Commit Graph

172 Commits

Author SHA1 Message Date
Jaegeuk Kim
f1a3b98e73 f2fs: fix accessing wrong indexed data blocks
This patch fixes the following test.

This causes:
 attempt to access beyond end of device
 sdb2: rw=16384, want=14413962000, limit=16777216

The reason is:
 - f2fs_write_begin
  - f2fs_convert_inline_inode returns -ENOSPC
  - f2fs_write_failed
   - truncate_blocks
    - truncate_partial_data_page
     - find_data_page
      - get_dnode_of_data returns wrong data index retrieved from inline_data
      - f2fs_submit_page_bio(wrong data index)
       - submit_bio(wrong data index)

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-11 17:04:51 -08:00
Jaegeuk Kim
aaf9607516 f2fs: check node page contents all the time
In get_node_page, if the page is up-to-date, we assumed that the page was not
reclaimed at all.
But, sometimes it was reported that its contents was missing.
So, just for sure, let's check its mapping and contents.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-11 17:04:46 -08:00
Chao Yu
487261f39b f2fs: merge {invalidate,release}page for meta/node/data pages
This patch merges ->{invalidate,release}page function for meta/node/data pages.

After this, duplication of codes could be removed.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-11 17:04:44 -08:00
Jaegeuk Kim
f68daeebba f2fs: keep PagePrivate during releasepage
If PagePrivate is removed by releasepage, f2fs loses counting dirty pages.

e.g., try_to_release_page will not release page when the page is dirty,
but our releasepage removes PagePrivate.

    [<ffffffff81188d75>] try_to_release_page+0x35/0x50
    [<ffffffff811996f9>] invalidate_inode_pages2_range+0x2f9/0x3b0
    [<ffffffffa02a7f54>] ? truncate_blocks+0x384/0x4d0 [f2fs]
    [<ffffffffa02b7583>] ? f2fs_direct_IO+0x283/0x290 [f2fs]
    [<ffffffffa02b7fb0>] ? get_data_block_fiemap+0x20/0x20 [f2fs]
    [<ffffffff8118aa53>] generic_file_direct_write+0x163/0x170
    [<ffffffff8118ad06>] __generic_file_write_iter+0x2a6/0x350
    [<ffffffff8118adef>] generic_file_write_iter+0x3f/0xb0
    [<ffffffff81203081>] new_sync_write+0x81/0xb0
    [<ffffffff81203837>] vfs_write+0xb7/0x1f0
    [<ffffffff81204459>] SyS_write+0x49/0xb0
    [<ffffffff817c286d>] system_call_fastpath+0x16/0x1b

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-11 17:04:42 -08:00
Chao Yu
caf0047e7e f2fs: merge flags in struct f2fs_sb_info
Currently, there are several variables with Boolean type as below:

struct f2fs_sb_info {
...
	int s_dirty;
	bool need_fsck;
	bool s_closing;
...
	bool por_doing;
...
}

For this there are some issues:
1. there are some space of f2fs_sb_info is wasted due to aligning after Boolean
   type variables by compiler.
2. if we continuously add new flag into f2fs_sb_info, structure will be messed
   up.

So in this patch, we try to:
1. switch s_dirty to Boolean type variable since it has two status 0/1.
2. merge s_dirty/need_fsck/s_closing/por_doing variables into s_flag.
3. introduce an enum type which can indicate different states of sbi.
4. use new introduced universal interfaces is_sbi_flag_set/{set,clear}_sbi_flag
   to operate flags for sbi.

After that, above issues will be fixed.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-11 17:04:38 -08:00
Jaegeuk Kim
7aed0d4537 f2fs: free radix_tree_nodes used by nat_set entries
In the normal case, the radix_tree_nodes are freed successfully.
But, when cp_error was detected, we should destroy them forcefully.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:28 -08:00
Jaegeuk Kim
3547ea961d f2fs: avoid potential unnecessary codes
This patch relocates some operations to avoid unnecessary execution.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:26 -08:00
Jaegeuk Kim
9e4ded3f30 f2fs: activate f2fs_trace_pid
This patch activates f2fs_trace_pid.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:24 -08:00
Jaegeuk Kim
cf04e8eb55 f2fs: use f2fs_io_info to clean up messy parameters during IO path
This patch cleans up parameters on IO paths.
The key idea is to use f2fs_io_info adding a parameter, block address, and then
use this structure as parameters.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:23 -08:00
Chao Yu
9ecf4b80bd f2fs: use ra_meta_pages to simplify readahead code in restore_node_summary
Use more common function ra_meta_pages() with META_POR to readahead node blocks
in restore_node_summary() instead of ra_sum_pages(), hence we can simplify the
readahead code there, and also we can remove unused function ra_sum_pages().

changes from v2:
 o use invalidate_mapping_pages as before suggested by Changman Lee.
changes from v1:
 o fix one bug when using truncate_inode_pages_range which is pointed out by
   Jaegeuk Kim.

Reviewed-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:23 -08:00
Chao Yu
5c27f4ee44 f2fs: merge two uchar variable in struct node_info to reduce memory cost
This patch moves one member of struct nat_entry: _flag_ to struct node_info,
so _version_ in struct node_info and _flag_ which are unsigned char type will
merge to one 32-bit space in register/memory. So the size of nat_entry will be
reduced from 28 bytes to 24 bytes (for 64-bit machine, reduce its size from 40
bytes to 32 bytes) and then slab memory using by f2fs will be reduced.

changes from v2:
 o update description of memory usage gain for 64-bit machine suggested by
   Changman Lee.
changes from v1:
 o introduce inline copy_node_info() to copy valid data from node info suggested
   by Jaegeuk Kim, it can avoid bug.

Reviewed-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:23 -08:00
Jaegeuk Kim
1e84371ffe f2fs: change atomic and volatile write policies
This patch adds two new ioctls to release inmemory pages grabbed by atomic
writes.
 o f2fs_ioc_abort_volatile_write
  - If transaction was failed, all the grabbed pages and data should be written.
 o f2fs_ioc_release_volatile_write
  - This is to enhance the performance of PERSIST mode in sqlite.

In order to avoid huge memory consumption which causes OOM, this patch changes
volatile writes to use normal dirty pages, instead blocked flushing to the disk
as long as system does not suffer from memory pressure.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:22 -08:00
Jaegeuk Kim
cd52b6368f f2fs: remove checking dirty_exceed
We don't need to force to write dirty_exceeded for f2fs_balance_fs_bg.
This flag was only meaningful to write bypassing conditions.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-01-09 17:02:21 -08:00
Jaegeuk Kim
9be32d72be f2fs: do retry operations with cond_resched
This patch revists retrial paths in f2fs.
The basic idea is to use cond_resched instead of retrying from the very early
stage.

Suggested-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-12-08 10:35:05 -08:00
Jaegeuk Kim
769ec6e5b7 f2fs: call radix_tree_preload before radix_tree_insert
This patch tries to fix:

 BUG: using smp_processor_id() in preemptible [00000000] code: f2fs_gc-254:0/384
  (radix_tree_node_alloc+0x14/0x74) from [<c033d8a0>] (radix_tree_insert+0x110/0x200)
  (radix_tree_insert+0x110/0x200) from [<c02e8264>] (gc_data_segment+0x340/0x52c)
  (gc_data_segment+0x340/0x52c) from [<c02e8658>] (f2fs_gc+0x208/0x400)
  (f2fs_gc+0x208/0x400) from [<c02e8a98>] (gc_thread_func+0x248/0x28c)
  (gc_thread_func+0x248/0x28c) from [<c0139944>] (kthread+0xa0/0xac)
  (kthread+0xa0/0xac) from [<c0105ef8>] (ret_from_fork+0x14/0x3c)

The reason is that f2fs calls radix_tree_insert under enabled preemption.
So, before calling it, we need to call radix_tree_preload.

Otherwise, we should use _GFP_WAIT for the radix tree, and use mutex or
semaphore to cover the radix tree operations.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-12-05 09:51:04 -08:00
Jaegeuk Kim
8b26ef98da f2fs: use rw_semaphore for nat entry lock
Previoulsy, we used rwlock for nat_entry lock.
But, now we have a lot of complex operations in set_node_addr.
(e.g., allocating kernel memories, handling radix_trees, and so on)

So, this patches tries to change spinlock to rw_semaphore to give CPUs to other
threads.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-12-03 21:23:29 -08:00
Jaegeuk Kim
4634d71ed1 f2fs: fix missing kmem_cache_free
This patch fixes missing kmem_cache_free when handling errors.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-12-03 16:40:28 -08:00
Changman Lee
80ec2e914d f2fs: no more dirty_nat_entires when flushing
After flushing dirty nat entries, it has to be no more dirty nat
entries.

Signed-off-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-25 17:26:36 -08:00
Changman Lee
20d047c876 f2fs: check dirty_nat_cnt before flushing nat entries in journal
It's meaningless to check dirty_nat_cnt after re-dirtying nat entries in
journal. And although there are rooms for dirty nat entires if dirty_nat_cnt
is zero, it's also meaningless to check __has_cursum_space.

Signed-off-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-25 17:26:34 -08:00
Markus Elfring
ce3e6d25f3 f2fs: fix typos for the word "destroy" in jump labels
Two jump labels were adjusted in the implementation of the
create_node_manager_caches() function because these identifiers
contained typos.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-25 12:08:22 -08:00
Jaegeuk Kim
27c6bd60ac f2fs: submit bio for node blocks in the reclaim path
If a node page is request to be written during the reclaiming path, we should
submit the bio to avoid pending to recliam it.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-19 22:49:32 -08:00
Chao Yu
67298804f3 f2fs: introduce struct inode_management to wrap inner fields
Now in f2fs, we have three inode cache: ORPHAN_INO, APPEND_INO, UPDATE_INO,
and we manage fields related to inode cache separately in struct f2fs_sb_info
for each inode cache type.
This makes codes a bit messy, so that this patch intorduce a new struct
inode_management to wrap inner fields as following which make codes more neat.

/* for inner inode cache management */
struct inode_management {
	struct radix_tree_root ino_root;	/* ino entry array */
	spinlock_t ino_lock;			/* for ino entry lock */
	struct list_head ino_list;		/* inode list head */
	unsigned long ino_num;			/* number of entries */
};

struct f2fs_sb_info {
	...
	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
	...
}

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-19 22:49:32 -08:00
Jaegeuk Kim
2f97c326bf f2fs: write node pages if checkpoint is not doing
It needs to write node pages if checkpoint is not doing in order to avoid
memory pressure.

Reviewed-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-10 06:51:28 -08:00
Jaegeuk Kim
e5e7ea3c86 f2fs: control the memory footprint used by ino entries
This patch adds to control the memory footprint used by ino entries.
This will conduct best effort, not strictly.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-11-06 15:24:46 -08:00
Jaegeuk Kim
309cc2b6e7 f2fs: refactor flush_nat_entries to remove costly reorganizing ops
Previously, f2fs tries to reorganize the dirty nat entries into multiple sets
according to its nid ranges. This can improve the flushing nat pages, however,
if there are a lot of cached nat entries, it becomes a bottleneck.

This patch introduces a new set management flow by removing dirty nat list and
adding a series of set operations when the nat entry becomes dirty.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-30 15:30:41 -07:00
Jaegeuk Kim
90a893c749 f2fs: use MAX_BIO_BLOCKS(sbi)
This patch cleans up a simple macro.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-23 11:10:18 -07:00
Jaegeuk Kim
88bd02c947 f2fs: fix conditions to remain recovery information in f2fs_sync_file
This patch revisited whole the recovery information during the f2fs_sync_file.

In this patch, there are three information to make a decision.

a) IS_CHECKPOINTED,	/* is it checkpointed before? */
b) HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
c) HAS_LAST_FSYNC,	/* has the latest node fsync mark? */

And, the scenarios for our rule are based on:

[Term] F: fsync_mark, D: dentry_mark

1. inode(x) | CP | inode(x) | dnode(F)
2. inode(x) | CP | inode(F) | dnode(F)
3. inode(x) | CP | dnode(F) | inode(x) | inode(F)
4. inode(x) | CP | dnode(F) | inode(F)
5. CP | inode(x) | dnode(F) | inode(DF)
6. CP | inode(DF) | dnode(F)
7. CP | dnode(F) | inode(DF)
8. CP | dnode(F) | inode(x) | inode(DF)

For example, #3, the three conditions should be changed as follows.

   inode(x) | CP | dnode(F) | inode(x) | inode(F)
a)    x       o      o          o          o
b)    x       x      x          x          o
c)    x       o      o          x          o

If f2fs_sync_file stops   ------^,
 it should write inode(F)    --------------^

So, the need_inode_block_update should return true, since
 c) get_nat_flag(e, HAS_LAST_FSYNC), is false.

For example, #8,
      CP | alloc | dnode(F) | inode(x) | inode(DF)
a)    o      x        x          x          x
b)    x               x          x          o
c)    o               o          x          o

If f2fs_sync_file stops   -------^,
 it should write inode(DF)    --------------^

Note that, the roll-forward policy should follow this rule, which means,
if there are any missing blocks, we doesn't need to recover that inode.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-23 11:10:15 -07:00
Jaegeuk Kim
7ef35e3b9e f2fs: introduce a flag to represent each nat entry information
This patch introduces a flag in the nat entry structure to merge various
information such as checkpointed and fsync_done marks.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-23 11:10:14 -07:00
Chao Yu
184a5cd2ce f2fs: refactor flush_sit_entries codes for reducing SIT writes
In commit aec71382c6 ("f2fs: refactor flush_nat_entries codes for reducing NAT
writes"), we descripte the issue as below:

"Although building NAT journal in cursum reduce the read/write work for NAT
block, but previous design leave us lower performance when write checkpoint
frequently for these cases:
1. if journal in cursum has already full, it's a bit of waste that we flush all
   nat entries to page for persistence, but not to cache any entries.
2. if journal in cursum is not full, we fill nat entries to journal util
   journal is full, then flush the left dirty entries to disk without merge
   journaled entries, so these journaled entries may be flushed to disk at next
   checkpoint but lost chance to flushed last time."

Actually, we have the same problem in using SIT journal area.

In this patch, firstly we will update sit journal with dirty entries as many as
possible. Secondly if there is no space in sit journal, we will remove all
entries in journal and walk through the whole dirty entry bitmap of sit,
accounting dirty sit entries located in same SIT block to sit entry set. All
entry sets are linked to list sit_entry_set in sm_info, sorted ascending order
by count of entries in set. Later we flush entries in set which have fewest
entries into journal as many as we can, and then flush dense set with merged
entries to disk.

In this way we can use sit journal area more effectively, also we will reduce
SIT update, result in gaining in performance and saving lifetime of flash
device.

In my testing environment, it shows this patch can help to reduce SIT block
update obviously.

virtual machine + hard disk:
fsstress -p 20 -n 400 -l 5
		sit page num	cp count	sit pages/cp
based		2006.50		1349.75		1.486
patched		1566.25		1463.25		1.070

Our latency of merging op is small when handling a great number of dirty SIT
entries in flush_sit_entries:
latency(ns)	dirty sit count
36038		2151
49168		2123
37174		2232

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-09 13:15:05 -07:00
Jaegeuk Kim
9850cf4a89 f2fs: need fsck.f2fs when f2fs_bug_on is triggered
If any f2fs_bug_on is triggered, fsck.f2fs is needed.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-09 13:15:02 -07:00
Jaegeuk Kim
4081363fbe f2fs: introduce F2FS_I_SB, F2FS_M_SB, and F2FS_P_SB
This patch adds three inline functions to clean up dirty casting codes.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-03 17:37:13 -07:00
Jaegeuk Kim
c2e69583a4 f2fs: truncate stale block for inline_data
This verifies to truncate any allocated blocks, offset[0], by inline_data.
Not figured out, but for making sure.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-25 14:52:09 -07:00
Chao Yu
c200b1aa6c f2fs: fix incorrect calculation with total/free inode num
Theoretically, our total inodes number is the same as total node number, but
there are three node ids are reserved in f2fs, they are 0, 1 (node nid), and 2
(meta nid), and they should never be used by user, so our total/free inode
number calculated in ->statfs is wrong.

This patch indroduces F2FS_RESERVED_NODE_NUM and then fixes this issue by
recalculating total/free inode number with the macro.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-21 13:57:06 -07:00
Jaegeuk Kim
202095a7a0 f2fs: remove rewrite_node_page
I think we need to let the dirty node pages remain in the page cache instead
of rewriting them in their places.
So, after done with successful recovery, write_checkpoint will flush all of them
through the normal write path.
Through this, we can avoid potential error cases in terms of block allocation.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-21 13:57:02 -07:00
Jaegeuk Kim
cf779cab14 f2fs: handle EIO not to break fs consistency
There are two rules when EIO is occurred.
1. don't write any checkpoint data to preserve the previous checkpoint
2. don't lose the cached dentry/node/meta pages

So, at first, this patch adds set_page_dirty in f2fs_write_end_io's failure.
Then, writing checkpoint/dentry/node blocks is not allowed.

Note that, for the data pages, we can't just throw away by redirtying them.
Otherwise, kworker can fall into infinite loop to flush them.
(Ref. xfstests/019)

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-21 13:55:05 -07:00
Jaegeuk Kim
5274651927 f2fs: unlock_page when node page is redirtied out
This patch fixes missing unlock_page when a node page is redirtied out.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-21 09:21:01 -07:00
Jaegeuk Kim
1c35a90e8a f2fs: fix to recover inline_xattr/data and blocks
This patch fixes not to skip xattr recovery and inline xattr/data recovery
order.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-19 10:01:34 -07:00
Jaegeuk Kim
e3b4d43f7c f2fs: should clear the inline_xattr flag
During the recovery, we should clear the inline_xattr flag if its xattr node
block is recovered.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-19 10:01:34 -07:00
Jaegeuk Kim
617deb8c05 f2fs: fix the initial inode page for recovery
If a new inode page is needed for recover_dentry, we should assing i_inline
as zero.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-19 10:01:34 -07:00
arter97
e1c4204520 f2fs: fix typo
Fix typo and some grammatical errors.

The words "filesystem" and "readahead" are being used without the space treewide.

Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-19 10:01:33 -07:00
Chao Yu
70cfed88ef f2fs: avoid skipping recover_inline_xattr after recover_inline_data
When we recover data of inode in roll-forward procedure, and the inode has both
inline data and inline xattr. We may skip recovering inline xattr if we recover
inline data form node page first.
This patch will fix the problem that we lost inline xattr data in above
scenario.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-08-02 07:43:51 -07:00
Chao Yu
b3582c6892 f2fs: reduce competition among node page writes
We do not need to block on ->node_write among different node page writers e.g.
fsync/flush, unless we have a node page writer from write_checkpoint.
So it's better use rw_semaphore instead of mutex type for ->node_write to
promote performance.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-30 23:28:37 -07:00
Chao Yu
aec71382c6 f2fs: refactor flush_nat_entries codes for reducing NAT writes
Although building NAT journal in cursum reduce the read/write work for NAT
block, but previous design leave us lower performance when write checkpoint
frequently for these cases:
1. if journal in cursum has already full, it's a bit of waste that we flush all
   nat entries to page for persistence, but not to cache any entries.
2. if journal in cursum is not full, we fill nat entries to journal util
   journal is full, then flush the left dirty entries to disk without merge
   journaled entries, so these journaled entries may be flushed to disk at next
   checkpoint but lost chance to flushed last time.

In this patch we merge dirty entries located in same NAT block to nat entry set,
and linked all set to list, sorted ascending order by entries' count of set.
Later we flush entries in sparse set into journal as many as we can, and then
flush merged entries to disk. In this way we can not only gain in performance,
but also save lifetime of flash device.

In my testing environment, it shows this patch can help to reduce NAT block
writes obviously. In hard disk test case: cost time of fsstress is stablely
reduced by about 5%.

1. virtual machine + hard disk:
fsstress -p 20 -n 200 -l 5
		node num	cp count	nodes/cp
based		4599.6		1803.0		2.551
patched		2714.6		1829.6		1.483

2. virtual machine + 32g micro SD card:
fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0
-f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5
-f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S

		node num	cp count	nodes/cp
based		84.5		43.7		1.933
patched		49.2		40.0		1.23

Our latency of merging op shows not bad when handling extreme case like:
merging a great number of dirty nats:
latency(ns)	dirty nat count
3089219		24922
5129423		27422
4000250		24523

change log from v1:
 o fix wrong logic in add_nat_entry when grab a new nat entry set.
 o swith to create slab cache in create_node_manager_caches.
 o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency.

change log from v2:
 o make comment position more appropriate suggested by Jaegeuk Kim.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-09 14:04:25 -07:00
Jaegeuk Kim
a014e037be f2fs: clean up an unused parameter and assignment
This patch cleans up simple unnecessary codes.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-09 14:04:25 -07:00
Jaegeuk Kim
2743f86554 f2fs: check bdi->dirty_exceeded when trying to skip data writes
If we don't check the current backing device status, balance_dirty_pages can
fall into infinite pausing routine.

This can be occurred when a lot of directories make a small number of dirty
dentry pages including files.

Reported-by: Brian Chadwick <brianchad@westnet.com.au>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-09 05:59:45 -07:00
Linus Torvalds
64b2d1fbbf f2fs updates for v3.16
This patch-set includes the following major enhancement patches.
  o enhance wait_on_page_writeback
  o support SEEK_DATA and SEEK_HOLE
  o enhance readahead flows
  o enhance IO flushes
  o support fiemap
  o add some tracepoints
 
 The other bug fixes are as follows.
  o fix to support a large volume > 2TB correctly
  o recovery bug fix wrt fallocated space
  o fix recursive lock on xattr operations
  o fix some cases on the remount flow
 
 And, there are a bunch of cleanups.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJTleLYAAoJEEAUqH6CSFDSdhEP/iY5hTZ02jH4ZiFPP/Nee4hS
 l0BHeZvrMjoccaWUDu0ZvIPC8BiJ7kLOgK+/VWS7LAfY1PY11ALEtYQOrW+RM47+
 jMfULegTod/F8WS2B6dk31QMhAZldtnsYvA5PS1VV3S0rht+qbOz+PDejZFgSMc3
 VVQ7OZzq30gMmtsw7oh3FHfeTu4xe/bxygdMRXgljQQD2MvorJiOb4MA+ovEDd9z
 CZMMTQvRKjc0d8LPf0gOkZEvG63GR6klCgFMuiappUsua0O8IPIEhCyEGFrE66vS
 fObVKpqNAsR2ABhS2grgn6Q7UUvn4xrF6jOwDH5tuw2yzmkQiMAWINwBdgnbEy1c
 D5S89PQ8TkQK9KBSoU0v8WKWC4HzWZF4ZEd6eq9VxVTS8iT0w8DtNHXK518FVC34
 82iqrLc0EhrcGNiW/7Nrc6WzHrWqorylCFN7atB3ruhVqeMh3MZsDU4Gq0WgB2oh
 pF9XVBEpJQpV35DYSAPzLkm+2+mwHVNqwdY3HcvUs7IP90+wZlrWSRG2FEfFt/e8
 6nwvbORrHMTI5VfdYlEPgpjuesFmYPZqEvRGdaDa1YrHqhvvgStEPT9qiq2qVn9+
 tr0HjpNRDD/etkaE6ujYOYqdxuk3mm6RY68h+KSbNcY1/VTvt2bN2telwWuDsxIq
 8yOsxV2x3JB/euDAJsSU
 =xqsO
 -----END PGP SIGNATURE-----

Merge tag 'for-f2fs-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, there is no special interesting feature, but we've
  investigated a couple of tuning points with respect to the I/O flow.
  Several major bug fixes and a bunch of clean-ups also have been made.

  This patch-set includes the following major enhancement patches:
   - enhance wait_on_page_writeback
   - support SEEK_DATA and SEEK_HOLE
   - enhance readahead flows
   - enhance IO flushes
   - support fiemap
   - add some tracepoints

  The other bug fixes are as follows:
   - fix to support a large volume > 2TB correctly
   - recovery bug fix wrt fallocated space
   - fix recursive lock on xattr operations
   - fix some cases on the remount flow

  And, there are a bunch of cleanups"

* tag 'for-f2fs-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (52 commits)
  f2fs: support f2fs_fiemap
  f2fs: avoid not to call remove_dirty_inode
  f2fs: recover fallocated space
  f2fs: fix to recover data written by dio
  f2fs: large volume support
  f2fs: avoid crash when trace f2fs_submit_page_mbio event in ra_sum_pages
  f2fs: avoid overflow when large directory feathure is enabled
  f2fs: fix recursive lock by f2fs_setxattr
  MAINTAINERS: add a co-maintainer from samsung for F2FS
  MAINTAINERS: change the email address for f2fs
  f2fs: use inode_init_owner() to simplify codes
  f2fs: avoid to use slab memory in f2fs_issue_flush for efficiency
  f2fs: add a tracepoint for f2fs_read_data_page
  f2fs: add a tracepoint for f2fs_write_{meta,node,data}_pages
  f2fs: add a tracepoint for f2fs_write_{meta,node,data}_page
  f2fs: add a tracepoint for f2fs_write_end
  f2fs: add a tracepoint for f2fs_write_begin
  f2fs: fix checkpatch warning
  f2fs: deactivate inode page if the inode is evicted
  f2fs: decrease the lock granularity during write_begin
  ...
2014-06-09 19:11:44 -07:00
Mel Gorman
2457aec637 mm: non-atomically mark page accessed during page cache allocation where possible
aops->write_begin may allocate a new page and make it visible only to have
mark_page_accessed called almost immediately after.  Once the page is
visible the atomic operations are necessary which is noticable overhead
when writing to an in-memory filesystem like tmpfs but should also be
noticable with fast storage.  The objective of the patch is to initialse
the accessed information with non-atomic operations before the page is
visible.

The bulk of filesystems directly or indirectly use
grab_cache_page_write_begin or find_or_create_page for the initial
allocation of a page cache page.  This patch adds an init_page_accessed()
helper which behaves like the first call to mark_page_accessed() but may
called before the page is visible and can be done non-atomically.

The primary APIs of concern in this care are the following and are used
by most filesystems.

	find_get_page
	find_lock_page
	find_or_create_page
	grab_cache_page_nowait
	grab_cache_page_write_begin

All of them are very similar in detail to the patch creates a core helper
pagecache_get_page() which takes a flags parameter that affects its
behavior such as whether the page should be marked accessed or not.  Then
old API is preserved but is basically a thin wrapper around this core
function.

Each of the filesystems are then updated to avoid calling
mark_page_accessed when it is known that the VM interfaces have already
done the job.  There is a slight snag in that the timing of the
mark_page_accessed() has now changed so in rare cases it's possible a page
gets to the end of the LRU as PageReferenced where as previously it might
have been repromoted.  This is expected to be rare but it's worth the
filesystem people thinking about it in case they see a problem with the
timing change.  It is also the case that some filesystems may be marking
pages accessed that previously did not but it makes sense that filesystems
have consistent behaviour in this regard.

The test case used to evaulate this is a simple dd of a large file done
multiple times with the file deleted on each iterations.  The size of the
file is 1/10th physical memory to avoid dirty page balancing.  In the
async case it will be possible that the workload completes without even
hitting the disk and will have variable results but highlight the impact
of mark_page_accessed for async IO.  The sync results are expected to be
more stable.  The exception is tmpfs where the normal case is for the "IO"
to not hit the disk.

The test machine was single socket and UMA to avoid any scheduling or NUMA
artifacts.  Throughput and wall times are presented for sync IO, only wall
times are shown for async as the granularity reported by dd and the
variability is unsuitable for comparison.  As async results were variable
do to writback timings, I'm only reporting the maximum figures.  The sync
results were stable enough to make the mean and stddev uninteresting.

The performance results are reported based on a run with no profiling.
Profile data is based on a separate run with oprofile running.

async dd
                                    3.15.0-rc3            3.15.0-rc3
                                       vanilla           accessed-v2
ext3    Max      elapsed     13.9900 (  0.00%)     11.5900 ( 17.16%)
tmpfs	Max      elapsed      0.5100 (  0.00%)      0.4900 (  3.92%)
btrfs   Max      elapsed     12.8100 (  0.00%)     12.7800 (  0.23%)
ext4	Max      elapsed     18.6000 (  0.00%)     13.3400 ( 28.28%)
xfs	Max      elapsed     12.5600 (  0.00%)      2.0900 ( 83.36%)

The XFS figure is a bit strange as it managed to avoid a worst case by
sheer luck but the average figures looked reasonable.

        samples percentage
ext3       86107    0.9783  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
ext3       23833    0.2710  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
ext3        5036    0.0573  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
ext4       64566    0.8961  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
ext4        5322    0.0713  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
ext4        2869    0.0384  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
xfs        62126    1.7675  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
xfs         1904    0.0554  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
xfs          103    0.0030  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
btrfs      10655    0.1338  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
btrfs       2020    0.0273  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
btrfs        587    0.0079  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
tmpfs      59562    3.2628  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
tmpfs       1210    0.0696  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
tmpfs         94    0.0054  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed

[akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:54:10 -07:00
Jaegeuk Kim
b6fe5873cb f2fs: fix to recover data written by dio
If data are overwritten through dio, previous f2fs doesn't remain the fsync mark
due to no additional node writes.

Note that this patch should resolve the xfstests:311.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-04 18:41:38 +09:00
Chao Yu
bac4eef653 f2fs: avoid crash when trace f2fs_submit_page_mbio event in ra_sum_pages
Previously we allocate pages with no mapping in ra_sum_pages(), so we may
encounter a crash in event trace of f2fs_submit_page_mbio where we access
mapping data of the page.

We'd better allocate pages in bd_inode mapping and invalidate these pages after
we restore data from pages. It could avoid crash in above scenario.

Changes from V1
 o remove redundant code in ra_sum_pages() suggested by Jaegeuk Kim.

Call Trace:
 [<f1031630>] ? ftrace_raw_event_f2fs_write_checkpoint+0x80/0x80 [f2fs]
 [<f10377bb>] f2fs_submit_page_mbio+0x1cb/0x200 [f2fs]
 [<f103c5da>] restore_node_summary+0x13a/0x280 [f2fs]
 [<f103e22d>] build_curseg+0x2bd/0x620 [f2fs]
 [<f104043b>] build_segment_manager+0x1cb/0x920 [f2fs]
 [<f1032c85>] f2fs_fill_super+0x535/0x8e0 [f2fs]
 [<c115b66a>] mount_bdev+0x16a/0x1a0
 [<f102f63f>] f2fs_mount+0x1f/0x30 [f2fs]
 [<c115c096>] mount_fs+0x36/0x170
 [<c1173635>] vfs_kern_mount+0x55/0xe0
 [<c1175388>] do_mount+0x1e8/0x900
 [<c1175d72>] SyS_mount+0x82/0xc0
 [<c16059cc>] sysenter_do_call+0x12/0x22

Suggested-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-04 13:34:30 +09:00
Chao Yu
e574843438 f2fs: add a tracepoint for f2fs_write_{meta,node,data}_pages
This patch adds a tracepoint for f2fs_write_{meta,node,data}_pages to trace when
pages are fsyncing/flushing.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2014-05-07 10:21:59 +09:00