The patch titled
SLUB: explain sizing of slabs in detail
has been added to the -mm tree. Its filename is
slub-core-explain-sizing-of-slabs-in-detail.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: SLUB: explain sizing of slabs in detail
From: Christoph Lameter <clameter@xxxxxxx>
Signed-off-by: Christoph Lameter <clameter@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/slub.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 65 insertions(+), 3 deletions(-)
diff -puN mm/slub.c~slub-core-explain-sizing-of-slabs-in-detail mm/slub.c
--- a/mm/slub.c~slub-core-explain-sizing-of-slabs-in-detail
+++ a/mm/slub.c
@@ -1381,6 +1381,27 @@ static int slub_debug;
static char *slub_debug_slabs;
+/*
+ * Calculate the order of allocation given an slab object size.
+ *
+ * The order of allocation has significant impact on other elements
+ * of the system. Generally order 0 allocations should be preferred
+ * since they do not cause fragmentation in the page allocator. Larger
+ * objects may have problems with order 0 because there may be too much
+ * space left unused in a slab. We go to a higher order if more than 1/8th
+ * of the slab would be wasted.
+ *
+ * In order to reach satisfactory performance we must insure that
+ * a minimum number of objects is in one slab. Otherwise we may
+ * generate too much activity on the partial lists. This is less a
+ * concern for large slabs though. slub_max_order specified the order
+ * where we begin to stop considering the number of objects in a slab.
+ *
+ * Higher order allocations also allow the placement of more objects
+ * in a slab and thereby reduce object handling overhead. If the user
+ * has requested a higher mininum order then we start with that one
+ * instead of zero.
+ */
static int calculate_order(int size)
{
int order;
@@ -1408,6 +1429,10 @@ static int calculate_order(int size)
return order;
}
+/*
+ * Function to figure out which alignment to use from the
+ * various ways of specifying it.
+ */
static unsigned long calculate_alignment(unsigned long flags,
unsigned long align)
{
@@ -1520,28 +1545,48 @@ static int init_kmem_cache_nodes(struct
}
#endif
+/*
+ * calculate_sizes() determines the order and the distribution of data within
+ * a slab object.
+ */
static int calculate_sizes(struct kmem_cache *s)
{
unsigned long flags = s->flags;
unsigned long size = s->objsize;
unsigned long align = s->align;
+ /*
+ * Determine if we can poison the object itself. If the user of
+ * the slab may touch the object after free or before allocation
+ * then we should never poison the object itself.
+ */
if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
!s->ctor && !s->dtor)
flags |= __OBJECT_POISON;
else
flags &= ~__OBJECT_POISON;
+ /*
+ * Round up object size to the next word boundary. We can only
+ * place the free pointer at word boundaries and this determines
+ * the possible location of the free pointer.
+ */
size = ALIGN(size, sizeof(void *));
/*
- * If we redzone then check if we have space through above
- * alignment. If not then add an additional word, so
- * that we have a guard value to check for overwrites.
+ * If we redzone then check if we there is some space between the
+ * end of the object and the free pointer. If not then add an
+ * additional word, so that we can establish a redzone between
+ * the object and the freepointer to be able to chek for overwrites.
*/
if ((flags & SLAB_RED_ZONE) && size == s->objsize)
size += sizeof(void *);
+ /*
+ * With that we have determined how much of the slab is in actual
+ * use by the object. This is the potential offset to the free
+ * pointer.
+ */
s->inuse = size;
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
@@ -1559,10 +1604,24 @@ static int calculate_sizes(struct kmem_c
}
if (flags & SLAB_STORE_USER)
+ /*
+ * Need to store information about allocs and frees after
+ * the object.
+ */
size += 2 * sizeof(struct track);
+ /*
+ * Determine the alignment based on various parameters that the
+ * user specified (this is unecessarily complex due to the attempt
+ * to be compatible with SLAB. Should be cleaned up some day).
+ */
align = calculate_alignment(flags, align);
+ /*
+ * SLUB stores one object immediately after another beginning from
+ * offset 0. In order to align the objects we have to simply size
+ * each object to conform to the alignment.
+ */
size = ALIGN(size, align);
s->size = size;
@@ -1570,6 +1629,9 @@ static int calculate_sizes(struct kmem_c
if (s->order < 0)
return 0;
+ /*
+ * Determine the number of objects per slab
+ */
s->objects = (PAGE_SIZE << s->order) / size;
/*
_
Patches currently in -mm which might be from clameter@xxxxxxx are
slab-introduce-krealloc.patch
slab-introduce-krealloc-fix.patch
paravirt_ops-allow-paravirt-backend-to-choose-kernel-pmd-sharing.patch
add-apply_to_page_range-which-applies-a-function-to-a-pte-range.patch
safer-nr_node_ids-and-nr_node_ids-determination-and-initial.patch
use-zvc-counters-to-establish-exact-size-of-dirtyable-pages.patch
slab-ensure-cache_alloc_refill-terminates.patch
smaps-extract-pmd-walker-from-smaps-code.patch
smaps-add-pages-referenced-count-to-smaps.patch
smaps-add-clear_refs-file-to-clear-reference.patch
smaps-add-clear_refs-file-to-clear-reference-fix.patch
smaps-add-clear_refs-file-to-clear-reference-fix-fix.patch
slab-use-num_possible_cpus-in-enable_cpucache.patch
extend-print_symbol-capability-fix.patch
i386-use-page-allocator-to-allocate-thread_info-structure.patch
slub-core.patch
slub-fix-numa-bootstrap.patch
slub-use-correct-flags-to-check-for-dma-cache.patch
slub-treat-slab_hwcache_align-as-a-mininum-and-not-as-the-alignment.patch
slub-core-minor-fixes.patch
slub-core-use-enum-for-tracking-modes-instead-of-integers.patch
slub-core-fix-another-numa-bootstrap-issue.patch
slub-core-fix-object-counting.patch
slub-core-drop-version-number.patch
slub-core-tidy.patch
slub-core-tidy-2.patch
slub-core-tidy-3.patch
slub-core-tidy-4.patch
slub-core-tidy-5.patch
slub-core-tidy-6.patch
slub-core-tidy-7.patch
slub-core-tidy-8.patch
slub-core-tidy-9.patch
slub-core-we-do-not-need-ifdef-config_smp-around-bit-spinlocks.patch
slub-core-printk-facility-level-cleanup.patch
slub-core-kmem_cache_close-is-static-and-should-not-be-exported.patch
slub-core-add-explanation-for-defrag_ratio-=-100.patch
slub-core-add-explanation-for-locking.patch
slub-core-add-explanation-for-locking-fix.patch
slub-core-explain-the-64k-limits.patch
slub-core-explain-sizing-of-slabs-in-detail.patch
slub-add-slabinfo-tool.patch
slub-add-slabinfo-tool-update-slabinfoc.patch
make-page-private-usable-in-compound-pages-v1.patch
make-page-private-usable-in-compound-pages-v1-hugetlb-fix.patch
optimize-compound_head-by-avoiding-a-shared-page.patch
add-virt_to_head_page-and-consolidate-code-in-slab-and-slub.patch
slub-fix-object-tracking.patch
slub-enable-tracking-of-full-slabs.patch
slub-enable-tracking-of-full-slabs-fix.patch
slub-validation-of-slabs-metadata-and-guard-zones.patch
slub-add-ability-to-list-alloc--free-callers-per-slab.patch
slub-add-ability-to-list-alloc--free-callers-per-slab-tidy.patch
quicklists-for-page-table-pages.patch
quicklists-for-page-table-pages-avoid-useless-virt_to_page-conversion.patch
quicklist-support-for-ia64.patch
quicklist-support-for-x86_64.patch
quicklist-support-for-sparc64.patch
slab-shutdown-cache_reaper-when-cpu-goes-down.patch
mm-implement-swap-prefetching.patch
readahead-state-based-method-aging-accounting.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
