Re: [PATCH v18 06/32] mm/thp: narrow lru locking

2020-09-18 Thread Hugh Dickins
On Sun, 13 Sep 2020, Matthew Wilcox wrote: > On Fri, Sep 11, 2020 at 11:37:50AM +0800, Alex Shi wrote: > > 在 2020/9/10 下午9:49, Matthew Wilcox 写道: > > > On Mon, Aug 24, 2020 at 08:54:39PM +0800, Alex Shi wrote: > > >> lru_lock and page cache xa_lock have no reason with current sequence, > > >> put

Re: [PATCH v18 06/32] mm/thp: narrow lru locking

2020-09-13 Thread Matthew Wilcox
On Fri, Sep 11, 2020 at 11:37:50AM +0800, Alex Shi wrote: > > > 在 2020/9/10 下午9:49, Matthew Wilcox 写道: > > On Mon, Aug 24, 2020 at 08:54:39PM +0800, Alex Shi wrote: > >> lru_lock and page cache xa_lock have no reason with current sequence, > >> put them together isn't necessary. let's narrow the

Re: [PATCH v18 06/32] mm/thp: narrow lru locking

2020-09-10 Thread Alex Shi
在 2020/9/10 下午9:49, Matthew Wilcox 写道: > On Mon, Aug 24, 2020 at 08:54:39PM +0800, Alex Shi wrote: >> lru_lock and page cache xa_lock have no reason with current sequence, >> put them together isn't necessary. let's narrow the lru locking, but >> left the local_irq_disable to block interrupt

Re: [PATCH v18 06/32] mm/thp: narrow lru locking

2020-09-10 Thread Matthew Wilcox
On Mon, Aug 24, 2020 at 08:54:39PM +0800, Alex Shi wrote: > lru_lock and page cache xa_lock have no reason with current sequence, > put them together isn't necessary. let's narrow the lru locking, but > left the local_irq_disable to block interrupt re-entry and statistic update. What stats are

[PATCH v18 06/32] mm/thp: narrow lru locking

2020-08-24 Thread Alex Shi
lru_lock and page cache xa_lock have no reason with current sequence, put them together isn't necessary. let's narrow the lru locking, but left the local_irq_disable to block interrupt re-entry and statistic update. Hugh Dickins point: split_huge_page_to_list() was already silly,to be using the