Just after 1200 UTC on Tuesday, June 7, the Africa-Asia-Europe-1 (AAE-1) and SEA-ME-WE-5 (SMW-5) submarine cables suffered cable cuts. The damage reportedly occurred in Egypt, and impacted Internet connectivity for millions of Internet users across multiple countries in the Middle East and Africa, as well as thousands of miles away in Asia. In addition, Google Cloud Platform and OVHcloud reported connectivity issues due to these cable cuts.

Data from Cloudflare Radar showed significant drops in traffic across the impacted countries as the cable damage occurred, recovering approximately four hours later as the cables were repaired.

It appears that Saudi Arabia may have also been affected by the cable cut(s), but the impact was much less significant, and traffic recovered almost immediately.

In the graphs above, we show that Ethiopia was one of the impacted countries. However, as it is landlocked, there are obviously no submarine cable landing points within the country. The Afterfibre map from the Network Startup Resource Center (NSRC) shows that that fiber in Ethiopia connects to fiber in Somalia, which experienced an impact. In addition, Ethio Telecom also routes traffic through network providers in Kenya and Djibouti. Djibouti Telecom, one of these providers, in turn peers with larger global providers like Telecom Italia (TI) Sparkle, which is one of the owners of SMW5.

In addition to impacting end-user connectivity in the impacted countries, the cable cuts also reportedly impacted cloud providers including Google Cloud Platform and OVHcloud. In their incident report, Google Cloud noted “Google Cloud Networking experienced increased packet loss for egress traffic from Google to the Middle East, and elevated latency between our Europe and Asia Regions as a result, for 3 hours and 12 minutes, affecting several related products including Cloud NAT, Hybrid Connectivity and Virtual Private Cloud (VPC). From preliminary analysis, the root cause of the issue was a capacity shortage following two simultaneous fiber-cuts.” OVHcloud noted that “Backbone links between Marseille and Singapore are currently down” and that “Upon further investigation, our Network OPERATION teams advised that the fault was related to our partner fiber cuts.”

When concurrent disruptions like those highlighted above are observed across multiple countries in one or more geographic areas, the culprit is often a submarine cable that connects the impacted countries to the global Internet. The impact of such cable cuts will vary across countries, largely due to the levels of redundancy that they may have in place. That is, are these countries solely dependent on an impacted cable for global Internet connectivity, or do they have redundant connectivity across other submarine or terrestrial cables? Additionally, the location of the country relative to the cable cut will also impact how connectivity in a given country may be affected. Due to these factors, we didn’t see a similar impact across all of the countries connected to the AAE-1 and SMW5 cables.

Specific details are sparse, but as noted above, the cable damage reportedly occurred in Egypt – both of the impacted cables land in Abu Talat and Zafarana, which also serve as landing points for a number of other submarine cables. According to a 2021 article in Middle East Eye, “There are 10 cable landing stations on Egypt’s Mediterranean and Red Sea coastlines, and some 15 terrestrial crossing routes across the country.” Alan Mauldin, research director at telecommunications research firm TeleGeography, notes that routing cables between Europe and the Middle East to India is done via Egypt, because there is the least amount of land to cross. This places the country in a unique position as a choke point for international Internet connectivity, with damage to infrastructure locally impacting the ability of millions of people thousands of miles away to access websites and applications, as well as impacting connectivity for leading cloud platform providers.

As the graphs above show, traffic returned to normal levels within a matter of hours, with tweets from telecommunications authorities in Pakistan and Oman also noting that Internet services had returned to their countries. Such rapid repairs to submarine cable infrastructure are unusual, as repair timeframes are often measured in days or weeks, as we saw with the cables damaged by the volcanic eruption in Tonga earlier this year. This is due to the need to locate the fault, send repair ships to the appropriate location, and then retrieve the cable and repair it. Given this, the damage to these cables likely occurred on land, after they came ashore.

By deploying in data centers close to end users, Cloudflare helps to keep traffic local, which can mitigate the impact of catastrophic events like cable cuts, while improving performance, availability, and security. Being able to deliver content from our network generally requires first retrieving it from an origin, and with end users around the world, Cloudflare needs to be able to reach origins from multiple points around the world at the same time. However, a customer origin may be reachable from some networks but not from others, due to a cable cut or some other network disruption.

In September 2021, Cloudflare announced Orpheus, which provides reachability benefits for customers by finding unreachable paths on the Internet in real time, and guiding traffic away from those paths, ensuring that Cloudflare will always be able to reach an origin no matter what is happening on the Internet.

Because the Internet is an interconnected network of networks, an event such as a cable cut can have a ripple effect across the whole Internet, impacting connectivity for users thousands of miles away from where the incident occurred. Users may be unable to access content or applications, or the content/applications may suffer from reduced performance. Additionally, the providers of those applications may experience problems within their own network infrastructure due to such an event.

For network providers, the impact of such events can be mitigated through the use of multiple upstream providers/peers, and diverse physical paths for critical infrastructure like submarine cables. Cloudflare’s globally deployed network can help content and application providers ensure that their content and applications remain available and performant in the face of network disruptions.

So far in 2019, we’ve added a score of new locations: Amman, Antananarivo*, Arica*, Asunción, Baku, Bengaluru, Buffalo, Casablanca, Córdoba*, Cork, Curitiba, Dakar*, Dar es Salaam, Fortaleza, Geneva, Göteborg, Guatemala City, Hyderabad, Kigali, Kolkata, Male*, Maputo, Nagpur, Neuquén*, Nicosia, Nouméa, Ottawa, Port-au-Prince, Porto Alegre, Querétaro, Ramallah, and Thessaloniki.

When Cloudflare launched in 2010, we focused on putting servers at the Internet’s crossroads: large data centers with key connections, like the Amsterdam Internet Exchange and Equinix Ashburn. This not only provided the most value to the most people at once but was also easier to manage by keeping our servers in the same buildings as all the local ISPs, server providers, and other people they needed to talk to streamline our services.

This is a great approach for bootstrapping a global network, but we’re obsessed with speed in general. There are over five hundred cities in the world with over one million inhabitants, but only a handful of them have the kinds of major Internet exchanges that we targeted. Our goal as a company is to help make a better Internet for all, not just those lucky enough to live in areas with affordable and easily-accessible interconnection points. However, we ran up against two broad, nasty problems: a) running out of major Internet exchanges and b) latency still wasn’t as low as we wanted. Clearly, we had to start scaling in new ways.

One of our first big steps was entering into partnerships around the world with local ISPs, who have many of the same problems we do: ISPs want to save money and provide fast Internet to their customers, but they often don’t have a major Internet exchange nearby to connect to. Adding Cloudflare equipment to their infrastructure effectively brought more of the Internet closer to them. We help them speed up millions of Internet properties while reducing costs by serving traffic locally. Additionally, since all of our servers are designed to support all our products, a relatively small physical footprint can also provide security, performance, reliability, and more.

Though it may be obvious and easy to overlook, continuing to build out existing locations is also a key facet of building a global network. This year, we have significantly increased the computational capacity at the edge of our network. Additionally, by making it easier to interconnect with Cloudflare, we have increased the number of unique networks directly connected with us to over 8,000. This makes for a faster, more reliable Internet experience for the >1 billion IPs that we see daily.

To make these capacity upgrades possible for our customers, efficient infrastructure deployment has been one of our keys to success. We want our infrastructure deployment to be targeted and flexible.

The next Cloudflare customer through our door could be a small restaurant owner on a Pro plan with thousands of monthly pageviews or a fast-growing global tech company like Discord. As a result, we need to always stay one step ahead and synthesize a lot of data all at once for our customers.

To accommodate this expansion, our Capacity Planning team is learning new ways to optimize our servers. One key strategy is targeting exactly where to send our servers. However, staying on top of everything isn’t easy - we are a global anycast network, which introduces unpredictability as to where incoming traffic goes. To make things even more difficult, each city can contain as many as five distinct deployments. Planning isn’t just a question of what city to send servers to, it’s one of which address.

To make sense of it all, we tackle the problem with simulations. Some, but not all, of the variables we model include historical traffic growth rates, foreseeable anomalous spikes (e.g., Cyber Day in Chile), and consumption states from our live deal pipeline, as well as product costs, user growth, end-customer adoption. We also add in site reliability, potential for expansion, and expected regional expansion and partnerships, as well as strategic priorities and, of course, feedback from our fantastic Systems Reliability Engineers.

Knowing where to send a server is only the first challenge of many when it comes to a global network. Just like our user base, our supply chain must span the entire world while also staying flexible enough to quickly react to time constraints, pricing changes including taxes and tariffs, import/export restrictions and required certifications - not to mention local partnerships many more dynamic location-specific variables. Even more reason we have to stay quick on our feet, there will always be unforeseen roadblocks and detours even in the most well-prepared plans. For example, a planned expansion in our Prague location might warrant an expanded presence in Vienna for failover.

Once servers arrive at our data centers, our Data Center Deployment and Technical Operations teams work with our vendors and on-site data center personnel (our “Remote Hands” and “Smart Hands”) to install the physical server, manage the cabling, and handle other early-stage provisioning processes.

Our architecture, which is designed so that every server can support every service, makes it easier to withstand hardware failures and efficiently load balance workloads between equipment and between locations.

If working at a rapidly expanding, globally diverse company interests you, we’re hiring for scores of positions, including in the Infrastructure group. If you want to help increase hardware efficiency, deploy and maintain servers, work on our supply chain, or strengthen ISP partnerships, get in touch.

*Represents cities where we have data centers with active Internet ports and where we are configuring our servers to handle traffic for more customers (at the time of publishing)

Cloudflare has a rich history in EMEA where London was one of the earliest bases for both the company’s engineering and also its customer-facing activities. In the subsequent years, we have expanded our customer-facing activity to include coverage into all the major EMEA countries and regions. We’ve built up a team of professional sales and business development people, capable systems engineers, dedicated customer success managers, thoughtful marketeers and a responsive customer support team who serve our existing customers and develop new ones as a committed and focused team.

We work on developing brand awareness for Cloudflare and extending our reach into the market through communications, events and most of all through ongoing close engagement with customers, prospective customers and partners. We carry the Cloudflare mission of helping build a better Internet to the market and reinforce it every chance we get.

I’m a British-Canadian with more than 25 years experience growing international businesses, mostly in the Internet area with leading companies such as Cisco. I speak a little French and Japanese as a result of my travels and have a great appreciation for the rich cultures and incredible diversity that we have in the EMEA region. I see opportunity throughout EMEA and am excited to apply what I’ve learned to help Cloudflare expand and serve our customers here.

EMEA is a vast, diverse region encompassing approximately 120 countries across 3 continents with a huge variety of cultures, languages and backgrounds of its people. From large, influential countries like Germany, the United Kingdom and France to dynamic, innovative countries such as Sweden, Finland, and the Netherlands to fast-growing, emerging countries like Poland, the United Arab Emirates and South Africa there is a tremendous breadth of opportunity and demand for Cloudflare in these attractive and diverse markets.

Image courtesy of YourFreeTemplates

Our customers in EMEA are some of the most innovative and advanced in the world. Building on Cloudflare’s usual strengths around securing and making more performant our customers’ websites and digital assets, we are increasingly having new conversations with customers in their key areas of their innovation. For example, many companies in EMEA are at the forefront of the trend towards serverless computing and Cloudflare is enabling them on that path with Cloudflare Workers.  

Another area of focus is corporate security including identity and access management where Cloudflare Access is being deployed by a number of forward-looking organisations. Customers using additional network protocols such as UDP in the gaming industry and TCP in financial trading markets are leveraging Cloudflare’s Spectrum capability for enhanced security and network traffic handling. This exciting progress is leading our customers to enjoy increasing breadth of usage and strategic value from Cloudflare’s solutions.

On the security and privacy front, in the European market in particular, there is a strong focus on data privacy and GDPR (General Data Protection Regulations).  Cloudflare is closely engaged with policymakers at the European Union in Brussels to align with and influence these important policy developments.

Our customers continue to be from digital, online, born on the web/cloud sectors while increasingly we are also adding customers from more traditional corporate, and in many cases global, environments where Cloud-based services are seeing rapid adoption as these customers go through digital transformation. Multi-cloud is also an important theme in particular with larger customers who are diversifying away from a single Cloud provider. Cloudflare is well placed to serve customer needs around all these trends.

Here are a few of our exciting EMEA customer stories:  

• AO.com

• AllSaints

• AutoTrader

• Debijenkorf

• Eurovision

• Le Cab

• RTE

• All

London continues to be the base camp for our activities where we have a customer facing the team of approximately 100 people carrying out our activities supporting and developing customers. We have over 20 nationalities represented on the team and 29 and counting languages covered. It’s a diverse and committed team that is well aligned to the broad, diverse markets we serve. We represent a significant portion of Cloudflare’s business globally and are growing fast.

We’ve recently moved to a large new office space in a great location at London County Hall. In fact, we can see a number of our important customers in the UK public sector and corporate sector from our new office. We celebrated this new office opening with an event in April where our co-founders CEO Matthew Prince and COO Michelle Zatlyn both made the journey from San Francisco to co-host.  This new modern office space is well set up to receive existing and prospective customers as well as other key parties such as partners and developers in a professional and comfortable environment conveniently located in central London.

Alongside our customer-facing team in London is, of course, a significant portion of our global engineering team which is led by our CTO John Graham-Cumming. So, our customers and our employees benefit by having all elements of Cloudflare’s business from engineering to product management to all customers facing activities under one roof.

In 2018 we’ve added a second important customer-facing base in Munich, Germany to serve the Germany, Austria, and Switzerland (DACH) markets under the leadership of Stefan Henke. Our DACH team has been growing rapidly, approaching 20 people to support an exciting rate of new customer growth in the region.

We work with a number of committed channel partners throughout the region and are working to extend that cooperation while developing new partners such that we can best serve Cloudflare customers throughout the region. We’ve appointed a Head of EMEA Channel partnerships, Anwar Karzazi, who leads our team and activities building these partnerships in the region.  

The Cloudflare network is powered by data centers in over 180 cities around the world including 70+ in EMEA.  With our strong coverage In most parts of EMEA, we are typically able to process requests of our customers web site traffic very rapidly ensuring a great experience for their customers and visitors.

Our annual London Connect customer event is happening today at our County Hall location.  The event brings together our customers, prospective customers, partners, developers and other interested parties for a full day of information exchange and presentations focusing on the success our customers are having with Cloudflare solutions.   If you are already planning to attend, keep an eye on our Twitter account for schedule updates!

If you’re interested in exploring your career at Cloudflare, we are hiring in Europe and globally! Our team in London and in Munich is looking to expand across the region for roles including Account Executives, Business Development Representatives, Customer Success Engineering, Solutions Engineering, Technical Support, Network Engineering, Systems Reliability Engineering, Sales Operations and also in Product Development/Engineering and more. Check out our careers page to learn more!

I’m looking forward to helping Cloudflare grow substantially in EMEA in the coming years!

Thanks to everyone within Cloudflare who is helping us to build up a great EMEA business with the aim of serving our growing base of EMEA and global customers exceptionally well.  

If you are a Cloudflare customer in EMEA reading this, thank you and expect our continued innovation and commitment to you and your organisation. Thinking about becoming a customer? We’d love to have you with us. Our EMEA team looks forward to serving you and extending the value we bring to you in the future.

Today, Cloudflare can quantitatively confirm that Internet access has been shut down in the Democratic Republic of the Congo, information already reported by many press organisations. This shutdown occurred as the presidential election was taking place on December the 30th, and continues as the results are published.

Sadly, this act is far from unprecedented. We have published many posts about events like this in the past, including a different post about roughly three days of Internet disruption in the Democratic Republic of the Congo less than a year ago. A painfully familiar shape can be seen on our network monitoring platform, showing that the traffic in the country is barely reaching a quarter of its typical level:

Note that the graph is based on UTC and Democratic Republic of the Congo’s capital Kinshasa has the timezone of GMT+1.

The drop in bandwidth started just before midday on 31 December 2018 (around 10:30 UTC, 11:30 local time in Kinshasa). This can be clearly seen if we overlay each 24 hour day over each other:

The red line is 31 December, the gray lines the previous eight days. Looking at today’s overlay bandwidth graph, we can confirm this has continued and is an abnormal behaviour.

Other actors on the Internet have also been reporting similar figures. We hope that we can soon inform our readers the country is normally connected to the Internet again.

While 85 million people live in the country, very few people have internet access (6.21% according to Wikipedia’s List of countries by number of Internet users page). The country is also very large (2,344,858 square kms or 905,355 sq miles) and the 11th largest country in the world - around a quarter the landmass of the USA and nearly twice as big as South Africa. These facts play together and because of limited fiber deployment within the country; there are many places that still use very limited and expensive satellite Internet access. We can see in our bandwidth kgraphs that traffic to these satellite connected locations was not affected by this shutdown:

Note that the bandwidth levels are very low and represent a very small percentage of the overall traffic into Democratic Republic of the Congo.

Comparing that graph to the one from the largest mobile provider in the country; we clearly see the distinct cutoff.

15 months ago we wrote about an outage in Togo, were we noted that this adds Togo to the list of countries like Syria (twice), Iraq, Turkey, Libya, Tunisia, etc that have restricted or revoked Internet access. We have also written about unrest in Gabon (in 2016) and The Gambia (also in 2016). In Gambia’s case, the incumbent president lost the election! In fact we wrote “Rather than clamping down on the opposition by blocking the access to the Internet, it is quite possible that the blackout in Gambia may have infuriated voters and increased the vote against the president.”. Let’s see what happens in Democratic Republic of the Congo.

We'll update this blog once we see changes to these traffic levels. The Congolese government says they will restore internet access after election results are published on January 6th. That’s four days from now.

At Cloudflare, we’ll continue to do our part to try to ensure that vulnerable voices have access to the Internet. Cloudflare’s Project Galileo and Athenian Project help protect at risk websites -- such as those run by human rights organizations, journalists, and government entities reporting election results -- from being knocked offline by cyber attack.

We also support the principles for a Contract for the Web, which urge governments to commit to keeping all of the Internet available, all of the time, and Access Now’s #KeepitOn campaign. We can only hope that these efforts will yield more positive results in 2019.

According to a published report earlier this year, 84% of the Nigerian population own a mobile device (193 million population and 162 million mobile subscriptions). Again, that’s #1 for any country in Africa. But why so connected? Maybe because Nigeria (and Lagos specifically) is always on the move!

Lagos, as those that know the city say, never sleeps, it’s filled with color from the food to fashion to even the diverse people going about their business. The vibrancy of the city is like a hard slap to the face, no matter what you have been told, your first time here will still knock you out. In Lagos, anything is possible, from the sadness of poverty to the clearly visible upper class, the city sucks you in like a surfers dream wave. Visitor come into Lagos and leave feeling like they’ve been through a unique experience. The traffic is mind blowing and the same goes for the work pace.

Lagos, a city always on the move!

Cloudflare has now entered Lagos with a secure facility colocated and interconnected to one of the primary undersea cable operators along with a full connection to both the local Internet Exchange (IXPN) and the newly announced WAF-IX Lagos exchange. With every data center we add, local users not only connect faster and more reliably to sites proxied by Cloudflare, but our global DDoS mitigation becomes stronger and more robust.  Instead of serving Nigeria from Europe (London, Lisbon, etc), content can be delivered locally from Lagos.

If you follow the African telecom industry; then you'll know that West Africa’s economy is dominated by Nigeria; but few outside the region know that Nigeria is dominated by the phrase mobile-first. A country thats mobile-first means that mobile has eclipsed all other connectivity methods. Other countries with this status include Indonesia, China, Kenya, Philippines, Myanmar and many others. Being mobile-first doesn’t mean smartphone dominance (Myanmar qualifies because of the availability of $20 phones); but it does mean dependence on mobile infrastructure. In fact SMS or texting is still the number one common communications method for most of these places. But smartphone penetration in Nigeria is growing fast and sitting at around 21 million according to the recent report referenced above.

La la land has Hollywood, India has Bollywood and Nigeria has Nollywood. Yes, movie-making in Nigeria is a booming business with 1,500 or more movies produced a year and yet Nollywood is only twenty-five years old. That’s still less movies than Bollywood; but that doesn’t worry any of the Nigerian statisticians because they restate the revenue number based on a per-capita basis and that makes Nollywood bigger than Bollywood. But we digress.

The one thing that all that mobile penetration can provide is a distribution method for Nollywood’s movies and while this has nothing to do with Cloudflare’s commitment to Nigeria; it’s interesting to see that Netflix (the movie and tv streaming giant) has just invested heavily into Nollywood!

Even Hollywood has tapped Nigerians for major roles. David Oyelowo, the British actor of Nigerian descent, played Martin Luther King Jr. in the 2014 movie Selma. Danny Glover (of Lethal Weapon and The Color Purple fame) is of Nigerian descent and has acted in a Nigeria based movie called 93 Days. Then there’s Forest Whitaker (Last King of Scotland), John Boyega (Finn in Star Wars: The Force Awakens and The Last Jedi), and geek-favorite Richard Ayoade (Maurice Moss in the IT Crowd); all of Nigerian descent.

Lagos is well served by undersea cables that reach northwards to Europe and south towards South Africa. In fact every African west coast undersea cable lands in Lagos Nigeria.

• ACE (Africa Coast to Europe))

• Glo-1 (and Glo-2)

• MainOne

• NCSCS (Nigeria Cameroon Submarine Cable System)

• SAT-3/WASC

• WACS (West African Cable System)

While most of these cables are pumping bandwidth from North to South (i.e. Europe to Africa); some are now being used for inter-country connectivity at the IP backbone level. WACS has Nigeria, Angola, and South Africa connected. MainOne has Ghana and Nigeria connected, etc.

When we look at the Alexa-top-50 list for Nigerian users we find that 18 of those sites are Cloudflare customers. That means an instant win for both consumers (those smartphone users) and the website or app operators. BTW: of the remaining 32 sites, 15 are owned by massive content players (search, online video, social media, operating systems or phones) and of the remaining 17 sites (Wikipedia being one of highest visited on that list); they are mainly non-CDN’ed websites that are hosted outside the country (Europe or USA).

Cloudflare in West Africa far from finished! We still have places like Senegal, Côte d’Ivoire, and Ghana to do (just to name a few). As always, stay tuned as Cloudflare grows the network! Oh, and by now any regular reader of our blogs will know that we are growing, both in network deployment and in fantastic staff. So pop over to the jobs page and see what interests you!

Cloudflare’s mission is to help build a better Internet. To do that we operate datacenters across the globe. By having datacenters close to end user we provide a fast, secure experience for everyone. Today I’d like to talk about our datacenters in Africa and our plans to serve a population of 1.2 billion people over 58 countries.

Internet penetration in developed countries skyrocketed since the 2000s, Internet usage is growing rapidly across Africa. We are seeing a 4% to 7% increase in traffic month on month. As of July 2018, we have 8 datacenters on the African Continent:

• Angola

• Djibouti

• Egypt

• Kenya

• Mauritius

• Three in South Africa

While we see changes on the horizon, the majority of Internet content providers are located in North America and Western Europe. This means that only the billion people living in those areas close to the content they are trying to reach. When it comes to Africa, submarine cables will usually bring back the packets to Europe to hubs like Marseille, Paris, London, Lisbon and sometimes Frankfurt or Amsterdam, adding precious milliseconds, slowing down communications.

By setting up datacenters on the African continent, Cloudflare is able to serve content locally, increasing download speed in the region, improving the end-user experience, and ultimately increasing Internet usage.

We wondered if the Internet usage increased when we set-up a datacenter in a region which was previously not well served.

It was surprising to see a fast growth in the following months in each of the countries we turn on our equipment. We took into account bandwidth and also quantity of information exchanged. The increase in bandwidth usually leads to an increase in usage.

Bandwidth is the maximum rate information can be transferred over a link. The interpretation of maximum depends on the type of transmission.

The explanation why the rate is dependent on latency comes from the TCP protocol specification on which run most of the web applications. Every transmission ends with an acknowledgement, to determine if the data was correctly received. The next transmission will begin after the sender receives the acknowledgement. This means while the acknowledgement is transmitting, nothing is actually being received. The difference of data received over time is the transfer rate.

This is summarized in the following diagram:

With the most common algorithms, the amount of data sent before an acknowledgment increases until an error appears. Any link will drop packets: whether there is a transmission issue (wireless and perturbations) or a processing issue (router dropping packets to reduce load). This contributes never reaching the maximum bandwidth of a link. This is why above 80 milliseconds latency, performances start to worsen drastically. Coast to coast in the USA is around 70 milliseconds. Paris to London is 10 milliseconds. Satellites connections implement proxies to allow sustainable throughput despite 600 milliseconds round-time-trip.

The explanation is behavioral. If an Internet connection is slow and frustrating, chances are we will use it only if we are forced to. While getting access to the content immediately, people are likely to fetch more content and click on links.

The following chart shows the growth of requests from a country after every datacenter turn up. Traffic is normalized on the latest value (July 2018).

Djibouti shows the biggest increase in traffic after the launch.

For the rest of the continent, we are seeing a steady increase in delivered traffic over the last four years.

Overall, Sierra Leone is the country which grew the most at around 8% per month. At the opposite scale, Algeria only increased its traffic by 2% per month. The mean of all those countries is 6.2% per month, which is also the Internet traffic growth of South Africa.

In comparison to Europe, North America, it will take, at the current rate, 4 years and 3 months for Africa to reach today’s traffic levels of those two continents. However, if Europe, North America keeps its current 4% growth rate, then the African continent will take approximately eight to twelve years to catch up.

Please note these estimations are not perfectly representative as Cloudflare only see a part of the Internet and the numbers also includes our growing base of customers.

The units on the vertical axis represent the growth based on the initial ratio between Europe/USA/Canada and Africa.

We analyzed the latencies between Europe and African IP addresses that hit our edge. On the following Demer map from Vasco Asturiano, the area of the country is exponentially proportional to the response time in milliseconds.

All the coastal Africa is well connected with submarines cables. The only exception is Eritrea, where the main provider (EriTel) which uses two satellite providers for its outbound links.

The island of Saint Helena is on the path of the future SAex cable, but the only connection at the moment for its 5000 inhabitants is through satellite, causing a latency of 600ms.Central African Republic also uses satellite or connections through Cameroon.

On average a packet round trip from Northern Africa to Europe will take around 50-100ms while a round trip from the South will take 250ms.

Regarding inter-African routing, Africa has only a limited number of cities where interconnection happens successfully: Johannesburg in South Africa, Nairobi in Kenya, and Djibouti with datacenters and internet exchange points. The rest of the continent is mostly split between providers which will interconnect in Europe or Asia. Chances are, a user in Cameroon talking to a user in Ghana will likely go through Paris.

Using RIPE Atlas, we are able to show inter-provider routing usually happens in Europe. Only one traceroute showed packets being exchanged in South Africa.

Traceroute to two Ghana Atlas probes from other Atlas Probes

To Ghana only via Europe

To Ghana with one through South Africa

Cloudflare and many network operators are using extensively RIPE Atlas to determine performance and troubleshoot issues. If you want to help us improve Internet quality in Africa, become a probe host here.

What you may be wondering is: what are the countries in Europe that route the African traffic? We are using an anycast network ; when a user fetch a website on Cloudflare, the packets will take the shortest path seen by the router to reach its destination. In telecommunications, the shortest path does necessarily mean geographical proximity. The selection metric of a path usually involve cost and performance.

An anycast address will have the same metric everywhere on our side. This mean a service provider having links to London and Paris will see our IP addresses originating from London datacenter and Paris datacenter. The choice between the two will only be depending on metrics set by the provider: will it cost more to reach London?

Cloudflare has a significant number of points of presence to be able to show small metric differences. Due to the density of its network in Europe, it is common to have datacenters one hop away from each others (London and Paris, Paris and Amsterdam). Our analysis of the next-hop will show a provider’s preference.

In the case of Africa, a provider can rent capacity on submarine cable to a city, for instance Lisbon, Paris, London. Ideally, the provider wants to maximize the resources it can obtain without adding more hops (costlier).

Paris, London, Amsterdam and Frankfurt have a lot of content providers and interconnections options, the differences are going to be on the content. One major bias will be the language: France will have more francophone content hosted in Parisian datacenters, it also helps running operations to if both parties speak French.

As an example case: if Paris is chosen, for the content that can only be found in London, another provider will carry the packets to London from Paris, adding one hop to the path, reducing preference. We will see the landing point in Paris.

Why isn’t the provider getting a link to London? On thing to know is any Internet link has a flat rate price plus a variable rate based on consumption.

Bandwidth within major European cities is among the cheapest in the world. The flat rate for submarine capacity is high, as a result, the quantity of content that is available from London for cheaper than Paris has to make up the difference.

If you are interested to know more about the costs of bandwidth around the world, check out this article by Nitin Rao.

The following map represents the most common Cloudflare datacenter reached for each country. The countries filled with color are where Cloudflare datacenters are. The border color indicates the destination country.

As aforementioned, we can notice most of the French-speaking countries will tend to go towards our datacenter in Paris. South Africa remains well connected with its neighbors.

Previously, we mentioned there are some content providers in South Africa and Djibouti. We took a look at the popular news and banking websites.

Over the top 200 origins of the websites (Alexa ranking) for African countries in 2017, only 42 were attached to an African country and only 10 among those were serving non-education/government content (news websites, banks).They were located mostly in South Africa and Zimbabwe.

We also took a look at our 10 millions zones behind Cloudflare. The ones that are using Afrinic IPs are hosted in the following countries:

Only four countries out of sixty four are using IPv6 in a measurable way. Egypt (1%), Kenya (2%), Gabon (2%) and Zimbabwe (9%). In each of these countries we found that only one provider that deployed IPv6 at any significant scale. Since the beginning of the year, IPv6 usage in Egypt has doubled. In Gabon, a major provider rolled IPv6 at the end of December 2017.

As Mathieu Paonessa from Group Vivendi Afrique told us, “Gabon went from 0% to 2% IPv6 in only 9 months, following the opening of our CanalBox Gabon FTTH service.”

The timeline is similar with a small ISP in Kenya and has been increasing steadily. We can maybe hope they double their IPv6 usage by the end of 2018.

Compared to the rest of the world, Belgium is still ahead with 37%, followed by India at 35%. Most European countries are above 10%. USA is 22% and Canada is 15%.

One explanation for the small number of deployments is the size of the remaining IPv4 pool of addresses.

As of July 2018, there were 36,245 /24 available (approximately 9.2 millions IPs). The total Afrinic size is 6 /8 (approximately 100 millions IPs). 9% are left.

The following graphs shows the allocations and usage of each /24 in the Afrinic allocations.

This is the Hilbert graph of Afrinic IPv4 exhaustion. It was inspired by Ben Cartwright-Cox’s blog post and used masscan and ipv4-heatmap.

Prefix

Announced (yellow) vs Available (green) vs Reserved (red)

Response to ICMP (blue = low reply, red = all reply)

41.0.0.0/8

102.0.0.0/8

105.0.0.0/8

154.0.0.0/8

196.0.0.0/8

197.0.0.0/8

We notice that even if allocated, some blocks remain dark. 102.0.0.0/8 remains the range with the most IP space left in the world.

Africa is the largest continent on earth, yet it is very lagging behind on Internet connectivity and traffic levels. Historically it's been entirely relying on its European interconnections. However we predict that its traffic will outgrow EU and US by 2027. This will be enabled by the fast deployment of local content, IPv6, and alternative submarine cables.

We are working on deploying even more points of presence in Africa and increasing our current capacity in the existing ones. Fifteen new locations in the African continent are part of our global expansion plans. These include: Algeria (Algiers), Cameroon (Yaoundé), Congo (Kinshasa), Côte d’Ivoire (Abidjan), Egypt (Alexandria), Ghana (Accra), Kenya (Nairobi), La Réunion (Sainte-Marie), Madagascar (Antananarivo), Morocco (Casablanca), Nigeria (Lagos), Tanzania (Dar es Salaam), Tunisia (Tunis), Uganda (Kampala), and Zimbabwe (Harare)

Header image source

Our newest data centers in Durban (South Africa) and Port Louis (Mauritius) expand the Cloudflare network to 137 cities globally. We are delighted to reach this special milestone, and even more excited to help improve the performance and security of over 7 million Internet properties (and growing!) across 69 countries.

Just in March, so far, we've launched new data centers across Beirut, Phnom Penh, Kathmandu, Istanbul, Reykjavík, Riyadh, Macau, Baghdad, Houston, Indianapolis, Montgomery, Pittsburgh, Sacramento, Mexico City and Tel Aviv!

Just three years (and about 100 cities ago!), we launched our very first Africa deployment in Johannesburg (South Africa). It was an exciting day for members of our team to facilitate an especially substantial latency improvement for our customers.

Since then, we’ve turned up additional deployments in Cairo (Egypt), Cape Town (South Africa), Djibouti (Djibouti), Luanda (Angola), and Mombasa (Kenya).

Durban is our third deployment in South Africa, where mobile adoption continues to drive traffic growth amongst 20 million Internet users. Other countries with three (or more) Cloudflare data centers are Australia, Canada, China, Germany and United States (with two European states joining this list very soon!). In addition to better serving KwaZulu-Natal, our Durban data center will provide additional redundancy and expand the surface area for Cloudflare to withstand potential DDoS attacks. We are participants at two interconnection points: NAP Africa IX Durban and DINX (Durban Internet Exchange).

Photo by Jörg Angeli / Unsplash

Port Louis (Mauritius), which used to be served out of our Mombasa data center, will see the latency-equivalent of 1,500 miles shaved off on every web request. Mauritius welcomes 1.3 million visitors from world over to experience the idyllic island - as many visitors as the local population! Even if you’re traveling on vacation (and choose to go online!), we’d love to ensure that you access a Cloudflare data center close to you. The reduction in latency and improvement in availability result in higher throughput to visitors. We do already do more traffic to Port Louis today than we did from Johannesburg in late 2014.

Throughput to Mauritius Telecom visitors increases for millions of Cloudflare customers

Several additional Africa data centers are actively in the works, with many expected to go live in the second half of 2018. We are especially keen to partner with ISPs in Central and West Africa, including in countries such as Nigeria, where four of the ten most popular Internet properties are protected by Cloudflare.

Correctly guess at least five of the upcoming cities being turned up in March, and we’ll send you some Cloudflare gear.

This map reflects the network as of the publish date of this blog post. For the most up to date directory of locations please refer to our Network Map on the Cloudflare site.

Today, it appears that Internet access in the Democratic Republic of Congo has been greatly curtailed. The BBC reports that Internet access in the capital, Kinshasa was cut on Saturday and iAfrikan reports that the cut is because of anti-Kabila protests.

Our monitoring of traffic from the Democratic Republic of Congo shows a distinct drop off starting around midnight UTC on January 21, 2018. Traffic is down to about 1/3 of its usual level.

We'll update this blog once we have more information about traffic levels.

Update January 24, 2018

Internet access in the Democratic Republic of Congo looks to have been restored with traffic returning to typical levels after roughly three days of disruption.

Five fun facts:

• Cape Town is where the Atlantic Ocean and the Indian Ocean meet deep in the Southern Hemisphere.

• The city is the start of the Garden Route, a 185 mile (300 km) glorious coastal drive brimming with native flowers and stunning vistas.

• Cape Town is the gateway into the Stellenbosch and Franschhoek wine districts that make for very popular weekend excursions.

• The imposing Table Mountain can be seen from most of Cape Town. When you take the cable car to the top of the mountain, the view from up there is even more stunning.

• Cape Town is where Cloudflare has placed its 113th data center.

Back in December 2014, Cloudflare opened our first data center in Africa and our 30th datacenter globally. That was in Johannesburg, which has since seen over 10x growth in traffic delivered to South Africa and surrounding countries.

Now, we are expanding into our second city in South Africa — Cape Town, bringing us 870 miles (1,400km) closer to millions of Internet users. Only 15% smaller than Johannesburg by population, Cape Town commands a majority of the tourism business for the country.

For Cloudflare, our newest deployment reinforces our commitment to helping build a better Internet in South Africa and Southern Africa as a whole. Expanding on our existing peering at the JINX and NAPAfrica Internet exchanges in Johannesburg, we are now also a member at NAPAfrica Cape Town. As we enable the interconnections with in-country hosts and ISPs, we will distribute and optimize traffic delivery, while providing in-country redundancy for millions of Internet properties.

Cloudflare now operates six data centers across Africa. Cape Town joins existing facilities in Cairo (Egypt), Luanda (Angola), Mombasa (Kenya), Djibouti (Djibouti), and Johannesburg (South Africa).

In the graph below, Gauteng is the province containing Johannesburg and the nation's capital Pretoria, whereas the Western Cape province includes Cape Town and the aforementioned wine districts. With the second data center now operational in South Africa, we are seeing near equivalent performance over both major cities.

Latency (ms) decreases to Cloudflare customers. Source: Cedexis

Colombo and Cape Town are the first two of four data centers going live this week. Our next two deployments, yet to be revealed, will provide additional redundancy to existing facilities in North America. Can you guess the cities they are in?

CC-BY 2.0 image by Nelo Hotsuma

Curaçao is located in the Southern Caribbean Sea (just north of Venezuela) and has a strong Dutch heritage. Along with Aruba and Bonaire, Curaçao is part of the Lesser Antilles (they are called the ABC islands).

More importantly, Willemstad - the capital of Curaçao is where the Amsterdam Internet Exchange operates AMS-IX Caribbean. Why AMS-IX? Because of that Dutch relationship!

It’s AMS-IX’s goal (along with its local partners) to promote Curaçao as an interconnection location for the Caribbean. Cloudflare is there with all its services ready for that day!

Djibouti is a country of around 850,000 people with ~60% of the population living in the nation's capital, also called Djibouti. The country is about the same size as New Hampshire and its location (on the Horn of Africa) makes it a perfect location to bring ashore undersea fiber-optic cables.

Image of landing the EASSy cable, Djibouti, Feb. 2010 courtesy of WIOCC & EASSy

In fact, the number of undersea fiber-optic cables that have become active in the last five years along the coast of Africa is impressive. The African west coast has seen a boom and, the East African coast (where Djibouti is located) has seen even more of a boom with fiber-optic cables radiating outwards towards the Middle East, India, Asia, Southern Africa and Europe from Djibouti. The list of submarine fiber-optic cables that land at Djibouti seems to be increasing year-over-year. Recently the SeaMeWe-5 cable was brought into service. SeaMeWe stands for “South East Asia–Middle East–Western Europe”. It connects Marseille France (via a landing station in Toulon, France) through Egypt, into Djibouti, then across to Sri Lanka and finaly finishing up in Singapore. Interestingly, Cloudflare has data centers in four of those five locations.

SeaMeWe-5 courtesy of Submarine Cable Map from TeleGeography

Some of the existing undersea cables connecting Djibouti to the rest of the world include:

• Eastern Africa Submarine System (EASSy) connecting South Africa to Sudan via landing points including Djibouti.

• Europe India Gateway (EIG) connnecting India and UAE via Djibouti to the UK.

• Middle East North Africa (MENA) Cable System/Gulf Bridge International connecting Oman via Djibouti to Italy.

• SEACOM/Tata TGN-Eurasia connecting South Africa, India, Djibouti, Egypt and onto Europe.

• SeaMeWe-3 connecting Asia, India, Middle East and Europe via Djibouti.

• SeaMeWe-5 connecting Asia, Bangladesh, Sri Lanka, Middle East and Europe via Djibouti.

The undersea cable business is always busy. There’s the following undersea cables being built, planned (or just dreamed about):

• Asia Africa Europe-1 (AAE-1) RFS March 2017

• Australia West Express (AWE) RFS Q2 2018

• Djibouti Africa Regional Express (DARE) RFS May 2018

• Liquid Sea RFC 2018

Djibouti is also a vital communications gateway for landlocked countries like Ethiopia and South Sudan. Landlocked countries are highly dependent on their path towards an ocean for access to the global Internet. That makes Djibouti a perfect location to provide Cloudflare services for specific areas of Eastern or Central Africa.

Right next to the landing station in Djibouti is the Djibouti Internet Exchange (DjIX) which is located inside the Djibouti Data Center (DDC). They are separate buildings; however, highly interconnected. Cloudflare is a member of the DjIX and because of that internet exchange we expect to increase our connectivity up and down the East Coast of Africa.

If you’re interested to learn more about global undersea cables, look forward to a follow up deep dive (pun intended) blog post.

Back around the start of the 20th century, the French built a one-meter gauge railway between the Ethiopian capital of Addis Ababa and the deep-water port in Djibouti. This old railway was recently disbanded and finally last year it was replaced by the modern electrified Addis Ababa-Djibouti Railway. This standard gauge international railway connects Addis Ababa and the Port of Doraleh in Djibouti. It’s used for freight, passengers and communications. The two railways are somewhat parallel and are the perfect path for fiber-optic cables linking Addis Ababa and Djibouti and hence connecting Ethiopia to the rest of the world. It’s very common for railways to be associated with fiber-optic cables. Ethiopia's single telecom company (Ethio telecom) is connected via Djibouti’s single telecom company (Djibouti Telecom).

A long time ago the oceans were perceived as a barrier to efficient communications. Whilst they still represent significant distances and hence latency (the speed of light hasn’t changed as far as we can tell); they are not the economic barrier they once were. In fact, in some cases they can be very cost-effective at moving bits globally. Undersea cables have been pushing the barriers for Dense Wave Division Multiplexing (DWDM) and optical encoding for quite some time. A single fiber-optic cable can now encode data in the multi-Terabit range (16 or 32 Tbps is not complex to implement anymore). This eclipses anything that satellites can provide!

When an undersea cable surfaces (actually they are always buried, as they traverse the beaches on the ocean edges, before reaching the landing stations where the optical signal is converted into an electrical signal, as it ultimately reaches an Internet core router or Internet Exchange Point (IXP).

If you ever have the privilege of visiting a cable landing station, you’re in for a wonderful treat. Both the optical hardware and the power subsystems are normally some of the most interesting equipment in the Internet interconnection industry. Here’s Andrew Blum giving a TED talk about undersea cables from his book Tubes; a great introduction to undersea cables.

Earth (where Cloudflare is presently located) is tilted when compared to the Sun. This is why the sun rises and sets differently during the year. Two lines can be drawn around the globe because of this tilt. The Tropic of Cancer is in the Northern Hemisphere and it's counterpart, the Tropic of Capricorn in the Southern Hemisphere.

By Peter Mercator CC BY-SA 3.0

Both Curaçao and Djibouti are located between the Equator and the Tropic of Cancer; however, they aren't the only ones. Out of 109 datacenters so far, 20 are within these two lines. Here’s the list:

    Latitude     Longitude  IATA
  23°26'13"N   -----------   ---  Tropic of Cancer
  23°24'00"N   113°18'00"E   CAN  Guangzhou, China
  23°05'00"N   113°04'15"E   FUO  Foshan, China 
  22°38'00"N   113°49'00"E   SZX  Dongguan, China
  22°37'00"N   108°10'00"E   NNG  Nanning, China
  22°18'32"N   113°54'53"E   HKG  Hong Kong, Hong Kong
  19°05'19"N    72°52'05"E   BOM  Mumbai, India 
  14°30'31"N   121°01'10"E   MNL  Manila, Philippines
  13°40'52"N   100°44'50"E   BKK  Bangkok, Thailand
  12°59'40"N    80°10'50"E   MAA  Chennai, India
  12°11'20"N    68°57'35"W   CUR  Willemstad, Curaçao
  11°32'50"N    43°09'34"E   JIB  Djibouti, Djibouti
   9°04'17"N    79°23'00"W   PTY  Panama City, Panama
   6°09'52"N    75°25'23"W   MDE  Medellín, Colombia
   2°44'44"N   101°42'36"E   KUL  Kuala Lumpur, Malaysia
   1°21'33"N   103°59'22"E   SIN  Singapore, Singapore
   0°00'00"    -----------   ---  Equator
   0°06'48"S    78°21'31"W   UIO  Quito, Ecuador
   4°02'05"S    39°35'39"E   MBA  Mombasa, Kenya
   8°51'30"S    13°13'52"E   LAD  Luanda, Angola
  12°01'19"S    77°06'52"W   LIM  Lima, Peru    
  23°26'08"S    46°28'23"W   GRU  São Paulo, Brazil
  23°26'13"S   -----------   ---  Tropic of Capricorn

Just so, you the reader, are fully informed: our most northern data center is a close tie between Helsinki, Finland at 60°19'02"N and Oslo, Norway at 60°11'38"N coming in second. Our most southern data center is also somewhat close with Melbourne, Australia at 37°40'24"S and Auckland, New Zealand at 37°00'29"S followed by Buenos Aires, Argentina at 34°49'20"S coming in third.

Cloudflare has previously deployed into locations like Fujairah, UAE (just less than 100 miles from Dubai), Mombasa Kenya, and Marseille France, which are strongly associated with undersea cables. They all have multiple landing stations that are well-connected to data centers where Cloudflare (and Internet Exchange Points) are present. Even cities like Hong Kong, Singapore, Los Angeles, New York and Miami are associated with undersea landing cables. You can explore plenty of undersea cables using the Submarine Cable Map from TeleGeography.

According to Wikipedia, Binary-coded decimal (BCD) is a method of encodings decimal numbers where each decimal digit is represented by a fixed number of bits, usually four or eight.

This is used heavily by classic LED and LCD displays on alarm clocks, microwaves and other wonderful legacy electronics. In the days of TTL circuits, every self-respecting circuit designer would know how to build a BCD-based circuit. Here’s an example of BCD in action with a TTL circuit feeding a seven-segment LCD.

Image courtesy of and with permission of Nuts & Volts Magazine

Unrelated to anything binary, Cloudflare seems to like the letters B, C & D recently. In fact datacenter number 107 was Belgrade, number 108 is Curaçao and number 109 Djibouti. It seems we like the letters BCD so much that we have four more BCD data center cities presently being deployed. There’s one B, two Cs and one D within the upcoming weeks and months. Want to guess the cities? Here's a clue. Two north of the Equator, one close to the Equator and one quite south of the Equator. The Cloudflare deployment continues all over the globe!

If you’re interest in bringing the fast Internet infrastructure of Cloudflare into diverse locations like these, then check out the jobs we have listed online.

Gambia has a population of 1.8 million people, and according to World Internet Stats, Internet penetration is growing fast and is almost 20%. The latest statistics indicate that at least ten percent of Gambians are using Facebook. As shown in the graph below, on Thursday, the Gambian government cut off access to the global Internet and for 39 hours hundreds of thousands of Gambians were unable to use online services on which they rely every day.

All the networks in Gambia disappeared from the global routing tables. This could have been caused by a soft reconfiguration of Internet routers; or by a physical powering down of telecommunications equipment. At this point, we do not know. What we do know is that we didn’t see any routes or traffic (similar to other Internet companies reporting). We also read a large number of complaints on Twitter from people failing to communicate with friends and relatives within the country. When the routing was restored, we instantly saw traffic.

There's only one RIPE Atlas probe active within the country; however, it provides a good inside view of how the Internet behaved before, during and after the blackout. The large red area is the period when connectivity was unavailable.

Data courtesy of RIPE Atlas

The results of the Gambian election surprised a lot of people, including the incumbent President, Yahya Jammeh, who has been in power since he staged a coup 22 years ago. He received only 36.7 percent of vote, compared to Adama Barrow, a property developer, who won with 45.5 percent of the vote. Late Friday (after the Internet was re-enabled) President Jammeh conceded and Barrow supporters are celebrating in the streets. Celebrating both the results of the election along with (we are sure) the return of the Internet.

It is not clear why the Gambian government cut off access to the Internet. In other national Internet blackouts during elections, governments were attempting to thwart local efforts to monitor voting and report incidents of fraud - or prevent rumors from spreading.

Unfortunately, blocking Internet access also prevents citizen reporting of election-related violence, such as the hundreds of incidents that happened after the Kenyan election at the end of December, 2007. In Kenya, the Internet was not blocked and the online mapping tool Ushahedi was able to help Kenyans monitor and respond to the violence.

President Yahya Jammeh has been criticized for years for human rights violations and just last month decided to remove Gambia from the jurisdiction of the International Criminal Court, which has prosecuted a number of African leaders for war crimes and human rights violations. His decision to limit free speech of Gambians by blocking Internet access triggered a flood of criticism on social media and activists’ blogs around the world (E.g., Access Now has been highlighting Internet blackouts for years.) Freedom House doesn’t paint a pretty picture either.

Rather than clamping down on the opposition by blocking the access to the Internet, it is quite possible that the blackout in Gambia may have infuriated voters and increased the vote against the president. This is what happened in Egypt during the Arab Spring protests in January, 2011, when President Mubarak cut off Internet access for everyone but the Egyptian stock market. Unable to protest on social media, Egyptians, particularly the youth, went to the street, occupied Tahrir Square in Cairo, and started the protests that led to the overthrow of a dictator who had been in power for thirty years.

When only a few percent of a country’s citizens are online, an Internet blackout might stymie opposition to the government. But when the Internet is part of the daily lives of a significant portion of the population, it has the opposite effect.

On Tuesday, December 6, the United Nations’ Internet Governance Forum (IGF) will start in Guadalajara, Mexico. During it’s four days, more than 2,000 Internet experts will participate in more than a hundred panels on issues shaping the evolution of the Internet. Internet blackouts and censorship, which are becoming more and more common, will be on the agenda - as will other examples of where governments are trying to limit the new power to communicate and organize that the Internet gives activists - and everyone else. Cloudflare will have representatives at the meeting and engaging in the many discussions that will take place.

Cloudflare will continue to fight for free speech online, by deploying better and easier-to-use encryption and through programs like Project Galileo. We participate in events like the IGF and other fora like AccessNow’s RightsCon and the UN’s World Summit on the Information Society (WSIS) into order to fight for technologies and policies that will make the Internet more reliable and more open. Let’s hope dictators like President Jammeh are listening and start to understand that censoring and blocking the Internet is less and less likely to help them cling to power. Instead, they should try harnessing social media and the Web to build community, communicate to their supporters, foster democracy, and unleash entrepreneurship. THAT’S the path to a better future.

Each birthday has given us the opportunity to thank our customers with new announcements, from our automatic IPv6 Gateway to making SSL free and easy for all to unveiling our China network. Launching 14 new data center locations is one of many gifts to our users we’ll reveal this week.

Cloudflare global network (orange: new data center, purple: existing data center)

Six years ago, within weeks of Cloudflare launching, we passed a major milestone: serving one billion web requests across our network every month. Since then, our traffic has grown 10,000x, and we now see over a billion web requests every month just from the country of Angola — located on the western coast of southern Africa and three times the geographic size of California. This led us on a journey to deploy our newest data center in Luanda, the capital city, shaving 150ms in latency off every request and joining our existing Africa data centers in Cairo, Mombasa and Johannesburg.

Latency (ms) decreases 10x for an Internet user in Luanda to Cloudflare. Source: Cedexis

Angola has seen a 280x increase in Internet users over the past 15 years, growing to 6 million Internet people. This figure is already higher than Denmark, and growing ten times as fast. That said, even today, fewer than one in four Angolans are online so there’s huge potential for more growth ahead. We’re committed to building infrastructure across Africa and to supporting the next billion people coming online.

In the United States, where Internet penetration is significantly higher (~90%), our expansion continues as we announce the launch of seven data centers at one go: Boston, Las Vegas, Nashville, Omaha, Philadelphia, St Louis, and Tampa. Many of our customers are businesses and blogs alike serving visitors in these markets in US states with a combined population of over 50 million people. Our newest US data centers not only reduce latency for millions of websites, but also provide additional redundancy to each other and to our existing North America data centers in Ashburn, Atlanta, Chicago, Dallas, Denver, Los Angeles, Miami, Minneapolis, Montréal, Newark, Phoenix, San Jose, Seattle, Toronto, and Vancouver.

Cloudflare began as winners of the Harvard Business Plan competition in Boston, and the admission programs at both Harvard and MIT — two great Boston-based universities — are proud Cloudflare customers. We are very proud to now operate a data center in Boston. Since our last birthday, we have doubled both the number of data centers, and our aggregate edge capacity in North America.

Iberian peninsula (including Lisbon, Portugal) courtesy of NASA Earth Observatory

Our newest European data centers in Athens, Lisbon and Helsinki truly represent the breadth of the 750 million person continent, and join our existing datacenters in Amsterdam, Berlin, Brussels, Bucharest, Copenhagen, Dublin, Düsseldorf, Frankfurt, Hamburg, Kiev, London, Madrid, Manchester, Marseille, Milan, Moscow, Oslo, Paris, Prague, Sofia, Stockholm, Vienna, Warsaw, and Zürich. (To close observers of the Iberian peninsula photo, there is another major city displayed which is days away from having a live Cloudflare data center).

While our Buenos Aires, Argentina data center has held the record for being our southernmost deployment (34° S), Helsinki now takes the prize for our northernmost deployment (60° N), and becomes our third PoP within 500 miles (800 km) of the Arctic Circle.

Over 9,000 miles away (14,500 km), one of the farthest cities from Helsinki is the sunny city of Brisbane, Australia, also home to a new Cloudflare data center. This is our fifth data center in the region, joining Auckland, Melbourne, Perth and Sydney.

There is no excuse now for Telstra and Optus not to peer with us as we have physical presence in the four largest population centers in Australia.

Manila, Philippines. Source: Jensen Ching (Flickr)

New data centers in Manila and Shanghai further grow our Asia network to 37 unique cities, joining Bangkok, Chengdu, Chennai, Doha, Dongguan, Dubai, Foshan, Fuzhou, Guangzhou, Hangzhou, Hengyang, Jinan, Hong Kong, Kuala Lumpur, Kuwait City, Langfang, Luoyang, Mumbai, Muscat, Nanning, New Delhi, Osaka, Qingdao, Seoul, Shenyang, Shijiazhuang, Singapore, Suzhou, Taipei, Tokyo, Wuhan, Wuxi, Xi’an, Zhengzhou, and Zhuzhou.

Our global expansion is by no means done with these fourteen freshly deployed data centers, as we have twice as many additional cities in the works right now.

While new cities make for especially fun announcements, under the hood, we’ve been making a series of upgrades to prepare for the demands of the next generation of Internet-facing applications. These include:

• achieving high security and compliance standards

• deploying our newest generation of servers and networking gear

• growing our interconnection through both private peering and at more public internet exchanges than any other company, while doubling our network capacity to 10 Tbps (more than the publicly announced DDoS scrubbing capacity of all our competitors combined)

• increasing our availability by solving gnarly edge cases and deploying greater automation

Every Cloudflare server globally can perform all our features such as DDoS mitigation, DNS, HTTP2 support, SSL and our newest offerings to be announced later this week. We’re grateful for our customers’ support on our journey to these first 100 data centers, and look forward to the next 100.

－ The Cloudflare Team

CC BY-SA 2.0 image by Quinn Dombrowski

Two years ago, we previewed the relative cost of bandwidth that we see in different parts of the world. Bandwidth is the largest recurring cost of providing our service. Compared with Europe and North America, there were considerably higher Internet costs in Australia, Asia and Latin America. Even while bandwidth costs tend to trend down over time, driven by competition and decreases in the costs of underlying hardware, we thought it might be interesting to provide an update.

Since August 2014, we have tripled the number of our data centers from 28 to 86, with more to come. CloudFlare hardware is also deployed in new regions such as the Middle East and Africa. Our network spans multiple countries in each continent, and, sometimes, multiple cities in each country.

Traffic across 86 data centers in the CloudFlare network

There are approximately thirteen networks called “Tier 1 networks” (e.g., Telia, GTT, Tata, Cogent) who sell “transit” to access any of thousands of other networks on the Internet using their global backbones, including networks who are not their customers. We connect to networks by either purchasing transit from a global "Tier 1 network" (or major regional network), or by exchanging traffic directly with a carrier or ISP using “peering”. Typically, peered traffic is exchanged without settlement between the peered parties.

We try to make it as easy as possible for networks to interconnect with us. CloudFlare has an “open peering” policy, and participates at nearly 150 internet exchanges, more than any other company.

As a benchmark, let's assume the cost of transit in Europe and North America is 10 units (per Mbps). With that benchmark in place, without disclosing exact pricing, we can compare regions by transit cost, percentage of peering, and their effective blended cost (transit + peering).

Europe Transit vs Peering (Last 30 Days)

Based on our benchmark, the transit cost is 10 units. The region has a large number of Internet exchanges, typically non-profit, where we peer around 60% of our traffic. This makes for an effective regional cost of 4 units.

With perhaps the notable exception of the incumbent in Germany, many networks are supportive of open interconnection. CloudFlare already participates at 40 European internet exchanges, and is in the process of joining at least five more.

North America Transit vs Peering (Last 30 Days)

The cost of transit in North America is equal to the cost in Europe, or 10 units. We peer around 40% of our traffic, resulting in an effective regional cost of 6 units.

The level of peering in North America is less than in Europe, but a significant improvement over two years ago. The share of peered traffic is expected to grow. Some material changes have occurred and are occurring in the North American market, such as Frontier acquiring Verizon FiOS customers in three U.S. States and Charter preparing to merge with Time Warner Cable. We can see these changes making an impact to the regional interconnection landscape.

Notably, our peering has particularly grown in smaller regional locations, closer to the end visitor, leading to an improvement in performance. This could be through private peering, or via an interconnection point such as the Midwest Internet Cooperative Exchange (MICE) in Minneapolis.

Africa Transit vs Peering (Last 30 Days)

Transit prices in Africa are amongst the highest in the world at 14 times the benchmark or 140 units, with notable variance across the continent, from Cairo to Mombasa to Johannesburg. Fortunately, of the traffic that we are currently able to serve locally in Africa, we manage to peer about 90% (with a mix of carriers and ISPs), making for an effective cost of 14 units.

Our African deployments help us avoid the significant latency of serving websites from London, Paris or Marseille. A particularly promising but challenging region where we hope to deploy a CloudFlare data center is West Africa - specifically Nigeria, which is already at just under 100 million Internet users.

Middle East Transit vs Peering (Last 30 Days)

CloudFlare currently has four data centers in the Middle East, each of which are cache deployments with strategic ISP partners to serve their respective customers. We are able to peer all the traffic currently served from these data centers. While these collectively provide significant coverage, there is additional traffic (reaching Europe) that we would like to localize in the region. We hope that the remaining ISPs, such as Saudi Telecom Company, deploy similar caches, and enhance the performance of their customers.

Because we can peer 100% of our traffic in the Middle East, our effective pricing for bandwidth in the region is 0 units. There are, of course, other costs to delivering our service beyond bandwidth. However, by driving up peering rates in the Middle East we’ve been able to make our service in the Middle East extremely cost competitive.

Asia Transit vs Peering (Last 30 Days)

In Asia (excluding the Middle East), transit costs 7 times times the benchmark, or 70 units. However, we peer about 60% of our traffic, resulting in an effective cost of 28 units.

Beyond the major meeting points in Hong Kong, Singapore and Tokyo, a significant portion of our interconnection is localized to take place closer to visitors in cities such as Bangkok, Chennai, Kuala Lumpur, Mumbai, Osaka, New Delhi, Seoul, and Taipei. These statistics do not include our network of strategically located data centers inside of mainland China, where the dynamics of interconnection are entirely unique.

Two Asian locations stand out as being especially expensive: Seoul and Taipei. In these markets, with powerful incumbents (Korea Telecom and HiNet), transit costs 15x as much as in Europe or North America, or 150 units.

South Korea is perhaps the only country in the world where bandwidth costs are going up. This may be driven by new regulations from the Ministry of Science, ICT and Future Planning, which mandate the commercial terms of domestic interconnection, based on predetermined “Tiers” of participating networks. This is contrary to the model in most parts of the world, where networks self-regulate, and often peer without settlement. The government even prescribes the rate at which prices should decrease per year (-7.5%), which is significantly slower than the annual drop in unit bandwidth costs elsewhere in the world. We are only able to peer 2% of our traffic in South Korea.

If you include HiNet and Korea Telecom in our blended bandwidth pricing, and take into account peering, our effective price is 28 units. If you exclude HiNet and Korea Telecom, our effective price is 14 units.

South America Transit vs Peering (Last 30 Days)

Transit prices in South America are very high, costing 17 times the benchmark, or 170 units. We peer about 60% of traffic in South America, making for an effective cost of 68 units.

One of the reasons that transit prices are high is that the Tier 1 networks which are newer entrants to this region have yet to pick up significant market share. While markets such as Brazil are less expensive and have greater peering, costs are highest in countries such as Peru and Argentina where, in each, a single incumbent provider, respectively Telefonica and Telecom Argentina, controls access for the last mile delivery of content to the majority of Internet users.

As we try to increase our share of peered traffic, one of the challenges we face is that many Internet exchanges (e.g., NAP Colombia) only permit domestically incorporated and licensed networks to publicly peer, or in another case, require a unanimous vote of all members on an IX to permit a new participant, effectively creating a separation between “international content” and “domestic content”.

If you include Telecom Argentina and Telefonica, our blended cost of bandwidth in South America is 68 units. If you exclude these two providers then our blended cost is 17 units.

Oceania Transit vs Peering (Last 30 Days)

Transit prices in Oceania (Australia and New Zealand) are lower than they used to be, but continue to be extremely high in relative terms, costing 17 times the benchmark from Europe, or 170 units. We peer 50% of our traffic, resulting in an effective cost of 85 units.

If you exclude Optus and Telstra, then the price falls to 17 units — because we peer with nearly everyone else.

Relative Cost of Bandwidth

CloudFlare has always optimized where we serve customers to take into account our effective costs. If you are a free customer using an excessive amount of expensive transit, we would serve you from fewer regions. The good news is that, over the last five years, we’ve been able to negotiate reasonable transit pricing or settlement-free peering with the vast majority of the world’s networks. That allows us to continue to provide the free version of our service as well as to keep prices low for all our paid services.

Today, however, there are six expensive networks (HiNet, Korea Telecom, Optus, Telecom Argentina, Telefonica, Telstra) that are more than an order of magnitude more expensive than other bandwidth providers around the globe and refuse to discuss local peering relationships. To give you a sense, these six networks represent less than 6% of the traffic but nearly 50% of our bandwidth costs.

While we’ve tried to engage all these providers to reduce their extremely high costs and ensure that even our Free customers can be served across their networks, we’ve hit an impasse. To that end, unfortunately, we’ve made the decision that the only thing that will change these providers’ pricing is to make it clear how out of step they are with the rest of the world. To demonstrate this, we’ve moved our Free customers off these six transit providers. Free customers will still be accessible across our network and served from another regional cache with more reasonable bandwidth pricing.

Ironically, this actually increases the cost to several of these providers because they now need to backhaul traffic to another CloudFlare data center and pay more in the process. For instance, if Telstra were to peer with CloudFlare then they would only have to move traffic over about 30 meters of fiber optic cable between our adjoining cages in the same data center. Now Telstra will need to backhaul traffic to Free customers to Los Angeles or Singapore over expensive undersea cables. Their behavior is irrational in any competitive market and so it is not a surprise that each of these providers is a relative monopolist in their home market.

If you’re a Free CloudFlare customer who cares about optimizing the best possible performance from one of these six providers then we encourage you to reach out to them and encourage them to follow a core principle of a free and open Internet and not abuse their monopoly position. We are committed to serving all our customers across every network that peers with us. To that end, help us convince these six networks to be on the right side of a free and open Internet by reaching out to your ISP.

• Ask HiNet to peer with CloudFlare in Taipei

• Ask Korea Telecom to peer with CloudFlare in Seoul

• Ask Optus to peer with CloudFlare across Australia

• Ask Telecom Argentina to peer with CloudFlare in Buenos Aires

• Ask Telefonica to peer with CloudFlare across South America

• Ask Telstra to peer with CloudFlare across Australia

We’ll post updates as we negotiate with these six networks and are hopeful that we’ll soon be able to serve all our customers across all the networks we interconnect with.

Photo sources: On The Go (Flickr) and Cedexis; images used under creative commons license.

It’s been a big year of expansion for CloudFlare’s global network as we added new data centers across six continents, and we’re certainly not done. Today we announce the launch of our newest data center in Cairo, Egypt and a partnership with Telecom Egypt. This marks our third data center in Africa, after Johannesburg and Mombasa, and our 74th data center globally.

For many years, CloudFlare has been trusted by Egyptian websites to be protected from attacks.

Over half of the 20 most popular websites in Egypt already use CloudFlare to be safe, and are now seeing a 2x improvement in performance.

Reduced latency to Egypt's largest network, Telecom Egypt

Just like in Egypt, we partner with ISPs globally by deploying caches directly into their facilities. These points of presence help major networks improve the performance of millions of websites, reduce their costs and capacity used in accessing our customers' content, and provide a direct local interconnect with critical Internet infrastructure. If you are a carrier or Internet service provider in Egypt, elsewhere in Africa or anywhere around the world that would like to request a CloudFlare cache deployment, please reach out to our peering team.

As 2016 approaches, we already have new data centers in the works on every inhabited continent. Which will be next?

Photo source: AMS-IX

Only two weeks after the announcement of our four new points of presence (PoPs) in the Middle East, it is with much hullabaloo that we announce our 43rd PoP, and second in Africa following Johannesburg, in Mombasa, Kenya (a.k.a. “The Castle”). In a challenge that vexed many of our readers, Mombasa is our first PoP to be located in a real life castle-turned-data center (see above). From this castle CloudFlare is already serving networks in every country across East Africa, with reach to many of the region's 30 million+ Internet users.

While today it feels as if Internet access is ubiquitous, this is most certainly not the case everywhere. The continent of Africa was connected relatively late to the Internet and, in the first years, access was limited to a small segment of the population due to lackluster investment and growth in underlying Infrastructure, and high access costs. Most Africans were also without access to broadband Internet, and were largely limited to viewing content created and hosted half a world away—for the same reason there was little access, there was also no local hosting industry to speak of. By now, if you’ve followed our blog, you know that locating content and applications far away from users is a recipe for latency (i.e. the Internet in slow motion). With CloudFlare, your content and applications are automatically served from the closest PoP in our global network directly to your users.

Fortunately, over the past several years, Africa in general, and East Africa in particular, has seen tremendous growth in the underlying Internet Infrastructure including the arrival of many submarine cable systems. International Internet bandwidth in the region has multiplied twenty-fold in the past 5 years alone. At the same time, an increasing number of Africans now have access to the Internet, reaching a milestone of 20% Internet penetration, a level that is considered the minimum to enable a country to get significant economic benefit from an Internet economy. This is something we’re fortunate to witness (and facilitate) first hand. Entrepreneurs throughout Africa, many of whom are CloudFlare customers, are beginning to seize on the opportunities afforded by Internet access.

To build on this growing momentum, and to continue to foster the development of the African Internet ecosystem, we’re pleased to announce our first deployment in East Africa. Prior to now, traffic to CloudFlare customers from East African countries was largely served from our London and Amsterdam data centers with round trip latency of 150-350ms or, in some cases, with better latency from our data center in South Africa. As of now, our Mombasa site is serving traffic to networks in Kenya, Tanzania, Rwanda, Uganda, Ethiopia and even Mauritius (among many others).

CloudFlare's new home in the SEACOM cable landing station in Mombasa, Kenya (Photo Source: AMS-IX)

As the latency measurements demonstrate below (note: all measurements represent round trip time to the closest CloudFlare PoP in milliseconds), in Uganda, latency has decreased from as high as 150ms to the closest CloudFlare PoP to 20ms, a 7.5x improvement.

The same can be seen in Tanzania where latency has decreased from 150ms to just under 15ms (another 7.5x improvement!).

Source: Measurements from RIPE Atlas

Even though access costs (i.e. the cost of Internet bandwidth) remain extremely high across Africa, we continue to work with local partners to expand and amplify these benefits throughout the continent. If you are an Internet operator that would like to bring the benefits of CloudFlare to your network—whether in Africa or globally—or are simply curious about how this network expansion can help your organization, get in touch with our team.

—The CloudFlare team

Fire up the celebration braai, Jozi! CloudFlare is here, and it’s a big one. An important milestone (our 30th data center) calls for an equally important new location: Johannesburg, South Africa, our first data center in Africa.

For the local audience: Steek aan 'n braai ter viering, Jozi! CloudFlare is hier en dis 'n groot een. 'n Belangrike mylpaal (ons 30ste datasentrum), vra vir ewe belangrike en nuwe ligging: Johannesburg, Suid-Afrika, ons eerste datasentrum in Afrika.

Prior to now nearly all CloudFlare traffic delivered to Africa was served from our London, Amsterdam and Hong Kong data centers with round trip latency of 200-350ms. Bandwidth in the region is notoriously expensive (it would make even the Australians blush) making it prohibitive to enter into the continent. That is, before now. Just a few months ago we were fortunate to enter into discussions with a number of partners in the region that share CloudFlare’s vision to help build a better Internet.

Our Johannesburg data center will not only make sites on CloudFlare more performant for Internet users in South Africa, but also for Internet users across all of Southern Africa (and beyond). From Botswana to Kenya, users across the region will see a significant performance improvement when visiting any site or mobile app using CloudFlare.

As the latency measurements below demonstrate, our data center in Johannesburg is already delivering serious performance improvement across all of Southern Africa. In South Africa itself, latency has decreased from over 300ms to as low as 3ms, a 100x improvement.

The same is true from the network of Telkom, the local South African incumbent, where latency decreased from 200ms to as low as 13ms (15x improvement).

In Zambia, latency has decreased from over 200ms to 28ms (7x improvement).

And even Kenya, nearly 2,400 miles (3,800 kilometers) from South Africa, has seen latency decline from 150ms to 71ms (2x improvement).

Source: Measurements from RIPE Atlas

Internet penetration, broadband subscriptions, IXP deployment and overall available bandwidth in Africa are measurably lower as compared to the rest of the world. But this is quickly changing. It is with great satisfaction that we do our part to help bridge the digital divide. We hope you enjoy this news as much as we had making it all happen.

Special thanks to South African CloudFlare engineers Albert and Gerhard for all translations