From: Mikulas Patocka <mpatocka@redhat.com>
To: Dave Chinner <david@fromorbit.com>, Mike Snitzer <msnitzer@redhat.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-xfs@vger.kernel.org, dm-devel@redhat.com,
Jens Axboe <axboe@kernel.dk>, NeilBrown <neilb@suse.de>
Subject: [PATCH] dm-bufio: do cleanup from a workqueue
Date: Fri, 3 Jul 2020 10:26:46 -0400 (EDT) [thread overview]
Message-ID: <alpine.LRH.2.02.2007031020150.23220@file01.intranet.prod.int.rdu2.redhat.com> (raw)
In-Reply-To: <20200629223410.GK2005@dread.disaster.area>
On Tue, 30 Jun 2020, Dave Chinner wrote:
> https://lore.kernel.org/linux-fsdevel/20190809215733.GZ7777@dread.disaster.area/
>
> If you did that when I suggested it, this problem would be solved.
> i.e. The only way to fix this problem once adn for all is to stop
> using the shrinker as a mechanism to issue and wait on IO. If you
> need background writeback of dirty buffers, do it from a
> WQ_MEM_RECLAIM workqueue that isn't directly in the memory reclaim
> path and so can issue writeback and block safely from a GFP_KERNEL
> context. Kick the workqueue from the shrinker context, but get rid
> of the IO submission and waiting from the shrinker and all the
> GFP_NOFS memory reclaim recursion problems go away.
>
> Cheers,
>
> Dave.
> --
> Dave Chinner
> david@fromorbit.com
Hi
This is a patch that moves buffer cleanup to a workqueue. Please review
it.
Mikulas
From: Mikulas Patocka <mpatocka@redhat.com>
kswapd should not block because it degrades system performance.
So, move reclaim of buffers to a workqueue.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
drivers/md/dm-bufio.c | 60 ++++++++++++++++++++++++++++++++++----------------
1 file changed, 41 insertions(+), 19 deletions(-)
Index: linux-2.6/drivers/md/dm-bufio.c
===================================================================
--- linux-2.6.orig/drivers/md/dm-bufio.c 2020-07-03 14:07:43.000000000 +0200
+++ linux-2.6/drivers/md/dm-bufio.c 2020-07-03 15:35:23.000000000 +0200
@@ -108,7 +108,10 @@ struct dm_bufio_client {
int async_write_error;
struct list_head client_list;
+
struct shrinker shrinker;
+ struct work_struct shrink_work;
+ atomic_long_t need_shrink;
};
/*
@@ -1634,8 +1637,7 @@ static unsigned long get_retain_buffers(
return retain_bytes;
}
-static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
- gfp_t gfp_mask)
+static void __scan(struct dm_bufio_client *c)
{
int l;
struct dm_buffer *b, *tmp;
@@ -1646,42 +1648,58 @@ static unsigned long __scan(struct dm_bu
for (l = 0; l < LIST_SIZE; l++) {
list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
- if (__try_evict_buffer(b, gfp_mask))
+ if (count - freed <= retain_target)
+ atomic_long_set(&c->need_shrink, 0);
+ if (!atomic_long_read(&c->need_shrink))
+ return;
+ if (__try_evict_buffer(b, GFP_KERNEL)) {
+ atomic_long_dec(&c->need_shrink);
freed++;
- if (!--nr_to_scan || ((count - freed) <= retain_target))
- return freed;
+ }
cond_resched();
}
}
- return freed;
}
-static unsigned long
-dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+static void shrink_work(struct work_struct *w)
+{
+ struct dm_bufio_client *c = container_of(w, struct dm_bufio_client, shrink_work);
+
+ dm_bufio_lock(c);
+ __scan(c);
+ dm_bufio_unlock(c);
+}
+
+static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c;
- unsigned long freed;
c = container_of(shrink, struct dm_bufio_client, shrinker);
- if (sc->gfp_mask & __GFP_FS)
- dm_bufio_lock(c);
- else if (!dm_bufio_trylock(c))
- return SHRINK_STOP;
+ atomic_long_add(sc->nr_to_scan, &c->need_shrink);
+ queue_work(dm_bufio_wq, &c->shrink_work);
- freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);
- dm_bufio_unlock(c);
- return freed;
+ return sc->nr_to_scan;
}
-static unsigned long
-dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
unsigned long count = READ_ONCE(c->n_buffers[LIST_CLEAN]) +
READ_ONCE(c->n_buffers[LIST_DIRTY]);
unsigned long retain_target = get_retain_buffers(c);
+ unsigned long queued_for_cleanup = atomic_long_read(&c->need_shrink);
+
+ if (unlikely(count < retain_target))
+ count = 0;
+ else
+ count -= retain_target;
- return (count < retain_target) ? 0 : (count - retain_target);
+ if (unlikely(count < queued_for_cleanup))
+ count = 0;
+ else
+ count -= queued_for_cleanup;
+
+ return count;
}
/*
@@ -1772,6 +1790,9 @@ struct dm_bufio_client *dm_bufio_client_
__free_buffer_wake(b);
}
+ INIT_WORK(&c->shrink_work, shrink_work);
+ atomic_long_set(&c->need_shrink, 0);
+
c->shrinker.count_objects = dm_bufio_shrink_count;
c->shrinker.scan_objects = dm_bufio_shrink_scan;
c->shrinker.seeks = 1;
@@ -1817,6 +1838,7 @@ void dm_bufio_client_destroy(struct dm_b
drop_buffers(c);
unregister_shrinker(&c->shrinker);
+ flush_work(&c->shrink_work);
mutex_lock(&dm_bufio_clients_lock);
next prev parent reply other threads:[~2020-07-03 14:26 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-25 11:31 [PATCH 0/6] Overhaul memalloc_no* Matthew Wilcox (Oracle)
2020-06-25 11:31 ` [PATCH 1/6] mm: Replace PF_MEMALLOC_NOIO with memalloc_noio Matthew Wilcox (Oracle)
2020-06-25 12:22 ` Michal Hocko
2020-06-25 12:34 ` Matthew Wilcox
2020-06-25 12:42 ` Michal Hocko
2020-06-25 11:31 ` [PATCH 2/6] mm: Add become_kswapd and restore_kswapd Matthew Wilcox (Oracle)
2020-06-25 12:31 ` Michal Hocko
2020-06-25 11:31 ` [PATCH 3/6] xfs: Convert to memalloc_nofs_save Matthew Wilcox (Oracle)
2020-06-25 11:31 ` [PATCH 4/6] mm: Replace PF_MEMALLOC_NOFS with memalloc_nofs Matthew Wilcox (Oracle)
2020-06-25 13:35 ` Michal Hocko
2020-06-25 11:31 ` [PATCH 5/6] mm: Replace PF_MEMALLOC_NOIO with memalloc_nocma Matthew Wilcox (Oracle)
2020-06-25 11:31 ` [PATCH 6/6] mm: Add memalloc_nowait Matthew Wilcox (Oracle)
2020-06-25 12:40 ` Michal Hocko
2020-06-25 13:10 ` Matthew Wilcox
2020-06-25 13:34 ` Michal Hocko
2020-06-25 19:05 ` kernel test robot
2020-06-25 23:51 ` kernel test robot
2020-06-29 5:08 ` Mike Rapoport
2020-06-29 12:18 ` Matthew Wilcox
2020-06-29 12:52 ` Michal Hocko
2020-06-29 13:45 ` Mike Rapoport
2020-06-29 21:28 ` Matthew Wilcox
2020-06-30 6:34 ` Michal Hocko
2020-07-01 4:12 ` Matthew Wilcox
2020-07-01 5:53 ` Michal Hocko
2020-07-01 7:04 ` Mike Rapoport
2020-09-24 0:39 ` Mike Snitzer
2020-09-24 1:10 ` Matthew Wilcox
2020-10-23 14:49 ` Daniel Vetter
2020-06-25 18:48 ` [PATCH 0/6] Overhaul memalloc_no* Darrick J. Wong
2020-06-25 20:34 ` Matthew Wilcox
2020-06-25 20:36 ` Michal Hocko
2020-06-25 20:40 ` Matthew Wilcox
2020-06-26 15:02 ` Mikulas Patocka
2020-06-26 23:08 ` Dave Chinner
2020-06-27 13:09 ` Mikulas Patocka
2020-06-29 0:35 ` Dave Chinner
2020-06-29 13:43 ` Mikulas Patocka
2020-06-29 22:34 ` Dave Chinner
2020-07-03 14:26 ` Mikulas Patocka [this message]
2020-06-29 8:22 ` Michal Hocko
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=alpine.LRH.2.02.2007031020150.23220@file01.intranet.prod.int.rdu2.redhat.com \
--to=mpatocka@redhat.com \
--cc=axboe@kernel.dk \
--cc=david@fromorbit.com \
--cc=dm-devel@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=msnitzer@redhat.com \
--cc=neilb@suse.de \
--cc=willy@infradead.org \
/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).