If right after starting the snapshot creation ioctl we perform a write against a
file followed by a truncate, with both operations increasing the file's size, we
can get a snapshot tree that reflects a state of the source subvolume's tree where
the file truncation happened but the write operation didn't. This leaves a gap
between 2 file extent items of the inode, which makes btrfs' fsck complain about it.
For example, if we perform the following file operations:
$ mkfs.btrfs -f /dev/vdd
$ mount /dev/vdd /mnt
$ xfs_io -f \
-c "pwrite -S 0xaa -b 32K 0 32K" \
-c "fsync" \
-c "pwrite -S 0xbb -b 32770 16K 32770" \
-c "truncate 90123" \
/mnt/foobar
and the snapshot creation ioctl was just called before the second write, we often
can get the following inode items in the snapshot's btree:
item 120 key (257 INODE_ITEM 0) itemoff 7987 itemsize 160
inode generation 146 transid 7 size 90123 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 flags 0x0
item 121 key (257 INODE_REF 256) itemoff 7967 itemsize 20
inode ref index 282 namelen 10 name: foobar
item 122 key (257 EXTENT_DATA 0) itemoff 7914 itemsize 53
extent data disk byte 1104855040 nr 32768
extent data offset 0 nr 32768 ram 32768
extent compression 0
item 123 key (257 EXTENT_DATA 53248) itemoff 7861 itemsize 53
extent data disk byte 0 nr 0
extent data offset 0 nr 40960 ram 40960
extent compression 0
There's a file range, corresponding to the interval [32K; ALIGN(16K + 32770, 4096)[
for which there's no file extent item covering it. This is because the file write
and file truncate operations happened both right after the snapshot creation ioctl
called btrfs_start_delalloc_inodes(), which means we didn't start and wait for the
ordered extent that matches the write and, in btrfs_setsize(), we were able to call
btrfs_cont_expand() before being able to commit the current transaction in the
snapshot creation ioctl. So this made it possibe to insert the hole file extent
item in the source subvolume (which represents the region added by the truncate)
right before the transaction commit from the snapshot creation ioctl.
Btrfs' fsck tool complains about such cases with a message like the following:
"root 331 inode 257 errors 100, file extent discount"
>From a user perspective, the expectation when a snapshot is created while those
file operations are being performed is that the snapshot will have a file that
either:
1) is empty
2) only the first write was captured
3) only the 2 writes were captured
4) both writes and the truncation were captured
But never capture a state where only the first write and the truncation were
captured (since the second write was performed before the truncation).
A test case for xfstests follows.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
To avoid duplicating this double filemap_fdatawrite_range() call for
inodes with async extents (compressed writes) so often.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
For compressed writes, after doing the first filemap_fdatawrite_range() we
don't get the pages tagged for writeback immediately. Instead we create
a workqueue task, which is run by other kthread, and keep the pages locked.
That other kthread compresses data, creates the respective ordered extent/s,
tags the pages for writeback and unlocks them. Therefore we need a second
call to filemap_fdatawrite_range() if we have compressed writes, as this
second call will wait for the pages to become unlocked, then see they became
tagged for writeback and finally wait for the writeback to finish.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
There are the branch hints that obviously depend on the data being
processed, the CPU predictor will do better job according to the actual
load. It also does not make sense to use the hints in slow paths that do
a lot of other operations like locking, waiting or IO.
Signed-off-by: David Sterba <dsterba@suse.cz>
When we do a fast fsync, we start all ordered operations and then while
they're running in parallel we visit the list of modified extent maps
and construct their matching file extent items and write them to the
log btree. After that, in btrfs_sync_log() we wait for all the ordered
operations to finish (via btrfs_wait_logged_extents).
The problem with this is that we were completely ignoring errors that
can happen in the extent write path, such as -ENOSPC, a temporary -ENOMEM
or -EIO errors for example. When such error happens, it means we have parts
of the on disk extent that weren't written to, and so we end up logging
file extent items that point to these extents that contain garbage/random
data - so after a crash/reboot plus log replay, we get our inode's metadata
pointing to those extents.
This worked in contrast with the full (non-fast) fsync path, where we
start all ordered operations, wait for them to finish and then write
to the log btree. In this path, after each ordered operation completes
we check if it's flagged with an error (BTRFS_ORDERED_IOERR) and return
-EIO if so (via btrfs_wait_ordered_range).
So if an error happens with any ordered operation, just return a -EIO
error to userspace, so that it knows that not all of its previous writes
were durably persisted and the application can take proper action (like
redo the writes for e.g.) - and definitely not leave any file extent items
in the log refer to non fully written extents.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
When the fsync callback (btrfs_sync_file) starts, it first waits for
the writeback of any dirty pages to start and finish without holding
the inode's mutex (to reduce contention). After this it acquires the
inode's mutex and repeats that process via btrfs_wait_ordered_range
only if we're doing a full sync (BTRFS_INODE_NEEDS_FULL_SYNC flag
is set on the inode).
This is not safe for a non full sync - we need to start and wait for
writeback to finish for any pages that might have been made dirty
before acquiring the inode's mutex and after that first step mentioned
before. Why this is needed is explained by the following comment added
to btrfs_sync_file:
"Right before acquiring the inode's mutex, we might have new
writes dirtying pages, which won't immediately start the
respective ordered operations - that is done through the
fill_delalloc callbacks invoked from the writepage and
writepages address space operations. So make sure we start
all ordered operations before starting to log our inode. Not
doing this means that while logging the inode, writeback
could start and invoke writepage/writepages, which would call
the fill_delalloc callbacks (cow_file_range,
submit_compressed_extents). These callbacks add first an
extent map to the modified list of extents and then create
the respective ordered operation, which means in
tree-log.c:btrfs_log_inode() we might capture all existing
ordered operations (with btrfs_get_logged_extents()) before
the fill_delalloc callback adds its ordered operation, and by
the time we visit the modified list of extent maps (with
btrfs_log_changed_extents()), we see and process the extent
map they created. We then use the extent map to construct a
file extent item for logging without waiting for the
respective ordered operation to finish - this file extent
item points to a disk location that might not have yet been
written to, containing random data - so after a crash a log
replay will make our inode have file extent items that point
to disk locations containing invalid data, as we returned
success to userspace without waiting for the respective
ordered operation to finish, because it wasn't captured by
btrfs_get_logged_extents()."
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
An user reported this, it is because that lseek's SEEK_SET/SEEK_CUR/SEEK_END
allow a negative value for @offset, but btrfs's SEEK_DATA/SEEK_HOLE don't
prepare for that and convert the negative @offset into unsigned type,
so we get (end < start) warning.
[ 1269.835374] ------------[ cut here ]------------
[ 1269.836809] WARNING: CPU: 0 PID: 1241 at fs/btrfs/extent_io.c:430 insert_state+0x11d/0x140()
[ 1269.838816] BTRFS: end < start 4094 18446744073709551615
[ 1269.840334] CPU: 0 PID: 1241 Comm: a.out Tainted: G W 3.16.0+ #306
[ 1269.858229] Call Trace:
[ 1269.858612] [<ffffffff81801a69>] dump_stack+0x4e/0x68
[ 1269.858952] [<ffffffff8107894c>] warn_slowpath_common+0x8c/0xc0
[ 1269.859416] [<ffffffff81078a36>] warn_slowpath_fmt+0x46/0x50
[ 1269.859929] [<ffffffff813b0fbd>] insert_state+0x11d/0x140
[ 1269.860409] [<ffffffff813b1396>] __set_extent_bit+0x3b6/0x4e0
[ 1269.860805] [<ffffffff813b21c7>] lock_extent_bits+0x87/0x200
[ 1269.861697] [<ffffffff813a5b28>] btrfs_file_llseek+0x148/0x2a0
[ 1269.862168] [<ffffffff811f201e>] SyS_lseek+0xae/0xc0
[ 1269.862620] [<ffffffff8180b212>] system_call_fastpath+0x16/0x1b
[ 1269.862970] ---[ end trace 4d33ea885832054b ]---
This assumes that btrfs starts finding DATA/HOLE from the beginning of file
if the assigned @offset is negative.
Also we add alignment for lock_extent_bits 's range.
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
The form
(value + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT
is equivalent to
(value + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE
The rest is a simple subsitution, no difference in the generated
assembly code.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
The nodesize and leafsize were never of different values. Unify the
usage and make nodesize the one. Cleanup the redundant checks and
helpers.
Shaves a few bytes from .text:
text data bss dec hex filename
852418 24560 23112 900090 dbbfa btrfs.ko.before
851074 24584 23112 898770 db6d2 btrfs.ko.after
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
btrfs_set_key_type and btrfs_key_type are used inconsistently along with
open coded variants. Other members of btrfs_key are accessed directly
without any helpers anyway.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
While we're doing a full fsync (when the inode has the flag
BTRFS_INODE_NEEDS_FULL_SYNC set) that is ranged too (covers only a
portion of the file), we might have ordered operations that are started
before or while we're logging the inode and that fall outside the fsync
range.
Therefore when a full ranged fsync finishes don't remove every extent
map from the list of modified extent maps - as for some of them, that
fall outside our fsync range, their respective ordered operation hasn't
finished yet, meaning the corresponding file extent item wasn't inserted
into the fs/subvol tree yet and therefore we didn't log it, and we must
let the next fast fsync (one that checks only the modified list) see this
extent map and log a matching file extent item to the log btree and wait
for its ordered operation to finish (if it's still ongoing).
A test case for xfstests follows.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
We should only be flushing on close if the file was flagged as needing
it during truncate. I broke this with my ordered data vs transaction
commit deadlock fix.
Thanks to Miao Xie for catching this.
Signed-off-by: Chris Mason <clm@fb.com>
Reported-by: Miao Xie <miaox@cn.fujitsu.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
When current btrfs finds that a new extent map is going to be insereted
but failed with -EEXIST, it will try again to insert the extent map
but with the length of sectorsize.
This is OK if we don't enable 'no-holes' feature since all extent space
is continuous, we will not go into the not found->insert routine.
But if we enable 'no-holes' feature, it will make things out of control.
e.g. in 4K sectorsize, we pass the following args to btrfs_get_extent():
btrfs_get_extent() args: start: 27874 len 4100
28672 27874 28672 27874+4100 32768
|-----------------------|
|---------hole--------------------|---------data----------|
1) not found and insert
Since no extent map containing the range, btrfs_get_extent() will go
into the not_found and insert routine, which will try to insert the
extent map (27874, 27847 + 4100).
2) first overlap
But it overlaps with (28672, 32768) extent, so -EEXIST will be returned
by add_extent_mapping().
3) retry but still overlap
After catching the -EEXIST, then btrfs_get_extent() will try insert it
again but with 4K length, which still overlaps, so -EEXIST will be
returned.
This makes the following patch fail to punch hole.
d77815461f btrfs: Avoid trucating page or punching hole in a already existed hole.
This patch will use the right length, which is the (exsisting->start -
em->start) to insert, making the above patch works in 'no-holes' mode.
Also, some small code style problems in above patch is fixed too.
Reported-by: Filipe David Manana <fdmanana@gmail.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Filipe David Manana <fdmanana@suse.com>
Tested-by: Filipe David Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
For a non-existent key, btrfs_search_slot() sets path->slots[0] to the slot
where the key could have been present, which in this case would be the slot
containing the extent item which would be the next neighbor of the file range
being punched. The current code passes an incremented path->slots[0] and we
skip to the wrong file extent item. This would mean that we would fail to
merge the "yet to be created" hole with the next neighboring hole (if one
exists). Fix this.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Reviewed-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Truncates and renames are often used to replace old versions of a file
with new versions. Applications often expect this to be an atomic
replacement, even if they haven't done anything to make sure the new
version is fully on disk.
Btrfs has strict flushing in place to make sure that renaming over an
old file with a new file will fully flush out the new file before
allowing the transaction commit with the rename to complete.
This ordering means the commit code needs to be able to lock file pages,
and there are a few paths in the filesystem where we will try to end a
transaction with the page lock held. It's rare, but these things can
deadlock.
This patch removes the ordered flushes and switches to a best effort
filemap_flush like ext4 uses. It's not perfect, but it should fix the
deadlocks.
Signed-off-by: Chris Mason <clm@fb.com>
Pull vfs updates from Al Viro:
"This the bunch that sat in -next + lock_parent() fix. This is the
minimal set; there's more pending stuff.
In particular, I really hope to get acct.c fixes merged this cycle -
we need that to deal sanely with delayed-mntput stuff. In the next
pile, hopefully - that series is fairly short and localized
(kernel/acct.c, fs/super.c and fs/namespace.c). In this pile: more
iov_iter work. Most of prereqs for ->splice_write with sane locking
order are there and Kent's dio rewrite would also fit nicely on top of
this pile"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (70 commits)
lock_parent: don't step on stale ->d_parent of all-but-freed one
kill generic_file_splice_write()
ceph: switch to iter_file_splice_write()
shmem: switch to iter_file_splice_write()
nfs: switch to iter_splice_write_file()
fs/splice.c: remove unneeded exports
ocfs2: switch to iter_file_splice_write()
->splice_write() via ->write_iter()
bio_vec-backed iov_iter
optimize copy_page_{to,from}_iter()
bury generic_file_aio_{read,write}
lustre: get rid of messing with iovecs
ceph: switch to ->write_iter()
ceph_sync_direct_write: stop poking into iov_iter guts
ceph_sync_read: stop poking into iov_iter guts
new helper: copy_page_from_iter()
fuse: switch to ->write_iter()
btrfs: switch to ->write_iter()
ocfs2: switch to ->write_iter()
xfs: switch to ->write_iter()
...
Pull btrfs updates from Chris Mason:
"The biggest change here is Josef's rework of the btrfs quota
accounting, which improves the in-memory tracking of delayed extent
operations.
I had been working on Btrfs stack usage for a while, mostly because it
had become impossible to do long stress runs with slab, lockdep and
pagealloc debugging turned on without blowing the stack. Even though
you upgraded us to a nice king sized stack, I kept most of the
patches.
We also have some very hard to find corruption fixes, an awesome sysfs
use after free, and the usual assortment of optimizations, cleanups
and other fixes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (80 commits)
Btrfs: convert smp_mb__{before,after}_clear_bit
Btrfs: fix scrub_print_warning to handle skinny metadata extents
Btrfs: make fsync work after cloning into a file
Btrfs: use right type to get real comparison
Btrfs: don't check nodes for extent items
Btrfs: don't release invalid page in btrfs_page_exists_in_range()
Btrfs: make sure we retry if page is a retriable exception
Btrfs: make sure we retry if we couldn't get the page
btrfs: replace EINVAL with EOPNOTSUPP for dev_replace raid56
trivial: fs/btrfs/ioctl.c: fix typo s/substract/subtract/
Btrfs: fix leaf corruption after __btrfs_drop_extents
Btrfs: ensure btrfs_prev_leaf doesn't miss 1 item
Btrfs: fix clone to deal with holes when NO_HOLES feature is enabled
btrfs: free delayed node outside of root->inode_lock
btrfs: replace EINVAL with ERANGE for resize when ULLONG_MAX
Btrfs: fix transaction leak during fsync call
btrfs: Avoid trucating page or punching hole in a already existed hole.
Btrfs: update commit root on snapshot creation after orphan cleanup
Btrfs: ioctl, don't re-lock extent range when not necessary
Btrfs: avoid visiting all extent items when cloning a range
...
If btrfs_log_dentry_safe() returns an error, we set ret to 1 and
fall through with the goal of committing the transaction. However,
in the case where the inode doesn't need a full sync, we would call
btrfs_wait_ordered_range() against the target range for our inode,
and if it returned an error, we would return without commiting or
ending the transaction.
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
btrfs_punch_hole() will truncate unaligned pages or punch hole on a
already existed hole.
This will cause unneeded zero page or holes splitting the original huge
hole.
This patch will skip already existed holes before any page truncating or
hole punching.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
In these instances, we are trying to determine if a page has been accessed
since we began the operation for the sake of retry. This is easily
accomplished by doing a gang lookup in the page mapping radix tree, and it
saves us the dependency on the flag (so that we might eventually delete
it).
btrfs_page_exists_in_range borrows heavily from find_get_page, replacing
the radix tree look up with a gang lookup of 1, so that we can find the
next highest page >= index and see if it falls into our lock range.
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Alex Gartrell <agartrell@fb.com>
Currently qgroups account for space by intercepting delayed ref updates to fs
trees. It does this by adding sequence numbers to delayed ref updates so that
it can figure out how the tree looked before the update so we can adjust the
counters properly. The problem with this is that it does not allow delayed refs
to be merged, so if you say are defragging an extent with 5k snapshots pointing
to it we will thrash the delayed ref lock because we need to go back and
manually merge these things together. Instead we want to process quota changes
when we know they are going to happen, like when we first allocate an extent, we
free a reference for an extent, we add new references etc. This patch
accomplishes this by only adding qgroup operations for real ref changes. We
only modify the sequence number when we need to lookup roots for bytenrs, this
reduces the amount of churn on the sequence number and allows us to merge
delayed refs as we add them most of the time. This patch encompasses a bunch of
architectural changes
1) qgroup ref operations: instead of tracking qgroup operations through the
delayed refs we simply add new ref operations whenever we notice that we need to
when we've modified the refs themselves.
2) tree mod seq: we no longer have this separation of major/minor counters.
this makes the sequence number stuff much more sane and we can remove some
locking that was needed to protect the counter.
3) delayed ref seq: we now read the tree mod seq number and use that as our
sequence. This means each new delayed ref doesn't have it's own unique sequence
number, rather whenever we go to lookup backrefs we inc the sequence number so
we can make sure to keep any new operations from screwing up our world view at
that given point. This allows us to merge delayed refs during runtime.
With all of these changes the delayed ref stuff is a little saner and the qgroup
accounting stuff no longer goes negative in some cases like it was before.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
While running a stress test with multiple threads writing to the same btrfs
file system, I ended up with a situation where a leaf was corrupted in that
it had 2 file extent item keys that had the same exact key. I was able to
detect this quickly thanks to the following patch which triggers an assertion
as soon as a leaf is marked dirty if there are duplicated keys or out of order
keys:
Btrfs: check if items are ordered when a leaf is marked dirty
(https://patchwork.kernel.org/patch/3955431/)
Basically while running the test, I got the following in dmesg:
[28877.415877] WARNING: CPU: 2 PID: 10706 at fs/btrfs/file.c:553 btrfs_drop_extent_cache+0x435/0x440 [btrfs]()
(...)
[28877.415917] Call Trace:
[28877.415922] [<ffffffff816f1189>] dump_stack+0x4e/0x68
[28877.415926] [<ffffffff8104a32c>] warn_slowpath_common+0x8c/0xc0
[28877.415929] [<ffffffff8104a37a>] warn_slowpath_null+0x1a/0x20
[28877.415944] [<ffffffffa03775a5>] btrfs_drop_extent_cache+0x435/0x440 [btrfs]
[28877.415949] [<ffffffff8118e7be>] ? kmem_cache_alloc+0xfe/0x1c0
[28877.415962] [<ffffffffa03777d9>] fill_holes+0x229/0x3e0 [btrfs]
[28877.415972] [<ffffffffa0345865>] ? block_rsv_add_bytes+0x55/0x80 [btrfs]
[28877.415984] [<ffffffffa03792cb>] btrfs_fallocate+0xb6b/0xc20 [btrfs]
(...)
[29854.132560] BTRFS critical (device sdc): corrupt leaf, bad key order: block=955232256,root=1, slot=24
[29854.132565] BTRFS info (device sdc): leaf 955232256 total ptrs 40 free space 778
(...)
[29854.132637] item 23 key (3486 108 667648) itemoff 2694 itemsize 53
[29854.132638] extent data disk bytenr 14574411776 nr 286720
[29854.132639] extent data offset 0 nr 286720 ram 286720
[29854.132640] item 24 key (3486 108 954368) itemoff 2641 itemsize 53
[29854.132641] extent data disk bytenr 0 nr 0
[29854.132643] extent data offset 0 nr 0 ram 0
[29854.132644] item 25 key (3486 108 954368) itemoff 2588 itemsize 53
[29854.132645] extent data disk bytenr 8699670528 nr 77824
[29854.132646] extent data offset 0 nr 77824 ram 77824
[29854.132647] item 26 key (3486 108 1146880) itemoff 2535 itemsize 53
[29854.132648] extent data disk bytenr 8699670528 nr 77824
[29854.132649] extent data offset 0 nr 77824 ram 77824
(...)
[29854.132707] kernel BUG at fs/btrfs/ctree.h:3901!
(...)
[29854.132771] Call Trace:
[29854.132779] [<ffffffffa0342b5c>] setup_items_for_insert+0x2dc/0x400 [btrfs]
[29854.132791] [<ffffffffa0378537>] __btrfs_drop_extents+0xba7/0xdd0 [btrfs]
[29854.132794] [<ffffffff8109c0d6>] ? trace_hardirqs_on_caller+0x16/0x1d0
[29854.132797] [<ffffffff8109c29d>] ? trace_hardirqs_on+0xd/0x10
[29854.132800] [<ffffffff8118e7be>] ? kmem_cache_alloc+0xfe/0x1c0
[29854.132810] [<ffffffffa036783b>] insert_reserved_file_extent.constprop.66+0xab/0x310 [btrfs]
[29854.132820] [<ffffffffa036a6c6>] __btrfs_prealloc_file_range+0x116/0x340 [btrfs]
[29854.132830] [<ffffffffa0374d53>] btrfs_prealloc_file_range+0x23/0x30 [btrfs]
(...)
So this is caused by getting an -ENOSPC error while punching a file hole, more
specifically, we get -ENOSPC error from __btrfs_drop_extents in the while loop
of file.c:btrfs_punch_hole() when it's unable to modify the btree to delete one
or more file extent items due to lack of enough free space. When this happens,
in btrfs_punch_hole(), we attempt to reclaim free space by switching our transaction
block reservation object to root->fs_info->trans_block_rsv, end our transaction and
start a new transaction basically - and, we keep increasing our current offset
(cur_offset) as long as it's smaller than the end of the target range (lockend) -
this makes use leave the loop with cur_offset == drop_end which in turn makes us
call fill_holes() for inserting a file extent item that represents a 0 bytes range
hole (and this insertion succeeds, as in the meanwhile more space became available).
This 0 bytes file hole extent item is a problem because any subsequent caller of
__btrfs_drop_extents (regular file writes, or fallocate calls for e.g.), with a
start file offset that is equal to the offset of the hole, will not remove this
extent item due to the following conditional in the while loop of
__btrfs_drop_extents:
if (extent_end <= search_start) {
path->slots[0]++;
goto next_slot;
}
This later makes the call to setup_items_for_insert() (at the very end of
__btrfs_drop_extents), insert a new file extent item with the same offset as
the 0 bytes file hole extent item that follows it. Needless is to say that this
causes chaos, either when reading the leaf from disk (btree_readpage_end_io_hook),
where we perform leaf sanity checks or in subsequent operations that manipulate
file extent items, as in the fallocate call as shown by the dmesg trace above.
Without my other patch to perform the leaf sanity checks once a leaf is marked
as dirty (if the integrity checker is enabled), it would have been much harder
to debug this issue.
This change might fix a few similar issues reported by users in the mailing
list regarding assertion failures in btrfs_set_item_key_safe calls performed
by __btrfs_drop_extents, such as the following report:
http://comments.gmane.org/gmane.comp.file-systems.btrfs/32938
Asking fill_holes() to create a 0 bytes wide file hole item also produced the
first warning in the trace above, as we passed a range to btrfs_drop_extent_cache
that has an end smaller (by -1) than its start.
On 3.14 kernels this issue manifests itself through leaf corruption, as we get
duplicated file extent item keys in a leaf when calling setup_items_for_insert(),
but on older kernels, setup_items_for_insert() isn't called by __btrfs_drop_extents(),
instead we have callers of __btrfs_drop_extents(), namely the functions
inode.c:insert_inline_extent() and inode.c:insert_reserved_file_extent(), calling
btrfs_insert_empty_item() to insert the new file extent item, which would fail with
error -EEXIST, instead of inserting a duplicated key - which is still a serious
issue as it would make all similar file extent item replace operations keep
failing if they target the same file range.
Cc: stable@vger.kernel.org
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
In a previous change, commit 12870f1c9b,
I accidentally moved the roundup of inode->i_size to outside of the
critical section delimited by the inode mutex, which is not atomic and
not correct since the size can be changed by other task before we acquire
the mutex. Therefore fix it.
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
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>
Now It Can Be Done(tm) - we don't need to do iov_shorten() in
generic_file_direct_write() anymore, now that all ->direct_IO()
instances are converted to proper iov_iter methods and honour
iter->count and iter->iov_offset properly.
Get rid of count/ocount arguments of generic_file_direct_write(),
while we are at it.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
For now, just use the same thing we pass to ->direct_IO() - it's all
iovec-based at the moment. Pass it explicitly to iov_iter_init() and
account for kvec vs. iovec in there, by the same kludge NFS ->direct_IO()
uses.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
all callers of ->aio_read() and ->aio_write() have iov/nr_segs already
checked - generic_segment_checks() done after that is just an odd way
to spell iov_length().
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull btrfs fixes from Chris Mason.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: limit the path size in send to PATH_MAX
Btrfs: correctly set profile flags on seqlock retry
Btrfs: use correct key when repeating search for extent item
Btrfs: fix inode caching vs tree log
Btrfs: fix possible memory leaks in open_ctree()
Btrfs: avoid triggering bug_on() when we fail to start inode caching task
Btrfs: move btrfs_{set,clear}_and_info() to ctree.h
btrfs: replace error code from btrfs_drop_extents
btrfs: Change the hole range to a more accurate value.
btrfs: fix use-after-free in mount_subvol()
There's a case which clone does not handle and used to BUG_ON instead,
(testcase xfstests/btrfs/035), now returns EINVAL. This error code is
confusing to the ioctl caller, as it normally signifies errorneous
arguments.
Change it to ENOPNOTSUPP which allows a fall back to copy instead of
clone. This does not affect the common reflink operation.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Commit 3ac0d7b96a fixed the btrfs expanding
write problem but the hole punched is sometimes too large for some
iovec, which has unmapped data ranges.
This patch will change to hole range to a more accurate value using the
counts checked by the write check routines.
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Pull vfs updates from Al Viro:
"The first vfs pile, with deep apologies for being very late in this
window.
Assorted cleanups and fixes, plus a large preparatory part of iov_iter
work. There's a lot more of that, but it'll probably go into the next
merge window - it *does* shape up nicely, removes a lot of
boilerplate, gets rid of locking inconsistencie between aio_write and
splice_write and I hope to get Kent's direct-io rewrite merged into
the same queue, but some of the stuff after this point is having
(mostly trivial) conflicts with the things already merged into
mainline and with some I want more testing.
This one passes LTP and xfstests without regressions, in addition to
usual beating. BTW, readahead02 in ltp syscalls testsuite has started
giving failures since "mm/readahead.c: fix readahead failure for
memoryless NUMA nodes and limit readahead pages" - might be a false
positive, might be a real regression..."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
missing bits of "splice: fix racy pipe->buffers uses"
cifs: fix the race in cifs_writev()
ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
kill generic_file_buffered_write()
ocfs2_file_aio_write(): switch to generic_perform_write()
ceph_aio_write(): switch to generic_perform_write()
xfs_file_buffered_aio_write(): switch to generic_perform_write()
export generic_perform_write(), start getting rid of generic_file_buffer_write()
generic_file_direct_write(): get rid of ppos argument
btrfs_file_aio_write(): get rid of ppos
kill the 5th argument of generic_file_buffered_write()
kill the 4th argument of __generic_file_aio_write()
lustre: don't open-code kernel_recvmsg()
ocfs2: don't open-code kernel_recvmsg()
drbd: don't open-code kernel_recvmsg()
constify blk_rq_map_user_iov() and friends
lustre: switch to kernel_sendmsg()
ocfs2: don't open-code kernel_sendmsg()
take iov_iter stuff to mm/iov_iter.c
process_vm_access: tidy up a bit
...
Pull second set of btrfs updates from Chris Mason:
"The most important changes here are from Josef, fixing a btrfs
regression in 3.14 that can cause corruptions in the extent allocation
tree when snapshots are in use.
Josef also fixed some deadlocks in send/recv and other assorted races
when balance is running"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (23 commits)
Btrfs: fix compile warnings on on avr32 platform
btrfs: allow mounting btrfs subvolumes with different ro/rw options
btrfs: export global block reserve size as space_info
btrfs: fix crash in remount(thread_pool=) case
Btrfs: abort the transaction when we don't find our extent ref
Btrfs: fix EINVAL checks in btrfs_clone
Btrfs: fix unlock in __start_delalloc_inodes()
Btrfs: scrub raid56 stripes in the right way
Btrfs: don't compress for a small write
Btrfs: more efficient io tree navigation on wait_extent_bit
Btrfs: send, build path string only once in send_hole
btrfs: filter invalid arg for btrfs resize
Btrfs: send, fix data corruption due to incorrect hole detection
Btrfs: kmalloc() doesn't return an ERR_PTR
Btrfs: fix snapshot vs nocow writting
btrfs: Change the expanding write sequence to fix snapshot related bug.
btrfs: make device scan less noisy
btrfs: fix lockdep warning with reclaim lock inversion
Btrfs: hold the commit_root_sem when getting the commit root during send
Btrfs: remove transaction from send
...
filemap_map_pages() is generic implementation of ->map_pages() for
filesystems who uses page cache.
It should be safe to use filemap_map_pages() for ->map_pages() if
filesystem use filemap_fault() for ->fault().
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ning Qu <quning@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When testing fsstress with snapshot making background, some snapshot
following problem.
Snapshot 270:
inode 323: size 0
Snapshot 271:
inode 323: size 349145
|-------Hole---|---------Empty gap-------|-------Hole-----|
0 122880 172032 349145
Snapshot 272:
inode 323: size 349145
|-------Hole---|------------Data---------|-------Hole-----|
0 122880 172032 349145
The fsstress operation on inode 323 is the following:
write: offset 126832 len 43124
truncate: size 349145
Since the write with offset is consist of 2 operations:
1. punch hole
2. write data
Hole punching is faster than data write, so hole punching in write
and truncate is done first and then buffered write, so the snapshot 271 got
empty gap, which will not pass btrfsck.
To fix the bug, this patch will change the write sequence which will
first punch a hole covering the write end if a hole is needed.
Reported-by: Gui Hecheng <guihc.fnst@cn.fujitsu.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Pull btrfs changes from Chris Mason:
"This is a pretty long stream of bug fixes and performance fixes.
Qu Wenruo has replaced the btrfs async threads with regular kernel
workqueues. We'll keep an eye out for performance differences, but
it's nice to be using more generic code for this.
We still have some corruption fixes and other patches coming in for
the merge window, but this batch is tested and ready to go"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (108 commits)
Btrfs: fix a crash of clone with inline extents's split
btrfs: fix uninit variable warning
Btrfs: take into account total references when doing backref lookup
Btrfs: part 2, fix incremental send's decision to delay a dir move/rename
Btrfs: fix incremental send's decision to delay a dir move/rename
Btrfs: remove unnecessary inode generation lookup in send
Btrfs: fix race when updating existing ref head
btrfs: Add trace for btrfs_workqueue alloc/destroy
Btrfs: less fs tree lock contention when using autodefrag
Btrfs: return EPERM when deleting a default subvolume
Btrfs: add missing kfree in btrfs_destroy_workqueue
Btrfs: cache extent states in defrag code path
Btrfs: fix deadlock with nested trans handles
Btrfs: fix possible empty list access when flushing the delalloc inodes
Btrfs: split the global ordered extents mutex
Btrfs: don't flush all delalloc inodes when we doesn't get s_umount lock
Btrfs: reclaim delalloc metadata more aggressively
Btrfs: remove unnecessary lock in may_commit_transaction()
Btrfs: remove the unnecessary flush when preparing the pages
Btrfs: just do dirty page flush for the inode with compression before direct IO
...
We know that "ret > 0" is true here. These tests were left over from
commit 02afc27fae ('direct-io: Handle O_(D)SYNC AIO') and aren't
needed any more.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
xfstests's btrfs/035 triggers a BUG_ON, which we use to detect the split
of inline extents in __btrfs_drop_extents().
For inline extents, we cannot duplicate another EXTENT_DATA item, because
it breaks the rule of inline extents, that is, 'start offset' needs to be 0.
We have set limitations for the source inode's compressed inline extents,
because it needs to decompress and recompress. Now the destination inode's
inline extents also need similar limitations.
With this, xfstests btrfs/035 doesn't run into panic.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
If the snapshot creation happened after the nocow write but before the dirty
data flush, we would fail to flush the dirty data because of no space.
So we must keep track of when those nocow write operations start and when they
end, if there are nocow writers, the snapshot creators must wait. In order
to implement this function, I introduce btrfs_{start, end}_nocow_write(),
which is similar to mnt_{want,drop}_write().
These two functions are only used for nocow file write operations.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
We can not release the reserved metadata space for the first write if we
find the write position is pre-allocated. Because the kernel might write
the data on the disk before we do the second write but after the can-nocow
check, if we release the space for the first write, we might fail to update
the metadata because of no space.
Fix this problem by end nocow write if there is dirty data in the range whose
space is pre-allocated.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
The write range may not be sector-aligned, for example:
|--------|--------| <- write range, sector-unaligned, size: 2blocks
|--------|--------|--------| <- correct lock range, size: 3blocks
But according to the old code, we used the size of write range to calculate
the lock range directly, not considered the offset, we would get a wrong lock
range:
|--------|--------| <- write range, sector-unaligned, size: 2blocks
|--------|--------| <- wrong lock range, size: 2blocks
And besides that, the old code also had the same problem when calculating
the real write size. Correct them.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
While droping extent map structures from the extent cache that cover our
target range, we would remove each extent map structure from the red black
tree and then add either 1 or 2 new extent map structures if the former
extent map covered sections outside our target range.
This change simply attempts to replace the existing extent map structure
with a new one that covers the subsection we're not interested in, instead
of doing a red black remove operation followed by an insertion operation.
The number of elements in an inode's extent map tree can get very high for large
files under random writes. For example, while running the following test:
sysbench --test=fileio --file-num=1 --file-total-size=10G \
--file-test-mode=rndrw --num-threads=32 --file-block-size=32768 \
--max-requests=500000 --file-rw-ratio=2 [prepare|run]
I captured the following histogram capturing the number of extent_map items
in the red black tree while that test was running:
Count: 122462
Range: 1.000 - 172231.000; Mean: 96415.831; Median: 101855.000; Stddev: 49700.981
Percentiles: 90th: 160120.000; 95th: 166335.000; 99th: 171070.000
1.000 - 5.231: 452 |
5.231 - 187.392: 87 |
187.392 - 585.911: 206 |
585.911 - 1827.438: 623 |
1827.438 - 5695.245: 1962 #
5695.245 - 17744.861: 6204 ####
17744.861 - 55283.764: 21115 ############
55283.764 - 172231.000: 91813 #####################################################
Benchmark:
sysbench --test=fileio --file-num=1 --file-total-size=10G --file-test-mode=rndwr \
--num-threads=64 --file-block-size=32768 --max-requests=0 --max-time=60 \
--file-io-mode=sync --file-fsync-freq=0 [prepare|run]
Before this change: 122.1Mb/sec
After this change: 125.07Mb/sec
(averages of 5 test runs)
Test machine: quad core intel i5-3570K, 32Gb of ram, SSD
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Filipe Manana