From b9ff43dd27434dbd850b908e2e0e1f6e794efd9b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 27 Apr 2022 17:01:28 -0400 Subject: mm/readahead: Fix readahead with large folios Reading 100KB chunks from a big file (eg dd bs=100K) leads to poor readahead behaviour. Studying the traces in detail, I noticed two problems. The first is that 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. Instead, we need to set the readahead flag on the first folio _after_ the one which contains the last byte that we're reading. The second is that we were looking for the index of the folio with the readahead flag set to exactly match the start + size - async_size. If we've rounded this, either down (as previously) or up (as now), we'll think we hit a folio marked as readahead by a different read, and try to read the wrong pages. So round the expected index to the order of the folio we hit. Reported-by: Guo Xuenan Signed-off-by: Matthew Wilcox (Oracle) --- mm/readahead.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/readahead.c b/mm/readahead.c index 8e3775829513..4a60cdb64262 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -474,7 +474,8 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (!folio) return -ENOMEM; - if (mark - index < (1UL << order)) + mark = round_up(mark, 1UL << order); + if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) @@ -555,8 +556,9 @@ static void ondemand_readahead(struct readahead_control *ractl, struct file_ra_state *ra = ractl->ra; unsigned long max_pages = ra->ra_pages; unsigned long add_pages; - unsigned long index = readahead_index(ractl); - pgoff_t prev_index; + pgoff_t index = readahead_index(ractl); + pgoff_t expected, prev_index; + unsigned int order = folio ? folio_order(folio) : 0; /* * If the request exceeds the readahead window, allow the read to @@ -575,8 +577,9 @@ static void ondemand_readahead(struct readahead_control *ractl, * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if ((index == (ra->start + ra->size - ra->async_size) || - index == (ra->start + ra->size))) { + expected = round_up(ra->start + ra->size - ra->async_size, + 1UL << order); + if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; @@ -662,7 +665,7 @@ readit: } ractl->_index = ra->start; - page_cache_ra_order(ractl, ra, folio ? folio_order(folio) : 0); + page_cache_ra_order(ractl, ra, order); } void page_cache_sync_ra(struct readahead_control *ractl, -- cgit v1.2.3-58-ga151