* [PATCH] ext4: unlock unused_pages timely when doing writeback
@ 2019-01-29 2:05 Xiaoguang Wang
2019-02-11 4:54 ` Theodore Y. Ts'o
0 siblings, 1 reply; 2+ messages in thread
From: Xiaoguang Wang @ 2019-01-29 2:05 UTC (permalink / raw)
To: linux-ext4; +Cc: Xiaoguang Wang
In mpage_add_bh_to_extent(), when accumulated extents length is greater
than MAX_WRITEPAGES_EXTENT_LEN or buffer head's b_stat is not equal, we
will not continue to search unmapped area for this page, but note this
page is locked, and will only be unlocked in mpage_release_unused_pages()
after ext4_io_submit, if io also is throttled by blk-throttle or similar
io qos, we will hold this page locked for a while, it's unnecessary.
I think the best fix is to refactor mpage_add_bh_to_extent() to let it
return some hints whether to unlock this page, but given that we will
improve dioread_nolock later, we can let it done later, so currently
the simple fix would just call mpage_release_unused_pages() before
ext4_io_submit().
Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
---
fs/ext4/inode.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 34d7e0703cc6..83a0d7c76736 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2836,12 +2836,12 @@ static int ext4_writepages(struct address_space *mapping,
goto unplug;
}
ret = mpage_prepare_extent_to_map(&mpd);
+ /* Unlock pages we didn't use */
+ mpage_release_unused_pages(&mpd, false);
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
ext4_put_io_end_defer(mpd.io_submit.io_end);
mpd.io_submit.io_end = NULL;
- /* Unlock pages we didn't use */
- mpage_release_unused_pages(&mpd, false);
if (ret < 0)
goto unplug;
@@ -2909,10 +2909,11 @@ static int ext4_writepages(struct address_space *mapping,
handle = NULL;
mpd.do_map = 0;
}
- /* Submit prepared bio */
- ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
+ /* Submit prepared bio */
+ ext4_io_submit(&mpd.io_submit);
+
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
--
2.17.2
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] ext4: unlock unused_pages timely when doing writeback
2019-01-29 2:05 [PATCH] ext4: unlock unused_pages timely when doing writeback Xiaoguang Wang
@ 2019-02-11 4:54 ` Theodore Y. Ts'o
0 siblings, 0 replies; 2+ messages in thread
From: Theodore Y. Ts'o @ 2019-02-11 4:54 UTC (permalink / raw)
To: Xiaoguang Wang; +Cc: linux-ext4
On Tue, Jan 29, 2019 at 10:05:31AM +0800, Xiaoguang Wang wrote:
> In mpage_add_bh_to_extent(), when accumulated extents length is greater
> than MAX_WRITEPAGES_EXTENT_LEN or buffer head's b_stat is not equal, we
> will not continue to search unmapped area for this page, but note this
> page is locked, and will only be unlocked in mpage_release_unused_pages()
> after ext4_io_submit, if io also is throttled by blk-throttle or similar
> io qos, we will hold this page locked for a while, it's unnecessary.
>
> I think the best fix is to refactor mpage_add_bh_to_extent() to let it
> return some hints whether to unlock this page, but given that we will
> improve dioread_nolock later, we can let it done later, so currently
> the simple fix would just call mpage_release_unused_pages() before
> ext4_io_submit().
>
> Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Thanks, applied.
- Ted
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2019-02-11 4:54 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-01-29 2:05 [PATCH] ext4: unlock unused_pages timely when doing writeback Xiaoguang Wang
2019-02-11 4:54 ` Theodore Y. Ts'o
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.