Messages in this thread Patch in this message |  | | | Date | Tue, 10 May 2011 17:57:46 +0900 | | From | KAMEZAWA Hiroyuki <> | | Subject | Re: mmotm 2011-05-06-16-39 uploaded |
| |
On Fri, 06 May 2011 16:39:31 -0700 akpm@linux-foundation.org wrote:
> memcg-reclaim-memory-from-nodes-in-round-robin-order.patch > memcg-reclaim-memory-from-nodes-in-round-robin-fix.patch
I'm very sorry that this fix is required for this logic. ==
next_scan_node_update is the time when scan_nodes nodemask should be updated. Then, time_after() is correct. Otherwise, next-scan_node_update is intialized to be 0 and time_before() returns always true, scan_nodes never be updated.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) Index: mmotm-May6/mm/memcontrol.c =================================================================== --- mmotm-May6.orig/mm/memcontrol.c +++ mmotm-May6/mm/memcontrol.c @@ -1517,7 +1517,7 @@ static void mem_cgroup_may_update_nodema { int nid; - if (time_before(mem->next_scan_node_update, jiffies)) + if (time_after(mem->next_scan_node_update, jiffies)) return; mem->next_scan_node_update = jiffies + 10*HZ;
|  |