[Bloat] Re: [Cake] Re: XDP2 is here - from one and only Tom Herbert (almost to the date, 10 years after XDP was released)

["David P. Reed" <dpreed@deepplum.com>]

Tom -
 
Well, we may have  to disagree on whether eBPF is a good language/system for writing networking stacks or interfacing to hardware devices.
 
In case I wasn't particularly clear about eBPF, here's a summary of that concern.


Perhaps the biggest drawback (beyond the fact that it is a terrible language) is that it's basically "sugared kretprobes" 1) its "abstractions" are whatever the Linux (or other OS) kernel code design allows to be "exported" within the kernel. You can't, for example, do co-routines or IPC that would be appropriate for a clean network stack. Just what Linus and crew decide to export symbols for. 2) Sadly eBPF is primarily maintained by folks who merely want "hooks" in the kernel for performance analysis. (the original BPF was for programming packet-processing pipelines). Its use for describing the implementation of full network stacks in a clean way, down to and including the semantics of, say, 802.11 devices or 802.2 devices is a masterful hack, but very much tied to the Linux kernel's control structure quirks.
 
As a guy who's been developing operating systems since 1970 starting with Multics and networking protocol implementations since 1976, I would never have thought that eBPF or any language designed to kludge with random APIs produced by a group like the Linux Kernel developers as a basis. There are so many alternatives that are far better that what eBPF is.
 
Go ahead and do whatever experiment you have planned. You don't need my approval to base it on eBPF.
 
Now, understand that I'm not saying DPDK is the answer either (nor is io_uring). It's got a number of design drawbacks, too. The main benefit is that it runs all the code in isolation from the monolithic kernel called Linux, and allows real-time execution in ring3 with interprocessor communication. I would throw most of the rest of DPDK away. I would think that your goals would be best suited by stepping back a bit.

David