linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 2/2] exfat: reduce block requests when zeroing a cluster
@ 2022-04-02  3:27 Yuezhang.Mo
  2022-04-04  4:52 ` Christoph Hellwig
  0 siblings, 1 reply; 2+ messages in thread
From: Yuezhang.Mo @ 2022-04-02  3:27 UTC (permalink / raw)
  To: sj1557.seo@samsung.com, Namjae Jeon
  Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	Andy.Wu@sony.com, Wataru.Aoyama@sony.com, axboe@kernel.dk,
	Christoph Hellwig

[-- Attachment #1: Type: text/plain, Size: 3087 bytes --]

If 'dirsync' is enabled, when zeroing a cluster, submitting
sector by sector will generate many block requests, will
cause the block device to not fully perform its performance.

This commit makes the sectors in a cluster to be submitted in
once, it will reduce the number of block requests. This will
make the block device to give full play to its performance.

Test create 1000 directories on SD card with:

$ time (for ((i=0;i<1000;i++)); do mkdir dir${i}; done)

Performance has been improved by more than 73% on imx6q-sabrelite.

Cluster size       Before         After       Improvement
64  KBytes         3m34.036s      0m56.052s   73.8%
128 KBytes         6m2.644s       1m13.354s   79.8%
256 KBytes         11m22.202s     1m39.451s   85.4%

imx6q-sabrelite:
  - CPU: 792 MHz x4
  - Memory: 1GB DDR3
  - SD Card: SanDisk 8GB Class 4

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
---
 fs/exfat/fatent.c | 41 +++++++++++++++++------------------------
 1 file changed, 17 insertions(+), 24 deletions(-)

diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index a3464e56a7e1..04e1126ce971 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -274,10 +275,9 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
 {
 	struct super_block *sb = dir->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
-	int nr_bhs = MAX_BUF_PER_PAGE;
+	struct buffer_head *bh;
 	sector_t blknr, last_blknr;
-	int err, i, n;
+	int i;
 
 	blknr = exfat_cluster_to_sector(sbi, clu);
 	last_blknr = blknr + sbi->sect_per_clus;
@@ -291,30 +291,23 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
 	}
 
 	/* Zeroing the unused blocks on this cluster */
-	while (blknr < last_blknr) {
-		for (n = 0; n < nr_bhs && blknr < last_blknr; n++, blknr++) {
-			bhs[n] = sb_getblk(sb, blknr);
-			if (!bhs[n]) {
-				err = -ENOMEM;
-				goto release_bhs;
-			}
-			memset(bhs[n]->b_data, 0, sb->s_blocksize);
-		}
-
-		err = exfat_update_bhs(bhs, n, IS_DIRSYNC(dir));
-		if (err)
-			goto release_bhs;
+	for (i = blknr; i < last_blknr; i++) {
+		bh = sb_getblk(sb, i);
+		if (!bh)
+			return -ENOMEM;
 
-		for (i = 0; i < n; i++)
-			brelse(bhs[i]);
+		memset(bh->b_data, 0, sb->s_blocksize);
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		brelse(bh);
 	}
-	return 0;
 
-release_bhs:
-	exfat_err(sb, "failed zeroed sect %llu\n", (unsigned long long)blknr);
-	for (i = 0; i < n; i++)
-		bforget(bhs[i]);
-	return err;
+	if (IS_DIRSYNC(dir))
+		return sync_blockdev_range(sb->s_bdev,
+				EXFAT_BLK_TO_B(blknr, sb),
+				EXFAT_BLK_TO_B(last_blknr, sb) - 1);
+
+	return 0;
 }
 
 int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
-- 
2.25.1

[-- Attachment #2: v2-0002-exfat-reduce-block-requests-when-zeroing-a-cluste.patch --]
[-- Type: application/octet-stream, Size: 2985 bytes --]

If 'dirsync' is enabled, when zeroing a cluster, submitting
sector by sector will generate many block requests, will
cause the block device to not fully perform its performance.

This commit makes the sectors in a cluster to be submitted in
once, it will reduce the number of block requests. This will
make the block device to give full play to its performance.

Test create 1000 directories on SD card with:

$ time (for ((i=0;i<1000;i++)); do mkdir dir${i}; done)

Performance has been improved by more than 73% on imx6q-sabrelite.

Cluster size       Before         After       Improvement
64  KBytes         3m34.036s      0m56.052s   73.8%
128 KBytes         6m2.644s       1m13.354s   79.8%
256 KBytes         11m22.202s     1m39.451s   85.4%

imx6q-sabrelite:
  - CPU: 792 MHz x4
  - Memory: 1GB DDR3
  - SD Card: SanDisk 8GB Class 4

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
---
 fs/exfat/fatent.c | 41 +++++++++++++++++------------------------
 1 file changed, 17 insertions(+), 24 deletions(-)

diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index a3464e56a7e1..04e1126ce971 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -274,10 +275,9 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
 {
 	struct super_block *sb = dir->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
-	int nr_bhs = MAX_BUF_PER_PAGE;
+	struct buffer_head *bh;
 	sector_t blknr, last_blknr;
-	int err, i, n;
+	int i;
 
 	blknr = exfat_cluster_to_sector(sbi, clu);
 	last_blknr = blknr + sbi->sect_per_clus;
@@ -291,30 +291,23 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
 	}
 
 	/* Zeroing the unused blocks on this cluster */
-	while (blknr < last_blknr) {
-		for (n = 0; n < nr_bhs && blknr < last_blknr; n++, blknr++) {
-			bhs[n] = sb_getblk(sb, blknr);
-			if (!bhs[n]) {
-				err = -ENOMEM;
-				goto release_bhs;
-			}
-			memset(bhs[n]->b_data, 0, sb->s_blocksize);
-		}
-
-		err = exfat_update_bhs(bhs, n, IS_DIRSYNC(dir));
-		if (err)
-			goto release_bhs;
+	for (i = blknr; i < last_blknr; i++) {
+		bh = sb_getblk(sb, i);
+		if (!bh)
+			return -ENOMEM;
 
-		for (i = 0; i < n; i++)
-			brelse(bhs[i]);
+		memset(bh->b_data, 0, sb->s_blocksize);
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		brelse(bh);
 	}
-	return 0;
 
-release_bhs:
-	exfat_err(sb, "failed zeroed sect %llu\n", (unsigned long long)blknr);
-	for (i = 0; i < n; i++)
-		bforget(bhs[i]);
-	return err;
+	if (IS_DIRSYNC(dir))
+		return sync_blockdev_range(sb->s_bdev,
+				EXFAT_BLK_TO_B(blknr, sb),
+				EXFAT_BLK_TO_B(last_blknr, sb) - 1);
+
+	return 0;
 }
 
 int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH v2 2/2] exfat: reduce block requests when zeroing a cluster
  2022-04-02  3:27 [PATCH v2 2/2] exfat: reduce block requests when zeroing a cluster Yuezhang.Mo
@ 2022-04-04  4:52 ` Christoph Hellwig
  0 siblings, 0 replies; 2+ messages in thread
From: Christoph Hellwig @ 2022-04-04  4:52 UTC (permalink / raw)
  To: Yuezhang.Mo@sony.com
  Cc: sj1557.seo@samsung.com, Namjae Jeon, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, Andy.Wu@sony.com,
	Wataru.Aoyama@sony.com, axboe@kernel.dk, Christoph Hellwig

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2022-04-04  4:52 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-04-02  3:27 [PATCH v2 2/2] exfat: reduce block requests when zeroing a cluster Yuezhang.Mo
2022-04-04  4:52 ` Christoph Hellwig

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).