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
debug.c
/*
* mm/debug.c
*
* mm/ specific debug routines.
*
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
static const struct trace_print_flags pageflag_names[] = {
{1UL << PG_locked, "locked" },
{1UL << PG_error, "error" },
{1UL << PG_referenced, "referenced" },
{1UL << PG_uptodate, "uptodate" },
{1UL << PG_dirty, "dirty" },
{1UL << PG_lru, "lru" },
{1UL << PG_active, "active" },
{1UL << PG_slab, "slab" },
{1UL << PG_owner_priv_1, "owner_priv_1" },
{1UL << PG_arch_1, "arch_1" },
{1UL << PG_reserved, "reserved" },
{1UL << PG_private, "private" },
{1UL << PG_private_2, "private_2" },
{1UL << PG_writeback, "writeback" },
#ifdef CONFIG_PAGEFLAGS_EXTENDED
{1UL << PG_head, "head" },
{1UL << PG_tail, "tail" },
#else
{1UL << PG_compound, "compound" },
#endif
{1UL << PG_swapcache, "swapcache" },
{1UL << PG_mappedtodisk, "mappedtodisk" },
{1UL << PG_reclaim, "reclaim" },
{1UL << PG_swapbacked, "swapbacked" },
{1UL << PG_unevictable, "unevictable" },
#ifdef CONFIG_MMU
{1UL << PG_mlocked, "mlocked" },
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
{1UL << PG_uncached, "uncached" },
#endif
#ifdef CONFIG_MEMORY_FAILURE
{1UL << PG_hwpoison, "hwpoison" },
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
{1UL << PG_compound_lock, "compound_lock" },
#endif
};
static void dump_flags(unsigned long flags,
const struct trace_print_flags *names, int count)
{
const char *delim = "";
unsigned long mask;
int i;
pr_emerg("flags: %#lx(", flags);
/* remove zone id */
flags &= (1UL << NR_PAGEFLAGS) - 1;
for (i = 0; i < count && flags; i++) {
mask = names[i].mask;
if ((flags & mask) != mask)
continue;
flags &= ~mask;
pr_cont("%s%s", delim, names[i].name);
delim = "|";
}
/* check for left over flags */
if (flags)
pr_cont("%s%#lx", delim, flags);
pr_cont(")\n");
}
void dump_page_badflags(struct page *page, const char *reason,
unsigned long badflags)
{
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
if (reason)
pr_alert("page dumped because: %s\n", reason);
if (page->flags & badflags) {
pr_alert("bad because of flags:\n");
dump_flags(page->flags & badflags,
pageflag_names, ARRAY_SIZE(pageflag_names));
}
#ifdef CONFIG_MEMCG
if (page->mem_cgroup)
pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
#endif
}
void dump_page(struct page *page, const char *reason)
{
dump_page_badflags(page, reason, 0);
}
EXPORT_SYMBOL(dump_page);
#ifdef CONFIG_DEBUG_VM
static const struct trace_print_flags vmaflags_names[] = {
{VM_READ, "read" },
{VM_WRITE, "write" },
{VM_EXEC, "exec" },
{VM_SHARED, "shared" },
{VM_MAYREAD, "mayread" },
{VM_MAYWRITE, "maywrite" },
{VM_MAYEXEC, "mayexec" },
{VM_MAYSHARE, "mayshare" },
{VM_GROWSDOWN, "growsdown" },
{VM_PFNMAP, "pfnmap" },
{VM_DENYWRITE, "denywrite" },
{VM_LOCKED, "locked" },
{VM_IO, "io" },
{VM_SEQ_READ, "seqread" },
{VM_RAND_READ, "randread" },
{VM_DONTCOPY, "dontcopy" },
{VM_DONTEXPAND, "dontexpand" },
{VM_ACCOUNT, "account" },
{VM_NORESERVE, "noreserve" },
{VM_HUGETLB, "hugetlb" },
{VM_NONLINEAR, "nonlinear" },
#if defined(CONFIG_X86)
{VM_PAT, "pat" },
#elif defined(CONFIG_PPC)
{VM_SAO, "sao" },
#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
{VM_GROWSUP, "growsup" },
#elif !defined(CONFIG_MMU)
{VM_MAPPED_COPY, "mappedcopy" },
#else
{VM_ARCH_1, "arch_1" },
#endif
{VM_DONTDUMP, "dontdump" },
#ifdef CONFIG_MEM_SOFT_DIRTY
{VM_SOFTDIRTY, "softdirty" },
#endif
{VM_MIXEDMAP, "mixedmap" },
{VM_HUGEPAGE, "hugepage" },
{VM_NOHUGEPAGE, "nohugepage" },
{VM_MERGEABLE, "mergeable" },
};
void dump_vma(const struct vm_area_struct *vma)
{
pr_emerg("vma %p start %p end %p\n"
"next %p prev %p mm %p\n"
"prot %lx anon_vma %p vm_ops %p\n"
"pgoff %lx file %p private_data %p\n",
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
vma->vm_prev, vma->vm_mm,
(unsigned long)pgprot_val(vma->vm_page_prot),
vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
vma->vm_file, vma->vm_private_data);
dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
}
EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
#ifdef CONFIG_MMU
"get_unmapped_area %p\n"
#endif
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
"pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n"
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
"start_brk %lx brk %lx start_stack %lx\n"
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
"binfmt %p flags %lx core_state %p\n"
#ifdef CONFIG_AIO
"ioctx_table %p\n"
#endif
#ifdef CONFIG_MEMCG
"owner %p "
#endif
"exe_file %p\n"
#ifdef CONFIG_MMU_NOTIFIER
"mmu_notifier_mm %p\n"
#endif
#ifdef CONFIG_NUMA_BALANCING
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
#endif
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
"tlb_flush_pending %d\n"
#endif
"%s", /* This is here to hold the comma */
mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
#ifdef CONFIG_MMU
mm->get_unmapped_area,
#endif
mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
mm->pgd, atomic_read(&mm->mm_users),
atomic_read(&mm->mm_count),
atomic_long_read((atomic_long_t *)&mm->nr_ptes),
mm->map_count,
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
mm->start_code, mm->end_code, mm->start_data, mm->end_data,
mm->start_brk, mm->brk, mm->start_stack,
mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
mm->binfmt, mm->flags, mm->core_state,
#ifdef CONFIG_AIO
mm->ioctx_table,
#endif
#ifdef CONFIG_MEMCG
mm->owner,
#endif
mm->exe_file,
#ifdef CONFIG_MMU_NOTIFIER
mm->mmu_notifier_mm,
#endif
#ifdef CONFIG_NUMA_BALANCING
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
#endif
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
mm->tlb_flush_pending,
#endif
"" /* This is here to not have a comma! */
);
dump_flags(mm->def_flags, vmaflags_names,
ARRAY_SIZE(vmaflags_names));
}
#endif /* CONFIG_DEBUG_VM */
Computing file changes ...
