On Mon 10-09-12 17:46:04, Wanpeng Li wrote:
> On Mon, Sep 10, 2012 at 10:22:39AM +0200, Michal Hocko wrote:
> >[Sorry for the late reply]
> >
> >On Fri 07-09-12 16:50:57, Andrew Morton wrote:
> >>
> >> The patch titled
> >> Subject: mm/memblock: reduce overhead in binary search
> >> has been added to the -mm tree. Its filename is
> >> mm-memblock-reduce-overhead-in-binary-search.patch
> >>
> >> Before you just go and hit "reply", please:
> >> a) Consider who else should be cc'ed
> >> b) Prefer to cc a suitable mailing list as well
> >> c) Ideally: find the original patch on the mailing list and do a
> >> reply-to-all to that, adding suitable additional cc's
> >>
> >> *** Remember to use Documentation/SubmitChecklist when testing your code ***
> >>
> >> The -mm tree is included into linux-next and is updated
> >> there every 3-4 working days
> >>
> >> ------------------------------------------------------
> >> From: Wanpeng Li <liwanp@xxxxxxxxxxxxxxxxxx>
> >> Subject: mm/memblock: reduce overhead in binary search
> >>
> >> When checking that the indicated address belongs to the memory region, the
> >> memory regions are checked one by one through a binary search, which will
> >> be time consuming.
> >
> >How many blocks do you have that O(long) is that time consuming?
> >
> >> If the indicated address isn't in the memory region, then we needn't do
> >> the time-consuming search.
> >
> >How often does this happen?
> >
> >> Add a check on the indicated address for that purpose.
> >
> >We have 2 users of this function. One is exynos_sysmmu_enable and the
> >other pfn_valid for unicore32. The first one doesn't seem to be used
> >anywhere (as per git grep). The other one could benefit from it but it
> >would be nice to hear about how much it really helps becuase if the
> >address is (almost) never outside of start,end DRAM bounds then you just
> >add a pointless check.
> >Besides that, if this kind of optimization is really worth, why don't we
> >do the same thing for memblock_is_reserved and memblock_is_region_memory
> >as well?
>
> As Yinghai said,
>
> BIOS could have reserved some ranges, and those ranges are not overlapped by
> RAM. and so those range will not be in memory and reserved array.
>
> later kernel will probe some range, and reserved those range, so those
> range get inserted into reserved array. reserved and memory array is
> different.
OK. Thanks for the clarification. The main question remains, though. Is
this worth for memblock_is_memory?
> >So, while the patch seems correct, I do not see how much it helps while
> >it definitely adds a code to maintain.
> >
> >> Signed-off-by: Wanpeng Li <liwanp@xxxxxxxxxxxxxxxxxx>
> >> Cc: Michal Hocko <mhocko@xxxxxxx>
> >> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> >> Cc: Minchan Kim <minchan@xxxxxxxxxx>
> >> Cc: Gavin Shan <shangw@xxxxxxxxxxxxxxxxxx>
> >> Cc: Yinghai Lu <yinghai@xxxxxxxxxx>
> >> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> >> ---
> >>
> >> mm/memblock.c | 5 +++++
> >> 1 file changed, 5 insertions(+)
> >>
> >> diff -puN mm/memblock.c~mm-memblock-reduce-overhead-in-binary-search mm/memblock.c
> >> --- a/mm/memblock.c~mm-memblock-reduce-overhead-in-binary-search
> >> +++ a/mm/memblock.c
> >> @@ -888,6 +888,11 @@ int __init memblock_is_reserved(phys_add
> >>
> >> int __init_memblock memblock_is_memory(phys_addr_t addr)
> >> {
> >> +
> >> + if (unlikely(addr < memblock_start_of_DRAM() ||
> >> + addr >= memblock_end_of_DRAM()))
> >> + return 0;
> >> +
> >> return memblock_search(&memblock.memory, addr) != -1;
> >> }
> >>
> >> _
> >>
> >> Patches currently in -mm which might be from liwanp@xxxxxxxxxxxxxxxxxx are
> >>
> >> mm-mmu_notifier-init-notifier-if-necessary.patch
> >> mm-vmscan-fix-error-number-for-failed-kthread.patch
> >> mm-memblock-reduce-overhead-in-binary-search.patch
> >> mm-memblock-rename-get_allocated_memblock_reserved_regions_info.patch
> >> mm-memblock-use-existing-interface-to-set-nid.patch
> >> mm-memblock-cleanup-early_node_map-related-comments.patch
> >>
> >
> >--
> >Michal Hocko
> >SUSE Labs
> >
> >--
> >To unsubscribe, send a message with 'unsubscribe linux-mm' in
> >the body to majordomo@xxxxxxxxx. For more info on Linux MM,
> >see: http://www.linux-mm.org/ .
> >Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
>
--
Michal Hocko
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>