Received-SPF: pass (google.com: domain of linux-kernel+bounces-47835-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Liu Shixin <liushixin2@huawei.com>
To: Alexander Viro <viro@zeniv.linux.org.uk>, Christian Brauner
	<brauner@kernel.org>, Jan Kara <jack@suse.cz>, Matthew Wilcox
	<willy@infradead.org>, Andrew Morton <akpm@linux-foundation.org>
CC: <linux-fsdevel@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<linux-mm@kvack.org>, Liu Shixin <liushixin2@huawei.com>
Subject: [PATCH 2/2] mm/readahead: limit sync readahead while too many active refault
Date: Thu, 1 Feb 2024 18:08:35 +0800
Message-ID: <20240201100835.1626685-3-liushixin2@huawei.com>
In-Reply-To: <20240201100835.1626685-1-liushixin2@huawei.com>
References: <20240201100835.1626685-1-liushixin2@huawei.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain

When the pagefault is not for write and the refault distance is close,
the page will be activated directly. If there are too many such pages in
a file, that means the pages may be reclaimed immediately.
In such situation, there is no positive effect to read-ahead since it will
only waste IO. So collect the number of such pages and when the number is
too large, stop bothering with read-ahead for a while until it decreased
automatically.

Define 'too large' as 10000 experientially, which can solves the problem
and does not affect by the occasional active refault.

Signed-off-by: Liu Shixin <liushixin2@huawei.com>
---
 include/linux/fs.h      |  2 ++
 include/linux/pagemap.h |  1 +
 mm/filemap.c            | 16 ++++++++++++++++
 mm/readahead.c          |  4 ++++
 4 files changed, 23 insertions(+)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a704951..f2a1825442f5a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -960,6 +960,7 @@ struct fown_struct {
  *      the first of these pages is accessed.
  * @ra_pages: Maximum size of a readahead request, copied from the bdi.
  * @mmap_miss: How many mmap accesses missed in the page cache.
+ * @active_refault: Number of active page refault.
  * @prev_pos: The last byte in the most recent read request.
  *
  * When this structure is passed to ->readahead(), the "most recent"
@@ -971,6 +972,7 @@ struct file_ra_state {
 	unsigned int async_size;
 	unsigned int ra_pages;
 	unsigned int mmap_miss;
+	unsigned int active_refault;
 	loff_t prev_pos;
 };
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2df35e65557d2..da9eaf985dec4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1256,6 +1256,7 @@ struct readahead_control {
 	pgoff_t _index;
 	unsigned int _nr_pages;
 	unsigned int _batch_count;
+	unsigned int _active_refault;
 	bool _workingset;
 	unsigned long _pflags;
 };
diff --git a/mm/filemap.c b/mm/filemap.c
index 750e779c23db7..4de80592ab270 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3037,6 +3037,7 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
 
 #ifdef CONFIG_MMU
 #define MMAP_LOTSAMISS  (100)
+#define ACTIVE_REFAULT_LIMIT	(10000)
 /*
  * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
  * @vmf - the vm_fault for this fault.
@@ -3142,6 +3143,18 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	if (mmap_miss > MMAP_LOTSAMISS)
 		return fpin;
 
+	ractl._active_refault = READ_ONCE(ra->active_refault);
+	if (ractl._active_refault)
+		WRITE_ONCE(ra->active_refault, --ractl._active_refault);
+
+	/*
+	 * If there are a lot of refault of active pages in this file,
+	 * that means the memory reclaim is ongoing. Stop bothering with
+	 * read-ahead since it will only waste IO.
+	 */
+	if (ractl._active_refault >= ACTIVE_REFAULT_LIMIT)
+		return fpin;
+
 	/*
 	 * mmap read-around
 	 */
@@ -3151,6 +3164,9 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	ra->async_size = ra->ra_pages / 4;
 	ractl._index = ra->start;
 	page_cache_ra_order(&ractl, ra, 0);
+
+	WRITE_ONCE(ra->active_refault, ractl._active_refault);
+
 	return fpin;
 }
 
diff --git a/mm/readahead.c b/mm/readahead.c
index cc4abb67eb223..d79bb70a232c4 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -263,6 +263,10 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			folio_set_readahead(folio);
 		ractl->_workingset |= folio_test_workingset(folio);
 		ractl->_nr_pages++;
+		if (unlikely(folio_test_workingset(folio)))
+			ractl->_active_refault++;
+		else if (unlikely(ractl->_active_refault))
+			ractl->_active_refault--;
 	}
 
 	/*
-- 
2.25.1