Latest revision as of 20:28, 24 February 2011

Abstract

In the past 20 years, advancements in computing have gravitated towards connectivity, specifically the rise of the internet. The last decade (2000 – 2010) has seen a global increase in the number of internet users by over 400%, and as expansion into the Middle East and Africa continues, the total number of people connected to the internet will only grow.[1] As we continue to build computer interfaces which simplify the user experience (iOS, for example) more of the population can make use of computers without knowledge of how a computer works. Specifically, terms like bandwidth or latency mean little to the average computer user in terms of the actual performance of their computer.

This paper will review what distributed computing means to an average user as well as how we can make better use of our networks by providing users with simple to use tools to understand bandwidth and how different applications utilize the finite resource. We will begin with an introduction describing typical internet traffic as well as how users typically interact with the internet. Following the introduction is a look into the need for user controlled bandwidth and what benefits it affords. Next we will examine a particular case study in which households were given a tool to monitor and adjust their bandwidth usage. The subsequent section will examine some current tools for implementing user controlled bandwidth. The final section of the paper provides a discussion on the current state of user controlled bandwidth and what direction it may take in the future.

Introduction

To understand user controlled bandwidth it is important to understand how internet traffic “flows” as well as trends in data movement and user interactions with the internet. A typical user of the internet does not care about concepts such as packets, they simply run applications, like web browsers, completely unaware of the size and duration of their connection to the internet. Most internet traffic is either based on Transmission Control Protocol (TCP) or User Datagram Protocol (UDP). UDP is not a guaranteed delivery protocol, it simply sends packets, regardless of congestion in the network, and does not provide any confirmation of receipt to the sender. Alternatively, TCP provides a delivery system analogous to stream delivery. TCP has a feedback mechanism to control the sending rate, it sends data as fast as it can until there is congestion at which point it scale back the rate, and it also confirms delivery of data.[2]

Due to the congestion control and guaranteed delivery properties, TCP is the delivery method used most frequently on the internet.[3] This makes sense for connections that last a long time, greater than 15 minutes, and/or transmit a lot of data as it allows the congestion control mechanism to provide some form of “fair” sharing of the available bandwidth. However, an analysis of actual internet traffic displays a usage landscape that is not dominated by large, long connections. Most internet streams are very short in duration, less than 15 minutes (98%), and almost half of those streams are less than 2 seconds in duration.[4] This means that the majority of streams on the internet are not actually connected long enough to take advantage of TCP’s congestion control mechanisms.

The remaining 2% of TCP streams, on the other hand, last longer than 15 minutes but account for approximately 50% to 60% of all bytes transmitted. This presents a transmission environment in which we need to consider streams both temporally as well as spatially as these two dimensions have very different affects on the network.[4] It becomes clear why internet traffic follows these patterns when further analysis is focused on how users typically interact with the internet. Although the number of users of the internet has been growing exponentially and similarly the number of web pages on the internet has grown exponentially, typical usage of the internet is fairly conservative. The average user will connect to the internet multiple times but each session is typically short in duration. While connected, users will typically visit a small, well-known group of sites as opposed to exploring new web pages. In fact, users will typically frequent a single website multiple times in a single session.[5]

User Controlled Bandwidth

Is Bandwidth the Correct Measurment for Network Speed?

The average internet user is not concerned with bandwidth or latency; he/she is only interested in how long it will take to complete a task. Typical tasks may include loading a web page, downloading a file, watching a video clip or conversing in a conversation on voice over IP (VoIP). Yet when we purchase an internet package from an internet service provider (ISP), we only get to choose by bandwidth allotment. By marketing internet connections with terms that a network technician would find useful, but to an average user are useless, users are left without a conceptual model for how their internet usage affects their connection “speed”.

Dukkipati and McKeown provide an interesting alternative in Why Flow-Congestion Time is the Right Metric for Congestion Control. A user is not concerned with full utilization of their bandwidth, network fairness or throughput; all they care about is how quickly a task may be completed. Dukkipati and McKeown propose measuring connections based on Flow Completion Time (FCT) which could allow for improvements to the way data is transmitted. As mentioned earlier, typical data streams on the internet do not last long enough to make full use of TCP’s congestion control mechanisms, such as “slow start”. Even worse, because of TCP’s slow start mechanism, many of these short flows have their lives prolonged in multiple orders of magnitude of round trip times (RTTs) causing unnecessary congestion. [6]

In order to combat these issues with TCP, Dukkipati and McKeown suggest adopting a Rate Control Protocol (RCP) which would simulate processor sharing at each router. Using such a protocol each flow would be assigned a single rate and each flow would have the same rate. This rate would be dynamic depending on how many flows are present and the input traffic rate. The benefit of RCP would be that the router no longer needs to maintain per-flow state or per-packet calculations. Furthermore, since there would be no “slow start”, the short streams (which make up 98% of the streams) would no longer have their lifetimes unnecessarily extended.[6]

The issue with altering network connection descriptions from bandwidth to Flow Completion Time is that it is very difficult to guarantee an FCT. However, this may not be such an issue as ISPs routinely advertise bandwidth amounts that are theoretical or are not based on the effect of others on the network sharing the resource. Thus, current ISP descriptions of network “speeds” based on bandwidth may be no more accurate than they would be if based on FCT. The benefit of basing them on FCT, however, is that users would be able to understand what their “expected” rate would be when it is a time limit as opposed to a size limit.

How Can Users Gain Control?

If we are unable to shift the focus of network speed measuring from bandwidths to a completion time related measurement, the question becomes how can networks be presented such that average users will be able to understand the limits of bandwidth? This is an important question not only for general, home-based internet use but also in the scientific community as well. In the scientific realm, users have a better understanding of what bandwidth is and how it relates to their distributed computing experience, but they need some method to setup and control guaranteed bandwidth connections for data transfer. These e-science experiments transfer massive amounts of critical data and bandwidth guarantees are required as well as proper scheduling to ensure connections are utilized as completely as possible.[8]

To support these experiments, scientists are turning to solutions that allow them to setup dedicated channels with guaranteed bandwidth allowances and lifetimes. These solutions provide the scientists with an interface to register channels with various parameters and the program will setup the connection and add it to a list of monitored connections across the network. As bandwidth needs change, the scientists can make requests to alter the parameters of the channels and the tool will accommodate accordingly.[7] In this manner, connections with known minimum parameters can be established such that a minimum completion time is known.

The programs which support the dynamic creation and maintenance of the connections are implemented similar to the way an operating system handles processes. The users make requests to a central component which knows all of the details of all connections. Passed on the request parameters (bandwidth, duration of connection, time of day to create, etc.) the tool schedules the connections using a scheduling algorithm. The details of all connections are also known to the users so they can make their requests based on the known connection schedule. Thus, if a certain experiment requires a larger share of bandwidth then is available in one slot, the scientists may opt to setup a connection during a low use time to request the extra bandwidth. If delaying the creation of the connection to a low period time is not an option, then the scientists need to negotiate bandwidth needs with their colleagues to obtain the necessary resources. In this manner, when bandwidth bottlenecks occur, it is not the scheduling program that resolves the issue, but rather the social interactions between the users of the network.[7][8]

This model is something that can be simplified to a general use case for typical internet users in a home environment. In order for an average user to understand how different types of usage demand differing levels of bandwidth, the users need a tool which presents a comprehensive view of their usage and allows them to alter what applications/users get “guaranteed” levels of bandwidth. Having such a tool, users how do not understand bandwidth would be able to obtain visual data to form a mental model regarding bandwidth and thus control, or setup social protocols among the users of the network, to limit bottlenecks and promote more efficient use of the network.

Case Study: Home Watcher

A tool which allows home internet users a method to view and manage bandwidth consumption is the focus of Who’s Hogging the Bandwidth?: The Consequences of Revealing the Invisible in the Home (Chetty et al.). As more appliances become connected to the internet, managing digital resources like bandwidth is necessary, but first the users must understand how bandwidth is consumed. In Who’s Hogging the Bandwidth?, the research team setup a tool called Home Watcher in several homes composed of various social make-ups (working parents with teenage children, a house of university students, etc.). The Home Watcher tool provided the users with a visual display of the bandwidth usage of each device connected to the network based on the percentage of bandwidth the device was using out of the total available bandwidth. The tool also allowed users the ability to limit the bandwidth usage of any device connected to the network, up to a minimum level of 20%.[9]

The focus of the study was to examine how providing visibility into bandwidth consumption would alter the usage patterns of household members as well as how it would affect the knowledge level of the study participants. The study results report that bandwidth management is a complicated socio-technical issue. Before installing the Home Watcher tool, the researchers interviewed the participants and found multiple concerns such as:

People who feel that they may be hogging the bandwidth usually feel guilty about how their usage may be affecting other users. At the same time, they feel like they are being victimized as they were just trying to use the internet just like the others and could not control how much bandwidth they consumed.

People generally had good ideas about why their internet connections were slow at points (multiple users streaming data, too many people all using the resource, congestion because of external users of the same ISP, hardware issues in their own CPU, etc.) they had no way to see or validate any of their claims. Thus, some relationships were strained due to “hogging” accusations.

Most users wanted to see the bandwidth graphically so that they could validate if their ISP is “shaping” their usage or if there are in fact users hogging larger portions of the bandwidth in the house. [9]

After installing the Home Watcher tool and allowing the households to utilize it for a few weeks the researchers again interviewed the participants and also analyzed the usage statistics. They found that by making bandwidth consumption visible, household members were allowed to use social interactions to partition the finite bandwidth resource appropriately. [9]

For example, household members were willing to change their usage based on the knowledge of what levels of bandwidth others required. If playing a game takes up a lot of bandwidth, someone may be willing to play at a different time then when another user needs the bandwidth for work related activities. Furthermore, increasing the visibility of bandwidth usage actually increased the understanding members of the households possessed as to what bandwidth was and how it is a shared resource. By the end of the study period, even those who were not the “technical” people of the house felt comfortable engaging in discussions of how bandwidth was being divided. The visual display of bandwidth consumption allowed participants to form a mental model of bandwidth using the graphical display. [9]

An interesting side effect of making the bandwidth usage visible was that household members were concerned that the usage patterns displayed on the Home Watcher device would cast a negative light on the activities of users. For example, the bandwidth spike for watching a work-related video would be misinterpreted as recreational viewing. This example brings into light how a digital resource like bandwidth can be extended in certain situations to be part of a person’s identity. Thus, social interactions would help resolve bandwidth sharing issues the same way that social interactions clear up misunderstanding between people. [9]

In addition to the association of bandwidth usage to personal identities, other complex etiquettes emerged with regards to when it was ok to limit a person’s bandwidth. In many households it was deemed unacceptable to limit bandwidth when someone was on a VoIP call or watching a video as this would immediately degrade the quality of the service. On the other hand, limiting bandwidth usage during a file download was perfectly acceptable as this just delayed the completion time of the download. These etiquettes reflect the capability of social interactions to facilitate appropriate partitioning of network bandwidth. [9]

Tools for Bandwidth Management

Currently there are multiple tools that provide bandwidth monitoring and management capabilities for both home and business networks. Below is a brief summary of some of these tools:

Bandwidth Manager for Windows

Bandwidth Manager for Windows provides a feature set that is common to a lot of the tools described in this section. The tool allows an administrator the ability to limit each connection’s bandwidth limit as well as providing the capability to prioritize some types of data, for example time-sensitive data for VoIP, over others. Priority of bandwidth can also be partitioned based on users or machines so that privileges can be but are not necessarily tied to physical devices. Any client computer can be used to configure the bandwidth sharing/limit rules, although an administrator profile can be established to ensure only authorized individuals can manipulate bandwidth rules. Bandwidth Manager for Windows also comes in different packages based on feature set. For example, the base level editions provide traffic shaping based on Level 3 (Network) layer. In comparison, the enterprise edition provides layer 7 classification so that the traffic can be altered based on the application that is running. This feature is referred to as Deep Packet Inspection”. [10]

NetLimiter for Windows

NetLimiter provides a variety of customization options including the ability to set both upload and download limits for applications and connections, the ability to block applications from connecting, determine rules for the connections, i.e. what time of day an application may connect, and filters which allow specific transfer speeds for IP ranges, groups of applications, etc. The main display of NetLimiter provides a visual representation of applications and their transfer rates as well as the option to obtain usage statistics and a traffic chart of real-time connections.[11]

Cyberoam Bandwidth Management

The focus of Cyberoam is primarily on large networks and businesses. In addition to the typical features of partitioning bandwidth across different machines, Cyberroam provides real-time data on network, application and user traffic from Layers 2 (Data Link) to the Application Layer. There is also an alert feature which allows administrators the ability to customize usage that is considered unproductive and have it reported automatically. Cyberroam allows bandwidth usage to be limited by application, based on time of day, type of data (video, VoIP, etc.) as well as allowing users to set their own limits within the overall limit provided by the administrator.

Speed Meter Pro

Speed Meter Pro attempts to make the process of bandwidth management more visual by providing graphical representations of real-time and trending usage. This tool is specifically designed with slowdown detection in mind with the goal of maximizing the connection usage at all times. In an attempt to be easier to use, Speed Meter Pro does not include all of the additional features of the other options described; instead it focuses on correcting network issues due to bandwidth hogging.[13]

Bandwidth Manager

Bandwidth Manager is very similar in terms of features provided to the other tools described in this section; it allows you to limit rates based on time of day, application, etc. The difference is that Bandwidth Manager has a specific focus is on limiting usage based on user accounts, not only in terms of bandwidth rate/percentage limits but also the total amount a user can download for a given period. There is no client software for Bandwidth Manager, all interaction takes place via a web service. This type of tool is used commonly in situations where unknown users may be allowed to connect to a network but at a slower speed, then provide better speeds at a later date (for example, an internet cafe, slow at first, pay for more minutes and the speed increases).[14]

BWMeter

Does allow control over network access and speed limit (bandwidth limiting) controls, but the focus of BWMeter is on usage statistics. This tool provides very detailed reports of the usage by port, application, IP address, and other measures so you can determine exactly what the usage is and where it is coming from. In this manner, BWMeter can allow users to decipher local network and internet traffic as well as isolate internet traffic that may be hostile. [15]

Discussion

It is clear that an average user is less concerned with network measurements, such as bandwidth and latency, than they are interested in how fast transactions will be completed. Although one option would be to restructure the way internet connections are marketed from a bandwidth-centric model to one that describes connections in terms of Flow Completion Time; this would require complete buy-in from internet service providers to be effective. Furthermore, FCT is potentially a more difficult measurement for an ISP to guarantee, although more research will be required to prove this fact.

Another, more realistic, alternative is to provide tools which allow average users to understand and manage their network resources. Through the Home Watcher case study we can see that such tools provide users with a way to better understand how the applications they use affect the limited bandwidth resource shared by all members of a household. Once users understand the relationship between bandwidth and their applications, they can make use of social protocols, such as setting up appropriate times for file downloads, to ensure that bandwidth usage has fewer bottlenecks. It is because of the transparency of bandwidth usage provided by tools like Home Watcher that users can better utilize their digital resources.

Currently the market has a number of tools which provide some form of bandwidth management capabilities. The problem is that many of these tools are either geared towards enterprise networks, or were originally built for large networks and have been ported to include home use scenarios. Although this is a step in the right direction, many of these tools (like Cyberoam) still include an extremely robust feature set that, although useful, may be confusing and a source creating avoidance for typical internet users unfamiliar with network technologies. On the other hand, tools that have attempted to simplify the user experience (like Speed Meter Pro) may not provide users with enough control over their bandwidth usage once they better understand the relationship between their applications and the bandwidth consumption. A good argument could be made that the future of user bandwidth management lies in the successful marriage of a robust feature set hidden beneath a simplified user interface which can be expanded as users become more knowledge in their bandwidth consumption.

References

[1] World Internet Usage Statistics: News and World Population Stats, Miniwatts Marketing Group, June 2010. [electronic resource] http://www.internetworldstats.com/stats.htm.

[2] Peterson, Larry L. And Bruce S. Davie, Computer Networks: A Systems Approach 4th Edition, Morgan Kaufman Publishers, San Francisco, 2007.

[3] The Cooperative Association for Internet Data Analysis, last modified Jan 14, 2010. [electronic resource] http://www.caida.org/research/traffic-analysis/tcpudpratio/

[4] Brownlee, Nevil, Understanding Internet Traffic Streams: Dragonflies and Tortoises, University of Auckland, New Zealand, 2002. [electronic source] http://www.bandwidthco.com/whitepapers/netforensics/tcpip/Understanding%20Internet%20Traffic%20Streams.pdf

[5] Montgomery, Alan L. And Christos Faloutsos, Identifying Web Browsing Trends and Patterns, Carnegie Mellon University, 2001. [electronic source] http://pages.cpsc.ucalgary.ca/~saul/personal/other_pubs/r7094.pdf

[6] Dukkipati, Nandita and Nick McKeown, Why Flow-Congestion Time is the Right Metric for Congestion Control, Stanford University, 2006. Link: http://yuba.stanford.edu/rcp/flowCompTime-dukkipati.pdf

[7] Boutaba, Raouf, et al., Lightpaths on Demand: A Web-Services-Based Management System, University of Waterloo, 2004. [electronic source] http://bcr2.uwaterloo.ca/~iraqi/Papers/Journal/IEEECOMMAG04-2.pdf

[8] Rao, Nageswara S. V. Et l., Control Plane for Advance Bandwidth Scheduling in Ultra High-Speed Networks, Oak Ridge National Laboratory, 2007. [electronic source] http://networks.cs.ucdavis.edu/~amitabha/papers/Raoetal-paper.pdf

[9] Chetty, Marshini et al., Who’s Hogging the Bandwidth?: The Consequences of Revealing the Invisible in the Home, Georgia Tech, 2010. Link: http://research.microsoft.com/en-us/people/asellen/pap0209-chetty.pdf.

[10] Bandwidth Manager for Windows, Bandwidth Controller, last accessed Feb. 24, 2011. [electronic source] http://bandwidthcontroller.com/traffic-shaping/traffic-shaping.html

[11] NetLimiter for Windows, Locktime Software, last accessed Feb. 24, 2011. [electronic source] http://www.netlimiter.com/featurelistnl3.php

[12] Cyberoam Bandwidth Management, Elitecore Technologies, last accessed Feb 24, 2011. [electronic source] http://www.cyberoam.com/bandwidthmanager.html

[13] Speed Meter Pro, Cisco, last accessed Feb. 24, 2011. [electronic source] http://www.linksysbycisco.com/ANZ/en/products/CSMPRO

[14] Bandwidth Manager, Antamedia, last accessed Feb. 24, 2011. [electronic source] http://www.antamedia.com/bandwidth-manager/

[15] BWMeter, Desksoft, last accessed Feb. 24, 2011. [electronic source] http://www.desksoft.com/BWMeter.htm