Revision 72853e2991a2702ae93aaf889ac7db743a415dd3 authored by Mel Gorman on 09 September 2010, 23:38:16 UTC, committed by Linus Torvalds on 10 September 2010, 01:57:25 UTC
When allocating a page, the system uses NR_FREE_PAGES counters to determine if watermarks would remain intact after the allocation was made. This check is made without interrupts disabled or the zone lock held and so is race-prone by nature. Unfortunately, when pages are being freed in batch, the counters are updated before the pages are added on the list. During this window, the counters are misleading as the pages do not exist yet. When under significant pressure on systems with large numbers of CPUs, it's possible for processes to make progress even though they should have been stalled. This is particularly problematic if a number of the processes are using GFP_ATOMIC as the min watermark can be accidentally breached and in extreme cases, the system can livelock. This patch updates the counters after the pages have been added to the list. This makes the allocator more cautious with respect to preserving the watermarks and mitigates livelock possibilities. [akpm@linux-foundation.org: avoid modifying incoming args] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Christoph Lameter <cl@linux.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5ee28a4
noop-iosched.c
/*
* elevator noop
*/
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
struct noop_data {
struct list_head queue;
};
static void noop_merged_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
list_del_init(&next->queuelist);
}
static int noop_dispatch(struct request_queue *q, int force)
{
struct noop_data *nd = q->elevator->elevator_data;
if (!list_empty(&nd->queue)) {
struct request *rq;
rq = list_entry(nd->queue.next, struct request, queuelist);
list_del_init(&rq->queuelist);
elv_dispatch_sort(q, rq);
return 1;
}
return 0;
}
static void noop_add_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
list_add_tail(&rq->queuelist, &nd->queue);
}
static int noop_queue_empty(struct request_queue *q)
{
struct noop_data *nd = q->elevator->elevator_data;
return list_empty(&nd->queue);
}
static struct request *
noop_former_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
if (rq->queuelist.prev == &nd->queue)
return NULL;
return list_entry(rq->queuelist.prev, struct request, queuelist);
}
static struct request *
noop_latter_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
if (rq->queuelist.next == &nd->queue)
return NULL;
return list_entry(rq->queuelist.next, struct request, queuelist);
}
static void *noop_init_queue(struct request_queue *q)
{
struct noop_data *nd;
nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
if (!nd)
return NULL;
INIT_LIST_HEAD(&nd->queue);
return nd;
}
static void noop_exit_queue(struct elevator_queue *e)
{
struct noop_data *nd = e->elevator_data;
BUG_ON(!list_empty(&nd->queue));
kfree(nd);
}
static struct elevator_type elevator_noop = {
.ops = {
.elevator_merge_req_fn = noop_merged_requests,
.elevator_dispatch_fn = noop_dispatch,
.elevator_add_req_fn = noop_add_request,
.elevator_queue_empty_fn = noop_queue_empty,
.elevator_former_req_fn = noop_former_request,
.elevator_latter_req_fn = noop_latter_request,
.elevator_init_fn = noop_init_queue,
.elevator_exit_fn = noop_exit_queue,
},
.elevator_name = "noop",
.elevator_owner = THIS_MODULE,
};
static int __init noop_init(void)
{
elv_register(&elevator_noop);
return 0;
}
static void __exit noop_exit(void)
{
elv_unregister(&elevator_noop);
}
module_init(noop_init);
module_exit(noop_exit);
MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("No-op IO scheduler");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...