a few thoughts

Jonathan S. Shapiro shap@eros-os.org
Sun, 16 Jul 2000 13:58:15 -0400


> The L4 HotOS 97 paper "Achieved IPC Performance" claims <1uS IPCs on
> Pentium-166s.  Is this bogus? If not, why is EROS fast-path IPC pipe
> latency an order of magnitude slower at 18uS?  (I know it involves
> several IPCs, but ten?)

One other bit on that. The EROS pipe test is using cruddy stub code that
rougly doubles the IPC times. I think this reinforces the message of that
paper.