[3.13.y.z extended stable] Patch "dm bufio: update last_accessed when relinking a buffer" has been added to staging queue

Kamal Mostafa kamal at canonical.com
Tue Oct 21 20:09:28 UTC 2014

This is a note to let you know that I have just added a patch titled

    dm bufio: update last_accessed when relinking a buffer

to the linux-3.13.y-queue branch of the 3.13.y.z extended stable tree 
which can be found at:


This patch is scheduled to be released in version

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.13.y.z tree, see



>From fa33f979e8735989a8bf2ef3823764bcc611fb45 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt at redhat.com>
Date: Tue, 30 Sep 2014 09:32:46 +0100
Subject: dm bufio: update last_accessed when relinking a buffer

commit eb76faf53b1ff7a77ce3f78cc98ad392ac70c2a0 upstream.

The 'last_accessed' member of the dm_buffer structure was only set when
the the buffer was created.  This led to each buffer being discarded
after dm_bufio_max_age time even if it was used recently.  In practice
this resulted in all thinp metadata being evicted soon after being read
-- this is particularly problematic for metadata intensive workloads
like multithreaded small random IO.

'last_accessed' is now updated each time the buffer is moved to the head
of the LRU list, so the buffer is now properly discarded if it was not
used in dm_bufio_max_age time.

Signed-off-by: Joe Thornber <ejt at redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka at redhat.com>
Signed-off-by: Mike Snitzer <snitzer at redhat.com>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
 drivers/md/dm-bufio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 5056c45..bb8d23d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -463,6 +463,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	b->list_mode = dirty;
 	list_move(&b->lru_list, &c->lru[dirty]);
+	b->last_accessed = jiffies;


More information about the kernel-team mailing list