Regression caused by commit 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings")
Subsystems (2)
Hello!
The commit 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings") causes a regression in our production for containers which are running short on memory. In some cases they are getting stuck for hours in a vicious reclaim cycle. Reverting this commit fixes the problem.
As I understand, the intention of the commit is to allocate large folios whenever possible, and the idea is to ignore device-specific readahead settings and the mmap_miss logic to achieve that, which makes total sense.
However under a heavy memory pressure there must be a mechanism to revert to order-0 folios, otherwise the memory pressure is inevitable increased. Maybe mmap_miss heuristics should still be applied? Any other ideas how to fix it?
Also, a side question: I wonder if it makes sense to allocate 1-2 PMD-sized folios if mapping_large_folio_support() is not there?
Thanks!
Matthew Wilcox
maintainerQuoted 11 lines · Roman Gushchin
The commit
4687fdbb805a("mm/filemap: SupportVM_HUGEPAGEfor file mappings") causes a regression in our production for containers which are running short on memory. In some cases they are getting stuck for hours in a vicious reclaim cycle. Reverting this commit fixes the problem.As I understand, the intention of the commit is to allocate large folios whenever possible, and the idea is to ignore device-specific readahead settings and the
mmap_misslogic to achieve that, which makes total sense.
Quoted 4 lines
However under a heavy memory pressure there must be a mechanism to revert to order-0 folios, otherwise the memory pressure is inevitable increased. Maybe
mmap_missheuristics should still be applied? Any other ideas how to fix it?
What's supposed to happen is that we should have logic like:
if (order > min_order)
alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
so we try a little bit to free memory if we can't allocate an order-9 folio immediately, but we shouldn't be retrying for hours. Maybe that got lost somewhere along the line because I don't see it now.
Quoted 2 lines
Also, a side question: I wonder if it makes sense to allocate 1-2 PMD-sized folios if
mapping_large_folio_support()is not there?
Um, we don't?
if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size)
goto fallback;Quoted 17 lines · Matthew Wilcox
Quoted 11 lines · Roman Gushchin
The commit
4687fdbb805a("mm/filemap: SupportVM_HUGEPAGEfor file mappings") causes a regression in our production for containers which are running short on memory. In some cases they are getting stuck for hours in a vicious reclaim cycle. Reverting this commit fixes the problem.As I understand, the intention of the commit is to allocate large folios whenever possible, and the idea is to ignore device-specific readahead settings and the
mmap_misslogic to achieve that, which makes total sense.Quoted 4 lines
However under a heavy memory pressure there must be a mechanism to revert to order-0 folios, otherwise the memory pressure is inevitable increased. Maybe
mmap_missheuristics should still be applied? Any other ideas how to fix it?
Quoted 8 lines
What's supposed to happen is that we should have logic like:
if (order >
min_order)
alloc_gfp|=__GFP_NORETRY|__GFP_NOWARN;so we try a little bit to free memory if we can't allocate an order-9 folio immediately, but we shouldn't be retrying for hours. Maybe that got lost somewhere along the line because I don't see it now.
Yeah, I see it in __filemap_get_folio(), but not in ra_alloc_folio(). I'll prepare a fix for this.
Quoted 8 lines
Quoted 3 lines
Also, a side question: I wonder if it makes sense to allocate 1-2 PMD-sized folios if
mapping_large_folio_support()is not there?Um, we don't?
if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback;
Sorry, I wasn't clear, I mean we're still allocating 2-4MB of readahead. Shouldn't we do something like this instead?
--
mm/filemap.c +2 -1
@@ -3222,7 +3222,8 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ -if ((vm_flags &VM_HUGEPAGE ) &&HPAGE_PMD_ORDER <=MAX_PAGECACHE_ORDER ) { +if ((vm_flags &VM_HUGEPAGE ) &&HPAGE_PMD_ORDER <=MAX_PAGECACHE_ORDER && +mapping_large_folio_support (mapping)) { fpin =maybe_unlock_mmap_for_io (vmf, fpin); ractl._index &= ~((unsigned long )HPAGE_PMD_NR -1 ); ra->size =HPAGE_PMD_NR ;
Quoted 24 lines · Roman Gushchin
Quoted 22 lines · Matthew Wilcox
Quoted 11 lines · Roman Gushchin
The commit
4687fdbb805a("mm/filemap: SupportVM_HUGEPAGEfor file mappings") causes a regression in our production for containers which are running short on memory. In some cases they are getting stuck for hours in a vicious reclaim cycle. Reverting this commit fixes the problem.As I understand, the intention of the commit is to allocate large folios whenever possible, and the idea is to ignore device-specific readahead settings and the
mmap_misslogic to achieve that, which makes total sense.Quoted 4 lines
However under a heavy memory pressure there must be a mechanism to revert to order-0 folios, otherwise the memory pressure is inevitable increased. Maybe
mmap_missheuristics should still be applied? Any other ideas how to fix it?What's supposed to happen is that we should have logic like:
if (order >
min_order)
alloc_gfp|=__GFP_NORETRY|__GFP_NOWARN;
Quoted 6 lines
Quoted 3 lines
so we try a little bit to free memory if we can't allocate an order-9 folio immediately, but we shouldn't be retrying for hours. Maybe that got lost somewhere along the line because I don't see it now.
Yeah, I see it in
__filemap_get_folio(), but not inra_alloc_folio(). I'll prepare a fix for this.
Actually I'm wrong. It's there, hidden in readahead_gfp_mask(), and it's not conditional on the folio order. However it's not helping/not enough.