diff options
author | Liam Howlett <liam.howlett@oracle.com> | 2023-01-05 19:05:34 +0300 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2023-01-19 04:12:54 +0300 |
commit | 541e06b772c1aaffb3b6a245ccface36d7107af2 (patch) | |
tree | dfcd1f0f1252479c4c4d5e6ad180a28c48cd1959 /tools | |
parent | fc5744881eabcc73ed24a4229034f0fbdeb3f46f (diff) | |
download | linux-541e06b772c1aaffb3b6a245ccface36d7107af2.tar.xz |
maple_tree: remove GFP_ZERO from kmem_cache_alloc() and kmem_cache_alloc_bulk()
Preallocations are common in the VMA code to avoid allocating under
certain locking conditions. The preallocations must also cover the
worst-case scenario. Removing the GFP_ZERO flag from the
kmem_cache_alloc() (and bulk variant) calls will reduce the amount of time
spent zeroing memory that may not be used. Only zero out the necessary
area to keep track of the allocations in the maple state. Zero the entire
node prior to using it in the tree.
This required internal changes to node counting on allocation, so the test
code is also updated.
This restores some micro-benchmark performance: up to +9% in mmtests mmap1
by my testing +10% to +20% in mmap, mmapaddr, mmapmany tests reported by
Red Hat
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2149636
Link: https://lkml.kernel.org/r/20230105160427.2988454-1-Liam.Howlett@oracle.com
Signed-off-by: Liam Howlett <Liam.Howlett@oracle.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Suggested-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/testing/radix-tree/maple.c | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 81fa7ec2e66a..1f36bc1c5d36 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -173,11 +173,11 @@ static noinline void check_new_node(struct maple_tree *mt) if (!MAPLE_32BIT) { if (i >= 35) - e = i - 35; + e = i - 34; else if (i >= 5) - e = i - 5; + e = i - 4; else if (i >= 2) - e = i - 2; + e = i - 1; } else { if (i >= 4) e = i - 4; @@ -305,17 +305,17 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 2); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); /* Check the limit of pop/push/pop */ mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 2); /* Request */ @@ -323,14 +323,14 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_alloc_req(&mas)); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mas_push_node(&mas, mn); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); |