linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Trond Myklebust <Trond.Myklebust@netapp.com>, linux-nfs@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Jan Kara <jack@suse.cz>, Christoph Hellwig <hch@lst.de>,
	Dave Chinner <david@fromorbit.com>,
	Greg Thelen <gthelen@google.com>,
	Minchan Kim <minchan.kim@gmail.com>,
	Vivek Goyal <vgoyal@redhat.com>,
	Andrea Righi <arighi@develer.com>, linux-mm <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: [RFC][PATCH 1/2] nfs: writeback pages wait queue
Date: Mon, 10 Oct 2011 21:10:51 +0800	[thread overview]
Message-ID: <20111010131051.GA16847@localhost> (raw)
In-Reply-To: <20111010130722.GA11387@localhost>

[known bug: this patch will block sync(1) in schecule() if dirty
threshold is set to as low as 1MB.]

The generic writeback routines are departing from congestion_wait()
in preference of get_request_wait(), aka. waiting on the block queues.

Introduce the missing writeback wait queue for NFS, otherwise its
writeback pages will grow out of control, exhausting all PG_dirty pages.

CC: Jens Axboe <axboe@kernel.dk>
CC: Chris Mason <chris.mason@oracle.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 fs/nfs/client.c           |    2 
 fs/nfs/write.c            |   89 +++++++++++++++++++++++++++++++-----
 include/linux/nfs_fs_sb.h |    1 
 3 files changed, 81 insertions(+), 11 deletions(-)

--- linux-next.orig/fs/nfs/write.c	2011-09-29 20:23:44.000000000 +0800
+++ linux-next/fs/nfs/write.c	2011-10-05 10:43:28.000000000 +0800
@@ -189,11 +189,64 @@ static int wb_priority(struct writeback_
  * NFS congestion control
  */
 
+#define NFS_WAIT_PAGES	(1024L >> (PAGE_SHIFT - 10))
 int nfs_congestion_kb;
 
-#define NFS_CONGESTION_ON_THRESH 	(nfs_congestion_kb >> (PAGE_SHIFT-10))
-#define NFS_CONGESTION_OFF_THRESH	\
-	(NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))
+/*
+ * SYNC requests will block on (2*limit) and wakeup on (2*limit-NFS_WAIT_PAGES)
+ * ASYNC requests will block on (limit) and wakeup on (limit - NFS_WAIT_PAGES)
+ * In this way SYNC writes will never be blocked by ASYNC ones.
+ */
+
+static void nfs_set_congested(long nr, struct backing_dev_info *bdi)
+{
+	long limit = nfs_congestion_kb >> (PAGE_SHIFT - 10);
+
+	if (nr > limit && !test_bit(BDI_async_congested, &bdi->state))
+		set_bdi_congested(bdi, BLK_RW_ASYNC);
+	else if (nr > 2 * limit && !test_bit(BDI_sync_congested, &bdi->state))
+		set_bdi_congested(bdi, BLK_RW_SYNC);
+}
+
+static void nfs_wait_congested(int is_sync,
+			       struct backing_dev_info *bdi,
+			       wait_queue_head_t *wqh)
+{
+	int waitbit = is_sync ? BDI_sync_congested : BDI_async_congested;
+	DEFINE_WAIT(wait);
+
+	if (!test_bit(waitbit, &bdi->state))
+		return;
+
+	for (;;) {
+		prepare_to_wait(&wqh[is_sync], &wait, TASK_UNINTERRUPTIBLE);
+		if (!test_bit(waitbit, &bdi->state))
+			break;
+
+		io_schedule();
+	}
+	finish_wait(&wqh[is_sync], &wait);
+}
+
+static void nfs_wakeup_congested(long nr,
+				 struct backing_dev_info *bdi,
+				 wait_queue_head_t *wqh)
+{
+	long limit = nfs_congestion_kb >> (PAGE_SHIFT - 10);
+
+	if (nr < 2 * limit - min(limit / 8, NFS_WAIT_PAGES)) {
+		if (test_bit(BDI_sync_congested, &bdi->state))
+			clear_bdi_congested(bdi, BLK_RW_SYNC);
+		if (waitqueue_active(&wqh[BLK_RW_SYNC]))
+			wake_up(&wqh[BLK_RW_SYNC]);
+	}
+	if (nr < limit - min(limit / 8, NFS_WAIT_PAGES)) {
+		if (test_bit(BDI_async_congested, &bdi->state))
+			clear_bdi_congested(bdi, BLK_RW_ASYNC);
+		if (waitqueue_active(&wqh[BLK_RW_ASYNC]))
+			wake_up(&wqh[BLK_RW_ASYNC]);
+	}
+}
 
 static int nfs_set_page_writeback(struct page *page)
 {
@@ -204,11 +257,8 @@ static int nfs_set_page_writeback(struct
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
 		page_cache_get(page);
-		if (atomic_long_inc_return(&nfss->writeback) >
-				NFS_CONGESTION_ON_THRESH) {
-			set_bdi_congested(&nfss->backing_dev_info,
-						BLK_RW_ASYNC);
-		}
+		nfs_set_congested(atomic_long_inc_return(&nfss->writeback),
+				  &nfss->backing_dev_info);
 	}
 	return ret;
 }
@@ -220,8 +270,10 @@ static void nfs_end_page_writeback(struc
 
 	end_page_writeback(page);
 	page_cache_release(page);
-	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
+	nfs_wakeup_congested(atomic_long_dec_return(&nfss->writeback),
+			     &nfss->backing_dev_info,
+			     nfss->writeback_wait);
 }
 
 static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
@@ -322,19 +374,34 @@ static int nfs_writepage_locked(struct p
 
 int nfs_writepage(struct page *page, struct writeback_control *wbc)
 {
+	struct inode *inode = page->mapping->host;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int ret;
 
 	ret = nfs_writepage_locked(page, wbc);
 	unlock_page(page);
+
+	nfs_wait_congested(wbc->sync_mode == WB_SYNC_ALL,
+			   &nfss->backing_dev_info,
+			   nfss->writeback_wait);
+
 	return ret;
 }
 
-static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data)
+static int nfs_writepages_callback(struct page *page,
+				   struct writeback_control *wbc, void *data)
 {
+	struct inode *inode = page->mapping->host;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int ret;
 
 	ret = nfs_do_writepage(page, wbc, data);
 	unlock_page(page);
+
+	nfs_wait_congested(wbc->sync_mode == WB_SYNC_ALL,
+			   &nfss->backing_dev_info,
+			   nfss->writeback_wait);
+
 	return ret;
 }
 
--- linux-next.orig/include/linux/nfs_fs_sb.h	2011-09-02 09:02:07.000000000 +0800
+++ linux-next/include/linux/nfs_fs_sb.h	2011-10-04 20:26:03.000000000 +0800
@@ -102,6 +102,7 @@ struct nfs_server {
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
 	struct backing_dev_info	backing_dev_info;
 	atomic_long_t		writeback;	/* number of writeback pages */
+	wait_queue_head_t	writeback_wait[2];
 	int			flags;		/* various flags */
 	unsigned int		caps;		/* server capabilities */
 	unsigned int		rsize;		/* read size */
--- linux-next.orig/fs/nfs/client.c	2011-08-22 13:59:52.000000000 +0800
+++ linux-next/fs/nfs/client.c	2011-10-04 20:26:03.000000000 +0800
@@ -1066,6 +1066,8 @@ static struct nfs_server *nfs_alloc_serv
 	INIT_LIST_HEAD(&server->layouts);
 
 	atomic_set(&server->active, 0);
+	init_waitqueue_head(&server->writeback_wait[BLK_RW_SYNC]);
+	init_waitqueue_head(&server->writeback_wait[BLK_RW_ASYNC]);
 
 	server->io_stats = nfs_alloc_iostats();
 	if (!server->io_stats) {

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2011-10-10 13:10 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-10-03 13:42 [PATCH 00/11] IO-less dirty throttling v12 Wu Fengguang
2011-10-03 13:42 ` [PATCH 01/11] writeback: account per-bdi accumulated dirtied pages Wu Fengguang
2011-10-03 13:42 ` [PATCH 02/11] writeback: dirty position control Wu Fengguang
2011-10-03 13:42 ` [PATCH 03/11] writeback: add bg_threshold parameter to __bdi_update_bandwidth() Wu Fengguang
2011-10-03 13:42 ` [PATCH 04/11] writeback: dirty rate control Wu Fengguang
2011-10-03 13:42 ` [PATCH 05/11] writeback: stabilize bdi->dirty_ratelimit Wu Fengguang
2011-10-03 13:42 ` [PATCH 06/11] writeback: per task dirty rate limit Wu Fengguang
2011-10-03 13:42 ` [PATCH 07/11] writeback: IO-less balance_dirty_pages() Wu Fengguang
2011-10-03 13:42 ` [PATCH 08/11] writeback: limit max dirty pause time Wu Fengguang
2011-10-03 13:42 ` [PATCH 09/11] writeback: control " Wu Fengguang
2011-10-03 13:42 ` [PATCH 10/11] writeback: dirty position control - bdi reserve area Wu Fengguang
2011-10-03 13:42 ` [PATCH 11/11] writeback: per-bdi background threshold Wu Fengguang
2011-10-03 13:59 ` [PATCH 00/11] IO-less dirty throttling v12 Wu Fengguang
2011-10-05  1:42   ` Wu Fengguang
2011-10-04 19:52 ` Vivek Goyal
2011-10-05 13:56   ` Wu Fengguang
2011-10-05 15:16   ` Andi Kleen
2011-10-10 12:14 ` Peter Zijlstra
2011-10-10 13:07   ` Wu Fengguang
2011-10-10 13:10     ` Wu Fengguang [this message]
2011-10-10 13:11       ` [RFC][PATCH 2/2] nfs: scale writeback threshold proportional to dirty threshold Wu Fengguang
2011-10-18  8:53         ` Wu Fengguang
2011-10-18  8:59           ` Wu Fengguang
2011-10-20  2:49             ` Wu Fengguang
2011-10-18  8:51       ` [RFC][PATCH 1/2] nfs: writeback pages wait queue Wu Fengguang
2011-10-20  3:59         ` Wu Fengguang
2011-10-10 14:28     ` [PATCH 00/11] IO-less dirty throttling v12 Wu Fengguang
2011-10-17  3:03       ` Wu Fengguang
2011-10-20  3:39 ` Wu Fengguang

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=20111010131051.GA16847@localhost \
    --to=fengguang.wu@intel.com \
    --cc=Trond.Myklebust@netapp.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=arighi@develer.com \
    --cc=david@fromorbit.com \
    --cc=gthelen@google.com \
    --cc=hch@lst.de \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=minchan.kim@gmail.com \
    --cc=vgoyal@redhat.com \
    /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).