The patch titled
cpusets: randomize node rotor used in cpuset_mem_spread_node()
has been added to the -mm tree. Its filename is
cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node()
From: Jack Steiner <steiner@xxxxxxx>
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.
Signed-off-by: Jack Steiner <steiner@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Jack Steiner <steiner@xxxxxxx>
Cc: Robin Holt <holt@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/mm/numa.c | 17 +++++++++++++++++
include/linux/bitmap.h | 1 +
include/linux/nodemask.h | 5 +++++
kernel/fork.c | 4 ++++
lib/bitmap.c | 2 +-
5 files changed, 28 insertions(+), 1 deletion(-)
diff -puN arch/x86/mm/numa.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node arch/x86/mm/numa.c
--- a/arch/x86/mm/numa.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node
+++ a/arch/x86/mm/numa.c
@@ -2,6 +2,7 @@
#include <linux/topology.h>
#include <linux/module.h>
#include <linux/bootmem.h>
+#include <linux/random.h>
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
# define DBG(x...) printk(KERN_DEBUG x)
@@ -65,3 +66,19 @@ const struct cpumask *cpumask_of_node(in
}
EXPORT_SYMBOL(cpumask_of_node);
#endif
+
+/*
+ * 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;
+}
+EXPORT_SYMBOL(__node_random);
diff -puN include/linux/bitmap.h~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node include/linux/bitmap.h
--- a/include/linux/bitmap.h~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node
+++ a/include/linux/bitmap.h
@@ -141,6 +141,7 @@ extern int bitmap_find_free_region(unsig
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 -puN include/linux/nodemask.h~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node include/linux/nodemask.h
--- a/include/linux/nodemask.h~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node
+++ a/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?
*
@@ -267,6 +269,9 @@ static inline int __first_unset_node(con
find_first_zero_bit(maskp->bits, MAX_NUMNODES));
}
+#define node_random(mask) __node_random(&(mask))
+extern int __node_random(const nodemask_t *maskp);
+
#define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES)
#if MAX_NUMNODES <= BITS_PER_LONG
diff -puN kernel/fork.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node kernel/fork.c
--- a/kernel/fork.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node
+++ a/kernel/fork.c
@@ -1080,6 +1080,10 @@ static struct task_struct *copy_process(
}
mpol_fix_fork_child_flag(p);
#endif
+#ifdef CONFIG_CPUSETS
+ p->cpuset_mem_spread_rotor = node_random(p->mems_allowed);
+ p->cpuset_slab_spread_rotor = node_random(p->mems_allowed);
+#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
diff -puN lib/bitmap.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node lib/bitmap.c
--- a/lib/bitmap.c~cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node
+++ a/lib/bitmap.c
@@ -672,7 +672,7 @@ static int bitmap_pos_to_ord(const unsig
*
* 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;
_
Patches currently in -mm which might be from steiner@xxxxxxx are
linux-next.patch
cpusets-new-round-robin-rotor-for-slab-allocations.patch
cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node.patch
pids-increase-pid_max-based-on-num_possible_cpus.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
