When using a zoned filesystem, while syncing the log, if we fail to
allocate the root node for the log root tree, we are not removing the
log context we allocated on stack from the list of log contexts of the
log root tree. This means after the return from btrfs_sync_log() we get
a corrupted linked list.
Fix this by allocating the node before adding our stack allocated context
to the list of log contexts of the log root tree.
Fixes: 3ddebf27fc ("btrfs: zoned: reorder log node allocation on zoned filesystem")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Lockdep with fstests test case btrfs/041 detected a unsafe locking
scenario when we allocate the log node on a zoned filesystem.
btrfs/041
============================================
WARNING: possible recursive locking detected
5.11.0-rc7+ #939 Not tainted
--------------------------------------------
xfs_io/698 is trying to acquire lock:
ffff88810cd673a0 (&root->log_mutex){+.+.}-{3:3}, at: btrfs_sync_log+0x3d1/0xee0 [btrfs]
but task is already holding lock:
ffff88810b0fc3a0 (&root->log_mutex){+.+.}-{3:3}, at: btrfs_sync_log+0x313/0xee0 [btrfs]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&root->log_mutex);
lock(&root->log_mutex);
*** DEADLOCK ***
May be due to missing lock nesting notation
2 locks held by xfs_io/698:
#0: ffff88810cd66620 (sb_internal){.+.+}-{0:0}, at: btrfs_sync_file+0x2c3/0x570 [btrfs]
#1: ffff88810b0fc3a0 (&root->log_mutex){+.+.}-{3:3}, at: btrfs_sync_log+0x313/0xee0 [btrfs]
stack backtrace:
CPU: 0 PID: 698 Comm: xfs_io Not tainted 5.11.0-rc7+ #939
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4-rebuilt.opensuse.org 04/01/2014
Call Trace:
dump_stack+0x77/0x97
__lock_acquire.cold+0xb9/0x32a
lock_acquire+0xb5/0x400
? btrfs_sync_log+0x3d1/0xee0 [btrfs]
__mutex_lock+0x7b/0x8d0
? btrfs_sync_log+0x3d1/0xee0 [btrfs]
? btrfs_sync_log+0x3d1/0xee0 [btrfs]
? find_first_extent_bit+0x9f/0x100 [btrfs]
? __mutex_unlock_slowpath+0x35/0x270
btrfs_sync_log+0x3d1/0xee0 [btrfs]
btrfs_sync_file+0x3a8/0x570 [btrfs]
__x64_sys_fsync+0x34/0x60
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
This happens, because we are taking the ->log_mutex albeit it has already
been locked.
Also while at it, fix the bogus unlock of the tree_log_mutex in the error
handling.
Fixes: 3ddebf27fc ("btrfs: zoned: reorder log node allocation on zoned filesystem")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since the zoned filesystem requires sequential write out of metadata, we
cannot proceed with a hole in tree-log pages. When such a hole exists,
btree_write_cache_pages() will return -EAGAIN. This happens when someone,
e.g., a concurrent transaction commit, writes a dirty extent in this
tree-log commit.
If we are not going to wait for the extents, we can hope the concurrent
writing fills the hole for us. So, we can ignore the error in this case and
hope the next write will succeed.
If we want to wait for them and got the error, we cannot wait for them
because it will cause a deadlock. So, let's bail out to a full commit in
this case.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is the 3/3 patch to enable tree-log on zoned filesystems.
The allocation order of nodes of "fs_info->log_root_tree" and nodes of
"root->log_root" is not the same as the writing order of them. So, the
writing causes unaligned write errors.
Reorder the allocation of them by delaying allocation of the root node of
"fs_info->log_root_tree," so that the node buffers can go out sequentially
to devices.
Cc: Filipe Manana <fdmanana@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is the 2/3 patch to enable tree-log on zoned filesystems.
Since we can start more than one log transactions per subvolume
simultaneously, nodes from multiple transactions can be allocated
interleaved. Such mixed allocation results in non-sequential writes at
the time of a log transaction commit. The nodes of the global log root
tree (fs_info->log_root_tree), also have the same problem with mixed
allocation.
Serializes log transactions by waiting for a committing transaction when
someone tries to start a new transaction, to avoid the mixed allocation
problem. We must also wait for running log transactions from another
subvolume, but there is no easy way to detect which subvolume root is
running a log transaction. So, this patch forbids starting a new log
transaction when other subvolumes already allocated the global log root
tree.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Tree manipulating operations like merging nodes often release
once-allocated tree nodes. Such nodes are cleaned so that pages in the
node are not uselessly written out. On zoned volumes, however, such
optimization blocks the following IOs as the cancellation of the write
out of the freed blocks breaks the sequential write sequence expected by
the device.
Introduce a list of clean and unwritten extent buffers that have been
released in a transaction. Redirty the buffers so that
btree_write_cache_pages() can send proper bios to the devices.
Besides it clears the entire content of the extent buffer not to confuse
raw block scanners e.g. 'btrfs check'. By clearing the content,
csum_dirty_buffer() complains about bytenr mismatch, so avoid the
checking and checksum using newly introduced buffer flag
EXTENT_BUFFER_NO_CHECK.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Whenever we fsync an inode, if it is a directory, a regular file that was
created in the current transaction or has last_unlink_trans set to the
generation of the current transaction, we check if any of its ancestor
inodes (and the inode itself if it is a directory) can not be logged and
need a fallback to a full transaction commit - if so, we return with a
value of 1 in order to fallback to a transaction commit.
However we often do not need to fallback to a transaction commit because:
1) The ancestor inode is not an immediate parent, and therefore there is
not an explicit request to log it and it is not needed neither to
guarantee the consistency of the inode originally asked to be logged
(fsynced) nor its immediate parent;
2) The ancestor inode was already logged before, in which case any link,
unlink or rename operation updates the log as needed.
So for these two cases we can avoid an unnecessary transaction commit.
Therefore remove check_parent_dirs_for_sync() and add a check at the top
of btrfs_log_inode() to make us fallback immediately to a transaction
commit when we are logging a directory inode that can not be logged and
needs a full transaction commit. All we need to protect is the case where
after renaming a file someone fsyncs only the old directory, which would
result is losing the renamed file after a log replay.
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging new directory entries of a directory, we log the inodes of
new dentries and the inodes of dentries pointing to directories that
may have been created in past transactions. For the case of directories
we log in full mode, which can be particularly expensive for large
directories.
We do use btrfs_inode_in_log() to skip already logged inodes, however for
that helper to return true, it requires that the log transaction used to
log the inode to be already committed. This means that when we have more
than one task using the same log transaction we can end up logging an
inode multiple times, which is a waste of time and not necessary since
the log will be committed by one of the tasks and the others will wait for
the log transaction to be committed before returning to user space.
So simply replace the use of btrfs_inode_in_log() with the new helper
function need_log_inode(), introduced in a previous commit.
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Some times when we fsync an inode we need to do a full log of all its
ancestors (due to unlink, link or rename operations), which can be an
expensive operation, specially if the directories are large.
However if we find an ancestor directory inode that is already logged in
the current transaction, and has no inserted/updated/deleted xattrs since
it was last logged, we can skip logging the directory again. We are safe
to skip that since we know that for logged directories, any link, unlink
or rename operations that implicate the directory will update the log as
necessary.
So use the helper need_log_dir(), introduced in a previous commit, to
detect already logged directories that can be skipped.
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we fsync a new file, created in the current transaction, we check
all its ancestor inodes and always log them if they were created in the
current transaction - even if we have already logged them before, which
is a waste of time.
So avoid logging new ancestor inodes if they were already logged before
and have no xattrs added/updated/removed since they were last logged.
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we fill an inode item for logging we are setting its nbytes field
with the value returned by inode_get_bytes() (a VFS API), however we do
not need it because it is not used during log replay. In fact, for fast
fsyncs, when we call inode_get_bytes() we may even get an outdated value
for nbytes because the nbytes field of the inode is only updated when
ordered extents complete, and a fast fsync only waits for writeback to
complete, it does not wait for ordered extent completion.
So just remove the setup of nbytes and add an explicit comment mentioning
why we do not set it. This also avoids adding contention on the inode's
i_lock (VFS) with concurrent stat() calls, since that spinlock is used by
inode_get_bytes() which is also called by our stat callback
(btrfs_getattr()).
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we remove a directory entry, as part of an unlink operation, if the
directory was logged before we must remove the directory index items from
the log. We are also updating the inode item of the directory to update
its i_size, but that is not necessary because during log replay we do not
need it and we correctly adjust the i_size in the inode item of the
subvolume as we process directory index items and replay deletes.
This is not needed since commit d555438b6e ("Btrfs: drop dir i_size
when adding new names on replay"), where we explicitly ignore the i_size
of directory inode items on log replay. Before that we used it but it
was buggy as mentioned in that commit's change log (i_size got a larger
value then it should have).
So stop updating the i_size of the directory inode item in the log, as
that is a waste of time, adds more log contention to the log tree and
often results in COWing more extent buffers for the log tree.
This code path is triggered often during dbench workloads for example.
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
Performance results, after applying all patches, are mentioned in the
change log of the last patch.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This function is used to initialize the in-memory
btrfs_root::highest_objectid member, which is used to get an available
objectid. Rename it to better reflect its semantics.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Early on during a transaction commit we acquire the tree_log_mutex and
hold it until after we write the super blocks. But before writing the
extent buffers dirtied by the transaction and the super blocks we unblock
the transaction by setting its state to TRANS_STATE_UNBLOCKED and setting
fs_info->running_transaction to NULL.
This means that after that and before writing the super blocks, new
transactions can start. However if any transaction wants to log an inode,
it will block waiting for the transaction commit to write its dirty
extent buffers and the super blocks because the tree_log_mutex is only
released after those operations are complete, and starting a new log
transaction blocks on that mutex (at start_log_trans()).
Writing the dirty extent buffers and the super blocks can take a very
significant amount of time to complete, but we could allow the tasks
wanting to log an inode to proceed with most of their steps:
1) create the log trees
2) log metadata in the trees
3) write their dirty extent buffers
They only need to wait for the previous transaction commit to complete
(write its super blocks) before they attempt to write their super blocks,
otherwise we could end up with a corrupt filesystem after a crash.
So change start_log_trans() to use the root tree's log_mutex to serialize
for the creation of the log root tree instead of using the tree_log_mutex,
and make btrfs_sync_log() acquire the tree_log_mutex before writing the
super blocks. This allows for inode logging to wait much less time when
there is a previous transaction that is still committing, often not having
to wait at all, as by the time when we try to sync the log the previous
transaction already wrote its super blocks.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
The following script that uses dbench was used to measure the impact of
the whole patchset:
$ cat test-dbench.sh
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd"
echo "performance" | \
tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
mkfs.btrfs -f -m single -d single $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -D $MNT -t 300 64
umount $MNT
The test was run on a machine with 12 cores, 64G of ram, using a NVMe
device and a non-debug kernel configuration (Debian's default).
Before patch set:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 11277211 0.250 85.340
Close 8283172 0.002 6.479
Rename 477515 1.935 86.026
Unlink 2277936 0.770 87.071
Deltree 256 15.732 81.379
Mkdir 128 0.003 0.009
Qpathinfo 10221180 0.056 44.404
Qfileinfo 1789967 0.002 4.066
Qfsinfo 1874399 0.003 9.176
Sfileinfo 918589 0.061 10.247
Find 3951758 0.341 54.040
WriteX 5616547 0.047 85.079
ReadX 17676028 0.005 9.704
LockX 36704 0.003 1.800
UnlockX 36704 0.002 0.687
Flush 790541 14.115 676.236
Throughput 1179.19 MB/sec 64 clients 64 procs max_latency=676.240 ms
After patch set:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 12687926 0.171 86.526
Close 9320780 0.002 8.063
Rename 537253 1.444 78.576
Unlink 2561827 0.559 87.228
Deltree 374 11.499 73.549
Mkdir 187 0.003 0.005
Qpathinfo 11500300 0.061 36.801
Qfileinfo 2017118 0.002 7.189
Qfsinfo 2108641 0.003 4.825
Sfileinfo 1033574 0.008 8.065
Find 4446553 0.408 47.835
WriteX 6335667 0.045 84.388
ReadX 19887312 0.003 9.215
LockX 41312 0.003 1.394
UnlockX 41312 0.002 1.425
Flush 889233 13.014 623.259
Throughput 1339.32 MB/sec 64 clients 64 procs max_latency=623.265 ms
+12.7% throughput, -8.2% max latency
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging an inode we may often have to fallback to a full transaction
commit, either because a new block group was allocated, there is some case
we can not deal with without a transaction commit or some error like an
ENOMEM happened. However after we fallback to a transaction commit, we
have a time window where we can make the next attempt to log any inode
commit the next transaction unnecessarily, adding additional overhead and
increasing latency.
A sequence of steps that leads to this issue is the following:
1) The current open transaction has a generation of 1000;
2) A new block group is allocated, and as a consequence we must make sure
any attempts to commit a log fallback to a transaction commit, so
btrfs_set_log_full_commit() is called from btrfs_make_block_group().
This sets fs_info->last_trans_log_full_commit to 1000;
3) Task A is holding a handle on transaction 1000 and tries to log inode X.
Once it gets to start_log_trans(), it calls btrfs_need_log_full_commit()
which returns true, since fs_info->last_trans_log_full_commit has a
value of 1000. So we end up returning EAGAIN and propagating it up to
btrfs_sync_file(), where we commit transaction 1000;
4) The transaction commit task (task A) sets the transaction state to
unblocked (TRANS_STATE_UNBLOCKED);
5) Some other task, task B, starts a new transaction with a generation of
1001;
6) Some stuff is done with transaction 1001, some btree blocks COWed, etc;
7) Transaction 1000 has not fully committed yet, we are still writing all
the extent buffers it created;
8) Some new task, task C, starts an fsync of inode Y, gets a handle for
transaction 1001, and it gets to btrfs_log_inode_parent() which does
the following check:
if (fs_info->last_trans_log_full_commit > last_committed) {
ret = 1;
goto end_no_trans;
}
At that point last_trans_log_full_commit has a value of 1000 and
last_committed (value of fs_info->last_trans_committed) has a value of
999, since transaction 1000 has not yet committed - it is either still
writing out dirty extent buffers, its super blocks or unpinning
extents.
As a consequence we return 1, which gets propagated up to
btrfs_sync_file(), which will then call btrfs_commit_transaction()
for transaction 1001.
As a consequence we have an unnecessary second transaction commit, we
previously committed transaction 1000 and now commit transaction 1001
as well, resulting in more overhead and increased latency.
So fix this double transaction commit issue simply by removing that check,
because all we need to do is wait for the previous transaction to finish
its commit, which we already do later when starting the log transaction at
start_log_trans(), because there we acquire the tree_log_mutex lock, which
is held by a transaction commit and only released after the transaction
commits its super blocks.
Another issue that check has is that it reads last_trans_log_full_commit
without using READ_ONCE(), which is incorrect since that member of
struct btrfs_fs_info is always updated with WRITE_ONCE() through the
helper btrfs_set_log_full_commit().
This double transaction commit issue can actually be triggered quite often
in long runs of dbench, since besides the creation of new block groups
that force inode logging to fallback to a transaction commit, there are
cases where dbench asks to fsync a directory which had files in it that
were previously renamed or subdirectories that were removed, resulting in
the inode logging to fallback to a full transaction commit.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
Performance results are mentioned in the change log of the last patch.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging an inode and the previous transaction is still committing, we
have a time window where we can end up incorrectly think an inode has its
last_unlink_trans field with a value greater than the last transaction
committed, which results in the logging to fallback to a full transaction
commit, which is usually much more expensive than doing a log commit.
The race is described by the following steps:
1) We are at transaction 1000;
2) We modify an inode X (a directory) using transaction 1000 and set its
last_unlink_trans field to 1000, because for example we removed one
of its subdirectories;
3) We create a new inode Y with a dentry in inode X using transaction 1000,
so its generation field is set to 1000;
4) The commit for transaction 1000 is started by task A;
5) The task committing transaction 1000 sets the transaction state to
unblocked, writes the dirty extent buffers and the super blocks, then
unlocks tree_log_mutex;
6) Some task starts a new transaction with a generation of 1001;
7) We do some modification to inode Y (using transaction 1001);
8) The transaction 1000 commit starts unpinning extents. At this point
fs_info->last_trans_committed still has a value of 999;
9) Task B starts an fsync on inode Y, and gets a handle for transaction
1001. When it gets to check_parent_dirs_for_sync() it does the checking
of the ancestor dentries because the following check does not evaluate
to true:
if (S_ISREG(inode->vfs_inode.i_mode) &&
inode->generation <= last_committed &&
inode->last_unlink_trans <= last_committed)
goto out;
The generation value for inode Y is 1000 and last_committed, which has
the value read from fs_info->last_trans_committed, has a value of 999,
so that check evaluates to false and we proceed to check the ancestor
inodes.
Once we get to the first ancestor, inode X, we call
btrfs_must_commit_transaction() on it, which evaluates to true:
static bool btrfs_must_commit_transaction(...)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
bool ret = false;
mutex_lock(&inode->log_mutex);
if (inode->last_unlink_trans > fs_info->last_trans_committed) {
/*
* Make sure any commits to the log are forced to be full
* commits.
*/
btrfs_set_log_full_commit(trans);
ret = true;
}
(...)
because inode's X last_unlink_trans has a value of 1000 and
fs_info->last_trans_committed still has a value of 999, it returns
true to check_parent_dirs_for_sync(), making it return 1 which is
propagated up to btrfs_sync_file(), causing it to fallback to a full
transaction commit of transaction 1001.
We should have not fallen back to commit transaction 1001, since inode
X had last_unlink_trans set to 1000 and the super blocks for
transaction 1000 were already written. So while not resulting in a
functional problem, it leads to a lot more work and higher latencies
for a fsync since committing a transaction is usually more expensive
than committing a log (if other filesystem changes happened under that
transaction).
Similar problem happens when logging directories, for the same reason as
btrfs_must_commit_transaction() returns true on an inode with its
last_unlink_trans having the generation of the previous transaction and
that transaction is still committing, unpinning its freed extents.
So fix this by comparing last_unlink_trans with the id of the current
transaction instead of fs_info->last_trans_committed.
This case is often hit when running dbench for a long enough duration, as
it does lots of rename and rmdir operations (both update the field
last_unlink_trans of an inode) and fsyncs of files and directories.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
Performance results are mentioned in the change log of the last patch.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging an inode and we are checking if we need to log ancestors that
are new, if the previous transaction is still committing we have a time
window where we can unnecessarily log ancestor inodes that were created in
the previous transaction.
The race is described by the following steps:
1) We are at transaction 1000;
2) Directory inode X is created, its generation is set to 1000;
3) The commit for transaction 1000 is started by task A;
4) The task committing transaction 1000 sets the transaction state to
unblocked, writes the dirty extent buffers and the super blocks, then
unlocks tree_log_mutex;
5) Inode Y, a regular file, is created under directory inode X, this
results in starting a new transaction with a generation of 1001;
6) The transaction 1000 commit is unpinning extents. At this point
fs_info->last_trans_committed still has a value of 999;
7) Task B calls fsync on inode Y and gets a handle for transaction 1001;
8) Task B ends up at log_all_new_ancestors() and then because inode Y has
only one hard link, ends up at log_new_ancestors_fast(). There it reads
a value of 999 from fs_info->last_trans_committed, and sees that the
parent inode X has a generation of 1000, so we end up logging inode X:
if (inode->generation > fs_info->last_trans_committed) {
ret = btrfs_log_inode(trans, root, inode,
LOG_INODE_EXISTS, ctx);
(...)
which is not necessary since it was created in the past transaction,
with a generation of 1000, and that transaction has already committed
its super blocks - it's still unpinning extents so it has not yet
updated fs_info->last_trans_committed from 999 to 1000.
So this just causes us to spend more time logging and allocating and
writing more tree blocks for the log tree.
So fix this by comparing an inode's generation with the generation of the
transaction our transaction handle refers to - if the inode's generation
matches the generation of the current transaction than we know it is a
new inode we need to log, otherwise don't log it.
This case is often hit when running dbench for a long enough duration.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
Performance results are mentioned in the change log of the last patch.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging the extents of an inode during a fast fsync, we have a time
window where we can log extents that are from the previous transaction and
already persisted. This only makes us waste time unnecessarily.
The following sequence of steps shows how this can happen:
1) We are at transaction 1000;
2) An ordered extent E from inode I completes, that is it has gone through
btrfs_finish_ordered_io(), and it set the extent maps' generation to
1000 when we unpin the extent, which is the generation of the current
transaction;
3) The commit for transaction 1000 starts by task A;
4) The task committing transaction 1000 sets the transaction state to
unblocked, writes the dirty extent buffers and the super blocks, then
unlocks tree_log_mutex;
5) Some change is made to inode I, resulting in creation of a new
transaction with a generation of 1001;
6) The transaction 1000 commit starts unpinning extents. At this point
fs_info->last_trans_committed still has a value of 999;
7) Task B starts an fsync on inode I, and when it gets to
btrfs_log_changed_extents() sees the extent map for extent E in the
list of modified extents. It sees the extent map has a generation of
1000 and fs_info->last_trans_committed has a value of 999, so it
proceeds to logging the respective file extent item and all the
checksums covering its range.
So we end up wasting time since the extent was already persisted and
is reachable through the trees pointed to by the super block committed
by transaction 1000.
So just fix this by comparing the extent maps generation against the
generation of the transaction handle - if it is smaller then the id in the
handle, we know the extent was already persisted and we do not need to log
it.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
Performance results are mentioned in the change log of the last patch.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we are doing a rename or a link operation for an inode that was logged
in the previous transaction and that transaction is still committing, we
have a time window where we incorrectly consider that the inode was logged
previously in the current transaction and therefore decide to log it to
update it in the log. The following steps give an example on how this
happens during a link operation:
1) Inode X is logged in transaction 1000, so its logged_trans field is set
to 1000;
2) Task A starts to commit transaction 1000;
3) The state of transaction 1000 is changed to TRANS_STATE_UNBLOCKED;
4) Task B starts a link operation for inode X, and as a consequence it
starts transaction 1001;
5) Task A is still committing transaction 1000, therefore the value stored
at fs_info->last_trans_committed is still 999;
6) Task B calls btrfs_log_new_name(), it reads a value of 999 from
fs_info->last_trans_committed and because the logged_trans field of
inode X has a value of 1000, the function does not return immediately,
instead it proceeds to logging the inode, which should not happen
because the inode was logged in the previous transaction (1000) and
not in the current one (1001).
This is not a functional problem, just wasted time and space logging an
inode that does not need to be logged, contributing to higher latency
for link and rename operations.
So fix this by comparing the inodes' logged_trans field with the
generation of the current transaction instead of comparing with the value
stored in fs_info->last_trans_committed.
This case is often hit when running dbench for a long enough duration, as
it does lots of rename operations.
This patch belongs to a patch set that is comprised of the following
patches:
btrfs: fix race causing unnecessary inode logging during link and rename
btrfs: fix race that results in logging old extents during a fast fsync
btrfs: fix race that causes unnecessary logging of ancestor inodes
btrfs: fix race that makes inode logging fallback to transaction commit
btrfs: fix race leading to unnecessary transaction commit when logging inode
btrfs: do not block inode logging for so long during transaction commit
Performance results are mentioned in the change log of the last patch.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's been deprecated since commit b547a88ea5 ("btrfs: start
deprecation of mount option inode_cache") which enumerates the reasons.
A filesystem that uses the feature (mount -o inode_cache) tracks the
inode numbers in bitmaps, that data stay on the filesystem after this
patch. The size is roughly 5MiB for 1M inodes [1], which is considered
small enough to be left there. Removal of the change can be implemented
in btrfs-progs if needed.
[1] https://lore.kernel.org/linux-btrfs/20201127145836.GZ6430@twin.jikos.cz/
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
When joining a log transaction we acquire the root's log mutex, then
increment the root's log batch and log writers counters while holding
the mutex. However we don't need to increment the log batch there,
because we are holding the mutex and incremented the log writers counter
as well, so any other task trying to sync log will wait for the current
task to finish its logging and still achieve the desired log batching.
Since the log batch counter is an atomic counter and is incremented twice
at the very beginning of the fsync callback (btrfs_sync_file()), once
before flushing delalloc and once again after waiting for writeback to
complete, eliminating its increment when joining the log transaction
may provide some performance gains in case we have multiple concurrent
tasks doing fsyncs against different files in the same subvolume, as it
reduces contention on the atomic (locking the cacheline and bouncing it).
When testing fio with 32 jobs, on a 8 cores VM, doing fsyncs against
different files of the same subvolume, on top of a zram device, I could
consistently see gains (higher throughput) between 1% to 2%, which is a
very low value and possibly hard to be observed with a real device (I
couldn't observe consistent gains with my low/mid end NVMe device).
So this change is mostly motivated to just simplify the logic, as updating
the log batch counter is only relevant when an fsync starts and while not
holding the root's log mutex.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Every time we log an inode we lookup in the fs/subvol tree for xattrs and
if we have any, log them into the log tree. However it is very common to
have inodes without any xattrs, so doing the search wastes times, but more
importantly it adds contention on the fs/subvol tree locks, either making
the logging code block and wait for tree locks or making the logging code
making other concurrent operations block and wait.
The most typical use cases where xattrs are used are when capabilities or
ACLs are defined for an inode, or when SELinux is enabled.
This change makes the logging code detect when an inode does not have
xattrs and skip the xattrs search the next time the inode is logged,
unless the inode is evicted and loaded again or a xattr is added to the
inode. Therefore skipping the search for xattrs on inodes that don't ever
have xattrs and are fsynced with some frequency.
The following script that calls dbench was used to measure the impact of
this change on a VM with 8 CPUs, 16Gb of ram, using a raw NVMe device
directly (no intermediary filesystem on the host) and using a non-debug
kernel (default configuration on Debian distributions):
$ cat test.sh
#!/bin/bash
DEV=/dev/sdk
MNT=/mnt/sdk
MOUNT_OPTIONS="-o ssd"
mkfs.btrfs -f -m single -d single $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -D $MNT -t 200 40
umount $MNT
The results before this change:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 5761605 0.172 312.057
Close 4232452 0.002 10.927
Rename 243937 1.406 277.344
Unlink 1163456 0.631 298.402
Deltree 160 11.581 221.107
Mkdir 80 0.003 0.005
Qpathinfo 5221410 0.065 122.309
Qfileinfo 915432 0.001 3.333
Qfsinfo 957555 0.003 3.992
Sfileinfo 469244 0.023 20.494
Find 2018865 0.448 123.659
WriteX 2874851 0.049 118.529
ReadX 9030579 0.004 21.654
LockX 18754 0.003 4.423
UnlockX 18754 0.002 0.331
Flush 403792 10.944 359.494
Throughput 908.444 MB/sec 40 clients 40 procs max_latency=359.500 ms
The results after this change:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 6442521 0.159 230.693
Close 4732357 0.002 10.972
Rename 272809 1.293 227.398
Unlink 1301059 0.563 218.500
Deltree 160 7.796 54.887
Mkdir 80 0.008 0.478
Qpathinfo 5839452 0.047 124.330
Qfileinfo 1023199 0.001 4.996
Qfsinfo 1070760 0.003 5.709
Sfileinfo 524790 0.033 21.765
Find 2257658 0.314 125.611
WriteX 3211520 0.040 232.135
ReadX 10098969 0.004 25.340
LockX 20974 0.003 1.569
UnlockX 20974 0.002 3.475
Flush 451553 10.287 331.037
Throughput 1011.77 MB/sec 40 clients 40 procs max_latency=331.045 ms
+10.8% throughput, -8.2% max latency
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There are several occasions where we do not update the inode's number of
used bytes atomically, resulting in a concurrent stat(2) syscall to report
a value of used blocks that does not correspond to a valid value, that is,
a value that does not match neither what we had before the operation nor
what we get after the operation completes.
In extreme cases it can result in stat(2) reporting zero used blocks, which
can cause problems for some userspace tools where they can consider a file
with a non-zero size and zero used blocks as completely sparse and skip
reading data, as reported/discussed a long time ago in some threads like
the following:
https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html
The cases where this can happen are the following:
-> Case 1
If we do a write (buffered or direct IO) against a file region for which
there is already an allocated extent (or multiple extents), then we have a
short time window where we can report a number of used blocks to stat(2)
that does not take into account the file region being overwritten. This
short time window happens when completing the ordered extent(s).
This happens because when we drop the extents in the write range we
decrement the inode's number of bytes and later on when we insert the new
extent(s) we increment the number of bytes in the inode, resulting in a
short time window where a stat(2) syscall can get an incorrect number of
used blocks.
If we do writes that overwrite an entire file, then we have a short time
window where we report 0 used blocks to stat(2).
Example reproducer:
$ cat reproducer-1.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
stat_loop()
{
trap "wait; exit" SIGTERM
local filepath=$1
local expected=$2
local got
while :; do
got=$(stat -c %b $filepath)
if [ $got -ne $expected ]; then
echo -n "ERROR: unexpected used blocks"
echo " (got: $got expected: $expected)"
fi
done
}
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f $DEV > /dev/null
# mkfs.ext4 -F $DEV > /dev/null
# mkfs.f2fs -f $DEV > /dev/null
# mkfs.reiserfs -f $DEV > /dev/null
mount $DEV $MNT
xfs_io -f -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null
expected=$(stat -c %b $MNT/foobar)
# Create a process to keep calling stat(2) on the file and see if the
# reported number of blocks used (disk space used) changes, it should
# not because we are not increasing the file size nor punching holes.
stat_loop $MNT/foobar $expected &
loop_pid=$!
for ((i = 0; i < 50000; i++)); do
xfs_io -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null
done
kill $loop_pid &> /dev/null
wait
umount $DEV
$ ./reproducer-1.sh
ERROR: unexpected used blocks (got: 0 expected: 128)
ERROR: unexpected used blocks (got: 0 expected: 128)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
-> Case 2
If we do a buffered write against a file region that does not have any
allocated extents, like a hole or beyond EOF, then during ordered extent
completion we have a short time window where a concurrent stat(2) syscall
can report a number of used blocks that does not correspond to the value
before or after the write operation, a value that is actually larger than
the value after the write completes.
This happens because once we start a buffered write into an unallocated
file range we increment the inode's 'new_delalloc_bytes', to make sure
any stat(2) call gets a correct used blocks value before delalloc is
flushed and completes. However at ordered extent completion, after we
inserted the new extent, we increment the inode's number of bytes used
with the size of the new extent, and only later, when clearing the range
in the inode's iotree, we decrement the inode's 'new_delalloc_bytes'
counter with the size of the extent. So this results in a short time
window where a concurrent stat(2) syscall can report a number of used
blocks that accounts for the new extent twice.
Example reproducer:
$ cat reproducer-2.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
stat_loop()
{
trap "wait; exit" SIGTERM
local filepath=$1
local expected=$2
local got
while :; do
got=$(stat -c %b $filepath)
if [ $got -ne $expected ]; then
echo -n "ERROR: unexpected used blocks"
echo " (got: $got expected: $expected)"
fi
done
}
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f $DEV > /dev/null
# mkfs.ext4 -F $DEV > /dev/null
# mkfs.f2fs -f $DEV > /dev/null
# mkfs.reiserfs -f $DEV > /dev/null
mount $DEV $MNT
touch $MNT/foobar
write_size=$((64 * 1024))
for ((i = 0; i < 16384; i++)); do
offset=$(($i * $write_size))
xfs_io -c "pwrite -S 0xab $offset $write_size" $MNT/foobar >/dev/null
blocks_used=$(stat -c %b $MNT/foobar)
# Fsync the file to trigger writeback and keep calling stat(2) on it
# to see if the number of blocks used changes.
stat_loop $MNT/foobar $blocks_used &
loop_pid=$!
xfs_io -c "fsync" $MNT/foobar
kill $loop_pid &> /dev/null
wait $loop_pid
done
umount $DEV
$ ./reproducer-2.sh
ERROR: unexpected used blocks (got: 265472 expected: 265344)
ERROR: unexpected used blocks (got: 284032 expected: 283904)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
-> Case 3
Another case where such problems happen is during other operations that
replace extents in a file range with other extents. Those operations are
extent cloning, deduplication and fallocate's zero range operation.
The cause of the problem is similar to the first case. When we drop the
extents from a range, we decrement the inode's number of bytes, and later
on, after inserting the new extents we increment it. Since this is not
done atomically, a concurrent stat(2) call can see and return a number of
used blocks that is smaller than it should be, does not match the number
of used blocks before or after the clone/deduplication/zero operation.
Like for the first case, when doing a clone, deduplication or zero range
operation against an entire file, we end up having a time window where we
can report 0 used blocks to a stat(2) call.
Example reproducer:
$ cat reproducer-3.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f -m reflink=1 $DEV > /dev/null
mount $DEV $MNT
extent_size=$((64 * 1024))
num_extents=16384
file_size=$(($extent_size * $num_extents))
# File foo has many small extents.
xfs_io -f -s -c "pwrite -S 0xab -b $extent_size 0 $file_size" $MNT/foo \
> /dev/null
# File bar has much less extents and has exactly the same data as foo.
xfs_io -f -c "pwrite -S 0xab 0 $file_size" $MNT/bar > /dev/null
expected=$(stat -c %b $MNT/foo)
# Now deduplicate bar into foo. While the deduplication is in progres,
# the number of used blocks/file size reported by stat should not change
xfs_io -c "dedupe $MNT/bar 0 0 $file_size" $MNT/foo > /dev/null &
dedupe_pid=$!
while [ -n "$(ps -p $dedupe_pid -o pid=)" ]; do
used=$(stat -c %b $MNT/foo)
if [ $used -ne $expected ]; then
echo "Unexpected blocks used: $used (expected: $expected)"
fi
done
umount $DEV
$ ./reproducer-3.sh
Unexpected blocks used: 2076800 (expected: 2097152)
Unexpected blocks used: 2097024 (expected: 2097152)
Unexpected blocks used: 2079872 (expected: 2097152)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
So fix this by:
1) Making btrfs_drop_extents() not decrement the VFS inode's number of
bytes, and instead return the number of bytes;
2) Making any code that drops extents and adds new extents update the
inode's number of bytes atomically, while holding the btrfs inode's
spinlock, which is also used by the stat(2) callback to get the inode's
number of bytes;
3) For ranges in the inode's iotree that are marked as 'delalloc new',
corresponding to previously unallocated ranges, increment the inode's
number of bytes when clearing the 'delalloc new' bit from the range,
in the same critical section that decrements the inode's
'new_delalloc_bytes' counter, delimited by the btrfs inode's spinlock.
An alternative would be to have btrfs_getattr() wait for any IO (ordered
extents in progress) and locking the whole range (0 to (u64)-1) while it
it computes the number of blocks used. But that would mean blocking
stat(2), which is a very used syscall and expected to be fast, waiting
for writes, clone/dedupe, fallocate, page reads, fiemap, etc.
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There are many arguments for __btrfs_drop_extents() and its wrapper
btrfs_drop_extents(), which makes it hard to add more arguments to it and
requires changing every caller. I have added a couple myself back in 2014
commit 1acae57b16 ("Btrfs: faster file extent item replace operations")
and therefore know firsthand that it is a bit cumbersome to add additional
arguments to these functions.
Since I will need to add more arguments in a subsequent bug fix, this
change is preparatory work and adds a data structure that holds all the
arguments, for both input and output, that are passed to this function,
with some comments in the structure's definition mentioning what each
field is and how it relates to other fields.
Callers of this function need only to zero out the content of the
structure and setup only the fields they need. This also removes the
need to have both __btrfs_drop_extents() and btrfs_drop_extents(), so
now we have a single function named btrfs_drop_extents() that takes a
pointer to this new data structure (struct btrfs_drop_extents_args).
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we've plumbed all of the callers to have the owner root and the
level, plumb it down into alloc_extent_buffer().
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we're using a rw_semaphore we no longer need to indicate if a
lock is blocking or not, nor do we need to flip the entire path from
blocking to spinning. Remove these helpers and all the places they are
called.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Just open code it in its sole caller and remove a level of indirection.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Logging directories with many entries can take a significant amount of
time, and in some cases monopolize a cpu/core for a long time if the
logging task doesn't happen to block often enough.
Johannes and Lu Fengqi reported test case generic/041 triggering a soft
lockup when the kernel has CONFIG_SOFTLOCKUP_DETECTOR=y. For this test
case we log an inode with 3002 hard links, and because the test removed
one hard link before fsyncing the file, the inode logging causes the
parent directory do be logged as well, which has 6004 directory items to
log (3002 BTRFS_DIR_ITEM_KEY items plus 3002 BTRFS_DIR_INDEX_KEY items),
so it can take a significant amount of time and trigger the soft lockup.
So just make tree-log.c:log_dir_items() reschedule when necessary,
releasing the current search path before doing so and then resume from
where it was before the reschedule.
The stack trace produced when the soft lockup happens is the following:
[10480.277653] watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [xfs_io:28172]
[10480.279418] Modules linked in: dm_thin_pool dm_persistent_data (...)
[10480.284915] irq event stamp: 29646366
[10480.285987] hardirqs last enabled at (29646365): [<ffffffff85249b66>] __slab_alloc.constprop.0+0x56/0x60
[10480.288482] hardirqs last disabled at (29646366): [<ffffffff8579b00d>] irqentry_enter+0x1d/0x50
[10480.290856] softirqs last enabled at (4612): [<ffffffff85a00323>] __do_softirq+0x323/0x56c
[10480.293615] softirqs last disabled at (4483): [<ffffffff85800dbf>] asm_call_on_stack+0xf/0x20
[10480.296428] CPU: 2 PID: 28172 Comm: xfs_io Not tainted 5.9.0-rc4-default+ #1248
[10480.298948] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba527-rebuilt.opensuse.org 04/01/2014
[10480.302455] RIP: 0010:__slab_alloc.constprop.0+0x19/0x60
[10480.304151] Code: 86 e8 31 75 21 00 66 66 2e 0f 1f 84 00 00 00 (...)
[10480.309558] RSP: 0018:ffffadbe09397a58 EFLAGS: 00000282
[10480.311179] RAX: ffff8a495ab92840 RBX: 0000000000000282 RCX: 0000000000000006
[10480.313242] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff85249b66
[10480.315260] RBP: ffff8a497d04b740 R08: 0000000000000001 R09: 0000000000000001
[10480.317229] R10: ffff8a497d044800 R11: ffff8a495ab93c40 R12: 0000000000000000
[10480.319169] R13: 0000000000000000 R14: 0000000000000c40 R15: ffffffffc01daf70
[10480.321104] FS: 00007fa1dc5c0e40(0000) GS:ffff8a497da00000(0000) knlGS:0000000000000000
[10480.323559] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[10480.325235] CR2: 00007fa1dc5befb8 CR3: 0000000004f8a006 CR4: 0000000000170ea0
[10480.327259] Call Trace:
[10480.328286] ? overwrite_item+0x1f0/0x5a0 [btrfs]
[10480.329784] __kmalloc+0x831/0xa20
[10480.331009] ? btrfs_get_32+0xb0/0x1d0 [btrfs]
[10480.332464] overwrite_item+0x1f0/0x5a0 [btrfs]
[10480.333948] log_dir_items+0x2ee/0x570 [btrfs]
[10480.335413] log_directory_changes+0x82/0xd0 [btrfs]
[10480.336926] btrfs_log_inode+0xc9b/0xda0 [btrfs]
[10480.338374] ? init_once+0x20/0x20 [btrfs]
[10480.339711] btrfs_log_inode_parent+0x8d3/0xd10 [btrfs]
[10480.341257] ? dget_parent+0x97/0x2e0
[10480.342480] btrfs_log_dentry_safe+0x3a/0x50 [btrfs]
[10480.343977] btrfs_sync_file+0x24b/0x5e0 [btrfs]
[10480.345381] do_fsync+0x38/0x70
[10480.346483] __x64_sys_fsync+0x10/0x20
[10480.347703] do_syscall_64+0x2d/0x70
[10480.348891] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[10480.350444] RIP: 0033:0x7fa1dc80970b
[10480.351642] Code: 0f 05 48 3d 00 f0 ff ff 77 45 c3 0f 1f 40 00 48 (...)
[10480.356952] RSP: 002b:00007fffb3d081d0 EFLAGS: 00000293 ORIG_RAX: 000000000000004a
[10480.359458] RAX: ffffffffffffffda RBX: 0000562d93d45e40 RCX: 00007fa1dc80970b
[10480.361426] RDX: 0000562d93d44ab0 RSI: 0000562d93d45e60 RDI: 0000000000000003
[10480.363367] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007fa1dc7b2a40
[10480.365317] R10: 0000562d93d0e366 R11: 0000000000000293 R12: 0000000000000001
[10480.367299] R13: 0000562d93d45290 R14: 0000562d93d45e40 R15: 0000562d93d45e60
Link: https://lore.kernel.org/linux-btrfs/20180713090216.GC575@fnst.localdomain/
Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
CC: stable@vger.kernel.org # 4.4+
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently regardless of a full or a fast fsync we always wait for ordered
extents to complete, and then start logging the inode after that. However
for fast fsyncs we can just wait for the writeback to complete, we don't
need to wait for the ordered extents to complete since we use the list of
modified extents maps to figure out which extents we must log and we can
get their checksums directly from the ordered extents that are still in
flight, otherwise look them up from the checksums tree.
Until commit b5e6c3e170 ("btrfs: always wait on ordered extents at
fsync time"), for fast fsyncs, we used to start logging without even
waiting for the writeback to complete first, we would wait for it to
complete after logging, while holding a transaction open, which lead to
performance issues when using cgroups and probably for other cases too,
as wait for IO while holding a transaction handle should be avoided as
much as possible. After that, for fast fsyncs, we started to wait for
ordered extents to complete before starting to log, which adds some
latency to fsyncs and we even got at least one report about a performance
drop which bisected to that particular change:
https://lore.kernel.org/linux-btrfs/20181109215148.GF23260@techsingularity.net/
This change makes fast fsyncs only wait for writeback to finish before
starting to log the inode, instead of waiting for both the writeback to
finish and for the ordered extents to complete. This brings back part of
the logic we had that extracts checksums from in flight ordered extents,
which are not yet in the checksums tree, and making sure transaction
commits wait for the completion of ordered extents previously logged
(by far most of the time they have already completed by the time a
transaction commit starts, resulting in no wait at all), to avoid any
data loss if an ordered extent completes after the transaction used to
log an inode is committed, followed by a power failure.
When there are no other tasks accessing the checksums and the subvolume
btrees, the ordered extent completion is pretty fast, typically taking
100 to 200 microseconds only in my observations. However when there are
other tasks accessing these btrees, ordered extent completion can take a
lot more time due to lock contention on nodes and leaves of these btrees.
I've seen cases over 2 milliseconds, which starts to be significant. In
particular when we do have concurrent fsyncs against different files there
is a lot of contention on the checksums btree, since we have many tasks
writing the checksums into the btree and other tasks that already started
the logging phase are doing lookups for checksums in the btree.
This change also turns all ranged fsyncs into full ranged fsyncs, which
is something we already did when not using the NO_HOLES features or when
doing a full fsync. This is to guarantee we never miss checksums due to
writeback having been triggered only for a part of an extent, and we end
up logging the full extent but only checksums for the written range, which
results in missing checksums after log replay. Allowing ranged fsyncs to
operate again only in the original range, when using the NO_HOLES feature
and doing a fast fsync is doable but requires some non trivial changes to
the writeback path, which can always be worked on later if needed, but I
don't think they are a very common use case.
Several tests were performed using fio for different numbers of concurrent
jobs, each writing and fsyncing its own file, for both sequential and
random file writes. The tests were run on bare metal, no virtualization,
on a box with 12 cores (Intel i7-8700), 64Gb of RAM and a NVMe device,
with a kernel configuration that is the default of typical distributions
(debian in this case), without debug options enabled (kasan, kmemleak,
slub debug, debug of page allocations, lock debugging, etc).
The following script that calls fio was used:
$ cat test-fsync.sh
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-d single -m single"
if [ $# -ne 5 ]; then
echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ BLOCK_SIZE [write|randwrite]"
exit 1
fi
NUM_JOBS=$1
FILE_SIZE=$2
FSYNC_FREQ=$3
BLOCK_SIZE=$4
WRITE_MODE=$5
if [ "$WRITE_MODE" != "write" ] && [ "$WRITE_MODE" != "randwrite" ]; then
echo "Invalid WRITE_MODE, must be 'write' or 'randwrite'"
exit 1
fi
cat <<EOF > /tmp/fio-job.ini
[writers]
rw=$WRITE_MODE
fsync=$FSYNC_FREQ
fallocate=none
group_reporting=1
direct=0
bs=$BLOCK_SIZE
ioengine=sync
size=$FILE_SIZE
directory=$MNT
numjobs=$NUM_JOBS
EOF
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
echo
echo "Using config:"
echo
cat /tmp/fio-job.ini
echo
umount $MNT &> /dev/null
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The results were the following:
*************************
*** sequential writes ***
*************************
==== 1 job, 8GiB file, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=36.6MiB/s (38.4MB/s), 36.6MiB/s-36.6MiB/s (38.4MB/s-38.4MB/s), io=8192MiB (8590MB), run=223689-223689msec
After patch:
WRITE: bw=40.2MiB/s (42.1MB/s), 40.2MiB/s-40.2MiB/s (42.1MB/s-42.1MB/s), io=8192MiB (8590MB), run=203980-203980msec
(+9.8%, -8.8% runtime)
==== 2 jobs, 4GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=35.8MiB/s (37.5MB/s), 35.8MiB/s-35.8MiB/s (37.5MB/s-37.5MB/s), io=8192MiB (8590MB), run=228950-228950msec
After patch:
WRITE: bw=43.5MiB/s (45.6MB/s), 43.5MiB/s-43.5MiB/s (45.6MB/s-45.6MB/s), io=8192MiB (8590MB), run=188272-188272msec
(+21.5% throughput, -17.8% runtime)
==== 4 jobs, 2GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=50.1MiB/s (52.6MB/s), 50.1MiB/s-50.1MiB/s (52.6MB/s-52.6MB/s), io=8192MiB (8590MB), run=163446-163446msec
After patch:
WRITE: bw=64.5MiB/s (67.6MB/s), 64.5MiB/s-64.5MiB/s (67.6MB/s-67.6MB/s), io=8192MiB (8590MB), run=126987-126987msec
(+28.7% throughput, -22.3% runtime)
==== 8 jobs, 1GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=64.0MiB/s (68.1MB/s), 64.0MiB/s-64.0MiB/s (68.1MB/s-68.1MB/s), io=8192MiB (8590MB), run=126075-126075msec
After patch:
WRITE: bw=86.8MiB/s (91.0MB/s), 86.8MiB/s-86.8MiB/s (91.0MB/s-91.0MB/s), io=8192MiB (8590MB), run=94358-94358msec
(+35.6% throughput, -25.2% runtime)
==== 16 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=79.8MiB/s (83.6MB/s), 79.8MiB/s-79.8MiB/s (83.6MB/s-83.6MB/s), io=8192MiB (8590MB), run=102694-102694msec
After patch:
WRITE: bw=107MiB/s (112MB/s), 107MiB/s-107MiB/s (112MB/s-112MB/s), io=8192MiB (8590MB), run=76446-76446msec
(+34.1% throughput, -25.6% runtime)
==== 32 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=93.2MiB/s (97.7MB/s), 93.2MiB/s-93.2MiB/s (97.7MB/s-97.7MB/s), io=16.0GiB (17.2GB), run=175836-175836msec
After patch:
WRITE: bw=111MiB/s (117MB/s), 111MiB/s-111MiB/s (117MB/s-117MB/s), io=16.0GiB (17.2GB), run=147001-147001msec
(+19.1% throughput, -16.4% runtime)
==== 64 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=108MiB/s (114MB/s), 108MiB/s-108MiB/s (114MB/s-114MB/s), io=32.0GiB (34.4GB), run=302656-302656msec
After patch:
WRITE: bw=133MiB/s (140MB/s), 133MiB/s-133MiB/s (140MB/s-140MB/s), io=32.0GiB (34.4GB), run=246003-246003msec
(+23.1% throughput, -18.7% runtime)
************************
*** random writes ***
************************
==== 1 job, 8GiB file, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=11.5MiB/s (12.0MB/s), 11.5MiB/s-11.5MiB/s (12.0MB/s-12.0MB/s), io=8192MiB (8590MB), run=714281-714281msec
After patch:
WRITE: bw=11.6MiB/s (12.2MB/s), 11.6MiB/s-11.6MiB/s (12.2MB/s-12.2MB/s), io=8192MiB (8590MB), run=705959-705959msec
(+0.9% throughput, -1.7% runtime)
==== 2 jobs, 4GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=12.8MiB/s (13.5MB/s), 12.8MiB/s-12.8MiB/s (13.5MB/s-13.5MB/s), io=8192MiB (8590MB), run=638101-638101msec
After patch:
WRITE: bw=13.1MiB/s (13.7MB/s), 13.1MiB/s-13.1MiB/s (13.7MB/s-13.7MB/s), io=8192MiB (8590MB), run=625374-625374msec
(+2.3% throughput, -2.0% runtime)
==== 4 jobs, 2GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=15.4MiB/s (16.2MB/s), 15.4MiB/s-15.4MiB/s (16.2MB/s-16.2MB/s), io=8192MiB (8590MB), run=531146-531146msec
After patch:
WRITE: bw=17.8MiB/s (18.7MB/s), 17.8MiB/s-17.8MiB/s (18.7MB/s-18.7MB/s), io=8192MiB (8590MB), run=460431-460431msec
(+15.6% throughput, -13.3% runtime)
==== 8 jobs, 1GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=19.9MiB/s (20.8MB/s), 19.9MiB/s-19.9MiB/s (20.8MB/s-20.8MB/s), io=8192MiB (8590MB), run=412664-412664msec
After patch:
WRITE: bw=22.2MiB/s (23.3MB/s), 22.2MiB/s-22.2MiB/s (23.3MB/s-23.3MB/s), io=8192MiB (8590MB), run=368589-368589msec
(+11.6% throughput, -10.7% runtime)
==== 16 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=29.3MiB/s (30.7MB/s), 29.3MiB/s-29.3MiB/s (30.7MB/s-30.7MB/s), io=8192MiB (8590MB), run=279924-279924msec
After patch:
WRITE: bw=30.4MiB/s (31.9MB/s), 30.4MiB/s-30.4MiB/s (31.9MB/s-31.9MB/s), io=8192MiB (8590MB), run=269258-269258msec
(+3.8% throughput, -3.8% runtime)
==== 32 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=36.9MiB/s (38.7MB/s), 36.9MiB/s-36.9MiB/s (38.7MB/s-38.7MB/s), io=16.0GiB (17.2GB), run=443581-443581msec
After patch:
WRITE: bw=41.6MiB/s (43.6MB/s), 41.6MiB/s-41.6MiB/s (43.6MB/s-43.6MB/s), io=16.0GiB (17.2GB), run=394114-394114msec
(+12.7% throughput, -11.2% runtime)
==== 64 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=45.9MiB/s (48.1MB/s), 45.9MiB/s-45.9MiB/s (48.1MB/s-48.1MB/s), io=32.0GiB (34.4GB), run=714614-714614msec
After patch:
WRITE: bw=48.8MiB/s (51.1MB/s), 48.8MiB/s-48.8MiB/s (51.1MB/s-51.1MB/s), io=32.0GiB (34.4GB), run=672087-672087msec
(+6.3% throughput, -6.0% runtime)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since commit d4682ba03e ("Btrfs: sync log after logging new name") we
started to commit logs, and fallback to transaction commits when we failed
to log the new names or commit the logs, after link and rename operations
when the target inodes (or their parents) were previously logged in the
current transaction. This was to avoid losing directories despite an
explicit fsync on them when they are ancestors of some inode that got a
new named logged, due to a link or rename operation. However that adds the
cost of starting IO and waiting for it to complete, which can cause higher
latencies for applications.
Instead of doing that, just make sure that when we log a new name for an
inode we don't mark any of its ancestors as logged, so that if any one
does an fsync against any of them, without doing any other change on them,
the fsync commits the log. This way we only pay the cost of a log commit
(or a transaction commit if something goes wrong or a new block group was
created) if the application explicitly asks to fsync any of the parent
directories.
Using dbench, which mixes several filesystems operations including renames,
revealed some significant latency gains. The following script that uses
dbench was used to test this:
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-m single -d single"
THREADS=16
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -t 300 -D $MNT $THREADS
umount $MNT
The test was run on bare metal, no virtualization, on a box with 12 cores
(Intel i7-8700), 64Gb of RAM and using a NVMe device, with a kernel
configuration that is the default of typical distributions (debian in this
case), without debug options enabled (kasan, kmemleak, slub debug, debug
of page allocations, lock debugging, etc).
Results before this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 10750455 0.011 155.088
Close 7896674 0.001 0.243
Rename 455222 2.158 1101.947
Unlink 2171189 0.067 121.638
Deltree 256 2.425 7.816
Mkdir 128 0.002 0.003
Qpathinfo 9744323 0.006 21.370
Qfileinfo 1707092 0.001 0.146
Qfsinfo 1786756 0.001 11.228
Sfileinfo 875612 0.003 21.263
Find 3767281 0.025 9.617
WriteX 5356924 0.011 211.390
ReadX 16852694 0.003 9.442
LockX 35008 0.002 0.119
UnlockX 35008 0.001 0.138
Flush 753458 4.252 1102.249
Throughput 1128.35 MB/sec 16 clients 16 procs max_latency=1102.255 ms
Results after this patch:
16 clients, after
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 11471098 0.012 448.281
Close 8426396 0.001 0.925
Rename 485746 0.123 267.183
Unlink 2316477 0.080 63.433
Deltree 288 2.830 11.144
Mkdir 144 0.003 0.010
Qpathinfo 10397420 0.006 10.288
Qfileinfo 1822039 0.001 0.169
Qfsinfo 1906497 0.002 14.039
Sfileinfo 934433 0.004 2.438
Find 4019879 0.026 10.200
WriteX 5718932 0.011 200.985
ReadX 17981671 0.003 10.036
LockX 37352 0.002 0.076
UnlockX 37352 0.001 0.109
Flush 804018 5.015 778.033
Throughput 1201.98 MB/sec 16 clients 16 procs max_latency=778.036 ms
(+6.5% throughput, -29.4% max latency, -75.8% rename latency)
Test case generic/498 from fstests tests the scenario that the previously
mentioned commit fixed.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During a rename we pin the log to make sure no one commits a log that
reflects an ongoing rename operation, as it might result in a committed
log where it recorded the unlink of the old name without having recorded
the new name. However we are taking the subvolume's log_mutex before
incrementing the log_writers counter, which is not necessary since that
counter is atomic and we only remove the old name from the log and add
the new name to the log after we have incremented log_writers, ensuring
that no one can commit the log after we have removed the old name from
the log and before we added the new name to the log.
By taking the log_mutex lock we are just adding unnecessary contention on
the lock, which can become visible for workloads that mix renames with
fsyncs, writes for files opened with O_SYNC and unlink operations (if the
inode or its parent were fsynced before in the current transaction).
So just remove the lock and unlock of the subvolume's log_mutex at
btrfs_pin_log_trans().
Using dbench, which mixes different types of operations that end up taking
that mutex (fsyncs, renames, unlinks and writes into files opened with
O_SYNC) revealed some small gains. The following script that calls dbench
was used:
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-m single -d single"
THREADS=32
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -s -t 600 -D $MNT $THREADS
umount $MNT
The test was run on bare metal, no virtualization, on a box with 12 cores
(Intel i7-8700), 64Gb of RAM and using a NVMe device, with a kernel
configuration that is the default of typical distributions (debian in this
case), without debug options enabled (kasan, kmemleak, slub debug, debug
of page allocations, lock debugging, etc).
Results before this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 4410848 0.017 738.640
Close 3240222 0.001 0.834
Rename 186850 7.478 1272.476
Unlink 890875 0.128 785.018
Deltree 128 2.846 12.081
Mkdir 64 0.002 0.003
Qpathinfo 3997659 0.009 11.171
Qfileinfo 701307 0.001 0.478
Qfsinfo 733494 0.002 1.103
Sfileinfo 359362 0.004 3.266
Find 1546226 0.041 4.128
WriteX 2202803 7.905 1376.989
ReadX 6917775 0.003 3.887
LockX 14392 0.002 0.043
UnlockX 14392 0.001 0.085
Flush 309225 0.128 1033.936
Throughput 231.555 MB/sec (sync open) 32 clients 32 procs max_latency=1376.993 ms
Results after this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 4603244 0.017 232.776
Close 3381299 0.001 1.041
Rename 194871 7.251 1073.165
Unlink 929730 0.133 119.233
Deltree 128 2.871 10.199
Mkdir 64 0.002 0.004
Qpathinfo 4171343 0.009 11.317
Qfileinfo 731227 0.001 1.635
Qfsinfo 765079 0.002 3.568
Sfileinfo 374881 0.004 1.220
Find 1612964 0.041 4.675
WriteX 2296720 7.569 1178.204
ReadX 7213633 0.003 3.075
LockX 14976 0.002 0.076
UnlockX 14976 0.001 0.061
Flush 322635 0.102 579.505
Throughput 241.4 MB/sec (sync open) 32 clients 32 procs max_latency=1178.207 ms
(+4.3% throughput, -14.4% max latency)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Delete repeated words in fs/btrfs/.
{to, the, a, and old}
and change "into 2 part" to "into 2 parts".
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With my new locking code dbench is so much faster that I tripped over a
transaction abort from ENOSPC. This turned out to be because
btrfs_del_dir_entries_in_log was checking for ret == -ENOSPC, but this
function sets err on error, and returns err. So instead of properly
marking the inode as needing a full commit, we were returning -ENOSPC
and aborting in __btrfs_unlink_inode. Fix this by checking the proper
variable so that we return the correct thing in the case of ENOSPC.
The ENOENT needs to be checked, because btrfs_lookup_dir_item_index()
can return -ENOENT if the dir item isn't in the tree log (which would
happen if we hadn't fsync'ed this guy). We actually handle that case in
__btrfs_unlink_inode, so it's an expected error to get back.
Fixes: 4a500fd178 ("Btrfs: Metadata ENOSPC handling for tree log")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add note and comment about ENOENT ]
Signed-off-by: David Sterba <dsterba@suse.com>
While logging an inode, at copy_items(), if we fail to lookup the checksums
for an extent we release the destination path, free the ins_data array and
then return immediately. However a previous iteration of the for loop may
have added checksums to the ordered_sums list, in which case we leak the
memory used by them.
So fix this by making sure we iterate the ordered_sums list and free all
its checksums before returning.
Fixes: 3650860b90 ("Btrfs: remove almost all of the BUG()'s from tree-log.c")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The possibility of extents being shared (through clone and deduplication
operations) requires special care when logging data checksums, to avoid
having a log tree with different checksum items that cover ranges which
overlap (which resulted in missing checksums after replaying a log tree).
Such problems were fixed in the past by the following commits:
commit 40e046acbd ("Btrfs: fix missing data checksums after replaying a
log tree")
commit e289f03ea7 ("btrfs: fix corrupt log due to concurrent fsync of
inodes with shared extents")
Test case generic/588 exercises the scenario solved by the first commit
(purely sequential and deterministic) while test case generic/457 often
triggered the case fixed by the second commit (not deterministic, requires
specific timings under concurrency).
The problems were addressed by deleting, from the log tree, any existing
checksums before logging the new ones. And also by doing the deletion and
logging of the cheksums while locking the checksum range in an extent io
tree (root->log_csum_range), to deal with the case where we have concurrent
fsyncs against files with shared extents.
That however causes more contention on the leaves of a log tree where we
store checksums (and all the nodes in the paths leading to them), even
when we do not have shared extents, or all the shared extents were created
by past transactions. It also adds a bit of contention on the spin lock of
the log_csums_range extent io tree of the log root.
This change adds a 'last_reflink_trans' field to the inode to keep track
of the last transaction where a new extent was shared between inodes
(through clone and deduplication operations). It is updated for both the
source and destination inodes of reflink operations whenever a new extent
(created in the current transaction) becomes shared by the inodes. This
field is kept in memory only, not persisted in the inode item, similar
to other existing fields (last_unlink_trans, logged_trans).
When logging checksums for an extent, if the value of 'last_reflink_trans'
is smaller then the current transaction's generation/id, we skip locking
the extent range and deletion of checksums from the log tree, since we
know we do not have new shared extents. This reduces contention on the
log tree's leaves where checksums are stored.
The following script, which uses fio, was used to measure the impact of
this change:
$ cat test-fsync.sh
#!/bin/bash
DEV=/dev/sdk
MNT=/mnt/sdk
MOUNT_OPTIONS="-o ssd"
MKFS_OPTIONS="-d single -m single"
if [ $# -ne 3 ]; then
echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ"
exit 1
fi
NUM_JOBS=$1
FILE_SIZE=$2
FSYNC_FREQ=$3
cat <<EOF > /tmp/fio-job.ini
[writers]
rw=write
fsync=$FSYNC_FREQ
fallocate=none
group_reporting=1
direct=0
bs=64k
ioengine=sync
size=$FILE_SIZE
directory=$MNT
numjobs=$NUM_JOBS
EOF
echo "Using config:"
echo
cat /tmp/fio-job.ini
echo
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The tests were performed for different numbers of jobs, file sizes and
fsync frequency. A qemu VM using kvm was used, with 8 cores (the host has
12 cores, with cpu governance set to performance mode on all cores), 16GiB
of ram (the host has 64GiB) and using a NVMe device directly (without an
intermediary filesystem in the host). While running the tests, the host
was not used for anything else, to avoid disturbing the tests.
The obtained results were the following (the last line of fio's output was
pasted). Starting with 16 jobs is where a significant difference is
observable in this particular setup and hardware (differences highlighted
below). The very small differences for tests with less than 16 jobs are
possibly just noise and random.
**** 1 job, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=23.8MiB/s (24.9MB/s), 23.8MiB/s-23.8MiB/s (24.9MB/s-24.9MB/s), io=1024MiB (1074MB), run=43075-43075msec
after this change:
WRITE: bw=24.4MiB/s (25.6MB/s), 24.4MiB/s-24.4MiB/s (25.6MB/s-25.6MB/s), io=1024MiB (1074MB), run=41938-41938msec
**** 2 jobs, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=37.7MiB/s (39.5MB/s), 37.7MiB/s-37.7MiB/s (39.5MB/s-39.5MB/s), io=2048MiB (2147MB), run=54351-54351msec
after this change:
WRITE: bw=37.7MiB/s (39.5MB/s), 37.6MiB/s-37.6MiB/s (39.5MB/s-39.5MB/s), io=2048MiB (2147MB), run=54428-54428msec
**** 4 jobs, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=67.5MiB/s (70.8MB/s), 67.5MiB/s-67.5MiB/s (70.8MB/s-70.8MB/s), io=4096MiB (4295MB), run=60669-60669msec
after this change:
WRITE: bw=68.6MiB/s (71.0MB/s), 68.6MiB/s-68.6MiB/s (71.0MB/s-71.0MB/s), io=4096MiB (4295MB), run=59678-59678msec
**** 8 jobs, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=128MiB/s (134MB/s), 128MiB/s-128MiB/s (134MB/s-134MB/s), io=8192MiB (8590MB), run=64048-64048msec
after this change:
WRITE: bw=129MiB/s (135MB/s), 129MiB/s-129MiB/s (135MB/s-135MB/s), io=8192MiB (8590MB), run=63405-63405msec
**** 16 jobs, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=78.5MiB/s (82.3MB/s), 78.5MiB/s-78.5MiB/s (82.3MB/s-82.3MB/s), io=16.0GiB (17.2GB), run=208676-208676msec
after this change:
WRITE: bw=110MiB/s (115MB/s), 110MiB/s-110MiB/s (115MB/s-115MB/s), io=16.0GiB (17.2GB), run=149295-149295msec
(+40.1% throughput, -28.5% runtime)
**** 32 jobs, file size 1G, fsync frequency 1 ****
before this change:
WRITE: bw=58.8MiB/s (61.7MB/s), 58.8MiB/s-58.8MiB/s (61.7MB/s-61.7MB/s), io=32.0GiB (34.4GB), run=557134-557134msec
after this change:
WRITE: bw=76.1MiB/s (79.8MB/s), 76.1MiB/s-76.1MiB/s (79.8MB/s-79.8MB/s), io=32.0GiB (34.4GB), run=430550-430550msec
(+29.4% throughput, -22.7% runtime)
**** 64 jobs, file size 512M, fsync frequency 1 ****
before this change:
WRITE: bw=65.8MiB/s (68.0MB/s), 65.8MiB/s-65.8MiB/s (68.0MB/s-68.0MB/s), io=32.0GiB (34.4GB), run=498055-498055msec
after this change:
WRITE: bw=85.1MiB/s (89.2MB/s), 85.1MiB/s-85.1MiB/s (89.2MB/s-89.2MB/s), io=32.0GiB (34.4GB), run=385116-385116msec
(+29.3% throughput, -22.7% runtime)
**** 128 jobs, file size 256M, fsync frequency 1 ****
before this change:
WRITE: bw=54.7MiB/s (57.3MB/s), 54.7MiB/s-54.7MiB/s (57.3MB/s-57.3MB/s), io=32.0GiB (34.4GB), run=599373-599373msec
after this change:
WRITE: bw=121MiB/s (126MB/s), 121MiB/s-121MiB/s (126MB/s-126MB/s), io=32.0GiB (34.4GB), run=271907-271907msec
(+121.2% throughput, -54.6% runtime)
**** 256 jobs, file size 256M, fsync frequency 1 ****
before this change:
WRITE: bw=69.2MiB/s (72.5MB/s), 69.2MiB/s-69.2MiB/s (72.5MB/s-72.5MB/s), io=64.0GiB (68.7GB), run=947536-947536msec
after this change:
WRITE: bw=121MiB/s (127MB/s), 121MiB/s-121MiB/s (127MB/s-127MB/s), io=64.0GiB (68.7GB), run=541916-541916msec
(+74.9% throughput, -42.8% runtime)
**** 512 jobs, file size 128M, fsync frequency 1 ****
before this change:
WRITE: bw=85.4MiB/s (89.5MB/s), 85.4MiB/s-85.4MiB/s (89.5MB/s-89.5MB/s), io=64.0GiB (68.7GB), run=767734-767734msec
after this change:
WRITE: bw=141MiB/s (147MB/s), 141MiB/s-141MiB/s (147MB/s-147MB/s), io=64.0GiB (68.7GB), run=466022-466022msec
(+65.1% throughput, -39.3% runtime)
**** 1024 jobs, file size 128M, fsync frequency 1 ****
before this change:
WRITE: bw=115MiB/s (120MB/s), 115MiB/s-115MiB/s (120MB/s-120MB/s), io=128GiB (137GB), run=1143775-1143775msec
after this change:
WRITE: bw=171MiB/s (180MB/s), 171MiB/s-171MiB/s (180MB/s-180MB/s), io=128GiB (137GB), run=764843-764843msec
(+48.7% throughput, -33.1% runtime)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When syncing the log, we used to update the log root tree without holding
neither the log_mutex of the subvolume root nor the log_mutex of log root
tree.
We used to have two critical sections delimited by the log_mutex of the
log root tree, so in the first one we incremented the log_writers of the
log root tree and on the second one we decremented it and waited for the
log_writers counter to go down to zero. This was because the update of
the log root tree happened between the two critical sections.
The use of two critical sections allowed a little bit more of parallelism
and required the use of the log_writers counter, necessary to make sure
we didn't miss any log root tree update when we have multiple tasks trying
to sync the log in parallel.
However after commit 06989c799f ("Btrfs: fix race updating log root
item during fsync") the log root tree update was moved into a critical
section delimited by the subvolume's log_mutex. Later another commit
moved the log tree update from that critical section into the second
critical section delimited by the log_mutex of the log root tree. Both
commits addressed different bugs.
The end result is that the first critical section delimited by the
log_mutex of the log root tree became pointless, since there's nothing
done between it and the second critical section, we just have an unlock
of the log_mutex followed by a lock operation. This means we can merge
both critical sections, as the first one does almost nothing now, and we
can stop using the log_writers counter of the log root tree, which was
incremented in the first critical section and decremented in the second
criticial section, used to make sure no one in the second critical section
started writeback of the log root tree before some other task updated it.
So just remove the mutex_unlock() followed by mutex_lock() of the log root
tree, as well as the use of the log_writers counter for the log root tree.
This patch is part of a series that has the following patches:
1/4 btrfs: only commit the delayed inode when doing a full fsync
2/4 btrfs: only commit delayed items at fsync if we are logging a directory
3/4 btrfs: stop incremening log_batch for the log root tree when syncing log
4/4 btrfs: remove no longer needed use of log_writers for the log root tree
After the entire patchset applied I saw about 12% decrease on max latency
reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of
ram, using kvm and using a raw NVMe device directly (no intermediary fs on
the host). The test was invoked like the following:
mkfs.btrfs -f /dev/sdk
mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk
dbench -D /mnt/sdk -t 300 8
umount /mnt/dsk
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We are incrementing the log_batch atomic counter of the root log tree but
we never use that counter, it's used only for the log trees of subvolume
roots. We started doing it when we moved the log_batch and log_write
counters from the global, per fs, btrfs_fs_info structure, into the
btrfs_root structure in commit 7237f18336 ("Btrfs: fix tree logs
parallel sync").
So just stop doing it for the log root tree and add a comment over the
field declaration so inform it's used only for log trees of subvolume
roots.
This patch is part of a series that has the following patches:
1/4 btrfs: only commit the delayed inode when doing a full fsync
2/4 btrfs: only commit delayed items at fsync if we are logging a directory
3/4 btrfs: stop incremening log_batch for the log root tree when syncing log
4/4 btrfs: remove no longer needed use of log_writers for the log root tree
After the entire patchset applied I saw about 12% decrease on max latency
reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of
ram, using kvm and using a raw NVMe device directly (no intermediary fs on
the host). The test was invoked like the following:
mkfs.btrfs -f /dev/sdk
mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk
dbench -D /mnt/sdk -t 300 8
umount /mnt/dsk
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging an inode we are committing its delayed items if either the
inode is a directory or if it is a new inode, created in the current
transaction.
We need to do it for directories, since new directory indexes are stored
as delayed items of the inode and when logging a directory we need to be
able to access all indexes from the fs/subvolume tree in order to figure
out which index ranges need to be logged.
However for new inodes that are not directories, we do not need to do it
because the only type of delayed item they can have is the inode item, and
we are guaranteed to always log an up to date version of the inode item:
*) for a full fsync we do it by committing the delayed inode and then
copying the item from the fs/subvolume tree with
copy_inode_items_to_log();
*) for a fast fsync we always log the inode item based on the contents of
the in-memory struct btrfs_inode. We guarantee this is always done since
commit e4545de5b0 ("Btrfs: fix fsync data loss after append write").
So stop running delayed items for a new inodes that are not directories,
since that forces committing the delayed inode into the fs/subvolume tree,
wasting time and adding contention to the tree when a full fsync is not
required. We will only do it in case a fast fsync is needed.
This patch is part of a series that has the following patches:
1/4 btrfs: only commit the delayed inode when doing a full fsync
2/4 btrfs: only commit delayed items at fsync if we are logging a directory
3/4 btrfs: stop incremening log_batch for the log root tree when syncing log
4/4 btrfs: remove no longer needed use of log_writers for the log root tree
After the entire patchset applied I saw about 12% decrease on max latency
reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of
ram, using kvm and using a raw NVMe device directly (no intermediary fs on
the host). The test was invoked like the following:
mkfs.btrfs -f /dev/sdk
mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk
dbench -D /mnt/sdk -t 300 8
umount /mnt/dsk
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Commit 2c2c452b0c ("Btrfs: fix fsync when extend references are added
to an inode") forced a commit of the delayed inode when logging an inode
in order to ensure we would end up logging the inode item during a full
fsync. By committing the delayed inode, we updated the inode item in the
fs/subvolume tree and then later when copying items from leafs modified in
the current transaction into the log tree (with copy_inode_items_to_log())
we ended up copying the inode item from the fs/subvolume tree into the log
tree. Logging an up to date version of the inode item is required to make
sure at log replay time we get the link count fixup triggered among other
things (replay xattr deletes, etc). The test case generic/040 from fstests
exercises the bug which that commit fixed.
However for a fast fsync we don't need to commit the delayed inode because
we always log an up to date version of the inode item based on the struct
btrfs_inode we have in-memory. We started doing this for fast fsyncs since
commit e4545de5b0 ("Btrfs: fix fsync data loss after append write").
So just stop committing the delayed inode if we are doing a fast fsync,
we are only wasting time and adding contention on fs/subvolume tree.
This patch is part of a series that has the following patches:
1/4 btrfs: only commit the delayed inode when doing a full fsync
2/4 btrfs: only commit delayed items at fsync if we are logging a directory
3/4 btrfs: stop incremening log_batch for the log root tree when syncing log
4/4 btrfs: remove no longer needed use of log_writers for the log root tree
After the entire patchset applied I saw about 12% decrease on max latency
reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of
ram, using kvm and using a raw NVMe device directly (no intermediary fs on
the host). The test was invoked like the following:
mkfs.btrfs -f /dev/sdk
mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk
dbench -D /mnt/sdk -t 300 8
umount /mnt/dsk
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It has only 4 uses of a vfs_inode for inode_sub_bytes but unifies the
interface with the non __ prefixed version. Will also makes converting
its callers to btrfs_inode easier.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This brings back an optimization that commit e678934cbe ("btrfs:
Remove unnecessary check from join_running_log_trans") removed, but in
a different form. So it's almost equivalent to a revert.
That commit removed an optimization where we avoid locking a root's
log_mutex when there is no log tree created in the current transaction.
The affected code path is triggered through unlink operations.
That commit was based on the assumption that the optimization was not
necessary because we used to have the following checks when the patch
was authored:
int btrfs_del_dir_entries_in_log(...)
{
(...)
if (dir->logged_trans < trans->transid)
return 0;
ret = join_running_log_trans(root);
(...)
}
int btrfs_del_inode_ref_in_log(...)
{
(...)
if (inode->logged_trans < trans->transid)
return 0;
ret = join_running_log_trans(root);
(...)
}
However before that patch was merged, another patch was merged first which
replaced those checks because they were buggy.
That other patch corresponds to commit 803f0f64d1 ("Btrfs: fix fsync
not persisting dentry deletions due to inode evictions"). The assumption
that if the logged_trans field of an inode had a smaller value then the
current transaction's generation (transid) meant that the inode was not
logged in the current transaction was only correct if the inode was not
evicted and reloaded in the current transaction. So the corresponding bug
fix changed those checks and replaced them with the following helper
function:
static bool inode_logged(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode)
{
if (inode->logged_trans == trans->transid)
return true;
if (inode->last_trans == trans->transid &&
test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) &&
!test_bit(BTRFS_FS_LOG_RECOVERING, &trans->fs_info->flags))
return true;
return false;
}
So if we have a subvolume without a log tree in the current transaction
(because we had no fsyncs), every time we unlink an inode we can end up
trying to lock the log_mutex of the root through join_running_log_trans()
twice, once for the inode being unlinked (by btrfs_del_inode_ref_in_log())
and once for the parent directory (with btrfs_del_dir_entries_in_log()).
This means if we have several unlink operations happening in parallel for
inodes in the same subvolume, and the those inodes and/or their parent
inode were changed in the current transaction, we end up having a lot of
contention on the log_mutex.
The test robots from intel reported a -30.7% performance regression for
a REAIM test after commit e678934cbe ("btrfs: Remove unnecessary check
from join_running_log_trans").
So just bring back the optimization to join_running_log_trans() where we
check first if a log root exists before trying to lock the log_mutex. This
is done by checking for a bit that is set on the root when a log tree is
created and removed when a log tree is freed (at transaction commit time).
Commit e678934cbe ("btrfs: Remove unnecessary check from
join_running_log_trans") was merged in the 5.4 merge window while commit
803f0f64d1 ("Btrfs: fix fsync not persisting dentry deletions due to
inode evictions") was merged in the 5.3 merge window. But the first
commit was actually authored before the second commit (May 23 2019 vs
June 19 2019).
Reported-by: kernel test robot <rong.a.chen@intel.com>
Link: https://lore.kernel.org/lkml/20200611090233.GL12456@shao2-debian/
Fixes: e678934cbe ("btrfs: Remove unnecessary check from join_running_log_trans")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we have extents shared amongst different inodes in the same subvolume,
if we fsync them in parallel we can end up with checksum items in the log
tree that represent ranges which overlap.
For example, consider we have inodes A and B, both sharing an extent that
covers the logical range from X to X + 64KiB:
1) Task A starts an fsync on inode A;
2) Task B starts an fsync on inode B;
3) Task A calls btrfs_csum_file_blocks(), and the first search in the
log tree, through btrfs_lookup_csum(), returns -EFBIG because it
finds an existing checksum item that covers the range from X - 64KiB
to X;
4) Task A checks that the checksum item has not reached the maximum
possible size (MAX_CSUM_ITEMS) and then releases the search path
before it does another path search for insertion (through a direct
call to btrfs_search_slot());
5) As soon as task A releases the path and before it does the search
for insertion, task B calls btrfs_csum_file_blocks() and gets -EFBIG
too, because there is an existing checksum item that has an end
offset that matches the start offset (X) of the checksum range we want
to log;
6) Task B releases the path;
7) Task A does the path search for insertion (through btrfs_search_slot())
and then verifies that the checksum item that ends at offset X still
exists and extends its size to insert the checksums for the range from
X to X + 64KiB;
8) Task A releases the path and returns from btrfs_csum_file_blocks(),
having inserted the checksums into an existing checksum item that got
its size extended. At this point we have one checksum item in the log
tree that covers the logical range from X - 64KiB to X + 64KiB;
9) Task B now does a search for insertion using btrfs_search_slot() too,
but it finds that the previous checksum item no longer ends at the
offset X, it now ends at an of offset X + 64KiB, so it leaves that item
untouched.
Then it releases the path and calls btrfs_insert_empty_item()
that inserts a checksum item with a key offset corresponding to X and
a size for inserting a single checksum (4 bytes in case of crc32c).
Subsequent iterations end up extending this new checksum item so that
it contains the checksums for the range from X to X + 64KiB.
So after task B returns from btrfs_csum_file_blocks() we end up with
two checksum items in the log tree that have overlapping ranges, one
for the range from X - 64KiB to X + 64KiB, and another for the range
from X to X + 64KiB.
Having checksum items that represent ranges which overlap, regardless of
being in the log tree or in the chekcsums tree, can lead to problems where
checksums for a file range end up not being found. This type of problem
has happened a few times in the past and the following commits fixed them
and explain in detail why having checksum items with overlapping ranges is
problematic:
27b9a8122f "Btrfs: fix csum tree corruption, duplicate and outdated checksums"
b84b8390d6 "Btrfs: fix file read corruption after extent cloning and fsync"
40e046acbd "Btrfs: fix missing data checksums after replaying a log tree"
Since this specific instance of the problem can only happen when logging
inodes, because it is the only case where concurrent attempts to insert
checksums for the same range can happen, fix the issue by using an extent
io tree as a range lock to serialize checksum insertion during inode
logging.
This issue could often be reproduced by the test case generic/457 from
fstests. When it happens it produces the following trace:
BTRFS critical (device dm-0): corrupt leaf: root=18446744073709551610 block=30625792 slot=42, csum end range (15020032) goes beyond the start range (15015936) of the next csum item
BTRFS info (device dm-0): leaf 30625792 gen 7 total ptrs 49 free space 2402 owner 18446744073709551610
BTRFS info (device dm-0): refs 1 lock (w:0 r:0 bw:0 br:0 sw:0 sr:0) lock_owner 0 current 15884
item 0 key (18446744073709551606 128 13979648) itemoff 3991 itemsize 4
item 1 key (18446744073709551606 128 13983744) itemoff 3987 itemsize 4
item 2 key (18446744073709551606 128 13987840) itemoff 3983 itemsize 4
item 3 key (18446744073709551606 128 13991936) itemoff 3979 itemsize 4
item 4 key (18446744073709551606 128 13996032) itemoff 3975 itemsize 4
item 5 key (18446744073709551606 128 14000128) itemoff 3971 itemsize 4
(...)
BTRFS error (device dm-0): block=30625792 write time tree block corruption detected
------------[ cut here ]------------
WARNING: CPU: 1 PID: 15884 at fs/btrfs/disk-io.c:539 btree_csum_one_bio+0x268/0x2d0 [btrfs]
Modules linked in: btrfs dm_thin_pool ...
CPU: 1 PID: 15884 Comm: fsx Tainted: G W 5.6.0-rc7-btrfs-next-58 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
RIP: 0010:btree_csum_one_bio+0x268/0x2d0 [btrfs]
Code: c7 c7 ...
RSP: 0018:ffffbb0109e6f8e0 EFLAGS: 00010296
RAX: 0000000000000000 RBX: ffffe1c0847b6080 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffffaa963988 RDI: 0000000000000001
RBP: ffff956a4f4d2000 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000526 R11: 0000000000000000 R12: ffff956a5cd28bb0
R13: 0000000000000000 R14: ffff956a649c9388 R15: 000000011ed82000
FS: 00007fb419959e80(0000) GS:ffff956a7aa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000fe6d54 CR3: 0000000138696005 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
btree_submit_bio_hook+0x67/0xc0 [btrfs]
submit_one_bio+0x31/0x50 [btrfs]
btree_write_cache_pages+0x2db/0x4b0 [btrfs]
? __filemap_fdatawrite_range+0xb1/0x110
do_writepages+0x23/0x80
__filemap_fdatawrite_range+0xd2/0x110
btrfs_write_marked_extents+0x15e/0x180 [btrfs]
btrfs_sync_log+0x206/0x10a0 [btrfs]
? kmem_cache_free+0x315/0x3b0
? btrfs_log_inode+0x1e8/0xf90 [btrfs]
? __mutex_unlock_slowpath+0x45/0x2a0
? lockref_put_or_lock+0x9/0x30
? dput+0x2d/0x580
? dput+0xb5/0x580
? btrfs_sync_file+0x464/0x4d0 [btrfs]
btrfs_sync_file+0x464/0x4d0 [btrfs]
do_fsync+0x38/0x60
__x64_sys_fsync+0x10/0x20
do_syscall_64+0x5c/0x280
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7fb41953a6d0
Code: 48 3d ...
RSP: 002b:00007ffcc86bd218 EFLAGS: 00000246 ORIG_RAX: 000000000000004a
RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fb41953a6d0
RDX: 0000000000000009 RSI: 0000000000040000 RDI: 0000000000000003
RBP: 0000000000040000 R08: 0000000000000001 R09: 0000000000000009
R10: 0000000000000064 R11: 0000000000000246 R12: 0000556cf4b2c060
R13: 0000000000000100 R14: 0000000000000000 R15: 0000556cf322b420
irq event stamp: 0
hardirqs last enabled at (0): [<0000000000000000>] 0x0
hardirqs last disabled at (0): [<ffffffffa96bdedf>] copy_process+0x74f/0x2020
softirqs last enabled at (0): [<ffffffffa96bdedf>] copy_process+0x74f/0x2020
softirqs last disabled at (0): [<0000000000000000>] 0x0
---[ end trace d543fc76f5ad7fd8 ]---
In that trace the tree checker detected the overlapping checksum items at
the time when we triggered writeback for the log tree when syncing the
log.
Another trace that can happen is due to BUG_ON() when deleting checksum
items while logging an inode:
BTRFS critical (device dm-0): slot 81 key (18446744073709551606 128 13635584) new key (18446744073709551606 128 13635584)
BTRFS info (device dm-0): leaf 30949376 gen 7 total ptrs 98 free space 8527 owner 18446744073709551610
BTRFS info (device dm-0): refs 4 lock (w:1 r:0 bw:0 br:0 sw:1 sr:0) lock_owner 13473 current 13473
item 0 key (257 1 0) itemoff 16123 itemsize 160
inode generation 7 size 262144 mode 100600
item 1 key (257 12 256) itemoff 16103 itemsize 20
item 2 key (257 108 0) itemoff 16050 itemsize 53
extent data disk bytenr 13631488 nr 4096
extent data offset 0 nr 131072 ram 131072
(...)
------------[ cut here ]------------
kernel BUG at fs/btrfs/ctree.c:3153!
invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI
CPU: 1 PID: 13473 Comm: fsx Not tainted 5.6.0-rc7-btrfs-next-58 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
RIP: 0010:btrfs_set_item_key_safe+0x1ea/0x270 [btrfs]
Code: 0f b6 ...
RSP: 0018:ffff95e3889179d0 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000051 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffffb7763988 RDI: 0000000000000001
RBP: fffffffffffffff6 R08: 0000000000000000 R09: 0000000000000001
R10: 00000000000009ef R11: 0000000000000000 R12: ffff8912a8ba5a08
R13: ffff95e388917a06 R14: ffff89138dcf68c8 R15: ffff95e388917ace
FS: 00007fe587084e80(0000) GS:ffff8913baa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe587091000 CR3: 0000000126dac005 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
btrfs_del_csums+0x2f4/0x540 [btrfs]
copy_items+0x4b5/0x560 [btrfs]
btrfs_log_inode+0x910/0xf90 [btrfs]
btrfs_log_inode_parent+0x2a0/0xe40 [btrfs]
? dget_parent+0x5/0x370
btrfs_log_dentry_safe+0x4a/0x70 [btrfs]
btrfs_sync_file+0x42b/0x4d0 [btrfs]
__x64_sys_msync+0x199/0x200
do_syscall_64+0x5c/0x280
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7fe586c65760
Code: 00 f7 ...
RSP: 002b:00007ffe250f98b8 EFLAGS: 00000246 ORIG_RAX: 000000000000001a
RAX: ffffffffffffffda RBX: 00000000000040e1 RCX: 00007fe586c65760
RDX: 0000000000000004 RSI: 0000000000006b51 RDI: 00007fe58708b000
RBP: 0000000000006a70 R08: 0000000000000003 R09: 00007fe58700cb61
R10: 0000000000000100 R11: 0000000000000246 R12: 00000000000000e1
R13: 00007fe58708b000 R14: 0000000000006b51 R15: 0000558de021a420
Modules linked in: dm_log_writes ...
---[ end trace c92a7f447a8515f5 ]---
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The inode lookup starting at btrfs_iget takes the full location key,
while only the objectid is used to match the inode, because the lookup
happens inside the given root thus the inode number is unique.
The entire location key is properly set up in btrfs_init_locked_inode.
Simplify the helpers and pass only inode number, renaming it to 'ino'
instead of 'objectid'. This allows to remove temporary variables key,
saving some stack space.
Signed-off-by: David Sterba <dsterba@suse.com>
The main function to lookup a root by its id btrfs_get_fs_root takes the
whole key, while only using the objectid. The value of offset is preset
to (u64)-1 but not actually used until btrfs_find_root that does the
actual search.
Switch btrfs_get_fs_root to use only objectid and remove all local
variables that existed just for the lookup. The actual key for search is
set up in btrfs_get_fs_root, reusing another key variable.
Signed-off-by: David Sterba <dsterba@suse.com>
The set/get token is supposed to cache the last page that was accessed
so it speeds up subsequential access to the eb. It does not make sense
to use that for just one change, which is the case of inode size in
overwrite_item.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that all set/get helpers use the eb from the token, we don't need to
pass it to many btrfs_token_*/btrfs_set_token_* helpers, saving some
stack space.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At btrfs_log_prealloc_extents() we are checking if copy_items() returns a
value greater than 0. That used to happen in the past to signal the caller
that the path given to it was released and reused for other searches, but
as of commit 0e56315ca1 ("Btrfs: fix missing hole after hole punching
and fsync when using NO_HOLES"), the copy_items() function does not have
that behaviour anymore and always returns 0 or a negative value. So just
remove that check at btrfs_log_prealloc_extents(), which the previously
mentioned commit forgot to remove.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
All callers pass the eb::level so we can get read it directly inside the
btrfs_bin_search and key_search.
This is inspired by the work of Marek in U-boot.
CC: Marek Behun <marek.behun@nic.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Filipe Manana