f2fs: enhance multithread dio write performance
PATCH 5/7 f2fs: enhance multithread dio write performance
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=16m --bs=2m --direct=1 --numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec, maxt=52083msec
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec, maxt=16329msec
--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
fs/f2fs/data.c +10 -3
@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */
@@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);__allocate_data_blocks (inode, offset, count); + } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err);
Signature · 1 line
2.4.2
Jaegeuk Kim
maintainerHi Chao,
Quoted 45 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=16m --bs=2m --direct=1 --numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec, maxt=52083msecpatched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec, maxt=16329msecSigned-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)fs/f2fs/data.c +2
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 6 lines
fs/f2fs/data.c +2
-1@@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);
Why do we have to share sbi->writepages?
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1562
Quoted 1 line
fs/f2fs/data.c +0
-0__allocate_data_blocks (inode, offset, count);
If the problem lies on the misaligned blocks, how about calling mutex_unlock here?
Thanks,
Quoted 15 lines
fs/f2fs/data.c +6
-2+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err);Signature · 1 line
2.4.2
Hi Jaegeuk,
Quoted 60 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 21 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)fs/f2fs/data.c +2
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
fs/f2fs/data.c +2
-1trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?
The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.
Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2
Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?
When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=4m --bs=64k --direct=1 --numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec, maxt=14119msec
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec, maxt=13454msec
So how about keep it in original place in this patch?
Thanks,
Quoted 18 lines
Thanks,
Quoted 15 lines
fs/f2fs/data.c +6
-3+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err); --2.4.2
Jaegeuk Kim
maintainerHi Chao,
Quoted 88 lines · Chao Yu
Hi Jaegeuk,
Quoted 60 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 21 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)fs/f2fs/data.c +2
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
fs/f2fs/data.c +2
-1trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
Quoted 8 lines
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
Understood, but the concern was the multi-thread performance as you mentioned. If one thread throws a big dio request, anybody cannot write at all? How about adding some limits likewise f2fs_write_data_pages whieh is for example nr_pages_to_write?
Thanks,
Quoted 39 lines
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=4m --bs=64k --direct=1 --numjobs=20unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec, maxt=14119msec
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec, maxt=13454msecSo how about keep it in original place in this patch?
Thanks,
Quoted 18 lines
Thanks,
Quoted 15 lines
fs/f2fs/data.c +6
-3+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err); --2.4.2
Hi Jaegeuk,
Quoted 104 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Thursday, September 17, 2015 2:13 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 45 lines · Chao Yu
Hi Jaegeuk,
Quoted 43 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
Quoted 6 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)Quoted 5 lines
Quoted 5 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 5 lines
fs/f2fs/data.c +0
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 43 lines
Quoted 12 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 10 lines
fs/f2fs/data.c +2
-0struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
fs/f2fs/data.c +2
-1trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
Quoted 6 lines
Quoted 3 lines
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
Understood, but the concern was the multi-thread performance as you mentioned. If one thread throws a big dio request, anybody cannot write at all?
Buffered write will not be stopped, but actually my way completely stops the concurrency of multithreads which are doing dio writes, for aspect of improving concurrency, moving mutex_unlock below __allocate_data_blocks is a good solution so far.
Quoted 2 lines
How about adding some limits likewise
f2fs_write_data_pageswhieh is for examplenr_pages_to_write?
Could you share more details about your idea?
As Yunlei reported, there is performance regression issue, so how about holding this patch and let me do some investigation?
Thanks,
Quoted 45 lines
Thanks,
Quoted 11 lines
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs--filesize=256m --size=4m --bs=64k --direct=1
Quoted 4 lines
--numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec,maxt=14119msec
Quoted 2 lines
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec,maxt=13454msec
Quoted 22 lines
So how about keep it in original place in this patch?
Thanks,
Quoted 18 lines
Thanks,
Quoted 15 lines
fs/f2fs/data.c +6
-3+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err); --2.4.2
Jaegeuk Kim
maintainerHi Chao,
Quoted 118 lines · Chao Yu
Hi Jaegeuk,
Quoted 104 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Thursday, September 17, 2015 2:13 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 45 lines · Chao Yu
Hi Jaegeuk,
Quoted 43 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
Quoted 6 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)Quoted 5 lines
Quoted 5 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 5 lines
fs/f2fs/data.c +0
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 43 lines
Quoted 12 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 10 lines
fs/f2fs/data.c +2
-0struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
fs/f2fs/data.c +2
-1trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
Quoted 6 lines
Quoted 3 lines
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
Understood, but the concern was the multi-thread performance as you mentioned. If one thread throws a big dio request, anybody cannot write at all?
Buffered write will not be stopped, but actually my way completely stops the concurrency of multithreads which are doing dio writes, for aspect of improving concurrency, moving
mutex_unlockbelow__allocate_data_blocksis a good solution so far.
Quoted 7 lines
Quoted 2 lines
How about adding some limits likewise
f2fs_write_data_pageswhieh is for examplenr_pages_to_write?Could you share more details about your idea?
As Yunlei reported, there is performance regression issue, so how about holding this patch and let me do some investigation?
It seems there is a mutex overhead when handling a bunch of 4KB small dios. Hmm, I meant, how about serializing pretty long-sized dios only?
Quoted 48 lines
Thanks,
Quoted 45 lines
Thanks,
Quoted 11 lines
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs--filesize=256m --size=4m --bs=64k --direct=1
Quoted 4 lines
--numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec,maxt=14119msec
Quoted 2 lines
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec,maxt=13454msec
Quoted 22 lines
So how about keep it in original place in this patch?
Thanks,
Quoted 18 lines
Thanks,
Quoted 15 lines
fs/f2fs/data.c +6
-3+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err); --2.4.2
Hi Jaegeuk,
Quoted 131 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Friday, September 18, 2015 1:49 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 121 lines · Chao Yu
Hi Jaegeuk,
Quoted 104 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Thursday, September 17, 2015 2:13 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 45 lines · Chao Yu
Hi Jaegeuk,
Quoted 43 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
Quoted 6 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)Quoted 5 lines
Quoted 5 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 5 lines
fs/f2fs/data.c +0
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 43 lines
Quoted 12 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 10 lines
fs/f2fs/data.c +2
-0struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
fs/f2fs/data.c +2
-1trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); -if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
Quoted 6 lines
Quoted 3 lines
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
Understood, but the concern was the multi-thread performance as you mentioned. If one thread throws a big dio request, anybody cannot write at all?
Buffered write will not be stopped, but actually my way completely stops the concurrency of multithreads which are doing dio writes, for aspect of improving concurrency, moving
mutex_unlockbelow__allocate_data_blocksis a good solution so far.Quoted 2 lines
How about adding some limits likewise
f2fs_write_data_pageswhieh is for examplenr_pages_to_write?
Quoted 7 lines
Quoted 4 lines
Could you share more details about your idea?
As Yunlei reported, there is performance regression issue, so how about holding this patch and let me do some investigation?
It seems there is a mutex overhead when handling a bunch of 4KB small dios. Hmm, I meant, how about serializing pretty long-sized dios only?
Oh, I got it, thanks for the idea. :)
I will take time to have a test.
Thanks,
Quoted 45 lines
Quoted 45 lines
Thanks,
Quoted 41 lines
Thanks,
Quoted 11 lines
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs--filesize=256m --size=4m --bs=64k --direct=1
Quoted 4 lines
--numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec,maxt=14119msec
Quoted 2 lines
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec,maxt=13454msec
Quoted 18 lines
So how about keep it in original place in this patch?
Thanks,
Quoted 14 lines
Thanks,
Quoted 11 lines
fs/f2fs/data.c +6
-2+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);--
2.4.2
------------------------------------------------------------------------------
Quoted 109 lines · Chao Yu
Hi Jaegeuk,
Quoted 60 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 21 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)fs/f2fs/data.c +2
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));fs/f2fs/data.c +2
-1-if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
If I'm missing something, please correct me.
Quoted 5 lines
Quoted 2 lines
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=4m --bs=64k --direct=1 --numjobs=20
Quoted 6 lines
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec, maxt=14119msec unlock after dio finished: WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec, maxt=13454msecSo how about keep it in original place in this patch?
Does share writepages mutex lock have an effect on cache write? Here is AndroBench result on my phone:
Before patch:
1R1W 8R8W 16R16W
Sequential Write 161.31 163.85 154.67
Random Write 9.48 17.66 18.09
After patch:
1R1W 8R8W 16R16W
Sequential Write 159.61 157.24 160.11
Random Write 9.17 8.51 8.8
Unit:Mb/s, File size: 64M, Buffer size: 4k
Quoted 33 lines
Thanks,
Quoted 14 lines
Thanks,
Quoted 11 lines
fs/f2fs/data.c +6
-2+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }Quoted 4 lines
Quoted 4 lines
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);--
2.4.2------------------------------------------------------------------------------
Monitor Your Dynamic Infrastructure at Any Scale With Datadog! Get real-time metrics from all of your servers, apps and tools in one place.
SourceForge users - Click here to start your Free Trial of Datadog now!
http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
_______________________________________________
Linux-f2fs-devel mailing list [email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
Quoted 2 lines
.
------------------------------------------------------------------------------
Monitor Your Dynamic Infrastructure at Any Scale With Datadog! Get real-time metrics from all of your servers, apps and tools in one place.
SourceForge users - Click here to start your Free Trial of Datadog now!
http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
Hi Yunlei,
Quoted 137 lines
-----Original Message-----
From: He YunLei [mailto:[email protected]]
Sent: Thursday, September 17, 2015 8:40 AM
To: Chao Yu
Cc: 'Jaegeuk Kim'; [email protected]; [email protected]
Subject: Re: [f2fs-dev] [PATCH 5/7] f2fs: enhance multithread dio write performanceQuoted 45 lines · Chao Yu
Hi Jaegeuk,
Quoted 43 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
Quoted 6 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)Quoted 5 lines
Quoted 5 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 5 lines
fs/f2fs/data.c +0
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 50 lines
Quoted 12 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 10 lines
fs/f2fs/data.c +2
-0struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, · line 1561
Quoted 5 lines
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));fs/f2fs/data.c +2
-1-if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
If I'm missing something, please correct me.
Quoted 1 line
Quoted 7 lines
Quoted 4 lines
Quoted 1 line
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs--filesize=256m --size=4m --bs=64k --direct=1
Quoted 4 lines
--numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec,maxt=14119msec
Quoted 2 lines
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec,maxt=13454msec
Quoted 2 lines
So how about keep it in original place in this patch?
Does share writepages mutex lock have an effect on cache write? Here is AndroBench result on my phone:
Before patch:
1R1W 8R8W 16R16W
Sequential Write 161.31 163.85 154.67
Random Write 9.48 17.66 18.09
Quoted 4 lines
After patch:
1R1W 8R8W 16R16W
Sequential Write 159.61 157.24 160.11
Random Write 9.17 8.51 8.8
Thanks for your report, I will do the investigation.
Thanks,
Quoted 38 lines
Unit:Mb/s, File size: 64M, Buffer size: 4k
Quoted 35 lines
Thanks,
Quoted 14 lines
Thanks,
Quoted 11 lines
fs/f2fs/data.c +6
-2+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }Quoted 4 lines
Quoted 4 lines
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);--
2.4.2------------------------------------------------------------------------------
Monitor Your Dynamic Infrastructure at Any Scale With Datadog! Get real-time metrics from all of your servers, apps and tools in one place.
SourceForge users - Click here to start your Free Trial of Datadog now!
http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
_______________________________________________
Linux-f2fs-devel mailing list [email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel.
Hi Yunlei,
Quoted 137 lines
-----Original Message-----
From: He YunLei [mailto:[email protected]]
Sent: Thursday, September 17, 2015 8:40 AM
To: Chao Yu
Cc: 'Jaegeuk Kim'; [email protected]; [email protected]
Subject: Re: [f2fs-dev] [PATCH 5/7] f2fs: enhance multithread dio write performanceQuoted 45 lines · Chao Yu
Hi Jaegeuk,
Quoted 43 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, September 16, 2015 5:21 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 5/7] f2fs: enhance multithread dio write performanceHi Chao,
Quoted 9 lines · Chao Yu
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks which allocated in Thread A being discontinuous.Quoted 8 lines
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.2+, intel i7-3770, 16g memory, 32g kingston sd card.fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs
--filesize=256m --size=16m --bs=2m --direct=1
Quoted 4 lines
--numjobs=10
before:
WRITE: io=163840KB, aggrb=3145KB/s, minb=314KB/s, maxb=411KB/s, mint=39836msec,maxt=52083msec
Quoted 3 lines
patched:
WRITE: io=163840KB, aggrb=10033KB/s, minb=1003KB/s, maxb=1124KB/s, mint=14565msec,maxt=16329msec
Quoted 6 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)Quoted 5 lines
Quoted 5 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 5 lines
fs/f2fs/data.c +0
-0@@ -1536,7 +1536,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 50 lines
Quoted 12 lines
fs/f2fs/data.c static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter
Quoted 10 lines
fs/f2fs/data.c +2
-0struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter);int err;/* we don't need to use inline_data strictly */ @@ -1555,12 +1557,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter*iter,
Quoted 1 line
Quoted 7 lines
fs/f2fs/data.c
Quoted 5 lines
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));fs/f2fs/data.c +2
-1-if (iov_iter_rw (iter) ==WRITE ) +if (rw ==WRITE ) { +mutex_lock (&sbi->writepages);Why do we have to share
sbi->writepages?The root cause of this issue is that: in f2fs, we have no suitable dispatcher which can do the following things as an atomic operation:
a) allocate position(s) in flash device for current block(s);
b) submit user data in allocated position(s) in block layer.Without the dispatcher, we will suffer performance issue in following scenario:
Thread A Thread B Thread C
allocate pos+1
allocate pos+2
allocate pos+3
submit pos+1
submit pos+3
submit pos+2Our final submitting series will: pos+1, pos+3, pos+2, this makes f2fs running into non-LFS mode, therefore resulting in bad performance.
writepages mutex lock supply us with a good solution for above issue. It not only make the allocating and submitting pair executing atomically, but also reduce the fragmentation for one file since we submit blocks belong to single inode as continuous as possible.
So here I choose to use writepages mutex lock to fix the performance issue caused by both dio write vs dio write and dio write vs buffered write.
If I'm missing something, please correct me.
Quoted 1 line
Quoted 7 lines
Quoted 4 lines
Quoted 1 line
__allocate_data_blocks(inode, offset, count);If the problem lies on the misaligned blocks, how about calling
mutex_unlockhere?When changing to unlock here, I got regression when testing with following command:
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs--filesize=256m --size=4m --bs=64k --direct=1
Quoted 4 lines
--numjobs=20
unlock here:
WRITE: io=81920KB, aggrb=5802KB/s, minb=290KB/s, maxb=292KB/s, mint=14010msec,maxt=14119msec
Quoted 2 lines
unlock after dio finished:
WRITE: io=81920KB, aggrb=6088KB/s, minb=304KB/s, maxb=1081KB/s, mint=3786msec,maxt=13454msec
Quoted 2 lines
So how about keep it in original place in this patch?
Does share writepages mutex lock have an effect on cache write? Here is AndroBench result on my phone:
Before patch:
1R1W 8R8W 16R16W
Sequential Write 161.31 163.85 154.67
Random Write 9.48 17.66 18.09
Quoted 6 lines
After patch:
1R1W 8R8W 16R16W
Sequential Write 159.61 157.24 160.11
Random Write 9.17 8.51 8.8Unit:Mb/s, File size: 64M, Buffer size: 4k
Could you help to test the following patch?
Quoted 1 line
From
0abff8a16bf87076ec70a7c1b8da913000e9c3b7Mon Sep 17 00:00:00 2001
From: Chao Yu <[email protected]>
Date: Wed, 21 Oct 2015 15:12:07 +0800
Subject: [PATCH v2] f2fs: enhance multithread dio write performance
When dio writes perform concurrently, our performace will be low because of Thread A's allocation of multi continuous blocks will be break by Thread B, there are two cases as below:
- In Thread B, we may change current segment to a new segment for LFS allocation if we dio write in the beginning of the file.
- In Thread B, we may allocate blocks in the middle of Thread A's allocation, which make blocks allocated in Thread A being inconsecutive.
This patch adds writepages mutex lock to make block allocation in dio write atomic to avoid above issues.
Test environment:
ubuntu os with linux kernel 4.4-rc4, intel i7-3770, 16g memory, 32g kingston sd card.
fio --name seqw --ioengine=sync --invalidate=1 --rw=write --directory=/mnt/f2fs --filesize=256m --size=16m --bs=2m --direct=1 --numjobs=10
before:
WRITE: io=163840KB, aggrb=5125KB/s, minb=512KB/s, maxb=776KB/s, mint=21105msec, maxt=31967msec
patched:
WRITE: io=163840KB, aggrb=10424KB/s, minb=1042KB/s, maxb=1172KB/s, mint=13975msec, maxt=15717msec
---
v2:
- only serialize block allocation.
- do not serialize small dio.
fs/f2fs/data.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-)
fs/f2fs/data.c +11 -4
@@ -1566,7 +1566,10 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,struct file *file = iocb->ki_filp;struct address_space *mapping = file->f_mapping;struct inode *inode = mapping->host; +struct f2fs_sb_info *sbi =F2FS_I_SB (inode);size_t count =iov_iter_count (iter); +int rw =iov_iter_rw (iter); +bool serialized = (F2FS_BYTES_TO_BLK (count) >=64 );int err;/* we don't need to use inline_data strictly */
@@ -1583,10 +1586,14 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,if (err)return err; -trace_f2fs_direct_IO_enter (inode, offset, count,iov_iter_rw (iter)); +trace_f2fs_direct_IO_enter (inode, offset, count, rw); -if (iov_iter_rw (iter) ==WRITE ) { +if (rw ==WRITE ) { +if (serialized) +mutex_lock (&sbi->writepages);__allocate_data_blocks (inode, offset, count); +if (serialized) +mutex_unlock (&sbi->writepages);if (unlikely (f2fs_cp_error (F2FS_I_SB (inode)))) { err = -EIO ; goto out;
@@ -1595,10 +1602,10 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); out: -if (err <0 &&iov_iter_rw (iter) ==WRITE ) +if (err <0 && rw ==WRITE )f2fs_write_failed (mapping, offset + count); -trace_f2fs_direct_IO_exit (inode, offset, count,iov_iter_rw (iter), err); +trace_f2fs_direct_IO_exit (inode, offset, count, rw, err);return err; }
Signature · 1 line
2.6.3
Quoted 36 lines
Quoted 36 lines
Thanks,
Quoted 14 lines
Thanks,
Quoted 11 lines
fs/f2fs/data.c +6
-2+ } err =blockdev_direct_IO (iocb, inode, iter, offset, get_data_block_dio); -if (err <0 &&iov_iter_rw (iter) ==WRITE ) -f2fs_write_failed (mapping, offset + count); +if (rw ==WRITE ) { +mutex_unlock (&sbi->writepages); +if (err) +f2fs_write_failed (mapping, offset + count); + }Quoted 4 lines
Quoted 4 lines
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);--
2.4.2------------------------------------------------------------------------------
Monitor Your Dynamic Infrastructure at Any Scale With Datadog! Get real-time metrics from all of your servers, apps and tools in one place.
SourceForge users - Click here to start your Free Trial of Datadog now!
http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
_______________________________________________
Linux-f2fs-devel mailing list [email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel.