ThousandEyes, a Cisco company, monitors how ISPs, cloud providers and conferencing services are handling performance challenges and provides Network World with a weekly roundup of events that impact service delivery.
Note: Prior-year outage updates have been archived, including reports from 2025, 2024, 2023, and the Covid-19 era.
Internet report for June 15–June 21
ThousandEyes reported 411 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 June 15 through June 21. The total of outage events decreased by 22% compared to the 528 outages from the week prior. Specific to the U.S., there were 285 outages, down by 7% from 306 outages the week prior. Here’s a breakdown by category:
- ISP outages: Globally, ISP outages decreased from 269 to 208, a 23% week-over-week decrease. In the U.S., ISP outages dropped from 154 to 129, a 16% decrease.
- Public cloud network outages: Globally, public cloud network outages dropped from 171 to 123, a 28% week-over-week decrease. In the U.S., outages decreased from 120 to 110, an 8% drop.
- Collaboration app network outages: Both globally and in the U.S., collaboration application network outages increased from zero to one.
Two notable outages
On June 17, Comcast Communications experienced an outage that impacted some of its partners and customers across multiple regions including the U.S., Singapore, and Japan. The outage, lasting a total of 29 minutes over a 55-minute period, was first observed around 3:40 AM EDT and appeared to be centered on Comcast nodes located in Los Angeles, CA. Thirty minutes into the outage, the number of nodes in Los Angeles exhibiting outage conditions appeared to rise, coinciding with an increase in the number of impacted downstream partners and customers. The outage was cleared around 4:35 AM EDT. View an interactive breakdown of this event.
On June 19, AT&T experienced an outage that affected some of its partners and customers across multiple regions including the U.S., Poland, and India. The outage, lasting a total of 45 minutes over a one-hour and 5-minute period, was first observed around 7:45 AM EDT and appeared to be centered on AT&T nodes located in New York, NY. Around forty minutes into the outage, the number of nodes in New York exhibiting outage conditions appeared to rise, coinciding with an increase in the number of impacted downstream partners. The outage was cleared around 8:55 AM EDT. View an interactive breakdown of this event.
Internet report for June 8–June 14
ThousandEyes reported 528 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 June 8 through June 14. The total of outage events increased by 9% compared to the 483 outages from the week prior. Specific to the U.S., there were 306 outages, down by 4% from 319 outages the week prior. Here’s a breakdown by category:
- ISP outages: Globally, ISP outages increased slightly from 265 to 269, a 2% week-over-week increase. In the U.S., ISP outages decreased from 187 to 154, an 18% decrease.
- Public cloud network outages: Globally, public cloud network outages increased from 132 to 171, a 30% week-over-week increase. In the U.S., outages rose from 95 to 120, a 26% increase.
- Collaboration app network outages: Both globally and in the U.S., collaboration application network outages decreased from 2 to zero.
Two notable outages
On June 10, Charter Communications, a U.S.-based Internet Service Provider operating as Spectrum, experienced a disruption that impacted a number of customers and partners across the U.S., France, Norway, Canada, Germany, India, the U.K., the Czech Republic, Peru, Italy, South Africa, Malaysia, and Spain. The outage, lasting a total of 16 minutes over a 37-minute period, was first observed around 2:18 AM EDT and appeared to initially center on nodes located in New York, NY and Dallas, TX. Ten minutes after appearing to clear, nodes in New York and Dallas began exhibiting outage conditions again. Three minutes after first being observed, the nodes in Dallas were replaced by nodes in Ashburn, VA, and Chicago, IL. Around fifteen minutes after appearing to clear, the nodes in New York once again began exhibiting outage conditions. The outage was cleared around 2:55 AM EDT. View an interactive breakdown of this event.
On June 10, Google Gemini experienced a service degradation that resulted in its AI chatbot failing to reply to some users globally. The disruption was first observed around 6:10 AM EDT and lasted approximately 7 hours, with Google confirming mitigation around 1:25 PM EDT. No network issues were observed connecting to Gemini’s frontend infrastructure, indicating the issue was related to backend systems. View an interactive breakdown of this event.
Internet report for June 1–June 7
ThousandEyes reported 483 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 June 1 through June 7. The total of outage events increased by 69% compared to the 286 outages from the week prior. Specific to the U.S., there were 319 outages, up by 70% from 195 outages the week prior. Here’s a breakdown by category:
- ISP outages: Globally, ISP outages rose from 156 to 265, a 70% week-over-week increase. In the U.S., ISP outages increased from 95 to 187, a 97% increase.
- Public cloud network outages: Globally, public cloud network outages increased from 87 to 132, a 52% week-over-week increase. In the U.S., outages rose from 77 to 95, a 23% increase.
- Collaboration app network outages: Both globally and in the U.S., collaboration application network outages increased from zero to 2.
Two notable outages
On June 4, GTT Communications, a Tier 1 provider headquartered in Tysons, VA, experienced an outage that affected some of its partners and customers across multiple regions including the U.S., Mexico, Germany, Indonesia, Hong Kong, Japan, Uruguay, Ireland, the U.K., Brazil, South Africa, Venezuela, Norway, the Netherlands, Australia, Singapore, Italy, France, Belgium, and Canada. The disruption, which lasted a total of 56 minutes over a one-hour and 31-minute period, was first observed around 3:44 PM EDT and appeared to initially center on GTT nodes in New York, NY. Around 26 minutes after first being observed, nodes in Washington, D.C., joined those in New York in exhibiting outages. Ten minutes after appearing to clear, nodes in New York again began exhibiting outage conditions, this time joined by nodes in Alexandria, VA. The outage was cleared around 5:15 PM EDT. View an interactive breakdown of this event.
On June 2, Arelion (formerly known as Telia Carrier), a global Tier 1 provider headquartered in Stockholm, Sweden, experienced an outage that impacted customers and downstream partners across multiple regions including the U.S., New Zealand, India, the United Arab Emirates, the Philippines, Japan, and Mexico. The disruption, which lasted a total of 15 minutes over a 24-minute period, was first observed around 4:36 AM EDT and appeared to be centered on nodes in Los Angeles, CA. Around four minutes into the outage, the number of Los Angeles nodes exhibiting outage conditions appeared to rise, coinciding with an increase in the number of downstream customers and partners impacted. The outage was cleared around 5:00 AM EDT. View an interactive breakdown of this event.
Internet report for May 25–May 31
ThousandEyes reported 286 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 May 25 through May 31. This report will be updated as additional weekly data becomes available.
