is there a nice way to find out *which* spinlocks are popular? i already
know that the 4-way is seeing a big performance hit -- i'd like to know
where.
> o i386 irq_desc cacheline aligned.
any chance this could make it into 2.2? it's a free 1% performance
improvement on SMP.
> o prune dcache before start swapping, the prune won't be a complete
> prune but will be in function of the priority and will scale nicely.
> Well the implementation it's not that clever but works fine here:
>
> - prune_dcache(0);
> + prune_dcache(dentry_stat.nr_unused / (priority+1));
this is a good idea -- it keeps the dcache hash table performing well;
i've actually measured some overall performance improvement. however, is
there a way to do this without a DIV operation?
> o rb-tree in the page cache (not per-inode rb but only one whole rb).
how about dcache too? :)
> o update_shared_mappings (will greatly improve performances while
> writing from many task to the same shared memory).
do you have performance numbers on this?
- Chuck Lever
-- corporate: <chuckl@netscape.com> personal: <chucklever@netscape.net> or <cel@monkey.org>The Linux Scalability project: http://www.citi.umich.edu/projects/linux-scalability/
- 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/