Re: [PATCH next] mm/swap.c: reduce lock contention in lru_cache_add

[Alex Shi]

在 2020/11/26 下午11:55, Matthew Wilcox 写道:
> On Thu, Nov 26, 2020 at 04:44:04PM +0100, Vlastimil Babka wrote:
>> However, Matthew wanted to increase pagevec size [1] and once 15^2 becomes
>> 63^2, it starts to be somewhat more worrying.
>>
>> [1] https://lore.kernel.org/linux-mm/20201105172651.2455-1-willy@xxxxxxxxxxxxx/
> 
> Well, Tim wanted it ;-)
> 
> I would suggest that rather than an insertion sort (or was it a bubble
> sort?), we should be using a Shell sort.  It's ideal for these kinds of
> smallish arrays.
> 
> https://en.wikipedia.org/wiki/Shellsort
> 

Uh, looks perfect good!. I gonna look into it. :)

Thanks!