提交 ae74138d 编写于 作者: D David Rientjes 提交者: Linus Torvalds

oom: convert zone_scan_lock from mutex to spinlock

There's no reason to sleep in try_set_zone_oom() or clear_zonelist_oom() if
the lock can't be acquired; it will be available soon enough once the zonelist
scanning is done.  All other threads waiting for the OOM killer are also
contingent on the exiting task being able to acquire the lock in
clear_zonelist_oom() so it doesn't make sense to put it to sleep.

Cc: Andrea Arcangeli <andrea@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 9aad369e
......@@ -28,7 +28,7 @@
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
static DEFINE_MUTEX(zone_scan_mutex);
static DEFINE_SPINLOCK(zone_scan_mutex);
/* #define DEBUG */
/**
......@@ -396,7 +396,7 @@ int try_set_zone_oom(struct zonelist *zonelist)
z = zonelist->zones;
mutex_lock(&zone_scan_mutex);
spin_lock(&zone_scan_mutex);
do {
if (zone_is_oom_locked(*z)) {
ret = 0;
......@@ -413,7 +413,7 @@ int try_set_zone_oom(struct zonelist *zonelist)
zone_set_flag(*z, ZONE_OOM_LOCKED);
} while (*(++z) != NULL);
out:
mutex_unlock(&zone_scan_mutex);
spin_unlock(&zone_scan_mutex);
return ret;
}
......@@ -428,11 +428,11 @@ void clear_zonelist_oom(struct zonelist *zonelist)
z = zonelist->zones;
mutex_lock(&zone_scan_mutex);
spin_lock(&zone_scan_mutex);
do {
zone_clear_flag(*z, ZONE_OOM_LOCKED);
} while (*(++z) != NULL);
mutex_unlock(&zone_scan_mutex);
spin_unlock(&zone_scan_mutex);
}
/**
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册