Hacker News Reader

One of the problems with microkernels is performance - messages are being sent between parts and that takes time. Here we have sort of an ultimate microkernel - can we have enough hardware support to have performance competitive, while keeping main advantages?

View on HN

This architecture also borrowed a lot from the exokernel philosophy, which would actually have provided significant speedups by cutting unnecessary bloat and abstraction.

My conjecture was that this would make up for most of the overhead, but I didn't have time during the thesis to optimize it sufficiently to do a fair comparison with existing architectures.

Andrew, I think it's a wonderful project, but to meaningfully evaluate it it definitely takes way more than an hour to figure out what, why and how is done here :) reading articles is hard. Thanks for your work!

Reply on news.ycombinator.com