Red Hat AI Factory with NVIDIA is a co-engineered, enterprise-grade AI solution for building, deploying, and managing AI at scale across hybrid cloud environments.
Linux user since late '90, kernel developer for too many years in closed source companies and finally landed to the Red Hat open-source paradise, Paolo contributes regularly to the Linux networking stack, focusing his effort to improve networking performances
This article, the second is a series about eXpress Data Path (XDP), explores maps--a more-advanced eBPF feature--and some common pitfalls and basic debugging techniques.
This article guides you through your first XDP program, building a working example from zero and allowing you to build a light-speed network application from there. With an XDP program, you can achieve unprecedented speed in packet filtering, because a modern driver with XDP support can easily handle more than 14 Mpps.
Networking hardware is becoming crazily fast, 10Gbs NICs are entry-level for server h/w, 100Gbs cards are increasingly popular and 200Gbs are already surfacing. While the Linux kernel is striving to cope with such speeds with large packets and all kind of aggregation, ISPs are requesting much more demanding workload with NFV and line rate packet processing even for 64 bytes packets. Is everything lost and are we all doomed to rely on some kernel bypass solution? Possibly, but let's first...