>If you have 100% CPU load, you don't do background zeroing and you
>fallback to old zero-after-alloc.
When I have to wait my CPUs are _always_ busy at 100%. (note even if the
disk is dogslow)
When the time is I/O dominated the memcpy is too little to make real
timing differences I think.
But my point is that if you would rework userspace to take the CPU busy
instead of optimizing the CPU-idle case you'll end waiting less time (and
as I am careful to take userspace smart and the CPU busy, I'd like to
continue waiting less time as now ;).
That's my point of view at least.
Andrea
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/