2012/7/10 Mel Gorman <mgor...@suse.de>:
> You say that invoking the function is very costly. I agree that a function
> call with that many parameters is hefty but it is also in the slow path of
> the allocator. For order-0 allocations we are about to enter direct reclaim
> where I would expect the cost far exceeds the cost of a function call.
Yes, I agree.
> If the cost is indeed high and you have seen this in profiles then I
> suggest you create a forced inline function alloc_pages_direct_compact
> that does this;
>
> if (order != 0)
> __alloc_pages_direct_compact(...)
>
> and then call alloc_pages_direct_compact instead of
> __alloc_pages_direct_compact. After that, recheck the profiles (although I
> expect the difference to be marginal) and the size of vmlinux (if it gets
> bigger, it's probably not worth it).
> That would be functionally similar to your patch but it will preserve git
> blame, churn less code and be harder to make mistakes with in the unlikely
> event a third call to alloc_pages_direct_compact is ever added.
Your suggestion looks good.
But, the size of page_alloc.o is more than before.
I test 3 approaches, vanilla, always_inline and
wrapping(alloc_page_direct_compact which is your suggestion).
In my environment (v3.5-rc5, gcc 4.6.3, x86_64), page_alloc.o shows
below number.
total, .text section, .text.unlikely
page_alloc_vanilla.o: 93432, 0x510a, 0x243
page_alloc_inline.o: 93336, 0x52ca, 0xa4
page_alloc_wrapping.o: 93528, 0x515a, 0x238
Andrew said that inlining add only 26 bytes to .text of page_alloc.o,
but in my system, need more bytes.
Currently, I think this patch doesn't have obvious benefit, so I want
to drop it.
Any objections?
Thanks for good comments.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
