sknat

Right, this also aligns with the our testing. Number of queues available seem to also be playing a role. But you're right RSS should spread traffic quite nicely when using 5-10 flows.

I'm a bit dubious about the networking results they present. I did some quite extensive network performence testing last winter on those three CSP, and even if single queue TCP+gso performence can behave like this, I find the claim 'GCP is 3x faster than AWS' a bit bold. It's definitely possible to get 50G of TCP traffic in AWS, and a lot of things are in the balance (MTU, number of queues, drivers...) that make this claim a bit weird to me.

You're right I think crowdfunding campaigns can be a really useful tool for such financing. Altought, I think recently, crowdfunding have a bit diverted from their original purpose to become marketing tools for some companies.

I think the ideal solution is hard to find, but I doubt we will come to something stable without a bit of regulation.

I think this comes down to the old socialism vs capitalism debate. Industries gain a lot at relying on 'free products' that are most of the time financed by states (think roads, infrastructure, etc...), but you can find counter examples where privately owned & sold products work better.

Concerning software, I agree the situation is a bit different as states are hardly strong players there. But I would disagree on the fact that the 'clut of free' is a sin. The whole industry gained a lot in terms of openness, sharing of best-practices and just innovation. Try finding how to build a washing-machine from scratch or just getting the PCB layout of your radio, it's a really painful process.

But I would agree that I'm worried too on the future of software, but I would rather push for more financing of open source (& free) projects - by states or NGOs - rather than pushing the whole industry to go sales first.