Revision a742994aa2e271eb8cd8e043d276515ec858ed73 authored by Filipe Manana on 13 February 2015, 16:56:14 UTC, committed by Chris Mason on 14 February 2015, 16:22:49 UTC
If we are recording in the tree log that an inode has new names (new hard links were added), we would drop items, belonging to the inode, that we shouldn't: 1) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime flags, we ended up dropping all the extent and xattr items that were previously logged. This was done only in memory, since logging a new name doesn't imply syncing the log; 2) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime flags, we ended up dropping all the xattr items that were previously logged. Like the case before, this was done only in memory because logging a new name doesn't imply syncing the log. This led to some surprises in scenarios such as the following: 1) write some extents to an inode; 2) fsync the inode; 3) truncate the inode or delete/modify some of its xattrs 4) add a new hard link for that inode 5) fsync some other file, to force the log tree to be durably persisted 6) power failure happens The next time the fs is mounted, the fsync log replay code is executed, and the resulting file doesn't have the content it had when the last fsync against it was performed, instead if has a content matching what it had when the last transaction commit happened. So change the behaviour such that when a new name is logged, only the inode item and reference items are processed. This is easy to reproduce with the test I just made for xfstests, whose main body is: _scratch_mkfs >> $seqres.full 2>&1 _init_flakey _mount_flakey # Create our test file with some data. $XFS_IO_PROG -f -c "pwrite -S 0xaa -b 8K 0 8K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Make sure the file is durably persisted. sync # Append some data to our file, to increase its size. $XFS_IO_PROG -f -c "pwrite -S 0xcc -b 4K 8K 4K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Fsync the file, so from this point on if a crash/power failure happens, our # new data is guaranteed to be there next time the fs is mounted. $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo # Now shrink our file to 5000 bytes. $XFS_IO_PROG -c "truncate 5000" $SCRATCH_MNT/foo # Now do an expanding truncate to a size larger than what we had when we last # fsync'ed our file. This is just to verify that after power failure and # replaying the fsync log, our file matches what it was when we last fsync'ed # it - 12Kb size, first 8Kb of data had a value of 0xaa and the last 4Kb of # data had a value of 0xcc. $XFS_IO_PROG -c "truncate 32K" $SCRATCH_MNT/foo # Add one hard link to our file. This made btrfs drop all of our file's # metadata from the fsync log, including the metadata relative to the # extent we just wrote and fsync'ed. This change was made only to the fsync # log in memory, so adding the hard link alone doesn't change the persisted # fsync log. This happened because the previous truncates set the runtime # flag BTRFS_INODE_NEEDS_FULL_SYNC in the btrfs inode structure. ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link # Now make sure the in memory fsync log is durably persisted. # Creating and fsync'ing another file will do it. # After this our persisted fsync log will no longer have metadata for our file # foo that points to the extent we wrote and fsync'ed before. touch $SCRATCH_MNT/bar $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/bar # As expected, before the crash/power failure, we should be able to see a file # with a size of 32Kb, with its first 5000 bytes having the value 0xaa and all # the remaining bytes with value 0x00. echo "File content before:" od -t x1 $SCRATCH_MNT/foo # Simulate a crash/power loss. _load_flakey_table $FLAKEY_DROP_WRITES _unmount_flakey _load_flakey_table $FLAKEY_ALLOW_WRITES _mount_flakey # After mounting the fs again, the fsync log was replayed. # The expected result is to see a file with a size of 12Kb, with its first 8Kb # of data having the value 0xaa and its last 4Kb of data having a value of 0xcc. # The btrfs bug used to leave the file as it used te be as of the last # transaction commit - that is, with a size of 8Kb with all bytes having a # value of 0xaa. echo "File content after:" od -t x1 $SCRATCH_MNT/foo The test case for xfstests follows soon. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
1 parent 1a4bcf4
mutex-xchg.h
/*
* include/asm-generic/mutex-xchg.h
*
* Generic implementation of the mutex fastpath, based on xchg().
*
* NOTE: An xchg based implementation might be less optimal than an atomic
* decrement/increment based implementation. If your architecture
* has a reasonable atomic dec/inc then you should probably use
* asm-generic/mutex-dec.h instead, or you could open-code an
* optimized version in asm/mutex.h.
*/
#ifndef _ASM_GENERIC_MUTEX_XCHG_H
#define _ASM_GENERIC_MUTEX_XCHG_H
/**
* __mutex_fastpath_lock - try to take the lock by moving the count
* from 1 to a 0 value
* @count: pointer of type atomic_t
* @fail_fn: function to call if the original value was not 1
*
* Change the count from 1 to a value lower than 1, and call <fail_fn> if it
* wasn't 1 originally. This function MUST leave the value lower than 1
* even when the "1" assertion wasn't true.
*/
static inline void
__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
if (unlikely(atomic_xchg(count, 0) != 1))
/*
* We failed to acquire the lock, so mark it contended
* to ensure that any waiting tasks are woken up by the
* unlock slow path.
*/
if (likely(atomic_xchg(count, -1) != 1))
fail_fn(count);
}
/**
* __mutex_fastpath_lock_retval - try to take the lock by moving the count
* from 1 to a 0 value
* @count: pointer of type atomic_t
*
* Change the count from 1 to a value lower than 1. This function returns 0
* if the fastpath succeeds, or -1 otherwise.
*/
static inline int
__mutex_fastpath_lock_retval(atomic_t *count)
{
if (unlikely(atomic_xchg(count, 0) != 1))
if (likely(atomic_xchg(count, -1) != 1))
return -1;
return 0;
}
/**
* __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
* @count: pointer of type atomic_t
* @fail_fn: function to call if the original value was not 0
*
* try to promote the mutex from 0 to 1. if it wasn't 0, call <function>
* In the failure case, this function is allowed to either set the value to
* 1, or to set it to a value lower than one.
* If the implementation sets it to a value of lower than one, the
* __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
* to return 0 otherwise.
*/
static inline void
__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
if (unlikely(atomic_xchg(count, 1) != 0))
fail_fn(count);
}
#define __mutex_slowpath_needs_to_unlock() 0
/**
* __mutex_fastpath_trylock - try to acquire the mutex, without waiting
*
* @count: pointer of type atomic_t
* @fail_fn: spinlock based trylock implementation
*
* Change the count from 1 to a value lower than 1, and return 0 (failure)
* if it wasn't 1 originally, or return 1 (success) otherwise. This function
* MUST leave the value lower than 1 even when the "1" assertion wasn't true.
* Additionally, if the value was < 0 originally, this function must not leave
* it to 0 on failure.
*
* If the architecture has no effective trylock variant, it should call the
* <fail_fn> spinlock-based trylock variant unconditionally.
*/
static inline int
__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
{
int prev = atomic_xchg(count, 0);
if (unlikely(prev < 0)) {
/*
* The lock was marked contended so we must restore that
* state. If while doing so we get back a prev value of 1
* then we just own it.
*
* [ In the rare case of the mutex going to 1, to 0, to -1
* and then back to 0 in this few-instructions window,
* this has the potential to trigger the slowpath for the
* owner's unlock path needlessly, but that's not a problem
* in practice. ]
*/
prev = atomic_xchg(count, prev);
if (prev < 0)
prev = 0;
}
return prev;
}
#endif
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...