From cc638f329ef605f5c2a57b87dd8e584e9d5f4c2f Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 13 Jan 2020 16:29:04 -0800 Subject: mm, thp: tweak reclaim/compaction effort of local-only and all-node allocations THP page faults now attempt a __GFP_THISNODE allocation first, which should only compact existing free memory, followed by another attempt that can allocate from any node using reclaim/compaction effort specified by global defrag setting and madvise. This patch makes the following changes to the scheme: - Before the patch, the first allocation relies on a check for pageblock order and __GFP_IO to prevent excessive reclaim. This however affects also the second attempt, which is not limited to single node. Instead of that, reuse the existing check for costly order __GFP_NORETRY allocations, and make sure the first THP attempt uses __GFP_NORETRY. As a side-effect, all costly order __GFP_NORETRY allocations will bail out if compaction needs reclaim, while previously they only bailed out when compaction was deferred due to previous failures. This should be still acceptable within the __GFP_NORETRY semantics. - Before the patch, the second allocation attempt (on all nodes) was passing __GFP_NORETRY. This is redundant as the check for pageblock order (discussed above) was stronger. It's also contrary to madvise(MADV_HUGEPAGE) which means some effort to allocate THP is requested. After this patch, the second attempt doesn't pass __GFP_THISNODE nor __GFP_NORETRY. To sum up, THP page faults now try the following attempts: 1. local node only THP allocation with no reclaim, just compaction. 2. for madvised VMA's or when synchronous compaction is enabled always - THP allocation from any node with effort determined by global defrag setting and VMA madvise 3. fallback to base pages on any node Link: http://lkml.kernel.org/r/08a3f4dd-c3ce-0009-86c5-9ee51aba8557@suse.cz Fixes: b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when compaction may not succeed") Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Linus Torvalds Cc: Andrea Arcangeli Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 10 +++++++--- mm/page_alloc.c | 24 +++++------------------- 2 files changed, 12 insertions(+), 22 deletions(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 067cf7d3daf5..b2920ae87a61 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2148,18 +2148,22 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); + /* + * First, try to allocate THP only on local node, but + * don't reclaim unnecessarily, just compact. + */ page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); + gfp | __GFP_THISNODE | __GFP_NORETRY, order); /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote - * memory as well. + * memory with both reclaim and compact as well. */ if (!page && (gfp & __GFP_DIRECT_RECLAIM)) page = __alloc_pages_node(hpage_node, - gfp | __GFP_NORETRY, order); + gfp, order); goto out; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4785a8a2040e..409be5ec7e2c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4476,8 +4476,11 @@ retry_cpuset: if (page) goto got_pg; - if (order >= pageblock_order && (gfp_mask & __GFP_IO) && - !(gfp_mask & __GFP_RETRY_MAYFAIL)) { + /* + * Checks for costly allocations with __GFP_NORETRY, which + * includes some THP page fault allocations + */ + if (costly_order && (gfp_mask & __GFP_NORETRY)) { /* * If allocating entire pageblock(s) and compaction * failed because all zones are below low watermarks @@ -4498,23 +4501,6 @@ retry_cpuset: if (compact_result == COMPACT_SKIPPED || compact_result == COMPACT_DEFERRED) goto nopage; - } - - /* - * Checks for costly allocations with __GFP_NORETRY, which - * includes THP page fault allocations - */ - if (costly_order && (gfp_mask & __GFP_NORETRY)) { - /* - * If compaction is deferred for high-order allocations, - * it is because sync compaction recently failed. If - * this is the case and the caller requested a THP - * allocation, we do not want to heavily disrupt the - * system, so we fail the allocation instead of entering - * direct reclaim. - */ - if (compact_result == COMPACT_DEFERRED) - goto nopage; /* * Looks like reclaim/compaction is worth trying, but -- cgit