The inaugural 2020 ThousandEyes internet performance report, a first-of-its-kind study of the impacts of changing network usage due to Covid-19, has found that while global internet disruptions saw an unprecedented rise since lockdowns were introduced, not all outages were equal and more disruptions did not necessarily indicate systemic performance degradation.
Measuring performance over time, the internet and cloud intelligence company’s internet performance report assessed the availability and performance of internet-related networks, including those of internet service providers (ISPs), public cloud, content delivery network (CDN) and domain name system (DNS) providers.
The findings were based on data gathered from continuously monitoring bidirectional network performance such as latency, packet loss and jitter, between fixed vantage points connected to ISP networks in three global regions – North America, Europe and Asia-Pacific – as well as cloud inter-region performance for Microsoft Azure, Google Cloud Platform (GCP) and Amazon Web Services (AWS) within those same geographic regions.
ThousandEyes found that global internet disruptions saw an unprecedented rise, increasing by 63% in March compared with January, and remained elevated through the first half of 2020 compared with pre-pandemic levels. In June, 44% more disruptions were recorded compared with January.
Yet overall, the internet held up. Despite unprecedented conditions and an increase in network disruptions, internet-related infrastructures were found to have held up well, suggesting overall healthy capacity, scalability and the operator agility needed to adjust to unforeseen demands, said ThousandEyes.
Negative performance indicators, such as traffic delay, loss and jitter, generally remained within tolerable ranges, showing no evidence of systemic network duress.
Although the total number of outages increased across all regions, the impact on internet users varied. Following pre-pandemic patterns, a larger proportion of disruptions in Europe, the Middle East and Africa (EMEA) tended to occur during peak business hours as compared with North America, where a majority of large outages typically took place outside traditional business hours and may not have had a meaningful impact on internet users, said ThousandEyes.
Increased network disruptions were also found to be caused by operator adjustments. Many of the network disruptions observed after February appeared to be related to network operators making more changes to their networks to compensate for changing traffic conditions.
Looking regionally, the report identified ISPs in North America and Asia-Pacific (APAC) as having experienced the largest spikes in March 2020, at 65% for North America and 99% for APAC compared with January, and have since returned to levels typical of those regions. By contrast, in EMEA, outages continued to increase month on month, with 45% more disruptions in June than in January.
As regards who was supplying the most reliable infrastructure, ISPs were found to have been hit the hardest, while cloud provider networks demonstrated greater overall stability. Between January and July 2020, cloud providers experienced about 400 outages globally, compared with more than 4,500 in ISP networks. Relative to total outages, more than 80% occurred within ISP networks and less than 10% within cloud provider networks.
Angelique Medina, research author and director of product marketing at ThousandEyes, noted that the internet was inherently unpredictable and outages were inevitable even in normal conditions. “However, with the overnight transition to a remote workforce, remote schooling and remote entertainment that many countries experienced in March, we saw outages spike to unprecedented levels – especially among ISPs who seem to have been more vulnerable to disruptions than cloud providers,” she said.
Going forward, the research noted that after businesses and service providers scrambled to adjust, almost overnight, to work-from-home environments, there was a definite shift towards accommodating a more permanent scenario of serving a remote workforce. This, said the report, was creating a realignment of network infrastructure that will look very different from the pre-March set-up.