M-Lab: measuring Internet performance in the Asia Pacific
Guest Post: People use the M-Lab platform to run more than two million measurements per day worldwide.
Tag: measurement
Sizing the buffer
If buffers are generally good and improve data throughput, then more (or larger) buffers are better, right?
Who’s scanning your network?
Guest Post: Study finds that a third of all scan traffic is by scanners that target specific prefixes or networks.
Is new always better? UDP vs DoH
Guest Post: Study seeks to understand which transport protocol works best with DNS-over-HTTPS.
How consumer IoT devices expose information
Guest Post: Do our Internet-of-Things (IoT) devices at home expose private information unexpectedly?
BBR evaluation at a large CDN
Guest Post: Verizon Media shares its experience using BBR to deliver traffic from its caches.
Internet clouds are (also) unpredictable
Guest Post: A recent study measures traffic engineering on the Amazon Web Services cloud network.
Dark Traffic
What is dark traffic, and why has it increased four-fold in the past three years?
Page load times not affected by DoH and DoT
Guest Post: TCP enables DoH and DoT to outperform Do53 in page load times, despite higher response times.
How to choose DNS TTL values
Guest Post: Study shows that even the use of anycast with a short TTL on the authoritative server-side cannot match the gains of longer TTLs.