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
cmpxchg.h
/*
* Generic UP xchg and cmpxchg using interrupt disablement. Does not
* support SMP.
*/
#ifndef __ASM_GENERIC_CMPXCHG_H
#define __ASM_GENERIC_CMPXCHG_H
#ifdef CONFIG_SMP
#error "Cannot use generic cmpxchg on SMP"
#endif
#include <linux/types.h>
#include <linux/irqflags.h>
#ifndef xchg
/*
* This function doesn't exist, so you'll get a linker error if
* something tries to do an invalidly-sized xchg().
*/
extern void __xchg_called_with_bad_pointer(void);
static inline
unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
{
unsigned long ret, flags;
switch (size) {
case 1:
#ifdef __xchg_u8
return __xchg_u8(x, ptr);
#else
local_irq_save(flags);
ret = *(volatile u8 *)ptr;
*(volatile u8 *)ptr = x;
local_irq_restore(flags);
return ret;
#endif /* __xchg_u8 */
case 2:
#ifdef __xchg_u16
return __xchg_u16(x, ptr);
#else
local_irq_save(flags);
ret = *(volatile u16 *)ptr;
*(volatile u16 *)ptr = x;
local_irq_restore(flags);
return ret;
#endif /* __xchg_u16 */
case 4:
#ifdef __xchg_u32
return __xchg_u32(x, ptr);
#else
local_irq_save(flags);
ret = *(volatile u32 *)ptr;
*(volatile u32 *)ptr = x;
local_irq_restore(flags);
return ret;
#endif /* __xchg_u32 */
#ifdef CONFIG_64BIT
case 8:
#ifdef __xchg_u64
return __xchg_u64(x, ptr);
#else
local_irq_save(flags);
ret = *(volatile u64 *)ptr;
*(volatile u64 *)ptr = x;
local_irq_restore(flags);
return ret;
#endif /* __xchg_u64 */
#endif /* CONFIG_64BIT */
default:
__xchg_called_with_bad_pointer();
return x;
}
}
#define xchg(ptr, x) \
((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
#endif /* xchg */
/*
* Atomic compare and exchange.
*
* Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
* a cmpxchg primitive faster than repeated local irq save/restore exists.
*/
#include <asm-generic/cmpxchg-local.h>
#ifndef cmpxchg_local
#define cmpxchg_local(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
(unsigned long)(n), sizeof(*(ptr))))
#endif
#ifndef cmpxchg64_local
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
#endif
#define cmpxchg(ptr, o, n) cmpxchg_local((ptr), (o), (n))
#define cmpxchg64(ptr, o, n) cmpxchg64_local((ptr), (o), (n))
#endif /* __ASM_GENERIC_CMPXCHG_H */
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...