summaryrefslogtreecommitdiffstats
path: root/include/linux/mempolicy.h
diff options
context:
space:
mode:
authorMiao Xie <miaox@cn.fujitsu.com>2010-05-24 14:32:07 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-25 08:06:57 -0700
commit708c1bbc9d0c3e57f40501794d9b0eed29d10fce (patch)
tree4b19caf68c420b32abdf05af3d413b1320f04fbe /include/linux/mempolicy.h
parent971ada0f6659488c3f36aed4c6f7670ff5ce4368 (diff)
downloadlinux-708c1bbc9d0c3e57f40501794d9b0eed29d10fce.tar.gz
linux-708c1bbc9d0c3e57f40501794d9b0eed29d10fce.tar.bz2
linux-708c1bbc9d0c3e57f40501794d9b0eed29d10fce.zip
mempolicy: restructure rebinding-mempolicy functions
Nick Piggin reported that the allocator may see an empty nodemask when changing cpuset's mems[1]. It happens only on the kernel that do not do atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG) But I found that there is also a problem on the kernel that can do atomic nodemask_t stores. The problem is that the allocator can't find a node to alloc page when changing cpuset's mems though there is a lot of free memory. The reason is like this: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom I can use the attached program reproduce it by the following step: # mkdir /dev/cpuset # mount -t cpuset cpuset /dev/cpuset # mkdir /dev/cpuset/1 # echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus # echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems # echo $$ > /dev/cpuset/1/tasks # numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog <nr_tasks> & <nr_tasks> = max(nr_cpus - 1, 1) # killall -s SIGUSR1 cpuset_mem_hog # ./change_mems.sh several hours later, oom will happen though there is a lot of free memory. This patchset fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. This patch: In order to fix no node to alloc memory, when we want to update mempolicy and mems_allowed, we expand the set of nodes first (set all the newly nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the mempolicy's rebind functions may breaks the expanding. So we restructure the mempolicy's rebind functions and split the rebind work to two steps, just like the update of cpuset's mems: The 1st step: expand the set of the mempolicy's nodes. The 2nd step: shrink the set of the mempolicy's nodes. It is used when there is no real lock to protect the mempolicy in the read-side. Otherwise we can do rebind work at once. In order to implement it, we define enum mpol_rebind_step { MPOL_REBIND_ONCE, MPOL_REBIND_STEP1, MPOL_REBIND_STEP2, MPOL_REBIND_NSTEP, }; If the mempolicy needn't be updated by two steps, we can pass MPOL_REBIND_ONCE to the rebind functions. Or we can pass MPOL_REBIND_STEP1 to do the first step of the rebind work and pass MPOL_REBIND_STEP2 to do the second step work. Besides that, it maybe long time between these two step and we have to release the lock that protects mempolicy and mems_allowed. If we hold the lock once again, we must check whether the current mempolicy is under the rebinding (the first step has been done) or not, because the task may alloc a new mempolicy when we don't hold the lock. So we defined the following flag to identify it: #define MPOL_F_REBINDING (1 << 2) The new functions will be used in the next patch. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Menage <menage@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/mempolicy.h')
-rw-r--r--include/linux/mempolicy.h15
1 files changed, 12 insertions, 3 deletions
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 1cc966cd3e5f..7b9ef6bf45aa 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -23,6 +23,13 @@ enum {
MPOL_MAX, /* always last member of enum */
};
+enum mpol_rebind_step {
+ MPOL_REBIND_ONCE, /* do rebind work at once(not by two step) */
+ MPOL_REBIND_STEP1, /* first step(set all the newly nodes) */
+ MPOL_REBIND_STEP2, /* second step(clean all the disallowed nodes)*/
+ MPOL_REBIND_NSTEP,
+};
+
/* Flags for set_mempolicy */
#define MPOL_F_STATIC_NODES (1 << 15)
#define MPOL_F_RELATIVE_NODES (1 << 14)
@@ -51,6 +58,7 @@ enum {
*/
#define MPOL_F_SHARED (1 << 0) /* identify shared policies */
#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
+#define MPOL_F_REBINDING (1 << 2) /* identify policies in rebinding */
#ifdef __KERNEL__
@@ -193,8 +201,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
extern void numa_default_policy(void);
extern void numa_policy_init(void);
-extern void mpol_rebind_task(struct task_struct *tsk,
- const nodemask_t *new);
+extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
+ enum mpol_rebind_step step);
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
extern void mpol_fix_fork_child_flag(struct task_struct *p);
@@ -308,7 +316,8 @@ static inline void numa_default_policy(void)
}
static inline void mpol_rebind_task(struct task_struct *tsk,
- const nodemask_t *new)
+ const nodemask_t *new,
+ enum mpol_rebind_step step)
{
}