Date: Mon, 28 Oct 2019 11:56:17 -0400 Johannes Weiner wrote:
>
> On Sat, Oct 26, 2019 at 07:28:08PM +0800, Hillf Danton wrote:
> >
> > The cpu preemption feature makes a task able to preempt other tasks
> > of lower priorities for cpu. It has been around for a while.
> >
> > This work introduces task prio into page reclaiming in order to add
> > the page preemption feature that makes a task able to preempt other
> > tasks of lower priorities for page.
> >
> > No page will be reclaimed on behalf of tasks of lower priorities
>
> ... at which point they'll declare OOM and kill the high-pri task?
Fixed. Thanks.
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -164,6 +164,11 @@ static bool oom_unkillable_task(struct t
return true;
if (p->flags & PF_KTHREAD)
return true;
+
+#ifdef CONFIG_PAGE_PREEMPTION
+ if (p->prio < current->prio)
+ return true;
+#endif
return false;
}
--
> Please have a look at the cgroup2 memory.low control. This memory
> prioritization problem has already been solved.
Scooter never runs in subway. Fixed.
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -197,8 +198,18 @@ struct page {
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
atomic_t _refcount;
+ /* 32/56 bytes above */
+
#ifdef CONFIG_MEMCG
struct mem_cgroup *mem_cgroup;
+#else
+#ifdef CONFIG_64BIT
+ union {
+ int prio;
+ void *__pad;
+ };
+#define CONFIG_PAGE_PREEMPTION PP
+#endif
#endif
/*
--
