lifo/fifo for unused slabs is obviously superflous - free is free, it
doesn't matter which free page is used first/last.
The partial slabs are already lifo: if a slab goes from full to partial,
it's added to the head of the partial list.
> You
> should benchmark it with a real load, not with dummy
> allocations/freeing.
>
Did you run any benchmarks? If yes, could you post them?
What I did was checking the number of branches in the hot path
(increased), the code length (increased) and execution time with dummy
loads (slower).
--
Manfred
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/