diff options
author | David Rientjes <rientjes@google.com> | 2010-08-10 00:18:52 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-08-10 03:44:56 (GMT) |
commit | 6f48d0ebd907ae419387f27b602ee98870cfa7bb (patch) | |
tree | 355bd8b616f5a78d8adabe5b9631d7aad970dbaa /mm | |
parent | 5e9d834a0e0c0485dfa487281ab9650fc37a3bb5 (diff) | |
download | linux-6f48d0ebd907ae419387f27b602ee98870cfa7bb.tar.xz |
oom: select task from tasklist for mempolicy ooms
The oom killer presently kills current whenever there is no more memory
free or reclaimable on its mempolicy's nodes. There is no guarantee that
current is a memory-hogging task or that killing it will free any
substantial amount of memory, however.
In such situations, it is better to scan the tasklist for nodes that are
allowed to allocate on current's set of nodes and kill the task with the
highest badness() score. This ensures that the most memory-hogging task,
or the one configured by the user with /proc/pid/oom_adj, is always
selected in such scenarios.
Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/mempolicy.c | 44 | ||||
-rw-r--r-- | mm/oom_kill.c | 104 |
2 files changed, 112 insertions, 36 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5bc0a96..8a73708 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1712,6 +1712,50 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) } #endif +/* + * mempolicy_nodemask_intersects + * + * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default + * policy. Otherwise, check for intersection between mask and the policy + * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' + * policy, always return true since it may allocate elsewhere on fallback. + * + * Takes task_lock(tsk) to prevent freeing of its mempolicy. + */ +bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask) +{ + struct mempolicy *mempolicy; + bool ret = true; + + if (!mask) + return ret; + task_lock(tsk); + mempolicy = tsk->mempolicy; + if (!mempolicy) + goto out; + + switch (mempolicy->mode) { + case MPOL_PREFERRED: + /* + * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to + * allocate from, they may fallback to other nodes when oom. + * Thus, it's possible for tsk to have allocated memory from + * nodes in mask. + */ + break; + case MPOL_BIND: + case MPOL_INTERLEAVE: + ret = nodes_intersects(mempolicy->v.nodes, *mask); + break; + default: + BUG(); + } +out: + task_unlock(tsk); + return ret; +} + /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7c8488f..13ceed7 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -27,6 +27,7 @@ #include <linux/module.h> #include <linux/notifier.h> #include <linux/memcontrol.h> +#include <linux/mempolicy.h> #include <linux/security.h> int sysctl_panic_on_oom; @@ -35,23 +36,57 @@ int sysctl_oom_dump_tasks; static DEFINE_SPINLOCK(zone_scan_lock); /* #define DEBUG */ -/* - * Is all threads of the target process nodes overlap ours? +#ifdef CONFIG_NUMA +/** + * has_intersects_mems_allowed() - check task eligiblity for kill + * @tsk: task struct of which task to consider + * @mask: nodemask passed to page allocator for mempolicy ooms + * + * Task eligibility is determined by whether or not a candidate task, @tsk, + * shares the same mempolicy nodes as current if it is bound by such a policy + * and whether or not it has the same set of allowed cpuset nodes. */ -static int has_intersects_mems_allowed(struct task_struct *tsk) +static bool has_intersects_mems_allowed(struct task_struct *tsk, + const nodemask_t *mask) { - struct task_struct *t; + struct task_struct *start = tsk; - t = tsk; do { - if (cpuset_mems_allowed_intersects(current, t)) - return 1; - t = next_thread(t); - } while (t != tsk); - - return 0; + if (mask) { + /* + * If this is a mempolicy constrained oom, tsk's + * cpuset is irrelevant. Only return true if its + * mempolicy intersects current, otherwise it may be + * needlessly killed. + */ + if (mempolicy_nodemask_intersects(tsk, mask)) + return true; + } else { + /* + * This is not a mempolicy constrained oom, so only + * check the mems of tsk's cpuset. + */ + if (cpuset_mems_allowed_intersects(current, tsk)) + return true; + } + tsk = next_thread(tsk); + } while (tsk != start); + return false; +} +#else +static bool has_intersects_mems_allowed(struct task_struct *tsk, + const nodemask_t *mask) +{ + return true; } +#endif /* CONFIG_NUMA */ +/* + * The process p may have detached its own ->mm while exiting or through + * use_mm(), but one or more of its subthreads may still have a valid + * pointer. Return p, or any of its subthreads with a valid ->mm, with + * task_lock() held. + */ static struct task_struct *find_lock_task_mm(struct task_struct *p) { struct task_struct *t = p; @@ -106,10 +141,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * The memory size of the process is the basis for the badness. */ points = p->mm->total_vm; - - /* - * After this unlock we can no longer dereference local variable `mm' - */ task_unlock(p); /* @@ -253,7 +284,8 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned long *ppoints, - struct mem_cgroup *mem) + struct mem_cgroup *mem, enum oom_constraint constraint, + const nodemask_t *mask) { struct task_struct *p; struct task_struct *chosen = NULL; @@ -269,7 +301,9 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, continue; if (mem && !task_in_mem_cgroup(p, mem)) continue; - if (!has_intersects_mems_allowed(p)) + if (!has_intersects_mems_allowed(p, + constraint == CONSTRAINT_MEMORY_POLICY ? mask : + NULL)) continue; /* @@ -497,7 +531,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) panic("out of memory(memcg). panic_on_oom is selected.\n"); read_lock(&tasklist_lock); retry: - p = select_bad_process(&points, mem); + p = select_bad_process(&points, mem, CONSTRAINT_NONE, NULL); if (!p || PTR_ERR(p) == -1UL) goto out; @@ -576,7 +610,8 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) /* * Must be called with tasklist_lock held for read. */ -static void __out_of_memory(gfp_t gfp_mask, int order) +static void __out_of_memory(gfp_t gfp_mask, int order, + enum oom_constraint constraint, const nodemask_t *mask) { struct task_struct *p; unsigned long points; @@ -590,7 +625,7 @@ retry: * Rambo mode: Shoot down a process and hope it solves whatever * issues we may have. */ - p = select_bad_process(&points, NULL); + p = select_bad_process(&points, NULL, constraint, mask); if (PTR_ERR(p) == -1UL) return; @@ -624,7 +659,8 @@ void pagefault_out_of_memory(void) panic("out of memory from page fault. panic_on_oom is selected.\n"); read_lock(&tasklist_lock); - __out_of_memory(0, 0); /* unknown gfp_mask and order */ + /* unknown gfp_mask and order */ + __out_of_memory(0, 0, CONSTRAINT_NONE, NULL); read_unlock(&tasklist_lock); /* @@ -640,6 +676,7 @@ void pagefault_out_of_memory(void) * @zonelist: zonelist pointer * @gfp_mask: memory allocation flags * @order: amount of memory being requested as a power of 2 + * @nodemask: nodemask passed to page allocator * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) @@ -678,24 +715,19 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ constraint = constrained_alloc(zonelist, gfp_mask, nodemask); read_lock(&tasklist_lock); - - switch (constraint) { - case CONSTRAINT_MEMORY_POLICY: - oom_kill_process(current, gfp_mask, order, 0, NULL, - "No available memory (MPOL_BIND)"); - break; - - case CONSTRAINT_NONE: - if (sysctl_panic_on_oom) { + if (unlikely(sysctl_panic_on_oom)) { + /* + * panic_on_oom only affects CONSTRAINT_NONE, the kernel + * should not panic for cpuset or mempolicy induced memory + * failures. + */ + if (constraint == CONSTRAINT_NONE) { dump_header(NULL, gfp_mask, order, NULL); - panic("out of memory. panic_on_oom is selected\n"); + read_unlock(&tasklist_lock); + panic("Out of memory: panic_on_oom is enabled\n"); } - /* Fall-through */ - case CONSTRAINT_CPUSET: - __out_of_memory(gfp_mask, order); - break; } - + __out_of_memory(gfp_mask, order, constraint, nodemask); read_unlock(&tasklist_lock); /* |