Re: [PATCH 4/4] f2fs: add blk plugging support in f2fs

[Jaegeuk Kim <jaegeuk.kim@samsung.com>]

[-- Attachment #1: Type: text/plain, Size: 3264 bytes --]

> Yes, You're right. I agree block plug is not needed in f2fs. So plz
> ignore this patch.
> note => Regardless of the intent in the patch, it has already been
> used in writepages (f2fs uses generic_writepages).
> So to make the overall code consistent, either we should remove blk
> plug from entire F2FS write part or change f2fs_write_data_pages to
> include blk plug properly - like the code change for this part we
> share in the patch.

Agreed. :)
How about this patch?

From 09e11ac9734cd085f9a92c46098fb083091f5429 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Date: Tue, 15 Jan 2013 16:45:24 +0900
Subject: [PATCH] f2fs: remove the blk_plug usage in
f2fs_write_data_pages

From: Namjae Jeon <namjae.jeon@samsung.com>

Let's consider the usage of blk_plug in f2fs_write_data_pages().
We can come up with the two issues: lock contention and task awareness.

1. Merging bios prior to grabing "queue lock"
 The f2fs merges consecutive IOs in the file system level before
 submitting any bios, which is similar with the back merge by the
 plugging mechanism in attempt_plug_merge(). Both of them need to
acquire no queue lock.

2. Merging policy with respect to tasks
 The f2fs merges IOs as much as possible regardless of tasks, while
 blk-plugging is conducted on a basis of tasks. As we can understand
 there are trade-offs, f2fs tries to maximize the write performance with
 well-merged bios.

As a result, if f2fs produces many consecutive but separated bios in
writepages(), it would be good to use blk-plugging since f2fs would be
able to avoid queue lock contention in the block layer by merging them.
But, f2fs merges IOs and submit one bio, which means that there are not
much chances to merge bios by attempt_plug_merge().

However, f2fs has already been used blk_plug by triggering
generic_writepages()
in f2fs_write_data_pages().
So to make the overall code consistency, I'd like to remove blk_plug
there.

Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com>
Signed-off-by: Amit Sahrawat <a.sahrawat@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 fs/f2fs/data.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 3aa5ce7..b1347fc 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -547,6 +547,15 @@ redirty_out:
 
 #define MAX_DESIRED_PAGES_WP	4096
 
+static int __f2fs_writepage(struct page *page, struct writeback_control
*wbc,
+			void *data)
+{
+	struct address_space *mapping = data;
+	int ret = mapping->a_ops->writepage(page, wbc);
+	mapping_set_error(mapping, ret);
+	return ret;
+}
+
 static int f2fs_write_data_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -563,7 +572,7 @@ static int f2fs_write_data_pages(struct
address_space *mapping,
 
 	if (!S_ISDIR(inode->i_mode))
 		mutex_lock(&sbi->writepages);
-	ret = generic_writepages(mapping, wbc);
+	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
 	if (!S_ISDIR(inode->i_mode))
 		mutex_unlock(&sbi->writepages);
 	f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
-- 
1.8.0.1.250.gb7973fb

-- 
Jaegeuk Kim
Samsung

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]