Enterprise organizations critically depend on the reliability of services offered by ISPs, cloud providers, and conferencing services. ThousandEyes, which is part of Cisco, keeps track of how these providers manage performance issues, providing a weekly roundup of events that influence service delivery for Network World. Make sure to return next week for more updates.
(We’ve stored updates from previous years, including the 2023 outage report as well as our coverage during the Covid-19 years, a period during which we started monitoring the performance of cloud providers and ISPs.)
ThousandEyes documented 227 global network outage incidents across cloud service provider networks, ISPs, collaboration app networks, and edge networks (which include DNS, content delivery networks, and security as a service) during the week of May 13-19. That’s a significant 43% rise from 159 outages the previous week. Specifically in the U.S., we recorded 84 outages, a 27% increase from 66 outages the previous week. The following is a category breakdown:
ISP outages: Worldwide, ISP outages increased by 50%, rising from 105 to 157 outages, compared with the previous week. In the U.S., we saw a 43% increase in ISP outages, rising from 40 to 57 outages.
Public cloud network outages: The number of network outages provided by public cloud globally increased from 18 to 33 outages. In the U.S., a rise was observed from nine to 10 outages.
Collaboration app network outages: Globally, a reduced number of network outages in collaboration apps was noted as it decreased from seven to six outages. However, in the U.S., an increment from two to three outages was reported.
On May 19, a multinational transit provider based in the U.S., Cogent Communications, encountered an outage. This outage affected multiple downstream providers as well as Cogent customers across various regions including the U.S., the U.K., Mexico, Spain, Singapore, Brazil, Turkey, Germany, Switzerland, the Netherlands, China, Portugal, Chile, Peru, Canada, India, Thailand, South Korea, France, and Japan. The outage lasted for 19 minutes and commenced around 4:55 PM EDT. It began with Cogent nodes situated in Nashville, TN. Five minutes after the outage was observed, the problem extended to the nodes located in Houston, TX, Atlanta, GA, New York, NY, Washington, D.C., and Philadelphia, PA. The expansion of nodes with outage conditions continued including nodes in Bilbao, Spain, Dallas, TX, Phoenix, AZ, Charlotte, NC, and Indianapolis, IN. Consequently, a rise in impacted customers and providers was noticed. Resolution of the outage was seen around 5:15 PM EDT. For an interactive study, click here.
On May 16, Rackspace technology, a managed cloud computing provider in the U.S., based in San Antonio, Texas, experienced a series of outages. These outages lasted for a period of four hours and fifteen minutes, affecting multiple downstream providers as well as Rackspace customers in the U.S., Canada, Mexico, Germany, Singapore, Chile, Brazil, France, Spain, South Africa, Vietnam, Turkey, and Switzerland. The entire outage observed lasted for 28 minutes. It started around 5:00 AM EDT and the problem seemed to be centered on Rackspace nodes situated in Chicago, IL. The solution of the outage was reported around 9:15 AM EDT. For an interactive analysis, click here.
ThousandEyes documented 159 network malfunction incidents worldwide, spanning ISPs, cloud service providers, collaborative application networks and edge networks (including DNS, content delivery networks, and security as a service) during the week of May 6-12. This is a 5% decrease from the previous week’s 151 incidents. In the U.S, there were 66 incidents, marking a 32% increase from the previous week’s 50 incidents. Here’s the data categorized by type:
ISP Incidents: On an international scale, the number of ISP incidents fell from 113 to 105, a 7% decrease compared to the previous week. However, in the U.S., the number of ISP incidents slightly rose (3%) from 39 to 40.
Public Cloud Network Incidents: Globally, incidents in cloud provider networks escalated from 15 to 18. In the U.S, incidents in cloud provider networks greatly increased, shooting up from two to nine incidents.
Collaboration App Network Incidents: Worldwide, incidents involving collaboration application networks saw a decrease from nine to seven. But in the U.S. the number dipped from three to two incidents.
Time Warner Cable, an ISP based in the U.S., faced a disruption on May 8, affecting numerous customers and partners throughout the country. The outage started around 7:45 PM EDT, particularly impacting the Time Warner Cable nodes situated in New York, NY. Five minutes into the disruption, more nodes in New York were witnessing the outage conditions. The total duration of the outage was approximately 23 minutes, with services resuming around 8:10 PM EDT. For a detailed view, click here.
Comcast Communications also experienced an outage on May 7, which had a significant impact on multiple partners and customers across the U.S. and Canada. The outage initially observed around 1:20 AM EDT, mainly affected the Comcast nodes in Chicago, IL and Ashburn, VA. However, within five minutes, the nodes in Ashburn, VA seemed to have recovered, leaving the nodes in Chicago, IL under outage conditions. The decrease in nodes with outage conditions seemed to align with a reduction in affected customers and partners. The services were restored around 1:30 AM EDT. For more information, click here.
During the week of April 29 to May 5, ThousandEyes registered a total of 151 global network outage events spread across ISPs, cloud service provider networks, collaboration app networks, and edge networks (this includes DNS, content delivery networks, and security as a service). This number is slightly down by 3% compared to the 156 outages reported the preceding week. Specifically, in the U.S., the number of outages was 50, representing a 7% decline from the 54 reported a week earlier. Details categorized as follows:
The number of ISP outages globally saw an increase from 104 to 113, a 9% surge compared to the preceding week. Whereas in the U.S., ISP outages showed a 5% growth, from 37 to 39 outages.
Public cloud network outages: Globally, there was a reduction in cloud provider network outages from 22 to 15 outages. There was also a decrease in the U.S., from six to two outages.
Collaboration app network outages: There was a slight increase in global collaboration app network outages, from eight to nine outages. However, in the U.S., there was a decrease from four to three outages.
On April 29, NTT America, a global Tier 1 ISP and subsidiary of NTT Global, suffered an outage impacting its customers and downstream partners in various regions. Affected areas included the U.S., Japan, South Korea, China, Taiwan, Singapore, the Netherlands, Hungary, Turkey, Brazil, India, Argentina, Australia, the U.K., Thailand, Malaysia, Mexico, and Canada. The outage lasted 24 minutes, beginning around 2:40 PM EDT. The outage initially affected NTT nodes located in San Jose, CA. About five minutes into the outage, the San Jose nodes cleared, but Tokyo, Japan nodes started showing outage signs. These were joined by nodes in Osaka, Japan, Singapore, Dallas, TX, and Los Angeles, CA. The outage ended approximately at 3:05 PM EDT. For an interactive view, click here.
Similarly, on April 29, Cogent Communications, a US-based multinational transit provider, had an outage. This affected many downstream providers and customers across several regions, including the U.S., Brazil, the U.K., Canada, Chile, Mexico, Japan, Germany, Spain, and France. The outage lasted one hour and 12 minutes and happened in two stages, with a gap of 35 minutes. The first signs of the outage were seen around 2:45 AM EDT, focusing on Cogent nodes located in Ashburn, VA, and Washington, D.C. Five minutes later, these nodes cleared but nodes located in Baltimore, MD, New York, NY, and Phoenix, AZ, started to show signs of outage. There seemed to be an increase in the number of impacted downstream customers, partners, and regions. After appearing to clear, nodes in New York, NY, and Washington, D.C., along with Houston, TX, went into outage conditions. The problem was resolved around 3:20 AM EDT. For an interactive view, click here.
ThousandEyes reported 156 global network outage events across ISPs, cloud service provider networks, collaboration app networks and edge networks (including DNS, content delivery networks, and security as a service) during the week of April 22-28. That’s a dip by 8%, compared to the 170 outages from the preceding week. For the U.S., the figure stood at 54 outages, down by 36% from 85 reported in the week prior. The statistics below elaborate on this, categorized accordingly:
ISP outages: Globally, ISP outages experienced a jump of 5%, from 99 to 104. However, the U.S. observed a decline in the number of ISP outages by 31%, falling from 54 to 37.
Public cloud network outages: In terms of global statistics, cloud provider network outages held steady as compared to the previous week, numbering at 22. On U.S. soil, the figure fell from 10 to six.
Collaboration app network outages: Globally, collaboration app network outages fell from nine to eight. The U.S., meanwhile, reported a steady figure from the week before: of four outages.
Time Warner Cable, a U.S. ISP, encountered a disruption on April 26, affecting many customers and partners across the country. The disturbance took place over two instances in a 25-minute interval. It first came to light around 7:45 PM EDT, seemingly focusing on New York-based Time Warner Cable nodes. Roughly ten minutes after initial detection, the number of nodes in New York displaying outage conditions rose. The outage persisted for 17 minutes and was resolved around 8:10 PM EDT. An interactive view is available here.
NTT America, a global Tier 1 ISP and a subsidiary of NTT Global, had an outage on April 24 that affected some of its customers and downstream partners in several regions, such as the U.S., Germany, India, China, Hong Kong, Canada, and Japan. The outage lasted for 9 minutes and was noticed around 7:15 AM EDT. It appeared to begin at the NTT nodes situated in San Jose, CA. About five minutes into the outage, nodes in Dallas, TX, also indicated outage conditions. The outage was rectified around 7:25 AM EDT. An interactive view is available here.
The week of April 15-21 saw ThousandEyes report 170 global network outage events spanning ISPs, cloud service provider networks, collaboration app networks, and edge networks, marking an 11% increase from the previous week’s 161 outages. Outages in the U.S. also increased from 72 to 85, marking an 18% increase. Here is the breakdown by category:
Globally, ISP outages decreased from 107 to 99, a 7% decline from the previous week. Conversely, in the U.S., ISP outages increased by 6% from 51 to 54.
Public cloud network outages: Both globally (22) and in the U.S. (10), cloud provider network outages remained the same as the week prior.
Collaboration app network outages: Globally, collaboration app network outages increased from five to nine outages. In the U.S., collaboration app network outages increased from two to four outages.
On April 20, Cogent Communications, a multinational transit provider based in the US, experienced an outage that impacted multiple downstream providers and its own customers across various regions, including the US, Canada, Portugal, Germany, the Netherlands, Luxembourg, South Africa, Hong Kong, Singapore, the U.K., Italy, France, and Spain. The outage, lasting a total of one hour and 32 minutes, was divided into a series of occurrences over a period of two hours and 28 minutes. The first occurrence was observed around 10:55 PM EDT and initially seemed to be centered on Cogent nodes located in Seattle, WA, Portland, OR, and Hong Kong. Five minutes into the outage, the nodes located in Hong Kong appeared to clear and were replaced by nodes located in Minneapolis, MN, and Cleveland OH, in exhibiting outage conditions. Thirty-five minutes into the first occurrence, the number of nodes exhibiting outage conditions increased to include nodes located in Seattle, WA, Washington, D.C., Minneapolis, MN, Cleveland, OH, Boston, MA, and Bilbao, Spain. This increase in nodes exhibiting outage conditions also appeared to coincide with an increase in the number of downstream customers, partners, and regions impacted. A second occurrence was observed around five minutes after the issue initially appeared to have cleared. This second occurrence lasted approximately fourteen minutes and seemed to initially be centered around nodes located in Cleveland, OH. Around five minutes into the second occurrence, nodes located in Cleveland, OH, appeared to be temporarily replaced by nodes located in Seattle, WA, and Chicago, IL, before they themselves were replaced once again by nodes located in Cleveland, OH. Around 15 minutes after appearing to clear, a third occurrence was observed, this time appearing to be centered around nodes located in Bilbao, Spain, and Cleveland, OH. The outage was cleared around 1:25 AM EDT. Click here for an interactive view.
On April 17, NTT America, a global Tier 1 ISP and subsidiary of NTT Global, experienced an outage that impacted some of its customers and downstream partners across multiple regions including the U.S., the U.K., the Netherlands, and Germany. The outage, lasting 17 minutes, was first observed around 2:55 AM EDT and appeared to initially center on NTT nodes located in Seattle, WA. Five minutes into the outage nodes located in Seattle, WA, were joined by nodes located in Dallas, TX, in exhibiting outage conditions. The outage was cleared around 3:15 AM EDT. Click here for an interactive view.
ThousandEyes reported an increase of 161 global network outage events across ISPs, cloud service provider networks, collaboration app networks, and edge networks (incorporating DNS, content delivery networks, and Security as a Service), during the week of April 8-14. This is an 11% increase from the 154 outages experienced in the previous week. In the U.S., the number of outages was 72, marking an increase of 4% from 69 outages recorded in the preceding week. Below is a category-based breakdown:
ISP outages: The count of global ISP outages rose from 97 to 107, indicating a hike of 10% compared to the week before. In the U.S., ISP outages have witnessed a rise of 13% from 45 to 51 outages.
Public cloud network outages: Globally, the frequency of cloud provider network outages ascended from 16 to 22 outages. However, in the U.S., there was a decline from 14 to 10 outages.
Collaboration app network outages: On the global front, the number of collaboration app network outages retained their previous level, registering 5 outages. Whereas in the U.S., collaboration app network outages decreased from three to two outages.
On April 8, the American managed cloud computing provider, Rackspace Technology, suffered an outage. This affected several downstream providers and the Rackspace customers in numerous regions such as the U.S., Japan, Vietnam, Spain, Canada, Germany, Singapore, France, the Netherlands, the U.K., Brazil, and South Africa. The nodes of Rackspace located in Chicago, IL, initially seemed to be the center of this 14-minute outage that began approximately around 9:00 AM EDT. Roughly five minutes into the outage, there was a decrease in the number of impacted nodes in Chicago, IL accompanied by a reduction in the number of affected regions. Around 9:15 AM EDT, the outage was resolved. An interactive view can be found here.
A Tier 1 ISP, GTT Communications, faced an outage on Apr 10. Their partners and customers across many regions, such as the U.S., the U.K., Brazil, and Canada, were affected. The nodes of GTT positioned in Los Angeles, CA, initially seemed to be the center of this 9-minute outage that started around 8:10 AM EDT. Approximately five minutes into the outage, nodes in Los Angeles appeared to have been fixed though nodes in New York, NY were experiencing outage conditions. This shift seemed to coincide with an increased number of impacted regions, downstream partners, and customers. Around 8:20 AM EDT, the outage was resolved. An interactive view of this can be found here.
Between April 1-7, ThousandEyes reported a total of 145 global network outage events. This is an increase of 23% from 118 outages the previous week. These events were spread across various ISPs, cloud-based networks, app networks for collaboration, and edge networks (comprising of DNS, content delivery networks, and security as a service). The U.S. in particular had 69 outages, 21% higher than the 57 outages in the previous week. The following details the breakdown by category:
ISP outages: both globally and in the U.S., ISP outages displayed an increase of 45% compared to the previous week. Globally, the number rose from 67 to 97, and in the U.S., it increased from 31 to 45 outages.
Public cloud network outages: Globally, the occurrence of network outages within cloud providers saw a slight decrease from 17 to 16. In the U.S., the statistic remained stable at 14, exhibiting no change from the previous week.
Collaboration app network outages: Globally, network outages in collaboration apps saw a sharp reduction, transitioning from 13 to merely five reported outages. Within the U.S., these types of outages dropped from a total of eight down to only three.
As of April 2, network transit provider Hurricane Electric, based out of Fremont, CA, reported a network outage that affected customers and downstream partners across several regions, including the U.S., Taiwan, Australia, Germany, Japan, the UK, Ireland, India, and China. This outage, which lasted about 12 minutes, was first noticed approximately at 12:40 PM EDT. Initially, the outage seemed to focus on Hurricane Electric nodes situated in New York, NY, Los Angeles, CA, and San Jose, CA. Nonetheless, five minutes into the outage, the implications of the issue broadened, affecting nodes located in Chicago, IL, and Ashburn, VA, and additionally increasing the number of affected downstream partners and countries. The network issue was resolved by around 12:55 PM EDT. An interactive view of the event can be found here.
Concurrently on April 2, BT, a multinational Tier 1 ISP based in London, U.K., reported a disruption on their European backbone. This disrupted their services for customers and downstream partners spread across the U.S., the U.K., Switzerland, Spain, and Germany. This disruption, lasting 24 minutes, was first noticed around 7:20 PM EDT and appeared to primarily affect nodes located in London, England. An interactive view of the event is available here.
During the week of March 18-24, there were 118 global network outage events noted by ThousandEyes. These outage events spanned ISPs, cloud service providers, collaboration app networks, and edge networks, including DNS, content delivery networks, and security as a service. This figure represents a 28% drop from 164 outages reported the previous week. In the U.S. alone, there were 57 outages, which is a slight decrease from the 58 outages reported the week before. Let’s break down these figures by category:
ISP outages: On a global scale, ISP outages were almost cut by half, falling from 128 to 67. This represents a 48% decrease from the previous week’s figures. In the U.S., the number of ISP outages also fell, albeit slightly from 43 to 31 outages, indicating a decrease of 28%.
Public cloud network outages: Looking at global trends, the number of total cloud provider network outages saw a dramatic rise, nearly tripling from six to 17 outages. The U.S followed a similar trend, with cloud provider network outages surging from a meager three to 14 outages
Collaboration app network outages: The number of global collaboration app network outages saw a bit more than a two-fold increase, rising from six to 13. In the U.S., the number of such outages also doubled, moving from four to eight.
On March 29, Arelion (formerly Telia Carrier), a Tier 1 ISP based in Sweden, suffered an outage that affected customers and downstream partners in various regions including the U.S., the Netherlands, and Japan. The downtime, which lasted for 8 minutes, started around 5:26 AM EDT and primarily affected nodes in Phoenix, AZ. By 5:35 AM EDT, the issue was resolved. For an in-depth view, click here.
On the same day, another outage was experienced by Cogent Communications, a multinational transit provider based in the U.S. This interrupted service to numerous downstream providers and Cogent customers across several regions, such as the U.S., Canada, Germany, and Japan. The disruption lasted for 9 minutes, commencing around 1:45 AM EDT with cities including San Francisco, Salt Lake, and Seattle initially affected. Five minutes into the downtime, nodes in San Francisco, Salt Lake, and Seattle regained function but Kansas City took a hit. This meant fewer customers and providers were disadvantaged. The issue was finally resolved around 1:55 AM EDT. For a comprehensive view, click
here.
After witnessing a rise the previous week, the frequency of global outages declined last week. According to ThousandEyes, there were 164 network disruption events across ISPs, cloud service provider networks, collaboration app networks, and edge networks (covering DNS, content delivery networks, and security as a service) during the week of March 18-24. This is lesser by 20% from 206 outages noted the previous week. Specifically in the U.S., 58 outages were reported, marking a drop of 33% from 87 outages the week before. Here’s a breakdown by category:
Referring to ISP outages, there was a slight fall in the global number of ISPs’ disruptions from 131 to 128 outages, showing a 2% decrease compared to the week prior. Likewise, in the U.S., the no of ISP outages decreased marginally from 46 to 43 outages.
Public cloud network outages: Globally, the number of network outages in the public cloud sector fell from 10 to six. Meanwhile, in the U.S., the number declined from six to three.
Collaboration app network outages: There was a significant worldwide drop in network outages of collaboration apps, going from 34 down to merely six. In the U.S., the drop was even more striking, with 28 going down to a mere four outages.
The 20th of March saw Cogent Communications, a multinational transit provider hailing from the U.S., face an outage that had a domino effect on multiple downstream providers and its personal clienteles across various corners of the globe. Countries affected ranged from the U.S., Italy, Saudi Arabia, France, Germany, Singapore, Mexico, to name but a few. This outage, stretched over an hour and fifteen minutes, was split into three instances, with each appearing to be centered around different Cogent nodes across the world. A comprehensive interactive view can be found here.
A similar incident was experienced on the 24th of March by Hurricane Electric, another transit provider which deals with networks. Headquartered in Fremont, CA, this outage, clocking a total of 7 minutes, impacted both customers and downstream partners across a sea of regions including the U.S., China, Australia, and Japan amongst others. More detailed observations can be found by clicking here.
Global outages have seen a significant rise in recent weeks after a period of steady decline. Throughout the week of March 11-17, ThousandEyes detected a total of 206 network outage events worldwide. These were spread across ISPs, networks of cloud service providers, collaboration applications, and edge networks, which encompass DNS, CDNs, and security as a service. This is a substantial rise of 45% from the 142 outages recorded the previous week. In the U.S. alone, outages increased by 38%, going up from 63 to 87. Here is a more detailed category-wise analysis:
ISP Outages: The number of ISP outages recorded worldwide saw a 44% rise, going up from 91 to 131 outages. A slight increase was also noted in the US, with outages going up from 44 to 46.
Public Cloud Network Outages: Globally, public cloud network outages increased from six to ten. The U.S saw a slight rise from four to six outages.
Collaboration App Network Outages: Outages in collaboration app network experienced a sharp increase globally, spiking from six outages to 34. In the U.S the increase was even higher, jumping from three outages to 28.
On March 16, Cogent Communications, a multinational transit provider headquartered in the U.S., suffered from an outage that affected various downstream providers as well as numerous Cogent customers in the U.S., Ireland, the U.K., Sweden, Austria, Germany, and Italy among other regions. The two-phase outage lasted a total of 12 minutes within a span of 70. The initial phase was noted around 6:30 PM EDT, primarily affecting the Baltimore, MD and New York, NY nodes. Five minutes into the outage, the affected nodes shifted from New York, NY to Philadelphia, PA. After an hour of the initial issue clearance, a second phase was noticed, lasting for about four minutes with the epicenter being nodes located in Baltimore, MD, Philadelphia, PA, New York, NY, and Newark, NJ. The outage was resolved around 7:45 PM EDT. For an interactive view, click here.
Just a few days earlier, on March 12, Hurricane Electric, another network transit provider based in Fremont, CA, also experienced an outage leading to service disruption for clients and downstream partners in the U.S. and Canada. The two-phase outage was first noted approximately at 2:00 AM EDT and lasted for a total of 7 minutes within a span of 30. The first phase seemed initially to be concentrated around Hurricane Electric nodes in Chicago, IL. After a twenty-minute clearance period, the nodes in Chicago, IL were joined by nodes in Seattle, WA in showing outage symptoms. This compounded node failure coincided with a surge in the number of affected downstream partners and clients. The outage was resolved by about 2:30 AM EDT. For an interactive view, click here.
For more information, detailed reports from ThousandEyes can be accessed here.
According to ThousandEyes, the week of March 4-10 noted 142 global network outage incidents across various categories like ISPs, cloud service provider networks, edge networks (including DNS, content delivery networks, and security as a service), and collaboration app networks. This is a decrease of 8% from the previous week that saw 155 outages. In the U.S. specifically, there were a total of 63 outages, marking a decrease of 10% from 70 outages the week before. Category-wise details are as follows:
ISP outages: Globally, the count of ISP outages dropped from 95 to 91 outages, a reduction by 4% compared to the preceding week. In the US, the number of ISP outages remained consistent at 44 outages.
Public cloud network outages: Globally, the number of outages in cloud provider networks fell from 13 to six. In the U.S., the statistics decreased from seven to four outages.
Collaboration app network outages: Around the globe, outages in collaboration app networks decreased from eight to six. In the U.S., the number of outages in collaboration app networks stayed constant just like the previous week: three outages.
On 5th March, several services by Meta, including Facebook and Instagram, faced disruptions impacting users who were trying to login, hence barring them from accessing those applications. The issue first appeared around 10:00 AM EST. Despite the disruption, Meta’s web servers were still accessible with network routes to Meta services indicating no notable error conditions. This suggests that a backend service like authentication was the problem. The service was completely restored around 11:40 AM EST. A more comprehensive analysis is available here.
On March 5, Comcast Communications had an outage that affected several downstream partners and customers. It also affected the accessibility of numerous applications and services like Webex, Salesforce, and AWS. This outage was noticed at about 2:45 PM EST, lasted for 1 hour and 48 minutes, and seemed to affect traffic through Comcast’s network backbone in Texas. Comcast nodes in Dallas, TX, and Houston, TX were seen to exhibit outage conditions. The outage was fully cleared by about 4:40 PM EST. You can find a more detailed analysis here.
On March 6, LinkedIn had a service disruption that affected its global user base on mobile and desktop. This disruption was first noticed at 3:45 PM EST and presented users with service unavailable error messages. The significant part of the disruption lasted about an hour. During this period, no network issues were noticed while connecting to LinkedIn web servers. This suggests that the problem was related to the application. The service began to recover around 4:38 PM EST and was completely clear for all users by around 4:50 PM EST. A more detailed analysis can be found here.
You can find further details from ThousandEyes here.
ThousandEyes reported 155 global network outage events across ISPs, cloud service provider networks, collaboration app networks. and edge networks during the week of February 26-March 3. These edge networks include DNS, content delivery networks, and security as a service. This is a decrease of 6% from 165 outages in the week before. In the U.S. specifically, 70 outages were reported, an increase of 19% from 59 outages the week before. The breakdown by category is as follows:
ISP outages: The number of ISP outages worldwide decreased from 111 to 95, which is a 14% decrease from the previous week. Meanwhile, in the U.S., ISP outages experienced a 10% increase, with the number going up from 40 to 44 outages.
Public cloud network outages: After a period of decrease, the number of cloud provider network outages started to rise again last week. Globally, cloud provider network outages increased from eight to 13. In the U.S., there was a rise from four to seven outages.
Collaboration app network outages: Around the globe, the number of collaboration app network outages increased from five to eight. The U.S. saw a rise from two to three outages.
On the 27th of February, Level 3 Communications, a U.S.-based Tier 1 carrier that was acquired by Lumen, experienced an outage that affected numerous downstream partners and customers across the U.S. The outage lasted 18 minutes over a time span of 25 minutes. It was first observed approximately at 2:25 AM EST and seemed to be centered around Level 3 nodes in Cleveland, OH. The outage was resolved around 2:50 AM EST. Click here for an interactive view.
Time Warner Cable, an ISP based in the U.S., experienced a disruption on February 28 that affected many customers and partners across the country. The disruption was initially noticed at roughly 2:00 PM EST and it seemed to primarily affect Time Warner Cable nodes situated in New York, NY. Approximately five minutes into the disruption, more nodes in New York, NY started showing signs of the outage. The disruption lasted for 14 minutes and was resolved by about 2:15 PM EST. For an interactive view, click here.
You can find more information from ThousandEyes here.
In the week of February 19-25, ThousandEyes reported 165 global network outage events across different platforms like ISPs, cloud service provider networks, collaboration app networks, and edge networks. This number was notably lower than the 243 outages recorded the previous week – marking a decrease of 32%. In the U.S. specifically, there were 59 outages, which represented a 34% reduction from the 90 outages observed the previous week. Here’s a category-wise breakdown:
ISP outages: The number of global ISP outages fell from 121 to 111 outages, a drop of 8% from the previous week. In the U.S., ISP outages went down from 48 to 40, marking a decrease of 17% compared to the week before.
Public cloud network outages: Globally, cloud provider network outages decreased significantly from 42 to eight outages, a 81% decrease compared to the week prior. In the U.S., they fell from eight to four outages.
Collaboration app network outages: Globally, collaboration app network outages decreased from seven outages to five. In the U.S., collaboration app network outages remained at the same level as the week prior: two outages.
On February 22, Hurricane Electric, a network transit provider headquartered in Fremont, CA, experienced an outage that impacted customers and downstream partners across multiple regions, including the U.S., Australia, China, the U.K., Japan, Singapore, India, France, and Canada. The outage, first observed around 9:10 AM EST, lasted 32 minutes in total and was divided into two occurrences over a forty-five-minute period. The first occurrence initially centered on Hurricane Electric nodes located in New York, NY, Phoenix, AZ, and Indianapolis, IN. Ten minutes later, nodes in New York, NY, were joined by nodes in San Jose, CA in exhibiting outage conditions. Five minutes into the second occurrence, disruption radiated out and the nodes in New York, NY, Phoenix, AZ, and Indianapolis, IN, were joined by nodes located in Seattle, WA, Denver, CO, Ashburn, VA, Kansas City, MO, and Omaha, NE in exhibiting outage conditions. An increase in impacted nodes seemed to coincide with an increase in the number of impacted downstream customers and partners. The outage was cleared at around 9:55 AM EST. Click
here for an interactive view.
On February 21, Time Warner Cable, a U.S. based ISP, experienced a disruption that impacted a multitude of customers and partners across the U.S. The outage was first observed at around 2:45 PM EST and seemed to center on Time Warner Cable nodes located in New York, NY. A quarter of an hour into the outage, nodes located in New York, NY, exhibiting outage conditions increased. The outage lasted 23 minutes and was cleared at around 3:10 PM EST. Click
here for an interactive view.
More details from ThousandEyes can be found here.
A report from ThousandEyes detailed 243 worldwide network outages that took place across ISPs, cloud service provider networks, collaboration app networks, and edge networks – including DNS, content delivery networks, and security as a service – between the 12th and 18th of February. This was a 24% decrease from the previous week’s 319 outages. Looking specifically at the United States, there were 90 outages instead of the 91 that occurred the previous week. Here’s how these numbers break down by category:
Global ISP outages: The number of ISP outages worldwide dropped by 10%, from 134 to 121 outages. Within the United States, there was a 20% decrease, from 60 to 48 outages.
Public cloud network outages: The number of global outages on cloud provider networks significantly decreased by 61%, going from 107 to 42 outages. Contrarily, in the United States, the number of outages doubled from four to eight.
Collaboration app network outages: Globally, collaboration app network outages decreased from 11 outages to seven. In the U.S., collaboration app network outages decreased from 5 to 2 outages.
On February 16, Hurricane Electric, a network transit provider headquartered in Fremont, CA, experienced an outage that impacted customers and downstream partners across multiple regions, including the U.S., Egypt, Sweden, the U.K., Japan, Mexico, Australia, Argentina, the Netherlands, Belgium, and Canada. The outage, first observed around 8:25 AM EST, lasted 23 minutes in total and was divided into two occurrences over a thirty-minute period. The first occurrence appeared to initially center on Hurricane Electric nodes located in New York, NY. Fifteen minutes into the first occurrence, the nodes located in New York, NY, were joined by nodes located in Paris, France, and Amsterdam, the Netherlands in exhibiting outage conditions. Five minutes after appearing to clear, nodes located in New York, NY once again began exhibiting outage conditions. The outage was cleared at around 8:55 AM EST. Click here for an interactive view.
On February 17, AT&T experienced an outage on their network that impacted AT&T customers and partners across the U.S. The outage, lasting around 14 minutes, was first observed around 3:40 PM EST, appearing to center on AT&T nodes located in Little Rock, AR. Five minutes after first being observed, the number of nodes exhibiting outage conditions located in Little Rock, AR, appeared to rise. This increase in nodes exhibiting outage conditions appeared to coincide with a rise in the number of impacted partners and customers. The outage was cleared at around 3:55 PM EST. Click here for an interactive view.
Additional details from ThousandEyes are available here.
ThousandEyes reported 319 global network outage events across ISPs, cloud service provider networks, collaboration app networks and edge networks (including DNS, content delivery networks, and security as a service) during the week of February 5-11. That’s up from 265 outages in the week prior – an increase of 20%. Specific to the U.S., there were 91 outages. That’s up from 45 outages the week prior, an increase of 102%. Here’s a breakdown by category:
ISP outages: Globally, the number of ISP outages increased from 106 to 134 outages, a 26% increase compared to the week prior. In the U.S., ISP outages more than doubled from 28 to 60 outages, a 114% increase compared to the previous week.
Public cloud network outages: Globally, cloud provider network outages decreased slightly from 117 to 107, a 9% decrease compared to the week prior. In the U.S., they decreased from five to four outages.
Collaboration app network outages: Globally, collaboration app network outages climbed from three outages to 11. In the U.S., there were five collaboration app network outages, up from zero the week prior.
Time Warner Cable, a U.S. based ISP, encountered a disruption on February 7 that affected numerous customers and partners in various regions, such as the U.S., Ireland, U.K., Canada, India, Australia, Singapore, Japan, the Netherlands, France, Germany, Indonesia, Hong Kong, South Korea, China, and Brazil. The disruption happened sporadically across a span of forty-five minutes and was first noticed at approximately 4:50 PM EST. The disruption was clustered around Time Warner Cable nodes primarily in New York, NY and lasted a total of 20 minutes before resolving at about 5:35 PM EST. For a detailed view, click here.
On the preceding day, NTT America, a global Tier 1 ISP and a branch of NTT Global, encountered a disruption that affected various customers and downstream partners in several regions, including U.S., Germany, U.K., the Netherlands, and Hong Kong. This disruption, lasting 24 minutes, was first detected around 8:10 PM EST. The disruption primarily centered on NTT nodes in Chicago, IL and Dallas, TX. The disruption was resolved around 8:35 PM EST. For a visual display, click here.
More details from ThousandEyes can be found here.
According to ThousandEyes, during the week of January 29- February 4, there were 265 global network outage events spanning ISPs, cloud service provider networks, collaboration application networks and edge networks. This is a significant increase compared to the previous week, which saw 126 outages. In the U.S., there were 45 outages, down from 55 outages the previous week, marking a decrease of 18%.
ISP outages: The number of ISP outages worldwide rose to 106, marking a 15% surge from 92 outages just the week prior. Meanwhile, ISP outages within the United States experienced a decrease of 28%, falling from 39 to 28 outages.
Public cloud network outages: On a global scale, the instances of network outages among cloud providers shot from five to a substantial 117 last week. This surge seemed to be due to a heightened increase in outage incidences within the APJC region. Within the United States, these outages escalated from two to five.
Collaboration app network outages: In comparison to the cloud network outages, the global collaboration app network outages seemed more under control, falling from five to three outages. Within the United States, these outages fell from the single instance to no outage at all.
On the 31st of January, Comcast Communications suffered an outage that affected a multitude of downstream partners and consumers across regions such as the United States, Malaysia, Singapore, Hong Kong, Canada, Germany, South Korea, Japan, and Australia. This outage, lasting a total of 18 minutes, started around 8:00 PM EST and mainly affected Comcast nodes located in Ashburn, VA. Around ten minutes into the outage, the nodes showing signs of outage conditions in Ashburn, VA seemed to multiply. This apparent surge in nodes undergoing outage conditions seemed to go hand in hand with the increase in the number of affected downstream consumers and partners. The outage event concluded around 8:20 PM EST. For an interactive view, visit here.
NTT America, a global Tier 1 ISP and a subsidiary of NTT Global, faced an outage on February 2. This outage affected some of their customers and downstream partners across many regions, such as the U.S., Germany, the Netherlands, and the U.K. This disruption began around 1:25 PM EST, seemed to focus on the NTT nodes in Dallas, TX and Chicago, IL, and lasted for roughly 23 minutes until it got resolved at around 1:50 PM EST. For an interactive view, click here.
More information from ThousandEyes can be found here.
According to ThousandEyes, during the week of January 22nd to 28th, there were 126 global network outage events involving ISPs, cloud service provider networks, collaboration app networks, and edge networks (including DNS, content delivery networks, and security as a service). This is a decline of 19% from the earlier week, which had 156 outages. Specifically, in the U.S, the number of outages was 55, a 40% decrease from the 91 outages observed the previous week. Here’s a category-wise breakdown:
ISP Outages: On a global level, ISP outages numbered 92, showing a 14% decline from the 107 outages reported in the previous week. In the U.S., the number of ISP outages fell by 35%, from 60 to 39 outages.
Public cloud network outages: Globally, the number of outages experienced by cloud providers fell from 14 to 5 last week. Within the U.S., outages decreased from seven to two.
Collaboration app network outages: Globally, the number of outages for collaboration apps remained unchanged from the previous week at five. In the U.S., the number of outages reduced from four to one.
On January 26, Microsoft encountered an issue that disrupted service for its customers in different regions worldwide. This issue was first noticed around 11:00 AM EST and caused failures in Microsoft Teams, impacting its functionality for users internationally. Even though there was no packet loss when connecting to the Microsoft Teams edge servers, the failures aligned with reported issues within Microsoft’s network that might have obstructed the edge servers from accessing the application elements in the backend. The issue was resolved for many users by 6:10 PM EST. An interactive view of the issue can be accessed here.
On January 24, an outage occurred on Akamai’s network that affected content delivery connectivity for its customers and partners using Akamai Edge delivery services based in the Washington D.C. area. The outage was first noticed around 12:10 PM EST and seemed to focus on Akamai nodes found in Washington D.C. The outage lasted for 24 minutes. Akamai announced that normal operations resumed at 1:00 PM EST. An interactive view of the issue can be viewed here.
On the 23rd of January, Internap, a U.S based cloud service enterprise noticed an outage. This hindered various customers and partners around the world, the U.S. and Singapore to be exact. This outage started around 2:30 AM EST and lasted a total of 18 minutes. The core of the outage seemed to be focussed on the Internap nodes in Boston, MA. The outage reached its peak about 15 minutes after it got noticed, affecting most regions, partners, and patrons. After 18 minutes, around 2:55 AM EST, the outage was taken care of. For an interactive perspective click here.
Further details from ThousandEyes can be seen here.
ThousandEyes logged 156 global network outage events that happened across ISPs, cloud service networks, and other network types (including DNS, content delivery networks and security as a service) during the week from January 15-21. This is a hike from 151 of last week, a rise of 3%. Particularly in the U.S., there were 91 outages, which is significantly higher than 63 from the former week, a surge of 44%. Here’s a brief categorised structure:
ISP outages: On the global front, there were 107 ISP outages which is an 8% increase from 83 outages of the last week. In the U.S., ISP outages shot up by 58%, jumping from 38 to 60 outages.
Public cloud network outages: Globally, there was a decline in cloud provider network outages from 30 to 14 last week. However, within the U.S., a slight increase was noted, as the number ramped up from six to seven outages.
Collaboration app network outages: With a global perspective, collaboration app network outages saw a drop, coming down from seven to five outages. However, within the U.S, there was no change as the number of outages remained steady at four.
On the 16th of January, Oracle encountered a network outage which had a significant impact on Oracle customers as well as downstream partners who were engaging with Oracle Cloud services across several regions. These included the U.S., Canada, China, Panama, Norway, the Netherlands, India, Germany, Malaysia, Sweden, Czech Republic, and Norway. The initial observation of the outage was at 8:45 AM EST and the cause seemed to be centralized to Oracle nodes located in different regions worldwide. Fortunately, 35 minutes after its first observation, all nodes that were showing outage conditions seemed to clear up. However, after ten minutes, nodes from different locations started showing outage conditions again. The whole outage episode lasted 40 minutes and was resolved around 9:50 AM EST. An interactive view can be accessed here.
Fast forward to January 20, a network transit provider headquartered in Fremont, CA, named Hurricane Electric, also experienced an outage. This outage impacted customers and downstream partners across various regions, including the U.S., Thailand, Hong Kong, India, Japan, and Australia. The outage was first noted around 7:15 PM EST and lasted 11 minutes, divided into two occurrences over a period of an hour and five minutes. The first occurrence appeared to be centred around Hurricane Electric nodes located in Los Angeles, CA. Subsequenty, about fifty minutes after the first occurrence, the second occurrence was noted. This lasted 8 minutes and seemed to be focused on nodes in Los Angeles, CA. After five minutes, nodes in San Jose, CA, also started showing outage conditions. By approximately 8:20 PM EST, the outage was completely resolved. An interactive view can be accessed here.
For more information from ThousandEyes, visit here.
During the week of January 8-14, ThousandEyes reported 151 global network outages in ISPs, cloud service provider networks, collaboration app networks, and edge networks. This includes DNS, content delivery networks, and security as a service. The number indicates a rise from 122 in the previous week, amounting to a 24% increase. As for the U.S. specifically, there were 63 outages, up from 58 of the previous week, marking a 9% increase. The following is a breakdown of the outages by category:
ISP outages: The count of ISP outages around the world was 83, witnessing a surge of 8% compared to the previous week. In the U.S., there was a 6% increase, from 36 to 38 outages.
Public cloud network outages: Globally, outages in cloud provider networks leaped from 19 to 30 last week. However, in the U.S., there was a drop from 10 to six outages.
Collaboration app network outages: Across the globe, there was an increase in collaboration app network outages, growing from five to seven. In the U.S., the number of outages rose from one to four.
On the 14th of January, Zayo Group, a Tier 1 carrier based in the U.S. and located in Boulder, Colorado, suffered from an outage. This affected several of their partners and customers in various regions like Canada, U.S., Germany, and Sweden. The outage lasted for roughly 14 minutes, starting around 7:10 PM EST. It seemed to mainly affect the Zayo Group nodes in Houston, Texas at first, but about 10 minutes into the outage, nodes in Amsterdam, the Netherlands also showed signs of the outage. The increase in number of affected nodes seemed to go hand-in-hand with the increase of affected downstream customers and partners. By around 7:25 PM EST, the outage was resolved. Click here for an interactive view.
Another outage happened on the 13th of January, this time affecting Time Warner Cable, an Internet Service Provider based in the U.S.. This interruption impacted several customers and partners across the U.S. It started to be observed around 12:45 PM EST with nodes in New York, NY being affected. Approximately 15 minutes into the incident, more nodes in New York, NY were impacted by the outage. The outage lasted for 19 minutes, ending at around 1:05 PM EST. Click here for an interactive view.
More detailed information from ThousandEyes can be found here.
During the first week of January, ThousandEyes documented a total of 122 network outage events worldwide. These outages took place across different networks including Internet Service Providers, cloud service providers, collaboration app networks, and edge networks. Over the course of the three weeks leading up to this, the number of outages in all categories steadily decreased for two weeks before climbing back up in the last week. The United States accounted for 58 of these outages. Let’s break this down by each category:
ISP outages: There was a 43% global increase in ISP outages, rising from 77 compared to the previous week. The United States saw a significant increase, with the number of outages nearly doubling from 20 to 36.
Public cloud network outages: There was an increase in the number of public cloud network outages worldwide, increasing from 13 to 19 in the last week. In the United States specifically, the number of outages rose from 6 to 10.
Collaboration app network outages: Globally, the number of outages in collaboration app networks increased from a single outage to five. In the United States specifically, the number of outages grew from zero to one.
On January 4, Time Warner Cable – an ISP based in the U.S., suffered a breakdown affecting numerous customers and partners throughout the U.S. Initial observation of the interruption was around 10:45 AM EST, primarily involving Time Warner Cable nodes in New York, NY. Just five minutes into the failure, the count of nodes in New York, NY exhibiting issues began to rise. The interruption lasted for a span of 13 minutes and was resolved by approximately 11:00 AM EST. An interactive view can be found here.
On the same day, Telecom Italia Sparkle – a Tier 1 provider headquartered in Rome, Italy, and a part of the Italian-owned Telecom Italia, experienced a breakdown impacting a number of its downstream partners and customers in several regions, including the U.S., Argentina, Brazil, and Chile. The interruption lasted a total of 28 minutes, split into two instances over a duration of 35 minutes and was first observed around 4:00 AM EST. The first phase of the interruption, enduring approximately 24 minutes, appeared to be centered on Telecom Italia Sparkle nodes located in Miami, FL. Five minutes post seeming resolution, nodes sited in Miami, FL, started showing interruption conditions again. The interruption was resolved by around 4:35 AM EST. An interactive view can be accessed here.
Find additional details from ThousandEyes here.