On Tue, Sep 11, 2007 at 12:20:20PM +0100, Andrew Doran wrote:
> 
> So each alloc / free pair spends perhaps 450 cycles
> on locking, times 50,000 that's a lot of cycles, and it doesn't take into
> account the serializing properties of the interlocked instructions.

Compared to the overhead of an IPI which can be in the area of a 100
cycles as well to *occasionally* reorganise the CPU local caches on each
CPU. E.g. the mutex adds a lot of bus contention for extremely little
gain.

Joerg