From: Mel Gorman <mgorman@techsingularity.net>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Linux-MM <linux-mm@kvack.org>, Rik van Riel <riel@surriel.com>,
Johannes Weiner <hannes@cmpxchg.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps
Date: Thu, 16 Jun 2016 09:30:33 +0100 [thread overview]
Message-ID: <20160616083033.GF1868@techsingularity.net> (raw)
In-Reply-To: <6b6b9f95-869a-a9f2-c5cf-f0a3e4d6bd6a@suse.cz>
On Wed, Jun 15, 2016 at 05:18:00PM +0200, Vlastimil Babka wrote:
> >@@ -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 = -1;
> > }
> >
> > /* we can use NODE_DATA(nid) from here */
> >diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> >index 4ce578b969da..d8cb483d5cad 100644
> >--- a/mm/page_alloc.c
> >+++ b/mm/page_alloc.c
> >@@ -6036,7 +6036,7 @@ 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);
>
> Above you changed the reset value of kswapd_classzone_idx from 0 to -1, so
> won't this trigger? Also should we check kswapd_order that's newly reset
> too?
>
Good spot. The memory initialisation paths are ok but node memory hotplug
was broken.
> >
> > reset_deferred_meminit(pgdat);
> > pgdat->node_id = nid;
> >diff --git a/mm/vmscan.c b/mm/vmscan.c
> >index 96bf841f9352..14b34eebedff 100644
> >--- a/mm/vmscan.c
> >+++ b/mm/vmscan.c
> >@@ -2727,7 +2727,7 @@ 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);
> > }
> >@@ -3211,6 +3211,12 @@ 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 full sleep */
> >+ if (classzone_idx == -1) {
> >+ classzone_idx = balanced_classzone_idx = MAX_NR_ZONES - 1;
> >+ goto full_sleep;
>
> This will skip the wakeup_kcompactd() part.
>
I wrestled with this one. I decided to leave it alone on the grounds
that if kswapd has not been woken recently then compaction efforts also
have not failed and kcompactd is not required.
> >@@ -3311,38 +3316,25 @@ 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 = order = 0;
> >+ pgdat->kswapd_classzone_idx = classzone_idx = -1;
> > for ( ; ; ) {
> > bool ret;
> >
> >+kswapd_try_sleep:
> >+ kswapd_try_to_sleep(pgdat, order, classzone_idx, classzone_idx);
>
> The last two parameters are now the same, remove one?
>
Yes. A few more basic simplifications are then possible.
> >@@ -3352,12 +3344,19 @@ 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);
> >- }
> >+ /*
> >+ * Try reclaim the requested order but if that fails
> >+ * then try sleeping on the basis of the order reclaimed.
>
> Is the last word really meant to be "reclaimed", or "requested"?
>
No, I really meant reclaimed.
> >+ */
> >+ trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> >+ if (balance_pgdat(pgdat, order, classzone_idx) < order)
> >+ goto kswapd_try_sleep;
>
> AFAICS now kswapd_try_to_sleep() will use the "requested" order. That's
> needed for proper wakeup_kcompactd(), but won't it prevent kswapd from
> actually going to sleep, because zone_balanced() in prepare-sleep will be
> false? So I think you need to give it both orders to do the right thing?
>
You're right. There is a risk that kswapd stays awake longer in high
fragmentation scenarios.
Should be fixed now by passing in both orders.
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2016-06-16 8:30 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-09 18:04 [PATCH 00/27] Move LRU page reclaim from zones to nodes v6 Mel Gorman
2016-06-09 18:04 ` [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman
2016-06-10 13:31 ` Vlastimil Babka
2016-06-10 13:47 ` Mel Gorman
2016-06-13 17:26 ` Christoph Lameter
2016-06-14 14:25 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman
2016-06-10 16:39 ` Vlastimil Babka
2016-06-10 17:48 ` Peter Zijlstra
2016-06-14 14:41 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 03/27] mm, vmscan: Move LRU lists to node Mel Gorman
2016-06-10 18:00 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman
2016-06-15 12:52 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 05/27] mm, vmscan: Have kswapd only scan based on the highest requested zone Mel Gorman
2016-06-15 13:13 ` Vlastimil Babka
2016-06-16 7:44 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman
2016-06-15 14:23 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman
2016-06-15 14:28 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-06-15 15:18 ` Vlastimil Babka
2016-06-16 8:30 ` Mel Gorman [this message]
2016-06-16 9:16 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman
2016-06-16 8:59 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman
2016-06-16 9:29 ` Vlastimil Babka
2016-06-16 10:29 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 11/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-06-16 10:08 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman
2016-06-16 13:35 ` Vlastimil Babka
2016-06-16 14:47 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman
2016-06-16 15:06 ` Vlastimil Babka
2016-06-16 15:53 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 14/27] mm, workingset: Make working set detection node-aware Mel Gorman
2016-06-16 15:13 ` Vlastimil Babka
2016-06-16 15:56 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-06-16 15:45 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman
2016-06-16 15:52 ` Vlastimil Babka
2016-06-16 16:04 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-06-17 8:28 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman
2016-06-17 8:35 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 19/27] mm: Move vmscan writes and file write " Mel Gorman
2016-06-17 8:51 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman
2016-06-17 8:53 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-06-17 10:46 ` Vlastimil Babka
2016-06-17 12:03 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-06-17 10:55 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-06-17 10:57 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-06-17 11:27 ` Vlastimil Babka
2016-06-17 12:07 ` Mel Gorman
2016-06-09 18:04 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-06-17 11:31 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-06-17 11:36 ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-06-17 12:39 ` Vlastimil Babka
-- strict thread matches above, loose matches on Subject: below --
2016-06-21 14:15 [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
2016-06-21 14:15 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-06-22 15:30 ` Vlastimil Babka
2016-04-15 9:13 [PATCH 00/27] Move LRU page reclaim from zones to nodes v5 Mel Gorman
2016-04-15 9:13 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-04-06 11:19 [RFC PATCH 00/27] Move LRU page reclaim from zones to nodes v3 Mel Gorman
2016-04-06 11:20 ` [PATCH 08/27] 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=20160616083033.GF1868@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--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).