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
div64.c
/*
* Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
*
* Based on former do_div() implementation from asm-parisc/div64.h:
* Copyright (C) 1999 Hewlett-Packard Co
* Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
*
*
* Generic C version of 64bit/32bit division and modulo, with
* 64bit result and 32bit remainder.
*
* The fast case for (n>>32 == 0) is handled inline by do_div().
*
* Code generated for this function might be very inefficient
* for some CPUs. __div64_32() can be overridden by linking arch-specific
* assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
*/
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/math64.h>
/* Not needed on 64bit architectures */
#if BITS_PER_LONG == 32
uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
{
uint64_t rem = *n;
uint64_t b = base;
uint64_t res, d = 1;
uint32_t high = rem >> 32;
/* Reduce the thing a bit first */
res = 0;
if (high >= base) {
high /= base;
res = (uint64_t) high << 32;
rem -= (uint64_t) (high*base) << 32;
}
while ((int64_t)b > 0 && b < rem) {
b = b+b;
d = d+d;
}
do {
if (rem >= b) {
rem -= b;
res += d;
}
b >>= 1;
d >>= 1;
} while (d);
*n = res;
return rem;
}
EXPORT_SYMBOL(__div64_32);
#ifndef div_s64_rem
s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
{
u64 quotient;
if (dividend < 0) {
quotient = div_u64_rem(-dividend, abs(divisor), (u32 *)remainder);
*remainder = -*remainder;
if (divisor > 0)
quotient = -quotient;
} else {
quotient = div_u64_rem(dividend, abs(divisor), (u32 *)remainder);
if (divisor < 0)
quotient = -quotient;
}
return quotient;
}
EXPORT_SYMBOL(div_s64_rem);
#endif
/**
* div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
* @dividend: 64bit dividend
* @divisor: 64bit divisor
* @remainder: 64bit remainder
*
* This implementation is a comparable to algorithm used by div64_u64.
* But this operation, which includes math for calculating the remainder,
* is kept distinct to avoid slowing down the div64_u64 operation on 32bit
* systems.
*/
#ifndef div64_u64_rem
u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
{
u32 high = divisor >> 32;
u64 quot;
if (high == 0) {
u32 rem32;
quot = div_u64_rem(dividend, divisor, &rem32);
*remainder = rem32;
} else {
int n = 1 + fls(high);
quot = div_u64(dividend >> n, divisor >> n);
if (quot != 0)
quot--;
*remainder = dividend - quot * divisor;
if (*remainder >= divisor) {
quot++;
*remainder -= divisor;
}
}
return quot;
}
EXPORT_SYMBOL(div64_u64_rem);
#endif
/**
* div64_u64 - unsigned 64bit divide with 64bit divisor
* @dividend: 64bit dividend
* @divisor: 64bit divisor
*
* This implementation is a modified version of the algorithm proposed
* by the book 'Hacker's Delight'. The original source and full proof
* can be found here and is available for use without restriction.
*
* 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c.txt'
*/
#ifndef div64_u64
u64 div64_u64(u64 dividend, u64 divisor)
{
u32 high = divisor >> 32;
u64 quot;
if (high == 0) {
quot = div_u64(dividend, divisor);
} else {
int n = 1 + fls(high);
quot = div_u64(dividend >> n, divisor >> n);
if (quot != 0)
quot--;
if ((dividend - quot * divisor) >= divisor)
quot++;
}
return quot;
}
EXPORT_SYMBOL(div64_u64);
#endif
/**
* div64_s64 - signed 64bit divide with 64bit divisor
* @dividend: 64bit dividend
* @divisor: 64bit divisor
*/
#ifndef div64_s64
s64 div64_s64(s64 dividend, s64 divisor)
{
s64 quot, t;
quot = div64_u64(abs64(dividend), abs64(divisor));
t = (dividend ^ divisor) >> 63;
return (quot ^ t) - t;
}
EXPORT_SYMBOL(div64_s64);
#endif
#endif /* BITS_PER_LONG == 32 */
/*
* Iterative div/mod for use when dividend is not expected to be much
* bigger than divisor.
*/
u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
{
return __iter_div_u64_rem(dividend, divisor, remainder);
}
EXPORT_SYMBOL(iter_div_u64_rem);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...