From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: [PATCH] cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 + include/linux/nodemask.h | 13 +++++++++++++ kernel/cpuset.c | 8 ++++++++ kernel/fork.c | 4 ++++ lib/bitmap.c | 2 +- mm/mempolicy.c | 16 ++++++++++++++++ 6 files changed, 43 insertions(+), 1 deletion(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0bf000..3bac44cce14 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -144,6 +144,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index dba35e41337..7afc36334d5 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -66,6 +66,8 @@ * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * + * int node_random(mask) Random node with set bit in mask + * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * @@ -430,6 +432,7 @@ static inline void node_set_offline(int nid) node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } + #else static inline int node_state(int node, enum node_states state) @@ -460,6 +463,16 @@ static inline int num_node_state(enum node_states state) #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) + +#endif + +#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) +extern int node_random(const nodemask_t *maskp); +#else +static inline int node_random(const nodemask_t *mask) +{ + return 0; +} #endif #define node_online_map node_states[N_ONLINE] diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9c9b7545c81..f8bc977ccbb 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2460,11 +2460,19 @@ static int cpuset_spread_node(int *rotor) int cpuset_mem_spread_node(void) { + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } diff --git a/kernel/fork.c b/kernel/fork.c index 17bf7c8d651..e33177edb3b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1173,6 +1173,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; +#endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW diff --git a/lib/bitmap.c b/lib/bitmap.c index 3f3b68199d7..37ef4b04879 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -756,7 +756,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits) * * The bit positions 0 through @bits are valid positions in @buf. */ -static int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits) +int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits) { int pos = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e7fb9d25c54..8b57173c1dd 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -93,6 +93,7 @@ #include #include +#include #include "internal.h" @@ -1645,6 +1646,21 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } +/* + * Return the bit number of a random bit set in the nodemask. + * (returns -1 if nodemask is empty) + */ +int node_random(const nodemask_t *maskp) +{ + int w, bit = -1; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +} + #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol)