The common term for this is "full kernel bypass". By claiming the network card from one process you lose the ability to run, say an SSH session, concurrently with your servers.Īs crazy as it sounds, this is exactly what most off the shelf userspace network stack technologies propose. This is lost if we dedicate the network card hardware to a single application in order to run a userspace network stack. By using the general purpose operating system network stack we gain the ability to run multiple network applications. This is no different for the networking stack. All of the resources exposed by the kernel can be shared between multiple processes! Userspace Networking
Whether it's a second HTTP server or just a bash session, this ability to share resources between multiple processes is critical. This allows us to run more than one application at a time. Secondly, the OS adds a time sharing layer.
#NETMAP STACK CODE#
With these we can focus on writing the code for any machine - not only the specialized hardware we have at the moment. Firstly, the OS layer adds hardware independence and easy to use APIs. Let's start with a broader question - what is the point of running an operating system at all? If you planned on running a single application, having to use a kernel consisting of multiple million lines of code may sound like a burden.īut in fact most of us decide to run some kind of OS and we do that for two reasons. My experience mostly comes from working with thousands of production machines here and I can try to answer the question from that perspective. I've also thought about this question while working at CloudFlare.
It triggered a very interesting discussion on Hacker News. A recent blog post posed the question Why do we use the Linux kernel's TCP stack?.
0 kommentar(er)
