The patch titled
cpusets: new round-robin rotor for SLAB allocations
has been added to the -mm tree. Its filename is
cpusets-new-round-robin-rotor-for-slab-allocations.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: new round-robin rotor for SLAB allocations
From: Jack Steiner <steiner@xxxxxxx>
We have observed several workloads running on multi-node systems where
memory is assigned unevenly across the nodes in the system. There are
numerous reasons for this but one is the round-robin rotor in
cpuset_mem_spread_node().
For example, a simple test that writes a multi-page file will allocate
pages on nodes 0 2 4 6 ... Odd nodes are skipped. (Sometimes it
allocates on odd nodes & skips even nodes).
An example is shown below. The program "lfile" writes a file consisting
of 10 pages. The program then mmaps the file & uses get_mempolicy(...,
MPOL_F_NODE) to determine the nodes where the file pages were allocated.
The output is shown below:
# ./lfile
allocated on nodes: 2 4 6 0 1 2 6 0 2
There is a single rotor that is used for allocating both file pages & slab
pages. Writing the file allocates both a data page & a slab page
(buffer_head). This advances the RR rotor 2 nodes for each page
allocated.
A quick confirmation seems to confirm this is the cause of the uneven
allocation:
# echo 0 >/dev/cpuset/memory_spread_slab
# ./lfile
allocated on nodes: 6 7 8 9 0 1 2 3 4 5
This patch introduces a second rotor that is used for slab allocations.
Signed-off-by: Jack Steiner <steiner@xxxxxxx>
Acked-by: 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>
---
include/linux/cpuset.h | 6 ++++++
include/linux/sched.h | 1 +
kernel/cpuset.c | 20 ++++++++++++++++----
mm/slab.c | 2 +-
4 files changed, 24 insertions(+), 5 deletions(-)
diff -puN include/linux/cpuset.h~cpusets-new-round-robin-rotor-for-slab-allocations include/linux/cpuset.h
--- a/include/linux/cpuset.h~cpusets-new-round-robin-rotor-for-slab-allocations
+++ a/include/linux/cpuset.h
@@ -69,6 +69,7 @@ extern void cpuset_task_status_allowed(s
struct task_struct *task);
extern int cpuset_mem_spread_node(void);
+extern int cpuset_slab_spread_node(void);
static inline int cpuset_do_page_mem_spread(void)
{
@@ -159,6 +160,11 @@ static inline int cpuset_mem_spread_node
return 0;
}
+static inline int cpuset_slab_spread_node(void)
+{
+ return 0;
+}
+
static inline int cpuset_do_page_mem_spread(void)
{
return 0;
diff -puN include/linux/sched.h~cpusets-new-round-robin-rotor-for-slab-allocations include/linux/sched.h
--- a/include/linux/sched.h~cpusets-new-round-robin-rotor-for-slab-allocations
+++ a/include/linux/sched.h
@@ -1423,6 +1423,7 @@ struct task_struct {
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
int cpuset_mem_spread_rotor;
+ int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock */
diff -puN kernel/cpuset.c~cpusets-new-round-robin-rotor-for-slab-allocations kernel/cpuset.c
--- a/kernel/cpuset.c~cpusets-new-round-robin-rotor-for-slab-allocations
+++ a/kernel/cpuset.c
@@ -2427,7 +2427,8 @@ void cpuset_unlock(void)
}
/**
- * cpuset_mem_spread_node() - On which node to begin search for a page
+ * cpuset_mem_spread_node() - On which node to begin search for a file page
+ * cpuset_slab_spread_node() - On which node to begin search for a slab page
*
* If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
* tasks in a cpuset with is_spread_page or is_spread_slab set),
@@ -2452,16 +2453,27 @@ void cpuset_unlock(void)
* See kmem_cache_alloc_node().
*/
-int cpuset_mem_spread_node(void)
+static int cpuset_spread_node(int *rotor)
{
int node;
- node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
+ node = next_node(*rotor, current->mems_allowed);
if (node == MAX_NUMNODES)
node = first_node(current->mems_allowed);
- current->cpuset_mem_spread_rotor = node;
+ *rotor = node;
return node;
}
+
+int cpuset_mem_spread_node(void)
+{
+ return cpuset_spread_node(¤t->cpuset_mem_spread_rotor);
+}
+
+int cpuset_slab_spread_node(void)
+{
+ return cpuset_spread_node(¤t->cpuset_slab_spread_rotor);
+}
+
EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
/**
diff -puN mm/slab.c~cpusets-new-round-robin-rotor-for-slab-allocations mm/slab.c
--- a/mm/slab.c~cpusets-new-round-robin-rotor-for-slab-allocations
+++ a/mm/slab.c
@@ -3242,7 +3242,7 @@ static void *alternate_node_alloc(struct
return NULL;
nid_alloc = nid_here = numa_node_id();
if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
- nid_alloc = cpuset_mem_spread_node();
+ nid_alloc = cpuset_slab_spread_node();
else if (current->mempolicy)
nid_alloc = slab_node(current->mempolicy);
if (nid_alloc != nid_here)
_
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
