) is highly dependent on user requirements and measurement technique. A common misunderstanding is that having greater
throughputmeans a "faster" connection. However, throughput, latency, the type of information transmitted, and the way that information is applied all affect the "perceived speed" of a connection.
"Latency" is the delay between the initiation of a network transmission by a sender and the receipt of that transmission by a receiver. In two-way communication, it may be measured as the time from the transmission of a request for a message, to the time when the message is successfully received.
"Throughput" is the number of messages successfully delivered per unit time. Throughput is controlled by available bandwidth, as well as the available signal-to-noise ratio and hardware limitations. Throughput for the purpose of this article will be understood to be measured from the arrival of the first bit of data at the receiver, to decouple the concept of throughput from the concept of latency. For discussions of this type the terms 'throughput' and 'bandwidth' are often used interchangeably.
The "Time Window" is the period over which the throughput is measured. Choice of an appropriate time window will often dominate calculations of throughput, and whether latency is taken into account or not will determine whether the latency affects the throughput or not.
Interplay of factors
All of the factors above, coupled with user requirements and user perceptions, play a role in determining the perceived 'fastness' or utility, of a network connection. The relationship between throughput, latency, and user experience is most aptly understood in the context of a shared network medium, and as a scheduling problem. For systems that are heavily dominated by either latency or throughput considerations.
Speed of lightimposes a minimum propagation time on all electromagnetic signals. It is not possible to reduce the latency below t=(distance)/(speed of light).
* The available channel bandwidth and achievable signal-to-noise ratio dominate the throughput. It is not generally possible to send more data than dictated by the
Algorithms and protocols
For some systems, latency and throughput are coupled entities. In TCP/IP, latency can also directly affect throughput. In TCP connections, the large
bandwidth-delay productof high latency connections, combined with relatively small TCP window sizes on many devices, effectively causes the throughput of a high latency connection to drop sharply with latency. This can be remedied with various techniques, such as increasing the TCP congestion window size, or more drastic solutions, such as packet coalescing, TCP acceleration, and forward error correction, all of which are commonly used for high latency satellite links.
TCP acceleration converts the TCP packets into a stream that is similar to UDP. Because of this, the TCP acceleration software must provide its own mechanisms to ensure the reliability of the link, taking the latency and bandwidth of the link into account, and both ends of the high latency link must support the method used.
Examples of latency or throughput dominated systems
Many systems can be characterized as dominated either by throughput limitations or by latency limitations in terms of end-user utility or experience. In some cases, hard limit s such as the speed of light present unique problems to such systems and nothing can be done to correct this. Other systems allow for significant balancing and optimization for best user experience.
A telecom satellite in geosynchronous orbit imposes a path length of at least 71000 km between transmitter and receiver. [ Roddy, 2001, 67 - 90 ] which means a minimum delay between message request and message receipt, or latency of 473 ms. This delay can be very noticeable and affects satellite phone service regardless of available throughput capacity.
Deep space communication
These long path length considerations are exacerbated when communicating with space probes and other long-range targets beyond Earth's atmosphere. The
Deep Space Networkimplemented by NASA is one such system that must cope with these problems. Largely latency driven, the GAO has criticized the current architecture. [ GAO, 2006 ] Several different methods have been proposed to handle the intermittent connectivity and long delays between packets, such as Delay Tolerant Networking[ Fall, 2003 ] .
Even deeper space communication
At interstellar distances, the difficulties in designing radio systems that can achieve any throughput at all is massive. In these cases, maintaining communication is a bigger issue than how long that communication takes.
Offline data transport
Transportation is concerned almost entirely with throughput, which is why physical deliveries of backup tape archives are still largely done by vehicle.
Examples of optimizable systems
Users browsing the
Internetare usually tolerant of a latency of between 1000 and 3000 ms between mouse click and page download Fact|date=October 2008. Latency and throughput together affect the perceived speed of a connection. However, the perceived fastness of a connection can still vary widely, depending in part on the type of information transmitted and how it is used.
For example, to view a web page over a 56-kbit/s
modemtransmitted from a server 4,800 km (~3,000 mi.) away, latency over the Internet is fairly low – typically about a quarter of a second – and an average web page of 30-100 kilobytes would transfer in 10-30 seconds.
However, to transfer the contents of a
DVDover a modem could take a week or more at this rate. Simply packing the DVD into an envelope and mailing it could be faster.
Network gaming requires very low latency, but requires limited throughput, often as low as a few kilobits per second. The required maximum latency is game type dependent. In first person shooters under 100 ms is required (sometimes even lower) Fact|date=July 2008. In strategy games the maximum latency could be allowed to reach 600 ms, depending on the game. Fact|date=July 2008
*Rappaport, Theodore S. "Wireless Communications, Principles and Practice" second edition,
Prentice Hall, 2002, ISBN 0130422320
*Roddy, Dennis, "Satellite Communications" third edition,
McGraw-Hill, 2001, ISBN 0071371761
*Fall, Kevin, "A Delay-Tolerant Network Architecture for Challenged Internets", Intel Corporation, February, 2003, Doc No: IRB-TR-03-003 [http://www.dtnrg.org/docs/papers/IRB-TR-03-003.pdf The File]
*Government Accountability Office (GAO) report 06-445, NASA'S DEEP SPACE NETWORK: Current Management Structure is Not Conducive to Effectively Matching Resources with Future Requirements, April 27, 2006
* [http://deepspace.jpl.nasa.gov/dsn/ Nasa's Deep Space Network Website]
* [http://www.stuartcheshire.org/rants/Latency.html It's the Latency, Stupid]
* [http://www.stuartcheshire.org/papers/LatencyQuest.html more formal paper by same author]
* [http://www.cs.ucsd.edu/~varghese/PAPERS/webinfocom.pdf A technical article from Infocom 2001 on techniques for reducing web latency]
"As network technology becomes less dominated by bandwidth limitations, the round-trip times spent for protocol handshakes will become a dominant component in the overall transfer time" for many web pages.
Wikimedia Foundation. 2010.