On Fri, Dec 6, 2024 at 4:31 PM Yafang Shao <laoar.shao@xxxxxxxxx> wrote: > > When testing large folio support with XFS on our servers, we observed that > only a few large folios are mapped when reading large files via mmap. > After a thorough analysis, I identified it was caused by the > `/sys/block/*/queue/read_ahead_kb` setting. On our test servers, this > parameter is set to 128KB. After I tune it to 2MB, the large folio can > work as expected. However, I believe the large folio behavior should not > be dependent on the value of read_ahead_kb. It would be more robust if > the kernel can automatically adopt to it. > > With /sys/block/*/queue/read_ahead_kb set to 128KB and performing a > sequential read on a 1GB file using MADV_HUGEPAGE, the differences in > /proc/meminfo are as follows: > > - before this patch > FileHugePages: 18432 kB > FilePmdMapped: 4096 kB > > - after this patch > FileHugePages: 1067008 kB > FilePmdMapped: 1048576 kB > > This shows that after applying the patch, the entire 1GB file is mapped to > huge pages. The stable list is CCed, as without this patch, large folios > don't function optimally in the readahead path. > > It's worth noting that if read_ahead_kb is set to a larger value that > isn't aligned with huge page sizes (e.g., 4MB + 128KB), it may still fail > to map to hugepages. > > Link: https://lkml.kernel.org/r/20241108141710.9721-1-laoar.shao@xxxxxxxxx > Fixes: 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings") > Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx> > Tested-by: kernel test robot <oliver.sang@xxxxxxxxx> > Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> > Cc: David Hildenbrand <david@xxxxxxxxxx> > Cc: <stable@xxxxxxxxxxxxxxx> > --- > mm/readahead.c | 6 +++++- > 1 file changed, 5 insertions(+), 1 deletion(-) > > Changes: > v2->v3: > - Fix the softlockup reported by kernel test robot > https://lore.kernel.org/linux-fsdevel/202411292300.61edbd37-lkp@xxxxxxxxx/ > > v1->v2: https://lore.kernel.org/linux-mm/20241108141710.9721-1-laoar.shao@xxxxxxxxx/ > - Drop the alignment (Matthew) > - Improve commit log (Andrew) > > RFC->v1: https://lore.kernel.org/linux-mm/20241106092114.8408-1-laoar.shao@xxxxxxxxx/ > - Simplify the code as suggested by Matthew > > RFC: https://lore.kernel.org/linux-mm/20241104143015.34684-1-laoar.shao@xxxxxxxxx/ > > diff --git a/mm/readahead.c b/mm/readahead.c > index 3dc6c7a128dd..1dc3cffd4843 100644 > --- a/mm/readahead.c > +++ b/mm/readahead.c > @@ -642,7 +642,11 @@ void page_cache_async_ra(struct readahead_control *ractl, > 1UL << order); > if (index == expected) { > ra->start += ra->size; > - ra->size = get_next_ra_size(ra, max_pages); > + /* > + * In the case of MADV_HUGEPAGE, the actual size might exceed > + * the readahead window. > + */ > + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); > ra->async_size = ra->size; > goto readit; > } > -- > 2.43.5 > Andrew, could you please drop the previous version and apply this updated one instead? -- Regards Yafang
