Skip to contentSkip to conversation

f2fs: check all ones or zeros bitmap with integer data type for better mount performance

PATCH Superseded Chao Yu 2 participants 5 messages Oct 22, 2013 – Oct 24, 2013

Subsystems (2)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Chao Yu

author
#0 lore raw

PATCH 1/1 f2fs: check all ones or zeros bitmap with integer data type for better mount performance

Previously, check_block_count check valid_map with bit data type in common scenario that sit has all ones or zeros bitmap, it makes low mount performance.
So let's check the special bitmap with integer data type instead of the bit one.

---
 fs/f2fs/segment.h |   13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/segment.h +0 -0
index 7f94d78..d43ab9f 100644
@@ -543,6 +543,7 @@ static inline void check_block_count(struct f2fs_sb_info

*sbi,
{
struct f2fs_sm_info *sm_info = SM_I(sbi); unsigned int end_segno = sm_info->segment_count - 1;
+ int *valid_map = (int *)raw_sit->valid_map;
int valid_blocks = 0;
int i;

@@ -552,6 +553,19 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
/* check boundary of a given segment number */ BUG_ON(segno > end_segno);

+ /* check all ones or zeros valid_map */
+ if (GET_SIT_VBLOCKS(raw_sit) == 0) {
+ for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+ if (unlikely(valid_map[i] != 0))
+ BUG();
+ return;
+ } else if (GET_SIT_VBLOCKS(raw_sit) == sbi->blocks_per_seg) {
+ for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+ if (unlikely(valid_map[i] != -1))
+ BUG();
+ return;
+ }
+
/* check bitmap with valid block count */ for (i = 0; i < sbi->blocks_per_seg; i++)
if (f2fs_test_bit(i, raw_sit->valid_map))
---

#1 lore raw

Hi,

2013-10-22 (화), 17:28 +0800, Chao Yu:

Quoted 26 lines

Previously, check_block_count check valid_map with bit data type in common scenario that sit has all ones or zeros bitmap, it makes low mount performance.
So let's check the special bitmap with integer data type instead of the bit one.

---
 fs/f2fs/segment.h |   13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/segment.h +1 -0
index 7f94d78..d43ab9f 100644
@@ -543,6 +543,7 @@ static inline void check_block_count(struct f2fs_sb_info
 *sbi,
 {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
 	unsigned int end_segno = sm_info->segment_count - 1;
+	int *valid_map = (int *)raw_sit->valid_map;
 	int valid_blocks = 0;
 	int i;

fs/f2fs/segment.h static inline void check_block_count(struct · line 559

Quoted 7 lines
fs/f2fs/segment.h +3 -0
@@ -552,6 +553,19 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,
 	/* check boundary of a given segment number */
 	BUG_ON(segno > end_segno);
 
+	/* check all ones or zeros valid_map */
+	if (GET_SIT_VBLOCKS(raw_sit) == 0) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)

We cannot guarantee all the time that SIT_VBLOCK_MAP_SIZE is multiple of sizeof(int).
How about using memcmp() with __u8?

Quoted 19 lines
fs/f2fs/segment.h +10 -0
+			if (unlikely(valid_map[i] != 0))
+				BUG();
+		return;
+	} else if (GET_SIT_VBLOCKS(raw_sit) == sbi->blocks_per_seg) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+			if (unlikely(valid_map[i] != -1))
+				BUG();
+		return;
+	}
+
 	/* check bitmap with valid block count */
 	for (i = 0; i < sbi->blocks_per_seg; i++)

if (f2fs_test_bit(i, raw_sit->valid_map))
---

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

Signature · 14 lines
Jaegeuk Kim
Samsung


------------------------------------------------------------------------------
October Webinars: Code for Performance
Free Intel webinars can help you accelerate application performance.
Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from 
the latest Intel processors and coprocessors. See abstracts and register >
http://pubads.g.doubleclick.net/gampad/clk?id=60135991&iu=/4140/ostg.clktrk
_______________________________________________
Linux-f2fs-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
author
#2 lore raw

Hi, Kim:

Quoted 41 lines

-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Tuesday, October 22, 2013 8:24 PM
To: Chao Yu
Cc: [email protected]; [email protected]; [email protected]; 谭姝
Subject: Re: [f2fs-dev] [PATCH] f2fs: check all ones or zeros bitmap with integer data type for better mount performance

Hi,

2013-10-22 (화), 17:28 +0800, Chao Yu:

Quoted 29 lines

Previously, check_block_count check valid_map with bit data type in common scenario that sit has all ones or zeros bitmap, it makes low mount performance.
So let's check the special bitmap with integer data type instead of the bit one.

---
 fs/f2fs/segment.h |   13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/segment.h index renamed from fs/f2fs/segment.h +0 -0

7f94d78..d43ab9f 100644

fs/f2fs/segment.h +1 -0
@@ -543,6 +543,7 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,  {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
 	unsigned int end_segno = sm_info->segment_count - 1;
+	int *valid_map = (int *)raw_sit->valid_map;
 	int valid_blocks = 0;
 	int i;
 
@@ -552,6 +553,19 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,
 	/* check boundary of a given segment number */
 	BUG_ON(segno > end_segno);
 
Quoted 6 lines

fs/f2fs/segment.h static inline void check_block_count(struct · line 559

Quoted 3 lines
fs/f2fs/segment.h +3 -0
+	/* check all ones or zeros valid_map */
+	if (GET_SIT_VBLOCKS(raw_sit) == 0) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)

We cannot guarantee all the time that SIT_VBLOCK_MAP_SIZE is multiple of sizeof(int).

Well, It's really large changes for f2fs if SIT_VBLOCK_MAP_SIZE value is being modified.

Quoted 1 line

How about using memcmp() with __u8?

Do you mean that we can alloc all zeros or ones memory in SIT_VBLOCK_MAP_SIZE size, then memcmp() it with sit bitmap by __u8?

Quoted 16 lines
Quoted 16 lines
fs/f2fs/segment.h +10 -0
+			if (unlikely(valid_map[i] != 0))
+				BUG();
+		return;
+	} else if (GET_SIT_VBLOCKS(raw_sit) == sbi->blocks_per_seg) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+			if (unlikely(valid_map[i] != -1))
+				BUG();
+		return;
+	}
+
 	/* check bitmap with valid block count */
 	for (i = 0; i < sbi->blocks_per_seg; i++)

if (f2fs_test_bit(i, raw_sit->valid_map))
---

Quoted 8 lines
Quoted 4 lines

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

--
Jaegeuk Kim
Samsung

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#3 lore raw

Hi,

2013-10-23 (수), 11:23 +0800, Chao Yu:

Quoted 43 lines

Hi, Kim:

Quoted 41 lines

-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Tuesday, October 22, 2013 8:24 PM
To: Chao Yu
Cc: [email protected]; [email protected]; [email protected]; 谭姝
Subject: Re: [f2fs-dev] [PATCH] f2fs: check all ones or zeros bitmap with integer data type for better mount performance

Hi,

2013-10-22 (화), 17:28 +0800, Chao Yu:

Quoted 29 lines

Previously, check_block_count check valid_map with bit data type in common scenario that sit has all ones or zeros bitmap, it makes low mount performance.
So let's check the special bitmap with integer data type instead of the bit one.

---
 fs/f2fs/segment.h |   13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/segment.h index renamed from fs/f2fs/segment.h +0 -0

7f94d78..d43ab9f 100644

fs/f2fs/segment.h +1 -0
@@ -543,6 +543,7 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,  {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
 	unsigned int end_segno = sm_info->segment_count - 1;
+	int *valid_map = (int *)raw_sit->valid_map;
 	int valid_blocks = 0;
 	int i;
 
@@ -552,6 +553,19 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,
 	/* check boundary of a given segment number */
 	BUG_ON(segno > end_segno);
 
Quoted 7 lines
Quoted 6 lines

fs/f2fs/segment.h static inline void check_block_count(struct · line 559

Quoted 3 lines
fs/f2fs/segment.h +3 -0
+	/* check all ones or zeros valid_map */
+	if (GET_SIT_VBLOCKS(raw_sit) == 0) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)

We cannot guarantee all the time that SIT_VBLOCK_MAP_SIZE is multiple of sizeof(int).

Well, It's really large changes for f2fs if SIT_VBLOCK_MAP_SIZE value is being modified.

But, it can be changed.
Please do not add any unnecessary assumption.

Quoted 4 lines
Quoted 2 lines

How about using memcmp() with __u8?

Do you mean that we can alloc all zeros or ones memory in SIT_VBLOCK_MAP_SIZE size, then memcmp() it with sit bitmap by __u8?

Yap.
Ah, but there is another one.
It would be better to use find_next_bit_le() and
find_next_zero_bit_le().
Any idea?

Quoted 26 lines
Quoted 25 lines
Quoted 17 lines
fs/f2fs/segment.h +10 -0
+			if (unlikely(valid_map[i] != 0))
+				BUG();
+		return;
+	} else if (GET_SIT_VBLOCKS(raw_sit) == sbi->blocks_per_seg) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+			if (unlikely(valid_map[i] != -1))
+				BUG();
+		return;
+	}
+
 	/* check bitmap with valid block count */
 	for (i = 0; i < sbi->blocks_per_seg; i++)

if (f2fs_test_bit(i, raw_sit->valid_map))
---

Quoted 4 lines

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

--
Jaegeuk Kim
Samsung

Signature · 15 lines
Jaegeuk Kim
Samsung



------------------------------------------------------------------------------
October Webinars: Code for Performance
Free Intel webinars can help you accelerate application performance.
Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from 
the latest Intel processors and coprocessors. See abstracts and register >
http://pubads.g.doubleclick.net/gampad/clk?id=60135991&iu=/4140/ostg.clktrk
_______________________________________________
Linux-f2fs-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
author
#4 lore raw

Hi Kim,

Quoted 61 lines

-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, October 23, 2013 5:32 PM
To: Chao Yu
Cc: [email protected]; [email protected]; [email protected]; '谭姝'
Subject: RE: [f2fs-dev] [PATCH] f2fs: check all ones or zeros bitmap with integer data type for better mount performance

Hi,

2013-10-23 (수), 11:23 +0800, Chao Yu:

Quoted 49 lines

Hi, Kim:

Quoted 47 lines

-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Tuesday, October 22, 2013 8:24 PM
To: Chao Yu
Cc: [email protected]; [email protected]; [email protected]; 谭姝
Subject: Re: [f2fs-dev] [PATCH] f2fs: check all ones or zeros bitmap with integer data type for better mount performance

Hi,

2013-10-22 (화), 17:28 +0800, Chao Yu:

Quoted 25 lines

Previously, check_block_count check valid_map with bit data type in common scenario that sit has all ones or zeros bitmap, it makes low mount performance.
So let's check the special bitmap with integer data type instead of the bit one.

---
 fs/f2fs/segment.h |   13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/segment.h index renamed from fs/f2fs/segment.h +0 -0

7f94d78..d43ab9f 100644

fs/f2fs/segment.h +1 -0
@@ -543,6 +543,7 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,  {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
 	unsigned int end_segno = sm_info->segment_count - 1;
+	int *valid_map = (int *)raw_sit->valid_map;
 	int valid_blocks = 0;
 	int i;
 

fs/f2fs/segment.h static inline void check_block_count(struct · line 559

Quoted 7 lines
fs/f2fs/segment.h +3 -0
@@ -552,6 +553,19 @@ static inline void check_block_count(struct
 f2fs_sb_info *sbi,
 	/* check boundary of a given segment number */
 	BUG_ON(segno > end_segno);
 
+	/* check all ones or zeros valid_map */
+	if (GET_SIT_VBLOCKS(raw_sit) == 0) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)

We cannot guarantee all the time that SIT_VBLOCK_MAP_SIZE is multiple of sizeof(int).

Quoted 5 lines
Quoted 1 line

Well, It's really large changes for f2fs if SIT_VBLOCK_MAP_SIZE value is being

modified.

But, it can be changed.
Please do not add any unnecessary assumption.

Got it, sorry for the unmeaning assumption.

Quoted 10 lines
Quoted 5 lines
Quoted 3 lines

How about using memcmp() with __u8?

Do you mean that we can alloc all zeros or ones memory in SIT_VBLOCK_MAP_SIZE size, then memcmp() it with sit bitmap by __u8?

Yap.
Ah, but there is another one.
It would be better to use find_next_bit_le() and find_next_zero_bit_le(). Any idea?

Good point.
I try to use memcmp(bitmap, bitmap+1, size-1) and bitmap[0], But yours got better performance and readable. Thanks.

Quoted 29 lines
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
fs/f2fs/segment.h +10 -0
+			if (unlikely(valid_map[i] != 0))
+				BUG();
+		return;
+	} else if (GET_SIT_VBLOCKS(raw_sit) == sbi->blocks_per_seg) {
+		for (i = 0; i < SIT_VBLOCK_MAP_SIZE / sizeof(int); i++)
+			if (unlikely(valid_map[i] != -1))
+				BUG();
+		return;
+	}
+
 	/* check bitmap with valid block count */
 	for (i = 0; i < sbi->blocks_per_seg; i++)

if (f2fs_test_bit(i, raw_sit->valid_map))
---

Quoted 10 lines
Quoted 9 lines
Quoted 5 lines

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected] More majordomo info at
http://vger.kernel.org/majordomo-info.html

--
Jaegeuk Kim
Samsung

Quoted 3 lines

--
Jaegeuk Kim
Samsung

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html