From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
To: Mel Gorman <mgorman@techsingularity.net>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Linux-MM <linux-mm@kvack.org>, Rik van Riel <riel@surriel.com>,
Vlastimil Babka <vbabka@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
Date: Thu, 7 Jul 2016 10:20:39 +0900 [thread overview]
Message-ID: <20160707012038.GB27987@js1304-P5Q-DELUXE> (raw)
In-Reply-To: <1467403299-25786-9-git-send-email-mgorman@techsingularity.net>
On Fri, Jul 01, 2016 at 09:01:16PM +0100, Mel Gorman wrote:
> kswapd goes through some complex steps trying to figure out if it should
> stay awake based on the classzone_idx and the requested order. It is
> unnecessarily complex and passes in an invalid classzone_idx to
> balance_pgdat(). What matters most of all is whether a larger order has
> been requsted and whether kswapd successfully reclaimed at the previous
> order. This patch irons out the logic to check just that and the end
> result is less headache inducing.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> include/linux/mmzone.h | 5 ++-
> mm/memory_hotplug.c | 5 ++-
> mm/page_alloc.c | 2 +-
> mm/vmscan.c | 102 ++++++++++++++++++++++++++-----------------------
> 4 files changed, 62 insertions(+), 52 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 258c20758e80..eb74e63df5cf 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -667,8 +667,9 @@ typedef struct pglist_data {
> wait_queue_head_t pfmemalloc_wait;
> struct task_struct *kswapd; /* Protected by
> mem_hotplug_begin/end() */
> - int kswapd_max_order;
> - enum zone_type classzone_idx;
> + int kswapd_order;
> + enum zone_type kswapd_classzone_idx;
> +
> #ifdef CONFIG_COMPACTION
> int kcompactd_max_order;
> enum zone_type kcompactd_classzone_idx;
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index c5278360ca66..065140ecd081 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
>
> arch_refresh_nodedata(nid, pgdat);
> } else {
> - /* Reset the nr_zones and classzone_idx to 0 before reuse */
> + /* Reset the nr_zones, order and classzone_idx before reuse */
> pgdat->nr_zones = 0;
> - pgdat->classzone_idx = 0;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = 0;
> }
>
> /* we can use NODE_DATA(nid) from here */
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 59e4463e5dce..f58548139bf2 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -6084,7 +6084,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
> unsigned long end_pfn = 0;
>
> /* pg_data_t should be reset to zero when it's allocated */
> - WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
> + WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
>
> reset_deferred_meminit(pgdat);
> pgdat->node_id = nid;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index a52167eabc96..b524d3b72527 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
>
> /* kswapd must be awake if processes are being throttled */
> if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
> - pgdat->classzone_idx = min(pgdat->classzone_idx,
> + pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
> (enum zone_type)ZONE_NORMAL);
> wake_up_interruptible(&pgdat->kswapd_wait);
> }
> @@ -3238,8 +3238,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> return sc.order;
> }
>
> -static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> - int classzone_idx, int balanced_classzone_idx)
> +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
> + int classzone_idx)
> {
> long remaining = 0;
> DEFINE_WAIT(wait);
> @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
>
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
>
> + /*
> + * If kswapd has not been woken recently, then kswapd goes fully
> + * to sleep. kcompactd may still need to wake if the original
> + * request was high-order.
> + */
> + if (classzone_idx == -1) {
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> + classzone_idx = MAX_NR_ZONES - 1;
> + goto full_sleep;
> + }
Passing -1 to kcompactd would cause the problem?
> +
> /* Try to sleep for a short interval */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
> /*
> * Compaction records what page blocks it recently failed to
> * isolate pages from and skips them in the future scanning.
> @@ -3264,19 +3274,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> * We have freed the memory, now we should compact it to make
> * allocation of the requested order possible.
> */
> - wakeup_kcompactd(pgdat, order, classzone_idx);
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
>
> remaining = schedule_timeout(HZ/10);
> finish_wait(&pgdat->kswapd_wait, &wait);
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> }
>
> +full_sleep:
> /*
> * After a short sleep, check if it was a premature sleep. If not, then
> * go fully to sleep until explicitly woken up.
> */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
> trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
>
> /*
> @@ -3317,9 +3327,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> */
> static int kswapd(void *p)
> {
> - unsigned long order, new_order;
> - int classzone_idx, new_classzone_idx;
> - int balanced_classzone_idx;
> + unsigned int alloc_order, reclaim_order, classzone_idx;
> pg_data_t *pgdat = (pg_data_t*)p;
> struct task_struct *tsk = current;
>
> @@ -3349,38 +3357,26 @@ static int kswapd(void *p)
> tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
> set_freezable();
>
> - order = new_order = 0;
> - classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
> - balanced_classzone_idx = classzone_idx;
> + pgdat->kswapd_order = alloc_order = reclaim_order = 0;
> + pgdat->kswapd_classzone_idx = classzone_idx = -1;
> for ( ; ; ) {
> bool ret;
>
> +kswapd_try_sleep:
> + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
> + classzone_idx);
> +
> /*
> - * While we were reclaiming, there might have been another
> - * wakeup, so check the values.
> + * Read the new order and classzone_idx which may be -1 if
> + * kswapd_try_to_sleep() woke up after a short timeout instead
> + * of being woken by the page allocator.
> */
> - new_order = pgdat->kswapd_max_order;
> - new_classzone_idx = pgdat->classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> -
> - if (order < new_order || classzone_idx > new_classzone_idx) {
> - /*
> - * Don't sleep if someone wants a larger 'order'
> - * allocation or has tigher zone constraints
> - */
> - order = new_order;
> - classzone_idx = new_classzone_idx;
> - } else {
> - kswapd_try_to_sleep(pgdat, order, classzone_idx,
> - balanced_classzone_idx);
> - order = pgdat->kswapd_max_order;
> - classzone_idx = pgdat->classzone_idx;
> - new_order = order;
> - new_classzone_idx = classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> - }
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> + if (classzone_idx == -1)
> + classzone_idx = MAX_NR_ZONES - 1;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = -1;
>
> ret = try_to_freeze();
> if (kthread_should_stop())
> @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> * We can speed up thawing tasks if we don't call balance_pgdat
> * after returning from the refrigerator
> */
> - if (!ret) {
> - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> + if (ret)
> + continue;
>
> - /* return value ignored until next patch */
> - balance_pgdat(pgdat, order, classzone_idx);
> - }
> + /*
> + * Reclaim begins at the requested order but if a high-order
> + * reclaim fails then kswapd falls back to reclaiming for
> + * order-0. If that happens, kswapd will consider sleeping
> + * for the order it finished reclaiming at (reclaim_order)
> + * but kcompactd is woken to compact for the original
> + * request (alloc_order).
> + */
> + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> + if (reclaim_order < alloc_order)
> + goto kswapd_try_sleep;
This 'goto' would cause kswapd to sleep prematurely. We need to check
*new* pgdat->kswapd_order and classzone_idx even in this case.
> +
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> }
>
> tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
> @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> return;
> pgdat = zone->zone_pgdat;
> - if (pgdat->kswapd_max_order < order) {
> - pgdat->kswapd_max_order = order;
> - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> - }
> + if (pgdat->kswapd_classzone_idx == -1)
> + pgdat->kswapd_classzone_idx = classzone_idx;
> + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
> + pgdat->kswapd_order = max(pgdat->kswapd_order, order);
Now, updating pgdat->skwapd_max_order and classzone_idx happens
unconditionally. Before your patch, it is only updated toward hard
constraint (e.g. higher order).
And, I'd like to know why max() is used for classzone_idx rather than
min()? I think that kswapd should balance the lowest zone requested.
Thanks.
> if (!waitqueue_active(&pgdat->kswapd_wait))
> return;
> if (zone_balanced(zone, order, 0))
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2016-07-07 1:17 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
2016-07-04 23:50 ` Minchan Kim
2016-07-05 8:14 ` Mel Gorman
2016-07-06 0:15 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 02/31] mm, vmscan: move lru_lock to the node Mel Gorman
2016-07-05 0:03 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 03/31] mm, vmscan: move LRU lists to node Mel Gorman
2016-07-05 1:19 ` Minchan Kim
2016-07-05 10:14 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
2016-07-07 1:12 ` Joonsoo Kim
2016-07-07 9:48 ` Mel Gorman
2016-07-08 2:28 ` Joonsoo Kim
2016-07-08 10:05 ` Mel Gorman
2016-07-14 6:28 ` Joonsoo Kim
2016-07-14 7:48 ` Vlastimil Babka
2016-07-18 4:52 ` Joonsoo Kim
2016-07-18 12:11 ` Mel Gorman
2016-07-18 14:27 ` Mel Gorman
2016-07-19 8:30 ` Joonsoo Kim
2016-07-19 14:25 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 05/31] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
2016-07-01 20:01 ` [PATCH 06/31] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 07/31] mm, vmscan: remove balance gap Mel Gorman
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-07-05 5:59 ` Minchan Kim
2016-07-05 10:26 ` Mel Gorman
2016-07-06 0:30 ` Minchan Kim
2016-07-06 8:31 ` Mel Gorman
2016-07-07 5:51 ` Minchan Kim
2016-07-07 9:56 ` Mel Gorman
2016-07-07 1:20 ` Joonsoo Kim [this message]
2016-07-07 10:17 ` Mel Gorman
2016-07-08 2:44 ` Joonsoo Kim
2016-07-08 10:11 ` Mel Gorman
2016-07-14 5:23 ` Joonsoo Kim
2016-07-14 8:32 ` Vlastimil Babka
2016-07-18 5:07 ` Joonsoo Kim
2016-07-18 6:51 ` Vlastimil Babka
2016-07-18 7:24 ` Joonsoo Kim
2016-07-14 9:05 ` Mel Gorman
2016-07-18 5:03 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
2016-07-07 1:43 ` Joonsoo Kim
2016-07-07 10:27 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 10/31] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
2016-07-01 20:01 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-07-05 6:11 ` Minchan Kim
2016-07-05 10:38 ` Mel Gorman
2016-07-06 1:25 ` Minchan Kim
2016-07-06 8:42 ` Mel Gorman
2016-07-07 6:27 ` Minchan Kim
2016-07-07 10:55 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
2016-07-05 6:24 ` Minchan Kim
2016-07-05 10:40 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 13/31] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 14/31] mm, workingset: make working set detection node-aware Mel Gorman
2016-07-01 20:01 ` [PATCH 15/31] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 16/31] mm: move page mapped accounting to the node Mel Gorman
2016-07-01 20:01 ` [PATCH 17/31] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-07-01 20:01 ` [PATCH 18/31] mm: move most file-based accounting to the node Mel Gorman
2016-07-01 20:01 ` [PATCH 19/31] mm: move vmscan writes and file write " Mel Gorman
2016-07-01 20:01 ` [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-07-07 1:24 ` Joonsoo Kim
2016-07-07 10:58 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone Mel Gorman
2016-07-01 20:01 ` [PATCH 22/31] mm: convert zone_reclaim to node_reclaim Mel Gorman
2016-07-01 20:01 ` [PATCH 23/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
2016-07-01 20:01 ` [PATCH 24/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
2016-07-01 20:01 ` [PATCH 25/31] mm, vmscan: add classzone information to tracepoints Mel Gorman
2016-07-01 20:01 ` [PATCH 26/31] mm, page_alloc: remove fair zone allocation policy Mel Gorman
2016-07-01 20:01 ` [PATCH 27/31] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
2016-07-01 20:01 ` [PATCH 28/31] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-07-01 20:01 ` [PATCH 29/31] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-07-01 20:01 ` [PATCH 30/31] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
2016-07-06 0:02 ` Minchan Kim
2016-07-06 8:58 ` Mel Gorman
2016-07-06 9:33 ` Mel Gorman
2016-07-07 6:47 ` Minchan Kim
2016-07-06 18:12 ` Dave Hansen
2016-07-07 11:26 ` Mel Gorman
2016-07-04 1:37 ` [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Minchan Kim
2016-07-04 4:34 ` Mel Gorman
2016-07-04 8:04 ` Minchan Kim
2016-07-04 9:55 ` Mel Gorman
2016-07-06 1:51 ` Minchan Kim
-- strict thread matches above, loose matches on Subject: below --
2016-07-01 15:37 Mel Gorman
2016-07-01 15:37 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160707012038.GB27987@js1304-P5Q-DELUXE \
--to=iamjoonsoo.kim@lge.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=riel@surriel.com \
--cc=vbabka@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).