Measurement Lab (M-Lab) is the largest open source Internet measurement effort in the world. M-Lab provides performance tests that help consumers develop an accurate picture of their Internet service, by offering a robust, state-of-the-art server platform that supports diverse measurement needs. The data is aggregated and released in the public domain for policymakers, researchers, and anyone interested in Internet issues.

The graphic below illustrates the relationship between tests run by consumers and M-Lab’s data collection.

Right now, people can use tests to measure their broadband speed, analyze application performance, and run diagnostics. The most commonly run test is the Network Diagnostic Test (NDT), which provides metrics such as upload speed, download speed, and round trip time, as well as other data points that help to measure speed and throughput issues on your connection. To read about all of the tests available on the platform, please visit our tests page.

Absolutely not. M-Lab tests are designed to protect privacy by measuring only synthetic traffic (“fake” traffic generated by a test) between your device and an M-Lab server.

M-Lab collects and publishes all test data, which includes the IP address assigned to your device by your Internet service provider (ISP). However, this does not include any information about you as an Internet user, where you browse, or any other personal details.

M-Lab’s privacy and data collection policies prohibit the collection of personally-identifiable information and private user traffic.

Specific information on what type of data is collected by each M-Lab test and how it can be accessed is available on our tests page.

For most tests, M-Lab collects the raw test data and makes it publicly availalble on Google Cloud Storage.

For some tests, such as BISmark, the test maintainers collect their test’s data and publish it on their own site.

You can explore M-Lab’s NDT speed test data in Google’s Public Data Explorer. All M-Lab data is searchable using BigQuery, or can be downloaded in raw compressed file format. Please visit the test page and the section on Data for more information about how to access it using BigQuery or other tools.

Internet performance tests may provide different results for a wide variety of reasons. Three of the primary reasons for different results between tests are:

Differences in the placement of testing servers

All performance tests have two parts:

• client: This is the software that runs on the user’s machine and shows the user their speed results.
• server: This is the computer on the Internet to which the client connects to complete the test.

A test generates data between the client and the server, and measures performance between these two points. The location of these two points is important in terms of understanding the results of a given test.

If the server is located within your Internet Service Provider’s (ISP) own network (also known as the “last mile”), this is referred to as “on-net” measurement. This approach provides insight into the performance of your Internet connection within your ISP, but does not necessarily reflect the full experience of using the Internet, which almost always involves accessing content and services that are hosted somewhere outside of your ISP. Results achieved from “on-net” testing are often higher than those achieved via other methods, since the distance traveled is generally shorter, and the network is entirely controlled by one entity (your ISP).

So-called “off-net” measurements conduct measurements between your computer and a server located outside of your ISP’s network. This means that traffic crosses borders between networks, and often travels longer distances. Off-net testing generally produces results that are lower, relative to “on-net” testing.

M-Lab’s measurements are always conducted “off-net.” This allows M-Lab to measure performance to representative locations where popular Internet content is often hosted, and so test users get a real sense of the performance they can expect when using the Internet.

Differences in testing methodology

Different Internet performance tests measure different things in different ways. M-Lab’s NDT test attempts to transfer as much data as it can over the course of 10 seconds (both up and down), using a single connection to an M-Lab server. Other popular tests look to transfer as much data as possible across multiple connections to their server at once. Neither are “right” or “wrong,” but using a single stream is more likely to help diagnose problems in the network that multiple streams concurrently would likely bypass. Learn more about NDT’s methodology.

All NDT data collected by M-Lab is publicly available in both visualized and raw forms.

Changing network conditions and distinct test paths

The Internet is a dynamic place, and test results reflect that. A test conducted 5 minutes ago may show distinctly different results than a test conducted 20 minutes ago. This can be caused by the test traffic being routed differently. For example, one test might travel over a path with broken router, while another may not. A test run now may be directed to a test server further away than a test run yesterday.

In short, running one test will give you a sense of network conditions at that moment, across the best network path available at that time, to the specific server coordinating the test. But because Internet routing and infrastructure changes dynamically, testing regularly and looking at the data over time is a much more reliable way to gauge representative performance.

Most M-Lab tests should take less than 60 seconds to complete, so if it’s taking longer there may be something wrong.

• Try running the test again. Perhaps a sporadic network issue caused the problem.
• Try running the test from a different location. For example, if it failed at your home, does the test work at a coffee shop?
• If the test doesn’t start or never completes, is your connection is behind a firewall? This may be the case at some workplaces where the network is actively managed.

If you find that none of the above solves the issue you are experiencing, you can report a bug by emailing support@measurementlab.net.

When reporting a bug, please attempt to share specific information such as:

• Operating system
• Browser name and version
• The name of the test that is not working
• Any error messages you have received

M-Lab support will usually reply within 2 business days. You can also ask other M-Lab users about the issue you are reporting on the M-Lab Discuss group.

M-Lab aims to advance Internet research by empowering the public with useful information about their Internet performance. By providing free, open Internet measurement data, researchers, regulators, advocacy groups, and the general public can get a better sense of how the Internet is working for them, and how to maintain and improve it for the future.

M-Lab is supported by a diverse set of academic institutions, private foundations, private companies, and public interest organizations. M-Lab’s partners have committed resources to M-Lab either in the form of infrastructure, funding, data storage/analysis, staffing, or other assistance dedicated to furthering M-Lab’s mission. For a rundown of M-Lab’s partners, please see our list of supporters.

M-Lab was founded by New America’s Open Technology Institute (OTI), the PlanetLab Consortium, Google Open Source Research, and a large body of academic researchers. The founding researchers collectively make up the steering committee that leads development of M-Lab’s organizational policies and provides oversight of the platform. M-Lab is a community-based effort. We currently receive resources and financial assistance from our partners, and welcome others who would like to support the platform’s growth.

Interested in supporting M-Lab? Please see the FAQ section, Supporting or Contributing to M-Lab, and contact us for more information.

In 2008, Vint Cerf, one of the “fathers of the Internet,” began a series of conversations with Internet researchers to learn more about challenges they faced while trying to study Internet performance. Researchers identified several problems, including a lack of widely-deployed servers with ample connectivity to support Internet measurement experiments. They also reported an inability to share large data sets with one another easily.

There also was no public resource to provide aggregate performance data to policymakers, or consumers interested in understanding their Internet performance over time. As a result of these conversations, M-Lab was founded to help address the core impediments experienced by researchers, and promote at-scale open measurement of the Internet.

The Internet measurement tests running on the M-Lab platform are built and maintained by researchers interested in understanding the Internet and how people experience it. Interested researchers can build their own open source tests and apply to host them with M-Lab. Applications for new tests are reviewed by our operations team and reviewed by our Steering Committee, and if approved they are then deployed on M-Lab’s global Internet measurement infrastructure. By making researchers’ tests available in this way, and promoting their use by consumer, M-Lab serves both consumers and researchers, as well as regulators and others with longitudinal data that is openly available for analysis. For more information, please see our FAQ entry below Can I use M-Lab’s platform to host my own measurement test?

You can contact M-Lab by emailing support@measurementlab.net or by joining our discussion group.

For individuals, the best way to support M-Lab is to regularly use our tests. You gain the benefit of understanding more about your connection to the Internet, and the research community and the public benefits from the resulting public data.

People with web or application development, data analysis, or visualization expertise may also be interested in working with M-Lab’s tests, data, and analysis tools, all of which are open source and openly licensed. Contact us at support@measurementlab.net to learn more.

By becoming an M-Lab supporting partner, companies, non-profit organizations, academic and other institutions can help M-Lab in a number of key ways including:

Providing hardware to grow the M-Lab platform and donating the cost of network connectivity and hosting.

• Providing resources for data hosting, aggregation and publication.
• Providing data analysis or visualization.
• Embedding an M-Lab client tool in an application or service, allowing M-Lab to reach more people and generate more data.
• Provide direct financial support

If you’d like to get involved as an M-Lab supporting partner, contact the M-Lab team and join the public mailing list.

M-Lab welcomes researchers who want to dig into the M-Lab data. Our team provides documentation and support for those interested. If you are interested in working with M-Lab data in your research, check out our data documentation to help get you started and contact us with any questions. We also suggest you join our public mailing list for news and announcements.

M-Lab is open to applications from researchers who develop and maintain Open Source network measurement tests that conform to our goals and support our mission. However, the vast majority of proposed new M-Lab tests are not accepted because of the high bar M-Lab sets for tools we host: we require tests to have fully automatic operation within virtual machines running concurrently on servers distributed globally; and active, client-initiated, off-net network measurement tests looking at full-path performance.

Researchers maintaining the current tools on the M-Lab platform have secured sufficient funding to support their tool’s continued development, deployment, and ongoing maintenance throughout the entire lifecycle of the tool. Your decision to deploy and support a particular tool on M-Lab is a commitment to provide substantial resources over a period of years and to an ongoing relationship with the M-Lab operations team.

Applications for new tools are reviewed by the M-Lab Operations team and the M-Lab Steering Committee twice annually. The number of slots for tools running on M-Lab is finite, so we will only consider serious inquiries from researchers working on mature tools that both align with the M-Lab mission and do not significantly overlap with the functionality of existing tools.

If you are interested in deploying a new tool or test on the M-Lab platform, please first read our document outlining M-Lab’s requirements and procedures for accepting new tools on the platform, and then contact the M-Lab Operations team for more information.

M-Lab’s open source tests can be added to your website, mobile application, or other software. The Network Diagnostic Tool (NDT) from Internet 2, has been used by a number of third party websites and application developers, including internethealthtest.org, the city of Seattle’s broadband map, Bittorrent’s uTorrent client, and several others.

The M-Lab team regularly consults with and supports application and web developers interested in integrating our client tests. If you are interested in adding an M-Lab test to your website or application, please contact us.