On Wed, May 07, 2025 at 10:39:25PM +0000, H. Hartzer wrote: > I figure this may not be worthy of tech@. Just wanted to mention > some thoughts. > > I see a lot of work done around the various NIC offloading features. > Personally, I've had a lot of problems with these. Typically involving > virtualization at the guest level or the host level.
If you still see problems in your setup running current/stable OpenBSD. Please write a report about it to b...@openbsd.org. Your are also welcome give some feedback of your offloading Linux problems re-tested with OpenBSD. > Now a lot of my experience here comes from Linux many moons ago. > But I found a lot of hardware that wouldn't play nicely unless > offloading was disabled, with the most aggravating bugs. There's > also minor nuisances, like checksums not matching in tcpdump under > some circumstances. And some NICs would seem to "go bad" at some > point at not play nicely with those settings enabled. > > I'm not 100% sure what the CPU savings are, but for my cases I've > never found a situation that was impacted an obvious amount by > having offloading features disabled. I also think that there can > be some security issues where a packet might get by that the NIC > splits up (I think segmentation offloading can do this) and it gets > broken into another packet that would normally not be permitted. > > I certainly don't have all the answers here, and my experience on > the matter is rather old. I just had enough of a persistently poor > experience with offloading features to where I assume that I would > rather not have any offloading code at all. > > That said, maybe some chipsets work great. And maybe some of the > features, especially say outbound, are quite reliable. I'm just a > skeptic after being bitten by it. Maybe some of it was Linux related? > > I'm sure someone here has had a more positive experience with it, > or can attest that the performance gains are worthwhile, or that > it can be utilized only on hardware known to be reliable with it. > > Most of my experience involves gigabit hardware and performance > requirements, so I can see how at say 40gbit/sec, offloading is 40x > more valuable.
