From mboxrd@z Thu Jan 1 00:00:00 1970 From: bakul@bitblocks.com (Bakul Shah) Date: Wed, 3 Jan 2018 09:28:40 -0800 Subject: [TUHS] OT: critical Intel design flaw In-Reply-To: References: <20180103134358.3F16818C098@mercury.lcs.mit.edu> Message-ID: On Jan 3, 2018, at 6:26 AM, Clem Cole wrote: > > ​Yup microkernels are a tad slower and have more overhead, and might (probably will) cost a little more. But I really do think simplicity beats complexity and I'll pay a bit in over head to keep it simple. This slowdown (which is not much -- L4 shows it is about 5% or so) is more due to h/w security architecture that has not evolved for decades. None of the microkernel research has had any influence on x86/ARM etc. Look at how Mill solves the problem. A protection domain switch (a portal call) takes two extra fetches. Second, I think the protection ring idea was counterproductive. It allowed people to be lazy and stuff all sorts of things in the kernel.