On Monday, January 09, 2017 5:48 PM Mel Gorman wrote: > On Mon, Jan 09, 2017 at 11:14:29AM +0800, Hillf Danton wrote: > > > On Friday, January 06, 2017 6:16 PM Mel Gorman wrote: > > > > > > On Fri, Jan 06, 2017 at 11:26:46AM +0800, Hillf Danton wrote: > > > > > > > > On Wednesday, January 04, 2017 7:11 PM Mel Gorman wrote: > > > > > @@ -2647,9 +2644,8 @@ static struct page *rmqueue_pcplist(struct zone > > > > > *preferred_zone, > > > > > struct list_head *list; > > > > > bool cold = ((gfp_flags & __GFP_COLD) != 0); > > > > > struct page *page; > > > > > - unsigned long flags; > > > > > > > > > > - local_irq_save(flags); > > > > > + preempt_disable(); > > > > > pcp = &this_cpu_ptr(zone->pageset)->pcp; > > > > > list = &pcp->lists[migratetype]; > > > > > page = __rmqueue_pcplist(zone, order, gfp_flags, migratetype, > > > > > @@ -2658,7 +2654,7 @@ static struct page *rmqueue_pcplist(struct zone > > > > > *preferred_zone, > > > > > __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << > > > > > order); > > > > > zone_statistics(preferred_zone, zone, gfp_flags); > > > > > } > > > > > - local_irq_restore(flags); > > > > > + preempt_enable(); > > > > > return page; > > > > > } > > > > > > > > > With PREEMPT configured, preempt_enable() adds entry point to > > > > schedule(). > > > > Is that needed when we try to allocate a page? > > > > > > > > > > Not necessarily but what are you proposing as an alternative? > > > > preempt_enable_no_resched() looks at first glance a choice for us to > > avoid flipping interrupts. > > > > Ok, I wasn't sure if you were proposing something more drastic. I can > make it this although I have no reason to believe it will really matter. > The path should be short enough that it's unlikely a scheduler event > would ever occur at that point. Still, no harm in doing what you > suggest. > If spin, feel free to add
Acked-by: Hillf Danton <hillf...@alibaba-inc.com> to the patchset.
