When kmalloc_node() is called without __GFP_THISNODE and the target node lacks sufficient memory, SLUB allocates a folio from a different node other than the requested node, instead of taking a partial slab from it. However, since the allocated folio does not belong to the requested node, it is deactivated and added to the partial slab list of the node it belongs to. This behavior can result in excessive memory usage when the requested node has insufficient memory, as SLUB will repeatedly allocate folios from other nodes without reusing the previously allocated ones. To prevent memory wastage, when (node != NUMA_NO_NODE) && !(gfpflags & __GFP_THISNODE) is, 1) try to get a partial slab from target node with GFP_NOWAIT | __GFP_THISNODE opportunistically. 2) if 1) failed, try to allocate a new slab from target node with GFP_NOWAIT | __GFP_THISNODE opportunistically too. 3) if 2) failed, retry 1) and 2) with orignal gfpflags. when node != NUMA_NO_NODE || (gfpflags & __GFP_THISNODE), the behavior remains unchanged. On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times. cat /proc/slabinfo shows: kmalloc-256 4200530 13519712 256 32 2 : tunables.. after this patch, cat /proc/slabinfo shows: kmalloc-256 4200558 4200768 256 32 2 : tunables.. Signed-off-by: Chen Jun <chenjun102@xxxxxxxxxx> Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> --- v2: - try to alloc partial slab or new slab with GFP_NOWAIT(it includes __GFP_NOWARN) opportunistically, then fallback to orignal gfpflag, suggested by Vlastimil Babka, - update changelog v1: https://lore.kernel.org/linux-mm/20230314123403.100158-1-chenjun102@xxxxxxxxxx/ mm/slub.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 1bb2a93cf7b6..c1c51595a59f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2699,7 +2699,7 @@ static struct slab *get_partial(struct kmem_cache *s, int node, searchnode = numa_mem_id(); slab = get_partial_node(s, get_node(s, searchnode), pc); - if (slab || node != NUMA_NO_NODE) + if (slab || (node != NUMA_NO_NODE && (pc->flags & __GFP_THISNODE))) return slab; return get_any_partial(s, pc); @@ -3375,6 +3375,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, struct slab *slab; unsigned long flags; struct partial_context pc; + bool try_thisnode = true; stat(s, ALLOC_SLOWPATH); @@ -3501,6 +3502,17 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, new_objects: pc.flags = gfpflags; + /* + * when (node != NUMA_NO_NODE) && !(gfpflags & __GFP_THISNODE) + * 1) try to get a partial slab from target node with GPF_NOWAIT | + * __GFP_THISNODE opportunistically. + * 2) if 1) failed, try to allocate a new slab from target node with + * GPF_NOWAIT | __GFP_THISNODE opportunistically too. + * 3) if 2) failed, retry 1) and 2) with original gfpflags. + */ + if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) && try_thisnode) + pc.flags = GFP_NOWAIT | __GFP_THISNODE; + pc.orig_size = orig_size; slab = get_partial(s, node, &pc); if (slab) { @@ -3522,10 +3534,15 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, } slub_put_cpu_ptr(s->cpu_slab); - slab = new_slab(s, gfpflags, node); + slab = new_slab(s, pc.flags, node); c = slub_get_cpu_ptr(s->cpu_slab); if (unlikely(!slab)) { + if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) && + try_thisnode) { + try_thisnode = false; + goto new_objects; + } slab_out_of_memory(s, gfpflags, node); return NULL; } -- 2.27.0
