The quilt patch titled Subject: readahead: avoid multiple marked readahead pages has been removed from the -mm tree. Its filename was readahead-avoid-multiple-marked-readahead-pages.patch
This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------ From: Jan Kara jack@suse.cz Subject: readahead: avoid multiple marked readahead pages Date: Thu, 4 Jan 2024 09:58:39 +0100
ra_alloc_folio() marks a page that should trigger next round of async readahead. However it rounds up computed index to the order of page being allocated. This can however lead to multiple consecutive pages being marked with readahead flag. Consider situation with index == 1, mark == 1, order == 0. We insert order 0 page at index 1 and mark it. Then we bump order to 1, index to 2, mark (still == 1) is rounded up to 2 so page at index 2 is marked as well. Then we bump order to 2, index is incremented to 4, mark gets rounded to 4 so page at index 4 is marked as well. The fact that multiple pages get marked within a single readahead window confuses the readahead logic and results in readahead window being trimmed back to 1. This situation is triggered in particular when maximum readahead window size is not a power of two (in the observed case it was 768 KB) and as a result sequential read throughput suffers.
Fix the problem by rounding 'mark' down instead of up. Because the index is naturally aligned to 'order', we are guaranteed 'rounded mark' == index iff 'mark' is within the page we are allocating at 'index' and thus exactly one page is marked with readahead flag as required by the readahead code and sequential read performance is restored.
This effectively reverts part of commit b9ff43dd2743 ("mm/readahead: Fix readahead with large folios"). The commit changed the rounding with the rationale:
"... we were setting the readahead flag on the folio which contains the last byte read from the block. This is wrong because we will trigger readahead at the end of the read without waiting to see if a subsequent read is going to use the pages we just read."
Although this is true, the fact is this was always the case with read sizes not aligned to folio boundaries and large folios in the page cache just make the situation more obvious (and frequent). Also for sequential read workloads it is better to trigger the readahead earlier rather than later. It is true that the difference in the rounding and thus earlier triggering of the readahead can result in reading more for semi-random workloads. However workloads really suffering from this seem to be rare. In particular I have verified that the workload described in commit b9ff43dd2743 ("mm/readahead: Fix readahead with large folios") of reading random 100k blocks from a file like:
[reader] bs=100k rw=randread numjobs=1 size=64g runtime=60s
is not impacted by the rounding change and achieves ~70MB/s in both cases.
[jack@suse.cz: fix one more place where mark rounding was done as well] Link: https://lkml.kernel.org/r/20240123153254.5206-1-jack@suse.cz Link: https://lkml.kernel.org/r/20240104085839.21029-1-jack@suse.cz Fixes: b9ff43dd2743 ("mm/readahead: Fix readahead with large folios") Signed-off-by: Jan Kara jack@suse.cz Cc: Matthew Wilcox willy@infradead.org Cc: Guo Xuenan guoxuenan@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org ---
mm/readahead.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/readahead.c~readahead-avoid-multiple-marked-readahead-pages +++ a/mm/readahead.c @@ -469,7 +469,7 @@ static inline int ra_alloc_folio(struct
if (!folio) return -ENOMEM; - mark = round_up(mark, 1UL << order); + mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); @@ -575,7 +575,7 @@ static void ondemand_readahead(struct re * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - expected = round_up(ra->start + ra->size - ra->async_size, + expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; _
Patches currently in -mm which might be from jack@suse.cz are