Re: + mm-thp-avoid-unnecessary-swapin-in-khugepaged.patch added to -mm tree

[Michal Hocko <mhocko@kernel.org>]

On Tue 17-05-16 09:58:15, Michal Hocko wrote:
> On Thu 28-04-16 17:19:21, Michal Hocko wrote:
> > On Wed 27-04-16 14:17:20, Andrew Morton wrote:
> > [...]
> > > @@ -2484,7 +2485,14 @@ static void collapse_huge_page(struct mm
> > >  		goto out;
> > >  	}
> > >  
> > > -	__collapse_huge_page_swapin(mm, vma, address, pmd);
> > > +	swap = get_mm_counter(mm, MM_SWAPENTS);
> > > +	curr_allocstall = sum_vm_event(ALLOCSTALL);
> > > +	/*
> > > +	 * When system under pressure, don't swapin readahead.
> > > +	 * So that avoid unnecessary resource consuming.
> > > +	 */
> > > +	if (allocstall == curr_allocstall && swap != 0)
> > > +		__collapse_huge_page_swapin(mm, vma, address, pmd);
> > >  
> > >  	anon_vma_lock_write(vma->anon_vma);
> > >  
> > 
> > I have mentioned that before already but this seems like a rather weak
> > heuristic. Don't we really rather teach __collapse_huge_page_swapin
> > (resp. do_swap_page) do to an optimistic GFP_NOWAIT allocations and
> > back off under the memory pressure?
> 
> I gave it a try and it doesn't seem really bad. Untested and I might
> have missed something really obvious but what do you think about this
> approach rather than relying on ALLOCSTALL which is really weak
> heuristic:

Ups forgot to add mm/internal.h to the git index
---
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 87f09dc986ab..1a4d4c807d92 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2389,7 +2389,8 @@ static void __collapse_huge_page_swapin(struct mm_struct *mm,
 		swapped_in++;
 		ret = do_swap_page(mm, vma, _address, pte, pmd,
 				   FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT,
-				   pteval);
+				   pteval,
+				   GFP_HIGHUSER_MOVABLE | ~__GFP_DIRECT_RECLAIM);
 		if (ret & VM_FAULT_ERROR) {
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, 0);
 			return;
diff --git a/mm/internal.h b/mm/internal.h
index b6ead95a0184..0b3cc643eced 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -37,7 +37,7 @@
 
 extern int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *page_table, pmd_t *pmd,
-			unsigned int flags, pte_t orig_pte);
+			unsigned int flags, pte_t orig_pte, gfp_t gfp_mask);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
diff --git a/mm/memory.c b/mm/memory.c
index d79c6db41502..f897ec89bd79 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2490,7 +2490,7 @@ EXPORT_SYMBOL(unmap_mapping_range);
  */
 int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		unsigned int flags, pte_t orig_pte)
+		unsigned int flags, pte_t orig_pte, gfp_t gfp_mask)
 {
 	spinlock_t *ptl;
 	struct page *page, *swapcache;
@@ -2519,8 +2519,7 @@ int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
 	page = lookup_swap_cache(entry);
 	if (!page) {
-		page = swapin_readahead(entry,
-					GFP_HIGHUSER_MOVABLE, vma, address);
+		page = swapin_readahead(entry, gfp_mask, vma, address);
 		if (!page) {
 			/*
 			 * Back out if somebody else faulted in this pte
@@ -2573,7 +2572,7 @@ int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) {
+	if (mem_cgroup_try_charge(page, mm, gfp_mask, &memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -3349,7 +3348,7 @@ static int handle_pte_fault(struct mm_struct *mm,
 						flags, entry);
 		}
 		return do_swap_page(mm, vma, address,
-					pte, pmd, flags, entry);
+					pte, pmd, flags, entry, GFP_HIGHUSER_MOVABLE);
 	}
 
 	if (pte_protnone(entry))
-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>