The warning in use_block_rsv is not useful for users and may fill
the logs unnecessarily.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
The deadlock problem happened when running fsstress(a test program in LTP).
Steps to reproduce:
# mkfs.btrfs -b 100M <partition>
# mount <partition> <mnt>
# <Path>/fsstress -p 3 -n 10000000 -d <mnt>
The reason is:
btrfs_direct_IO()
|->do_direct_IO()
|->get_page()
|->get_blocks()
| |->btrfs_delalloc_resereve_space()
| |->btrfs_add_ordered_extent() ------- Add a new ordered extent
|->dio_send_cur_page(page0) -------------- We didn't submit bio here
|->get_page()
|->get_blocks()
|->btrfs_delalloc_resereve_space()
|->flush_space()
|->btrfs_start_ordered_extent()
|->wait_event() ---------- Wait the completion of
the ordered extent that is
mentioned above
But because we didn't submit the bio that is mentioned above, the ordered
extent can not complete, we would wait for its completion forever.
There are two methods which can fix this deadlock problem:
1. submit the bio before we invoke get_blocks()
2. reserve the space before we do dio
Though the 1st is the simplest way, we need modify the code of VFS, and it
is likely to break contiguous requests, and introduce performance regression
for the other filesystems.
So we have to choose the 2nd way.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Sometimes xfstest 83 will fail to remount the scratch device because we've
gotten ourselves so full that we cannot cleanup the orphan items. In this
case check to see if we're doing the orphan cleanup and if we are allow us
to steal our reservation from the global block rsv. With this patch I've
not been able to reproduce the failed mount problem. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
People have been complaining about random ENOSPC errors that will clear up
after a umount or just a given amount of time. Chris was able to reproduce
this with stress.sh and lots of processes and so was I. Basically the
overcommit stuff would really let us get out of hand, in my tests I saw up
to 30 gigs of outstanding reservations with only 2 gigs total of metadata
space. This usually worked out fine but with so much outstanding
reservation the flushing stuff short circuits to make sure we don't hang
forever flushing when we really need ENOSPC. Plus we allocate chunks in
order to alleviate the pressure, but this doesn't actually help us since we
only use the non-allocated area in our over commit logic.
So instead of basing overcommit on the amount of non-allocated space,
instead just do it based on how much total space we have, and then limit it
to the non-allocated space in case we are short on space to spill over into.
This allows us to have the same performance as well as no longer giving
random ENOSPC. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Because of how little we allocate chunks now we can get really tight on
metadata space before we will allocate a new chunk. This resulted in being
unable to add device extents when allocating a new metadata chunk as we did
not have enough space. This is because we were allowed to overcommit too
much metadata without actually making sure we had enough space to make
allocations. The idea behind overcommit is that we are allowed to say "sure
you can have that reservation" when most of the free space is occupied by
reservations, not actual allocations. But in this case where a majority of
the total space is in use by actual allocations we can screw ourselves by
not being able to make real allocations when it matters. So make sure we
have enough real space for our global reserve, and if not then don't allow
overcommitting. Thanks,
Reported-and-tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
There is no lock to protect
fs_info->avail_{data, metadata, system}_alloc_bits,
it may introduce some problem, such as the wrong profile
information, so we add a seqlock to protect them.
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
fs_info->delalloc_bytes is accessed very frequently, so use percpu
counter instead of the u64 variant for it to reduce the lock
contention.
This patch also fixed the problem that we access the variant
without the lock protection.At worst, we would not flush the
delalloc inodes, and just return ENOSPC error when we still have
some free space in the fs.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
The current code of raid attr arry is hard to understand and it is easy to
introduce some problem if we modify the array. So I changed it and made it
more readable.
Cc: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
This'd save us a rbtree search which may become expensive in large filesystem.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
commit d53ba47484
(Btrfs: use commit root when loading free space cache) has remove
the deadlock check, and the related comments can be removed as well.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
If we start running low on metadata space we will try to allocate a chunk,
which could then try to allocate a chunk to add the device entry. The thing
is we allocate a chunk before we try really hard to make the allocation, so
we should be able to find space for the device entry. Add a flag to the
trans handle so we know we're currently allocating a chunk so we can just
bail out if we try to allocate another chunk. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
We may try to flush some dirty pages when there is no enough space to reserve.
But it is possible that this operation fails, in order to get enough space to
reserve successfully, we will sync all the delalloc file. This operation is
safe, we needn't worry about the case that the filesystem goes from r/w to r/o.
because the filesystem should guarantee all the dirty pages have been written
into the disk after it becomes readonly, so the sync operation will do nothing
if the filesystem is already readonly. Though it may waste lots of time,
as a corner case, we needn't care.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Locking and unlocking delayed ref mutex are in the different functions,
and the name of lock functions is not uniform, so the readability is not
so good, this patch optimizes the lock logic and makes it more readable.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
The delayed reference allocation is in the fast path of the IO, so use slabs
to improve the speed of the allocation.
And besides that, it can do check for leaked objects when the module is removed.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Pull btrfs fixes from Chris Mason:
"We've got corner cases for updating i_size that ceph was hitting,
error handling for quotas when we run out of space, a very subtle
snapshot deletion race, a crash while removing devices, and one
deadlock between subvolume creation and the sb_internal code (thanks
lockdep)."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: move d_instantiate outside the transaction during mksubvol
Btrfs: fix EDQUOT handling in btrfs_delalloc_reserve_metadata
Btrfs: fix possible stale data exposure
Btrfs: fix missing i_size update
Btrfs: fix race between snapshot deletion and getting inode
Btrfs: fix missing release of the space/qgroup reservation in start_transaction()
Btrfs: fix wrong sync_writers decrement in btrfs_file_aio_write()
Btrfs: do not merge logged extents if we've removed them from the tree
btrfs: don't try to notify udev about missing devices
When btrfs_qgroup_reserve returned a failure, we were missing a counter
operation for BTRFS_I(inode)->outstanding_extents++, leading to warning
messages about outstanding extents and space_info->bytes_may_use != 0.
Additionally, the error handling code didn't take into account that we
dropped the inode lock which might require more cleanup.
Luckily, all the cleanup code we need is already there and can be shared
with reserve_metadata_bytes, which is exactly what this patch does.
Reported-by: Lev Vainblat <lev@zadarastorage.com>
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
We batch up operations to the extent allocation tree, which allows
us to deal with the recursive nature of using the extent allocation
tree to allocate extents to the extent allocation tree.
It also provides a mechanism to sort and collect extent
operations, which makes it much more efficient to record extents
that are close together.
The delayed extent operations must all be finished before the
running transaction commits, so we have code to make sure and run a few
of the batched operations when closing our transaction handles.
This creates a great deal of contention for the locks in the
delayed extent operation tree, and also contention for the lock on the
extent allocation tree itself. All the extra contention just slows
down the operations and doesn't get things done any faster.
This commit changes things to use a wait queue instead. As procs
want to run the delayed operations, one of them races in and gets
permission to hit the tree, and the others step back and wait for
progress to be made.
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
With the new raid56 code, we want to make sure we're
properly aligning our allocation clusters with -o ssd
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
This builds on David Woodhouse's original Btrfs raid5/6 implementation.
The code has changed quite a bit, blame Chris Mason for any bugs.
Read/modify/write is done after the higher levels of the filesystem have
prepared a given bio. This means the higher layers are not responsible
for building full stripes, and they don't need to query for the topology
of the extents that may get allocated during delayed allocation runs.
It also means different files can easily share the same stripe.
But, it does expose us to incorrect parity if we crash or lose power
while doing a read/modify/write cycle. This will be addressed in a
later commit.
Scrub is unable to repair crc errors on raid5/6 chunks.
Discard does not work on raid5/6 (yet)
The stripe size is fixed at 64KiB per disk. This will be tunable
in a later commit.
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Pull btrfs fixes from Chris Mason:
"It turns out that we had two crc bugs when running fsx-linux in a
loop. Many thanks to Josef, Miao Xie, and Dave Sterba for nailing it
all down. Miao also has a new OOM fix in this v2 pull as well.
Ilya fixed a regression Liu Bo found in the balance ioctls for pausing
and resuming a running balance across drives.
Josef's orphan truncate patch fixes an obscure corruption we'd see
during xfstests.
Arne's patches address problems with subvolume quotas. If the user
destroys quota groups incorrectly the FS will refuse to mount.
The rest are smaller fixes and plugs for memory leaks."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (30 commits)
Btrfs: fix repeated delalloc work allocation
Btrfs: fix wrong max device number for single profile
Btrfs: fix missed transaction->aborted check
Btrfs: Add ACCESS_ONCE() to transaction->abort accesses
Btrfs: put csums on the right ordered extent
Btrfs: use right range to find checksum for compressed extents
Btrfs: fix panic when recovering tree log
Btrfs: do not allow logged extents to be merged or removed
Btrfs: fix a regression in balance usage filter
Btrfs: prevent qgroup destroy when there are still relations
Btrfs: ignore orphan qgroup relations
Btrfs: reorder locks and sanity checks in btrfs_ioctl_defrag
Btrfs: fix unlock order in btrfs_ioctl_rm_dev
Btrfs: fix unlock order in btrfs_ioctl_resize
Btrfs: fix "mutually exclusive op is running" error code
Btrfs: bring back balance pause/resume logic
btrfs: update timestamps on truncate()
btrfs: fix btrfs_cont_expand() freeing IS_ERR em
Btrfs: fix a bug when llseek for delalloc bytes behind prealloc extents
Btrfs: fix off-by-one in lseek
...
We forgot to reset the path lock state to zero after we unlock the path block,
and this can lead to the ASSERT checker in tree unlock API.
Reported-by: Slava Barinov <rayslava@gmail.com>
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
This'd avoid us empty looping.
Say we have only one disk and the metadata raid type will be defaultly DUP,
and we do not need to start from index=0(RAID10) and get over two empty
loops to index=2(DUP).
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
We still need to say we're flushing if we're limit flushing to keep somebody
from coming in and stealing our reservation. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
writeback_inodes_sb(_nr)_if_idle() is re-implemented by replacing down_read()
with down_read_trylock() because
- If ->s_umount is write locked, then the sb is not idle. That is
writeback_inodes_sb(_nr)_if_idle() needn't wait for the lock.
- writeback_inodes_sb(_nr)_if_idle() grabs s_umount lock when it want to start
writeback, it may bring us deadlock problem when doing umount. In order to
fix the problem, ext4 and btrfs implemented their own writeback functions
instead of writeback_inodes_sb(_nr)_if_idle(), but it introduced the redundant
code, it is better to implement a new writeback_inodes_sb(_nr)_if_idle().
The name of these two functions is cumbersome, so rename them to
try_to_writeback_inodes_sb(_nr).
This idea came from Christoph Hellwig.
Some code is from the patch of Kamal Mostafa.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Pull btrfs update from Chris Mason:
"A big set of fixes and features.
In terms of line count, most of the code comes from Stefan, who added
the ability to replace a single drive in place. This is different
from how btrfs normally replaces drives, and is much much much faster.
Josef is plowing through our synchronous write performance. This pull
request does not include the DIO_OWN_WAITING patch that was discussed
on the list, but it has a number of other improvements to cut down our
latencies and CPU time during fsync/O_DIRECT writes.
Miao Xie has a big series of fixes and is spreading out ordered
operations over more CPUs. This improves performance and reduces
contention.
I've put in fixes for error handling around hash collisions. These
are going back to individual stable kernels as I test against them.
Otherwise we have a lot of fixes and cleanups, thanks everyone!
raid5/6 is being rebased against the device replacement code. I'll
have it posted this Friday along with a nice series of benchmarks."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (115 commits)
Btrfs: fix a bug of per-file nocow
Btrfs: fix hash overflow handling
Btrfs: don't take inode delalloc mutex if we're a free space inode
Btrfs: fix autodefrag and umount lockup
Btrfs: fix permissions of empty files not affected by umask
Btrfs: put raid properties into global table
Btrfs: fix BUG() in scrub when first superblock reading gives EIO
Btrfs: do not call file_update_time in aio_write
Btrfs: only unlock and relock if we have to
Btrfs: use tokens where we can in the tree log
Btrfs: optimize leaf_space_used
Btrfs: don't memset new tokens
Btrfs: only clear dirty on the buffer if it is marked as dirty
Btrfs: move checks in set_page_dirty under DEBUG
Btrfs: log changed inodes based on the extent map tree
Btrfs: add path->really_keep_locks
Btrfs: do not mark ems as prealloc if we are writing to them
Btrfs: keep track of the extents original block length
Btrfs: inline csums if we're fsyncing
Btrfs: don't bother copying if we're only logging the inode
...
This confuses and angers lockdep even though it's ok. We don't really need
the lock for free space inodes since only the transaction committer will be
reserving space. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
This happens because writeback_inodes_sb_nr_if_idle does down_read. This
doesn't work for us and it has not been fixed upstream yet, so do it
ourselves and use that instead so we can stop having this stupid long
standing lockup. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Raid properties can be shared among raid calculation code, we can put
them into a global table to keep it simple.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
We forget to release the reserved space in the error path of delalloc
reservatiom, fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
This patch adds some code to disallow operations on the device that
is used as the target for the device replace operation.
Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
This is required for the device replace procedure in a later step.
Two calling functions also had to be changed to have the fs_info
pointer: repair_io_failure() and scrub_setup_recheck_block().
Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
When committing a transaction, we may bail out of running delayed refs
due to ENOSPC, and then abort the current transaction to flip into readonly.
But we'll hit a deadlock on ref head's lock since we forget to release
its lock and other cleanup stuff.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Use WARN rather than printk followed by WARN_ON(1), for conciseness.
A simplified version of the semantic patch that makes this transformation
is as follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@
expression list es;
@@
-printk(
+WARN(1,
es);
-WARN_ON(1);
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Dave gave me an image of a very full file system that would abort the
transaction because it ran out of space while committing the transaction.
This is because we would think there was plenty of room to create a snapshot
even though the global reserve was not full. This happens because we
calculate the global reserve size before we unpin any space, so after we
unpin the space we allow reservations to occur even though we haven't
reserved all of the space for our global reserve. Fix this by adding to the
global reserve while unpinning in order to make sure we always have enough
space to do our work. With this patch we no longer end up with an aborted
transaction, we return ENOSPC properly to the person trying to create the
snapshot. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
In some places(such as: evicting inode), we just can not flush the reserved
space of delalloc, flushing the delayed directory index and delayed inode
is OK, but we don't try to flush those things and just go back when there is
no enough space to be reserved. This patch fixes this problem.
We defined 3 types of the flush operations: NO_FLUSH, FLUSH_LIMIT and FLUSH_ALL.
If we can in the transaction, we should not flush anything, or the deadlock
would happen, so use NO_FLUSH. If we flushing the reserved space of delalloc
would cause deadlock, use FLUSH_LIMIT. In the other cases, FLUSH_ALL is used,
and we will flush all things.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
The comment is not coincident with the code. Fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
div_factor{_fine} has been implemented for two times, cleanup it.
And I move them into a independent file named math.h because they are
common math functions.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
"Whether" is misspelled in various comments across the tree; this
fixes them. No code changes.
Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
I don't think we have the same problem that this was supposed to fix
originally since we can allocate chunks in the enospc path now. This code
is causing us to constantly commit the transaction as we get close to using
all of our available space in our currently allocated chunks, instead of
allocating another chunk and carrying on with life, which is not nice for
performance. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Everytime we write out dirty pages we search for an offset in the tree,
convert the bits in the state, and then when we wait we search for the
offset again and clear the bits. So for every dirty range in the io tree we
are doing 4 rb searches, which is suboptimal. With this patch we are only
doing 2 searches for every cycle (modulo weird things happening). Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Running delayed refs is faster than running delalloc, so lets do that first
to try and reclaim space. This makes my fs_mark test about 20% faster.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Call btrfs_abort_transaction as early as possible when an error
condition is detected, that way the line number reported is useful
and we're not clueless anymore which error path led to the abort.
Signed-off-by: David Sterba <dsterba@suse.cz>
Everybody is just making stuff up, and it's just used to see if we really do
need to alloc a chunk, and since we do this when we already know we really
do it's just a waste of space. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
So we have lots of places where we try to preallocate chunks in order to
make sure we have enough space as we make our allocations. This has
historically meant that we're constantly tweaking when we should allocate a
new chunk, and historically we have gotten this horribly wrong so we way
over allocate either metadata or data. To try and keep this from happening
we are going to make it so that the block group item insertion is done out
of band at the end of a transaction. This will allow us to create chunks
even if we are trying to make an allocation for the extent tree. With this
patch my enospc tests run faster (didn't expect this) and more efficiently
use the disk space (this is what I wanted). Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
I noticed I was seeing large lags when running my torrent test in a vm on my
laptop. While trying to make it lag less I noticed that our overcommit math
was taking into account the number of bytes we wanted to reclaim, not the
number of bytes we actually wanted to allocate, which means we wouldn't
overcommit as often. This patch fixes the overcommit math and makes
shrink_delalloc() use that logic so that it will stop looping faster. We
still have pretty high spikes of latency, but the test now takes 3 minutes
less time (about 5% faster). Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Mitch reported a problem where you could get an ENOSPC error when untarring
a kernel git tree onto a 16gb file system with compress-force=zlib. This is
because compression is a huge pain, it will return from ->writepages()
without having actually created any ordered extents. To get around this we
check to see if the async submit counter is up, and if it is wait until it
drops to 0 before doing our normal ordered wait dance. With this patch I
can now untar a kernel git tree onto a 16gb file system without getting
ENOSPC errors. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
We should insert/update 6 items(root ref, root backref, dir item, dir index,
root item and parent inode) when creating a snapshot, not 5 items, fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Sometimes we need choose the method of the reservation according to the type
of the block reservation, such as the reservation for the delayed inode update.
Now we identify the type just by comparing the address of the reservation
variants, it is very ugly if it is a temporary one because we need compare it
with all the common reservation variants. So we add a new "type" field to keep
the type the reservation variants.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
We will stop and restart a transaction every time we move to a different leaf
when truncating a file. This is for enospc reasons, but really we could
probably get away with doing this a little better by actually working until we
hit an ENOSPC. So add a ->failfast flag to the block_rsv and set it when we do
truncates which will fail as soon as the block rsv runs out of space, and then
at that point we can stop and restart the transaction and refill the block rsv
and carry on. This will make rm'ing of a file with lots of extents a bit
faster. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Swinging this pendulum back the other way. We've been allocating chunks up
to 2% of the disk no matter how much we actually have allocated. So instead
fix this calculation to only allocate chunks if we have more than 80% of the
space available allocated. Please test this as it will likely cause all
sorts of ENOSPC problems to pop up suddenly. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Daniel Blueman reported a bug with fio+balance on a ramdisk setup.
Basically what happens is the balance relocates a tree block which will drop
the implicit refs for all of its children and adds a full backref. Once the
block is relocated we have to add the implicit refs back, so when we cow the
block again we add the implicit refs for its children back. The problem
comes when the original drop ref doesn't get run before we add the implicit
refs back. The delayed ref stuff will specifically prefer ADD operations
over DROP to keep us from freeing up an extent that will have references to
it, so we try to add the implicit ref before it is actually removed and we
panic. This worked fine before because the add would have just canceled the
drop out and we would have been fine. But the backref walking work needs to
be able to freeze the delayed ref stuff in time so we have this ever
increasing sequence number that gets attached to all new delayed ref updates
which makes us not merge refs and we run into this issue.
So to fix this we need to merge delayed refs. So everytime we run a
clustered ref we need to try and merge all of its delayed refs. The backref
walking stuff locks the delayed ref head before processing, so if we have it
locked we are safe to merge any refs inside of the sequence number. If
there is no sequence number we can merge all refs. Doing this not only
fixes our bug but keeps the delayed ref code from adding and removing
useless refs and batching together multiple refs into one search instead of
one search per delayed ref, which will really help our commit times. I ran
this with Daniels test and 276 and I haven't seen any problems. Thanks,
Reported-by: Daniel J Blueman <daniel@quora.org>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
With commit
commit d1270cd91f
Author: Arne Jansen <sensille@gmx.net>
Date: Tue Sep 13 15:16:43 2011 +0200
Btrfs: put back delayed refs that are too new
I added a window where the delayed_ref's head->ref_mod code can diverge
from the sum of the remaining refs, because we release the head->mutex
in the middle. This leads to btrfs_lookup_extent_info returning wrong
numbers. This patch fixes this by adjusting the head's ref_mod with each
delayed ref we run.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Arne was complaining about the space cache having mismatching generation
numbers when debugging a deadlock. This is because we can run out of space
in our preallocated range for our space cache if you have a pretty
fragmented amount of space in your pinned space. So just increase the
amount of space we preallocate for space cache so we can be sure to have
enough space. This will only really affect data ranges since their the only
chunks that end up larger than 256MB. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
Commit a168650c introduced a waiting mechanism to prevent busy waiting in
btrfs_run_delayed_refs. This can deadlock with btrfs_run_ordered_operations,
where a tree_mod_seq is held while waiting for the io to complete, while
the end_io calls btrfs_run_delayed_refs.
This whole mechanism is unnecessary. If not enough runnable refs are
available to satisfy count, just return as count is more like a guideline
than a strict requirement.
In case we have to run all refs, commit transaction makes sure that no
other threads are working in the transaction anymore, so we just assert
here that no refs are blocked.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
For backref walking, we've introduce delayed ref's sequence. However,
it changes our preallocation behavior.
The story is that when we preallocate an extent and then mark it written
piece by piece, the ideal case should be that we don't need to COW the
extent, which is why we use 'preallocate'.
But we may not make use of preallocation, since when we check for cross refs on
the extent, we may have two ref entries which have the same content except
the sequence value, and we recognize them as cross refs and do COW to allocate
another extent.
So we end up with several pieces of space instead of an whole extent.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Inodes always allocate free space with BTRFS_BLOCK_GROUP_DATA type,
which means every inode has the same BTRFS_I(inode)->free_space pointer.
This shrinks struct btrfs_inode by 4 bytes (or 8 bytes on 64 bits).
Signed-off-by: Li Zefan <lizefan@huawei.com>
Block group has ro attributes, make dump_space_info show it.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Here is the whole story:
1)
A free space cache consists of two parts:
o free space cache inode, which is special becase it's stored in root tree.
o free space info, which is stored as the above inode's file data.
But we only build up another new inode and does not flush its free space info
onto disk when we _clear and setup_ free space cache, and this ends up with
that the block group cache's cache_state remains DC_SETUP instead of DC_WRITTEN.
And holding DC_SETUP means that we will not truncate this free space cache inode,
which means the disk offset of its file extent will remain _unchanged_ at least
until next transaction finishes committing itself.
2)
We can set a block group readonly when we relocate the block group.
However,
if the readonly block group covers the disk offset where our free space cache
inode is going to write, it will force the free space cache inode into
cow_file_range() and it'll end up hitting a BUG_ON.
3)
Due to the above analysis, we fix this bug by adding the missing dirty flag.
4)
However, it's not over, there is still another case, nospace_cache.
With nospace_cache, we do not want to set dirty flag, instead we just truncate
free space cache inode and bail out with setting cache state DC_WRITTEN.
We can benifit from it since it saves us another 'pre-allocation' part which
usually costs a lot.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
During disk balance, we prealloc new file extent for file data relocation,
but we may fail in 'no available space' case, and it leads to flipping btrfs
into readonly.
It is not necessary to bail out and abort transaction since we do have several
ways to rescue ourselves from ENOSPC case.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Since root can be fetched via BTRFS_I macro directly, we can save an args
for btrfs_is_free_space_inode().
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
So shrink_delalloc has grown all sorts of cruft over the years thanks to
many reworkings of how we track enospc. What happens now as we fill up the
disk is we will loop for freaking ever hoping to reclaim a arbitrary amount
of space of metadata, this was from when everybody flushed at the same time.
Now we only have people flushing one at a time. So instead of trying to
reclaim a huge amount of space, just try to flush a decent chunk of space,
and stop looping as soon as we have enough free space to satisfy our
reservation. This makes xfstests 224 go much faster. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
There is weird logic I had to put in place to make sure that when we were
adding csums that we'd used the delalloc block rsv instead of the global
block rsv. Part of this meant that we had to free up our transaction
reservation before we ran the delayed refs since csum deletion happens
during the delayed ref work. The problem with this is that when we release
a reservation we will add it to the global reserve if it is not full in
order to keep us going along longer before we have to force a transaction
commit. By releasing our reservation before we run delayed refs we don't
get the opportunity to drain down the global reserve for the work we did, so
we won't refill it as often. This isn't a problem per-se, it just results
in us possibly committing transactions more and more often, and in rare
cases could cause those WARN_ON()'s to pop in use_block_rsv because we ran
out of space in our block rsv.
This also helps us by holding onto space while the delayed refs run so we
don't end up with as many people trying to do things at the same time, which
again will help us not force commits or hit the use_block_rsv warnings.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Those crazy gentoo guys have been complaining about ENOSPC errors on their
portage volumes. This is because doing things like untar tends to create
lots of new files which will soak up all the reservation space in the
delayed inodes. Usually this gets papered over by the fact that we will try
and commit the transaction, however if this happens in the wrong spot or we
choose not to commit the transaction you will be screwed. So add the
ability to expclitly flush delayed inodes to free up space. Please test
this out guys to make sure it works since as usual I cannot reproduce.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Like block reserves, reserve a small piece of space on each
transaction start and for delalloc. These are the hooks that
can actually return EDQUOT to the user.
The amount of space reserved is tracked in the transaction
handle.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Normally delayed refs get processed in ascending bytenr order. This
correlates in most cases to the order added. To expose dependencies
on this order, we start to process the tree in the middle instead of
the beginning.
This code is only effective when SCRAMBLE_DELAYED_REFS is defined.
Signed-off-by: Arne Jansen <sensille@gmx.net>
We've got two mechanisms both required for reliable backref resolving (tree
mod log and holding back delayed refs). You cannot make use of one without
the other. So instead of requiring the user of this mechanism to setup both
correctly, we join them into a single interface.
Additionally, we stop inserting non-blockers into fs_info->tree_mod_seq_list
as we did before, which was of no value.
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
We track two conditions to decide if we should sleep while waiting for more
delayed refs, the number of delayed refs (num_refs) and the first entry in
the list of blockers (first_seq).
When we suspect staleness, we save num_refs and do one more cycle. If
nothing changes, we then save first_seq for later comparison and do
wait_event. We ought to save first_seq the very same moment we're saving
num_refs. Otherwise we cannot be sure that nothing has changed and we might
start waiting when we shouldn't, which could lead to starvation.
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
Miao pointed this out while I was working on an orphan problem that messing
with a bitfield where different ranges are protected by different locks
doesn't work out right. Turns out we've been doing this forever where we
have different parts of the bit field protected by either no lock at all or
different locks which could cause all sorts of weird problems including the
issue I was hitting. So instead make a runtime_flags thing that we use the
normal bit operations on that are all atomic so we can keep having our
no/different locking for the different flags and then make force_compress
it's own thing so it can be treated normally. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Three callers of btrfs_free_tree_block or btrfs_alloc_tree_block passed
parameter for_cow = 1. In fact, these two functions should never mark
their tree modification operations as for_cow, because they can change
the number of blocks referenced by a tree.
Hence, we remove the extra for_cow parameter from these functions and
make them pass a zero down.
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
It confuses Smatch that we use two names for the same lock. Plus the
shorter name is nicer. This doesn't change how the code works, it's
just a cleanup.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
verify_parent_transid needs to lock the extent range to make
sure no IO is underway, and so it can safely clear the
uptodate bits if our checks fail.
But, a few callers are using it with spinlocks held. Most
of the time, the generation numbers are going to match, and
we don't want to switch to a blocking lock just for the error
case. This adds an atomic flag to verify_parent_transid,
and changes it to return EAGAIN if it needs to block to
properly verifiy things.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
may_commit_transaction() calls
spin_lock(&space_info->lock);
spin_lock(&delayed_rsv->lock);
and update_global_block_rsv() calls
spin_lock(&block_rsv->lock);
spin_lock(&sinfo->lock);
Lockdep complains about this at run time.
Everywhere except in update_global_block_rsv(), the space_info lock is
the outer lock, therefore the locking order in update_global_block_rsv()
is changed.
Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
It is basically a good thing if we are interruptible when waiting for
free space, but the generality in which it is implemented currently
leads to system calls being interruptible that are not documented this
way. For example git can't handle interrupted unlink(), leading to
corrupt repos under space pressure.
Instead we raise the bar to only be interruptible by SIGKILL.
Thanks to David Sterba for suggesting this.
Signed-off-by: Arne Jansen <sensille@gmx.net>
The caller expects this function to return with the lock held and
releases it immediately on error.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
A user reported that booting his box up with btrfs root on 3.4 was way
slower than on 3.3 because I removed the ideal caching code. It turns out
that we don't load the free space cache if we're in a commit for deadlock
reasons, but since we're reading the cache and it hasn't changed yet we are
safe reading the inode and free space item from the commit root, so do that
and remove all of the deadlock checks so we don't unnecessarily skip loading
the free space cache. The user reported this fixed the slowness. Thanks,
Tested-by: Calvin Walton <calvin.walton@kepstin.ca>
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This fixes a regression introduced by fc67c450. spin_is_locked() always
returns 0 on UP kernels, which caused assert in get_restripe_target() to
be fired on every call from btrfs_reduce_alloc_profile() on UP systems.
Remove it completely for now, it's not clear if it's going to be needed
in future.
Reported-by: Bobby Powers <bobbypowers@gmail.com>
Reported-by: Mitch Harder <mitch.harder@sabayonlinux.org>
Tested-by: Mitch Harder <mitch.harder@sabayonlinux.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This reverts commit 5500cdbe14.
We've had a number of complaints of early enospc that bisect down
to this patch. We'll hae to fix the reservations differently.
CC: stable@kernel.org
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This deadlock comes from xfstests 251.
We'll hold the chunk_mutex throughout the whole of a chunk allocation.
But if we find that we've used up system chunk space, we need to allocate a
new system chunk, but this will lead to a recursion of chunk allocation and end
up with a deadlock on chunk_mutex.
So instead we need to allocate the system chunk first if we find we're in ENOSPC.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
o For space info, the type of space info is useful for debug.
o For transaction handle, its transid is useful.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Currently if we don't have enough space allocated we go ahead and loop
though devices in the hopes of finding enough space for a chunk of the
*same* type as the one we are trying to relocate. The problem with that
is that if we are trying to restripe the chunk its target type can be
more relaxed than the current one (eg require less devices or less
space). So, when restriping, run checks against the target profile
instead of the current one.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Add __get_block_group_index() helper to be able to derive block group
index from an arbitary set of flags. Implement get_block_group_index()
in terms of it.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Header file is not a good place to define functions. This also moves a
call to alloc_profile_is_valid() down the stack and removes a redundant
check from __btrfs_alloc_chunk() - alloc_profile_is_valid() takes it
into account.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
"0" is a valid value for an on-disk chunk profile, but it is not a valid
extended profile. (We have a separate bit for single chunks in extended
case)
Also rename it to alloc_profile_is_valid() for clarity.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Add functions to abstract the conversion between chunk and extended
allocation profile formats and switch everybody to use them.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This has been causing a lot of confusion for quite a while now and a lot
of users were surprised by this (some of them were even stuck in a
ENOSPC situation which they couldn't easily get out of). The addition
of restriper gives users a clear choice between raid0 and drive concat
setup so there's absolutely no excuse for us to keep doing this.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Because btrfs cow's we can end up with extent buffers that are no longer
necessary just sitting around in memory. So instead of evicting these pages, we
could end up evicting things we actually care about. Thus we have
free_extent_buffer_stale for use when we are freeing tree blocks. This will
make it so that the ref for the eb being in the radix tree is dropped as soon as
possible and then is freed when the refcount hits 0 instead of waiting to be
released by releasepage. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We have been passing nothing but (u64)-1 to find_free_extent for search_end in
all of the callers, so it's completely useless, and we've always been passing 0
in as search_start, so just remove them as function arguments and move
search_start into find_free_extent. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
This is a relic from before we had the disk space cache and it was to make
bootup times when you had btrfs as root not be so damned slow. Now that we have
the disk space cache this isn't a problem anymore and really having this code
casues uneeded fragmentation and complexity, so just remove it. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
btrfs currently handles most errors with BUG_ON. This patch is a work-in-
progress but aims to handle most errors other than internal logic
errors and ENOMEM more gracefully.
This iteration prevents most crashes but can run into lockups with
the page lock on occasion when the timing "works out."
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Commit cb1b69f4 (Btrfs: forced readonly when btrfs_drop_snapshot() fails)
made btrfs_drop_snapshot return void because there were no callers checking
the return value. That is the wrong order to handle error propogation since
the caller will have no idea that an error has occured and continue on
as if nothing went wrong.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
When doing IO with large amounts of data fragmentation, the global block
reserve calulations are too low. This increases them to avoid
ENOSPC crashes.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
A user reported a bug of btrfs's trim, that is we will trim 0 bytes
after a device delete.
The reproducer:
$ mkfs.btrfs disk1
$ mkfs.btrfs disk2
$ mount disk1 /mnt
$ fstrim -v /mnt
$ btrfs device add disk2 /mnt
$ btrfs device del disk1 /mnt
$ fstrim -v /mnt
This is because after we delete the device, the block group may start from
a non-zero place, which will confuse trim to discard nothing.
Reported-by: Lutz Euler <lutz.euler@freenet.de>
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
When we did sysbench test for inline files, enospc error happened easily though
there was lots of free disk space which could be allocated for new chunks.
Reproduce steps:
# mkfs.btrfs -b $((2 * 1024 * 1024 * 1024)) <test partition>
# mount <test partition> /mnt
# ulimit -n 102400
# cd /mnt
# sysbench --num-threads=1 --test=fileio --file-num=81920 \
> --file-total-size=80M --file-block-size=1K --file-io-mode=sync \
> --file-test-mode=seqwr prepare
# sysbench --num-threads=1 --test=fileio --file-num=81920 \
> --file-total-size=80M --file-block-size=1K --file-io-mode=sync \
> --file-test-mode=seqwr run
<soon later, BUG_ON() was triggered by enospc error>
The reason of this bug is:
Now, we can reserve space which is larger than the free space in the chunks if
we have enough free disk space which can be used for new chunks. By this way,
the space allocator should allocate a new chunk by force if there is no free
space in the free space cache. But there are two wrong checks which break this
operation.
One is
if (ret == -ENOSPC && num_bytes > min_alloc_size)
in btrfs_reserve_extent(), it is wrong, we should try to allocate a new chunk
even we fail to allocate free space by minimum allocable size.
The other is
if (space_info->force_alloc)
force = space_info->force_alloc;
in do_chunk_alloc(). It makes the allocator ignore CHUNK_ALLOC_FORCE If someone
sets ->force_alloc to CHUNK_ALLOC_LIMITED, and makes the enospc error happen.
Fix these two wrong checks. Especially the second one, we fix it by changing
the value of CHUNK_ALLOC_LIMITED and CHUNK_ALLOC_FORCE, and make
CHUNK_ALLOC_FORCE greater than CHUNK_ALLOC_LIMITED since CHUNK_ALLOC_FORCE has
higher priority. And if the value which is passed in by the caller is greater
than ->force_alloc, use the passed value.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
system chunks by default are very small. This makes them slightly
larger and also fixes the conditional checks to make sure we don't
allocate a billion of them at once.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
I was using i_mutex for this, but we're getting bogus lockdep warnings by doing
that and theres no real way to get rid of those, so just stop using i_mutex to
protect delalloc metadata reservations and use a delalloc mutex instead. This
shouldn't be contended often at all, only if you are writing and mmap writing to
the file at the same time. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
This in addition to a script in my btrfs-tracing tree will help track down space
leaks when we're getting space left over in block groups on umount. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
I used these tracepoints when figuring out what the cluster stuff was doing, so
add them to mainline in case we need to profile this stuff again. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Profile changing is done by launching a balance with
BTRFS_BALANCE_CONVERT bits set and target fields of respective
btrfs_balance_args structs initialized. Profile reducing code in this
case will pick restriper's target profile if it's available instead of
doing a blind reduce. If target profile is not yet available it goes
back to a plain reduce.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Every caller of do_chunk_alloc() feeds it the reduced allocation
profile, so stop trying to reduce it one more time. Instead check the
validity of the passed profile.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Currently when new chunks are created respective avail_alloc_bits field
is updated to reflect profiles of all chunks present in the system.
However when chunks are removed profile bits are never cleared.
This patch clears profile bit of respective avail_alloc_bits field when
the last chunk with that profile is removed. Restriper needs this to
properly operate when "downgrading".
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Right now on-disk BTRFS_BLOCK_GROUP_* profile bits are used for
avail_{data,metadata,system}_alloc_bits fields, which gather info about
available allocation profiles in the FS. When chunk is created or read
from disk, its profile is OR'ed with the corresponding avail_alloc_bits
field. Since SINGLE is denoted by 0 in the on-disk format, currently
there is no way to tell when such chunks become avaialble. Restriper
needs that information, so add a separate bit for SINGLE profile.
This bit is going to be in-memory only, it should never be written out
to disk, so it's not a disk format change. However to avoid remappings
in future, reserve corresponding on-disk bit.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Chunk's type and profile are encoded in u64 flags field. Introduce
masks to easily access them. Also fix the type of BTRFS_BLOCK_GROUP_*
constants, it should be ULL.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
A bug was triggered while using seed device:
# mkfs.btrfs /dev/loop1
# btrfstune -S 1 /dev/loop1
# mount -o /dev/loop1 /mnt
# btrfs dev add /dev/loop2 /mnt
btrfs: block rsv returned -28
------------[ cut here ]------------
WARNING: at fs/btrfs/extent-tree.c:5969 btrfs_alloc_free_block+0x166/0x396 [btrfs]()
...
Call Trace:
...
[<f7b7c31c>] btrfs_cow_block+0x101/0x147 [btrfs]
[<f7b7eaa6>] btrfs_search_slot+0x1b8/0x55f [btrfs]
[<f7b7f844>] btrfs_insert_empty_items+0x42/0x7f [btrfs]
[<f7b7f8c1>] btrfs_insert_item+0x40/0x7e [btrfs]
[<f7b8ac02>] btrfs_make_block_group+0x243/0x2aa [btrfs]
[<f7bb3f53>] __btrfs_alloc_chunk+0x672/0x70e [btrfs]
[<f7bb41ff>] init_first_rw_device+0x77/0x13c [btrfs]
[<f7bb5a62>] btrfs_init_new_device+0x664/0x9fd [btrfs]
[<f7bbb65a>] btrfs_ioctl+0x694/0xdbe [btrfs]
[<c04f55f7>] do_vfs_ioctl+0x496/0x4cc
[<c04f5660>] sys_ioctl+0x33/0x4f
[<c07b9edf>] sysenter_do_call+0x12/0x38
---[ end trace 906adac595facc7d ]---
Since seed device is readonly, there's no usable space in the filesystem.
Afterwards we add a sprout device to it, and the kernel creates a METADATA
block group and a SYSTEM block group where comes free space we can reserve,
but we still get revervation failure because the global block_rsv hasn't
been updated accordingly.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
We store the allocation start and length twice in ins, once right
after the other, but with intervening calls that may prevent the
duplicate from being optimized out by the compiler. Remove one of the
assignments.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Since the clustered allocation may be taking extents from a different
block group, there's no point in spin-locking and testing the current
block group free space before attempting to allocate space from a
cluster, even more so when we might refrain from even trying the
cluster in the current block group because, after the cluster was set
up, not enough free space remained. Furthermore, cluster creation
attempts fail fast when the block group doesn't have enough free
space, so the test was completely superfluous.
I've move the free space test past the cluster allocation attempt,
where it is more useful, and arranged for a cluster in the current
block group to be released before trying an unclustered allocation,
when we reach the LOOP_NO_EMPTY_SIZE stage, so that the free space in
the cluster stands a chance of being combined with additional free
space in the block group so as to succeed in the allocation attempt.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The chunk allocation code has tried to keep a pretty tight lid on creating new
metadata chunks. This is partially because in the past the reservation
code didn't give us an accurate idea of how much space was being used.
The new code is much more accurate, so we're able to get rid of some of these
checks.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs tries to batch extent allocation tree changes to improve performance
and reduce metadata trashing. But it doesn't allocate new metadata chunks
while it is doing allocations for the extent allocation tree.
This commit changes the delayed refence code to do chunk allocations if we're
getting low on room. It prevents crashes and improves performance.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Now that we may be holding back delayed refs for a limited period, we
might end up having no runnable delayed refs. Without this commit, we'd
do busy waiting in that thread until another (runnable) ref arives.
Instead, we're detecting this situation and use a waitqueue, such that
we only try to run more refs after
a) another runnable ref was added or
b) delayed refs are no longer held back
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
When processing a delayed ref, first check if there are still old refs in
the process of being added. If so, put this ref back to the tree. To avoid
looping on this ref, choose a newer one in the next loop.
btrfs_find_ref_cluster has to take care of that.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
Add a for_cow parameter to add_delayed_*_ref and pass the appropriate value
from every call site. The for_cow parameter will later on be used to
determine if a ref will change anything with respect to qgroups.
Delayed refs coming from relocation are always counted as for_cow, as they
don't change subvol quota.
Also pass in the fs_info for later use.
btrfs_find_all_roots() will use this as an optimization, as changes that are
for_cow will not change anything with respect to which root points to a
certain leaf. Thus, we don't need to add the current sequence number to
those delayed refs.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: unplug every once and a while
Btrfs: deal with NULL srv_rsv in the delalloc inode reservation code
Btrfs: only set cache_generation if we setup the block group
Btrfs: don't panic if orphan item already exists
Btrfs: fix leaked space in truncate
Btrfs: fix how we do delalloc reservations and how we free reservations on error
Btrfs: deal with enospc from dirtying inodes properly
Btrfs: fix num_workers_starting bug and other bugs in async thread
BTRFS: Establish i_ops before calling d_instantiate
Btrfs: add a cond_resched() into the worker loop
Btrfs: fix ctime update of on-disk inode
btrfs: keep orphans for subvolume deletion
Btrfs: fix inaccurate available space on raid0 profile
Btrfs: fix wrong disk space information of the files
Btrfs: fix wrong i_size when truncating a file to a larger size
Btrfs: fix btrfs_end_bio to deal with write errors to a single mirror
* 'for-linus-3.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
btrfs: lower the dirty balance poll interval
A user reported a problem booting into a new kernel with the old format inodes.
He was panicing in cow_file_range while writing out the inode cache. This is
because if the block group is not cached we'll just skip writing out the cache,
however if it gets dirtied again in the same transaction and it finished caching
we'd go ahead and write it out, but since we set cache_generation to the transid
we think we've already truncated it and will just carry on, running into
cow_file_range and blowing up. We need to make sure we only set
cache_generation if we've done the truncate. The user tested this patch and
verified that the panic no longer occured. Thanks,
Reported-and-Tested-by: Klaus Bitto <klaus.bitto@gmail.com>
Signed-off-by: Josef Bacik <josef@redhat.com>
Running xfstests 269 with some tracing my scripts kept spitting out errors about
releasing bytes that we didn't actually have reserved. This took me down a huge
rabbit hole and it turns out the way we deal with reserved_extents is wrong,
we need to only be setting it if the reservation succeeds, otherwise the free()
method will come in and unreserve space that isn't actually reserved yet, which
can lead to other warnings and such. The math was all working out right in the
end, but it caused all sorts of other issues in addition to making my scripts
yell and scream and generally make it impossible for me to track down the
original issue I was looking for. The other problem is with our error handling
in the reservation code. There are two cases that we need to deal with
1) We raced with free. In this case free won't free anything because csum_bytes
is modified before we dro the lock in our reservation path, so free rightly
doesn't release any space because the reservation code may be depending on that
reservation. However if we fail, we need the reservation side to do the free at
that point since that space is no longer in use. So as it stands the code was
doing this fine and it worked out, except in case #2
2) We don't race with free. Nobody comes in and changes anything, and our
reservation fails. In this case we didn't reserve anything anyway and we just
need to clean up csum_bytes but not free anything. So we keep track of
csum_bytes before we drop the lock and if it hasn't changed we know we can just
decrement csum_bytes and carry on.
Because of the case where we can race with free()'s since we have to drop our
spin_lock to do the reservation, I'm going to serialize all reservations with
the i_mutex. We already get this for free in the heavy use paths, truncate and
file write all hold the i_mutex, just needed to add it to page_mkwrite and
various ioctl/balance things. With this patch my space leak scripts no longer
scream bloody murder. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: drop spin lock when memory alloc fails
Btrfs: check if the to-be-added device is writable
Btrfs: try cluster but don't advance in search list
Btrfs: try to allocate from cluster even at LOOP_NO_EMPTY_SIZE
When we find an existing cluster, we switch to its block group as the
current block group, possibly skipping multiple blocks in the process.
Furthermore, under heavy contention, multiple threads may fail to
allocate from a cluster and then release just-created clusters just to
proceed to create new ones in a different block group.
This patch tries to allocate from an existing cluster regardless of its
block group, and doesn't switch to that group, instead proceeding to
try to allocate a cluster from the group it was iterating before the
attempt.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If we reach LOOP_NO_EMPTY_SIZE, we won't even try to use a cluster that
others might have set up. Odds are that there won't be one, but if
someone else succeeded in setting it up, we might as well use it, even
if we don't try to set up a cluster again.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: fix meta data raid-repair merge problem
Btrfs: skip allocation attempt from empty cluster
Btrfs: skip block groups without enough space for a cluster
Btrfs: start search for new cluster at the beginning
Btrfs: reset cluster's max_size when creating bitmap
Btrfs: initialize new bitmaps' list
Btrfs: fix oops when calling statfs on readonly device
Btrfs: Don't error on resizing FS to same size
Btrfs: fix deadlock on metadata reservation when evicting a inode
Fix URL of btrfs-progs git repository in docs
btrfs scrub: handle -ENOMEM from init_ipath()
If we don't have a cluster, don't bother trying to allocate from it,
jumping right away to the attempt to allocate a new cluster.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We test whether a block group has enough free space to hold the
requested block, but when we're doing clustered allocation, we can
save some cycles by testing whether it has enough room for the cluster
upfront, otherwise we end up attempting to set up a cluster and
failing. Only in the NO_EMPTY_SIZE loop do we attempt an unclustered
allocation, and by then we'll have zeroed the cluster size, so this
patch won't stop us from using the block group as a last resort.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Instead of starting at zero (offset is always zero), request a cluster
starting at search_start, that denotes the beginning of the current
block group.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When I ran the xfstests, I found the test tasks was blocked on meta-data
reservation.
By debugging, I found the reason of this bug:
start transaction
|
v
reserve meta-data space
|
v
flush delay allocation -> iput inode -> evict inode
^ |
| v
wait for delay allocation flush <- reserve meta-data space
And besides that, the flush on evicting inode will block the thread, which
is reclaiming the memory, and make oom happen easily.
Fix this bug by skipping the flush step when evicting inode.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: remove free-space-cache.c WARN during log replay
Btrfs: sectorsize align offsets in fiemap
Btrfs: clear pages dirty for io and set them extent mapped
Btrfs: wait on caching if we're loading the free space cache
Btrfs: prefix resize related printks with btrfs:
btrfs: fix stat blocks accounting
Btrfs: avoid unnecessary bitmap search for cluster setup
Btrfs: fix to search one more bitmap for cluster setup
btrfs: mirror_num should be int, not u64
btrfs: Fix up 32/64-bit compatibility for new ioctls
Btrfs: fix barrier flushes
Btrfs: fix tree corruption after multi-thread snapshots and inode_cache flush
We've been hitting panics when running xfstest 13 in a loop for long periods of
time. And actually this problem has always existed so we've been hitting these
things randomly for a while. Basically what happens is we get a thread coming
into the allocator and reading the space cache off of disk and adding the
entries to the free space cache as we go. Then we get another thread that comes
in and tries to allocate from that block group. Since block_group->cached !=
BTRFS_CACHE_NO it goes ahead and tries to do the allocation. We do this because
if we're doing the old slow way of caching we don't want to hold people up and
wait for everything to finish. The problem with this is we could end up
discarding the space cache at some arbitrary point in the future, which means we
could very well end up allocating space that is either bad, or when the real
caching happens it could end up thinking the space isn't in use when it really
is and cause all sorts of other problems.
The solution is to add a new flag to indicate we are loading the free space
cache from disk, and always try to cache the block group if cache->cached !=
BTRFS_CACHE_FINISHED. That way if we are loading the space cache anybody else
who tries to allocate from the block group will have to wait until it's finished
to make sure it completes successfully. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
btrfs: rename the option to nospace_cache
Btrfs: handle bio_add_page failure gracefully in scrub
Btrfs: fix deadlock caused by the race between relocation
Btrfs: only map pages if we know we need them when reading the space cache
Btrfs: fix orphan backref nodes
Btrfs: Abstract similar code for btrfs_block_rsv_add{, _noflush}
Btrfs: fix unreleased path in btrfs_orphan_cleanup()
Btrfs: fix no reserved space for writing out inode cache
Btrfs: fix nocow when deleting the item
Btrfs: tweak the delayed inode reservations again
Btrfs: rework error handling in btrfs_mount()
Btrfs: close devices on all error paths in open_ctree()
Btrfs: avoid null dereference and leaks when bailing from open_ctree()
Btrfs: fix subvol_name leak on error in btrfs_mount()
Btrfs: fix memory leak in btrfs_parse_early_options()
Btrfs: fix our reservations for updating an inode when completing io
Btrfs: fix oops on NULL trans handle in btrfs_truncate
btrfs: fix double-free 'tree_root' in 'btrfs_mount()'
btrfs_block_rsv_add{, _noflush}() have similar code, so abstract that code.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
People have been reporting ENOSPC crashes in finish_ordered_io. This is because
we try to steal from the delalloc block rsv to satisfy a reservation to update
the inode. The problem with this is we don't explicitly save space for updating
the inode when doing delalloc. This is kind of a problem and we've gotten away
with this because way back when we just stole from the delalloc reserve without
any questions, and this worked out fine because generally speaking the leaf had
been modified either by the mtime update when we did the original write or
because we just updated the leaf when we inserted the file extent item, only on
rare occasions had the leaf not actually been modified, and that was still ok
because we'd just use a block or two out of the over-reservation that is
delalloc.
Then came the delayed inode stuff. This is amazing, except it wants a full
reservation for updating the inode since it may do it at some point down the
road after we've written the blocks and we have to recow everything again. This
worked out because the delayed inode stuff just stole from the global reserve,
that is until recently when I changed that because it caused other problems.
So here we are, we're doing everything right and being screwed for it. So take
an extra reservation for the inode at delalloc reservation time and carry it
through the life of the delalloc reservation. If we need it we can steal it in
the delayed inode stuff. If we have already stolen it try and do a normal
metadata reservation. If that fails try to steal from the delalloc reservation.
If _that_ fails we'll get a WARN_ON() so I can start thinking of a better way to
solve this and in the meantime we'll steal from the global reserve.
With this patch I ran xfstests 13 in a loop for a couple of hours and didn't see
any problems.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (114 commits)
Btrfs: check for a null fs root when writing to the backup root log
Btrfs: fix race during transaction joins
Btrfs: fix a potential btrfs_bio leak on scrub fixups
Btrfs: rename btrfs_bio multi -> bbio for consistency
Btrfs: stop leaking btrfs_bios on readahead
Btrfs: stop the readahead threads on failed mount
Btrfs: fix extent_buffer leak in the metadata IO error handling
Btrfs: fix the new inspection ioctls for 32 bit compat
Btrfs: fix delayed insertion reservation
Btrfs: ClearPageError during writepage and clean_tree_block
Btrfs: be smarter about committing the transaction in reserve_metadata_bytes
Btrfs: make a delayed_block_rsv for the delayed item insertion
Btrfs: add a log of past tree roots
btrfs: separate superblock items out of fs_info
Btrfs: use the global reserve when truncating the free space cache inode
Btrfs: release metadata from global reserve if we have to fallback for unlink
Btrfs: make sure to flush queued bios if write_cache_pages waits
Btrfs: fix extent pinning bugs in the tree log
Btrfs: make sure btrfs_remove_free_space doesn't leak EAGAIN
Btrfs: don't wait as long for more batches during SSD log commit
...
We all keep getting those stupid warnings from use_block_rsv when running
stress.sh, and it's because the delayed insertion stuff is being stupid. It's
not the delayed insertion stuffs fault, it's all just stupid. When marking an
inode dirty for oh say updating the time on it, we just do a
btrfs_join_transaction, which doesn't reserve any space. This is stupid because
we're going to have to have space reserve to make this change, but we do it
because it's fast because chances are we're going to call it over and over again
and it doesn't matter. Well thanks to the delayed insertion stuff this is
mostly the case, so we do actually need to make this reservation. So if
trans->bytes_reserved is 0 then try to do a normal reservation. If not return
ENOSPC which will make the btrfs_dirty_inode start a proper transaction which
will let it do the whole ENOSPC dance and reserve enough space for the delayed
insertion to steal the reservation from the transaction.
The other stupid thing we do is not reserve space for the inode when writing to
the thing. Usually this is ok since we have to update the time so we'd have
already done all this work before we get to the endio stuff, so it doesn't
matter. But this is stupid because we could write the data after the
transaction commits where we changed the mtime of the inode so we have to cow
all the way down to the inode anyway. This used to be masked by the delalloc
reservation stuff, but because we delay the update it doesn't get masked in this
case. So again the delayed insertion stuff bites us in the ass. So if our
trans->block_rsv is delalloc, just steal the reservation from the delalloc
reserve. Hopefully this won't bite us in the ass, but I've said that before.
With this patch stress.sh no longer spits out those stupid warnings (famous last
words). Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Because of the overcommit stuff I had to make it so that we committed the
transaction all the time in reserve_metadata_bytes in case we had overcommitted
because of delayed items. This was because previously we had no way of knowing
how much space was reserved for delayed items. Now that we have the
delayed_block_rsv we can check it to see if committing the transaction would get
us anywhere. This patch breaks out the committing logic into a helper function
that will check to see if committing the transaction would free enough space for
us to get anything done. With this patch xfstests 83 goes from taking 445
seconds to taking 28 seconds on my box. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
I've been hitting warnings in use_block_rsv when running the delayed insertion
stuff. It's because we will readjust global block rsv based on what is in use,
which means we could end up discarding reservations that are for the delayed
insertion stuff. So instead create a seperate block rsv for the delayed
insertion stuff. This will also make it easier to debug problems with the
delayed insertion reservations since we will know that only the delayed
insertion code touches this block_rsv. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
fs_info has now ~9kb, more than fits into one page. This will cause
mount failure when memory is too fragmented. Top space consumers are
super block structures super_copy and super_for_commit, ~2.8kb each.
Allocate them dynamically. fs_info will be ~3.5kb. (measured on x86_64)
Add a wrapper for freeing fs_info and all of it's dynamically allocated
members.
Signed-off-by: David Sterba <dsterba@suse.cz>
The tree log had two important bugs that could cause corruptions after a
crash. Sometimes we were allowing tree log blocks to be reused after
the tree log was committed but before the transaction commit was done.
This allowed a future metadata write to overwrite the tree log data. It
is fixed by adding a new variant of freeing reserved extents that always
pins them. Credit goes to Stefan Behrens and Arne Jansen for many many
hours spent tracking this bug down.
During tree log replay, we do a pass through the tree log and pin all
the extents we find. This makes sure the replay code won't go in and
use any of those blocks for new allocations during replay. The problem
is the free space cache isn't honoring these pinned extents. So the
allocator can end up handing them out, leading to all kinds of problems
during replay.
The fix here is to force any free space cache to load while we pin the
extents, and then to make sure we remove the pinned extents from the
free space rbtree.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Reported-by: Stefan Behrens <sbehrens@giantdisaster.de>
This creates a new 'reason' field in a wb_writeback_work
structure, which unambiguously identifies who initiates
writeback activity. A 'wb_reason' enumeration has been
added to writeback.h, to enumerate the possible reasons.
The 'writeback_work_class' and tracepoint event class and
'writeback_queue_io' tracepoints are updated to include the
symbolic 'reason' in all trace events.
And the 'writeback_inodes_sbXXX' family of routines has had
a wb_stats parameter added to them, so callers can specify
why writeback is being started.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Curt Wohlgemuth <curtw@google.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
The WARN_ON under some circumstances heavily polute log and slow down
the machine. This is just a safety, as the warning should be fixed by
another patch, nevertheless, it still pops up during testing.
Signed-off-by: David Sterba <dsterba@suse.cz>
The task may fail to get free space though it is enough when multi-task
space allocation and caching space happen at the same time.
Task1 Caching Thread Task2
------------------------------------------------------------------------
find_free_extent
The space has not
be cached, and start
caching thread. And
wait for it.
cache space, if
the space is > 2MB
wake up Task1
find_free_extent
get all the space that
is cached.
try to allocate space,
but there is no space
now.
trigger BUG_ON()
The message is following:
btrfs allocation failed flags 1, wanted 4096
space_info has 1040187392 free, is not full
space_info total=1082130432, used=4096, pinned=41938944, reserved=0, may_use=40828928, readonly=0
block group 12582912 has 8388608 bytes, 0 used 8388608 pinned 0 reserved
block group has cluster?: no
0 blocks of free space at or bigger than bytes is
block group 1103101952 has 1073741824 bytes, 4096 used 33550336 pinned 0 reserved
block group has cluster?: no
0 blocks of free space at or bigger than bytes is
------------[ cut here ]------------
kernel BUG at fs/btrfs/inode.c:835!
[<ffffffffa031261b>] __extent_writepage+0x1bf/0x5ce [btrfs]
[<ffffffff810cbcb8>] ? __set_page_dirty_nobuffers+0xfe/0x108
[<ffffffffa02f8ada>] ? wait_current_trans+0x23/0xec [btrfs]
[<ffffffff810c3fbf>] ? find_get_pages_tag+0x73/0xe2
[<ffffffffa0312d12>] extent_write_cache_pages.clone.0+0x176/0x29a [btrfs]
[<ffffffffa0312e74>] extent_writepages+0x3e/0x53 [btrfs]
[<ffffffff8110ad2c>] ? do_sync_write+0xc6/0x103
[<ffffffffa0302d6e>] ? btrfs_submit_direct+0x414/0x414 [btrfs]
[<ffffffff811380fa>] ? fsnotify+0x236/0x266
[<ffffffffa02fc930>] btrfs_writepages+0x22/0x24 [btrfs]
[<ffffffff810cc215>] do_writepages+0x1c/0x25
[<ffffffff810c4958>] __filemap_fdatawrite_range+0x4e/0x50
[<ffffffff810c4982>] filemap_write_and_wait_range+0x28/0x51
[<ffffffffa0306b2e>] btrfs_sync_file+0x7d/0x198 [btrfs]
[<ffffffff8110aa26>] ? fsnotify_modify+0x5d/0x65
[<ffffffff8112d150>] vfs_fsync_range+0x18/0x21
[<ffffffff8112d170>] vfs_fsync+0x17/0x19
[<ffffffff8112d316>] do_fsync+0x29/0x3e
[<ffffffff8112d348>] sys_fsync+0xb/0xf
[<ffffffff81468352>] system_call_fastpath+0x16/0x1b
[SNIP]
RIP [<ffffffffa02fe08c>] cow_file_range+0x1c4/0x32b [btrfs]
We fix this bug by trying to allocate the space again if there are block groups
in caching.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Free space items are located in tree of tree roots, not in the extent
tree. It didn't pop up because lookup_free_space_inode() grabs the
inode all the time instead of actually searching the tree.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Mitch kept hitting a panic because he was getting ENOSPC. One of my previous
patches makes it so we are much better at not allocating new metadata chunks.
Unfortunately coupled with the overcommit patch this works us into a bit of a
problem if we are removing a bunch of space and end up chewing up all of our
space with pinned extents. We can allocate chunks fine and overflow is ok, but
the only way to reclaim this space is to commit the transaction. So if we go to
overcommit, first check and see how much pinned space we have. If we have more
than 80% of the free space chewed up with pinned extents, just commit the
transaction, this will free up enough space for our reservation and we won't
have this problem anymore. With this patch Mitch's test doesn't blow up
anymore. Thanks,
Reported-and-tested-by: Mitch Harder <mitch.harder@sabayonlinux.org>
Signed-off-by: Josef Bacik <josef@redhat.com>
Currently btrfs_block_rsv_check does 2 things, it will either refill a block
reserve like in the truncate or refill case, or it will check to see if there is
enough space in the global reserve and possibly refill it. However because of
overcommit we could be well overcommitting ourselves just to try and refill the
global reserve, when really we should just be committing the transaction. So
breack this out into btrfs_block_rsv_refill and btrfs_block_rsv_check. Refill
will try to reserve more metadata if it can and btrfs_block_rsv_check will not,
it will only tell you if the factor of the total space is still reserved.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We started setting trans->block_rsv = NULL to allow the delayed refs flushing
stuff to use the right block_rsv and then just made
btrfs_trans_release_metadata() unconditionally use the trans block rsv. The
problem with this is we need to reserve some space in the transaction and then
migrate it to the global block rsv, so we need to be able to free that out
properly. So instead just move btrfs_trans_release_metadata() before the
delayed ref flushing and use trans->block_rsv for the freeing. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Currently we only allow a maximum of 2 megabytes of pages to be flushed at a
time. This was ok before, but now we have overcommit which will screw us in a
heartbeat if we are quickly filling the disk. So instead pick either 2
megabytes or the number of pages we need to reclaim to be safe again, which ever
is larger. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
The only way we actually reclaim delalloc space is waiting for the IO to
completely finish. Usually we kick off a bunch of IO and wait for a little bit
and hope we can make our reservation, and usually this works out pretty well.
With overcommit however we can get seriously underwater if we're filling up the
disk quickly, so we need to be able to force the delalloc shrinker to wait for
the ordered IO to finish to give us a better chance of actually reclaiming
enough space to get our reservation. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Before the only reason to commit the transaction to recover space in
reserve_metadata_bytes() was if there were enough pinned_bytes to satisfy our
reservation. But now we have the delayed inode stuff which will hold it's
reservations until we commit the transaction. So say we max out our reservation
by creating a bunch of files but don't have any pinned bytes we will ENOSPC out
early even though we could commit the transaction and get that space back. So
now just unconditionally commit the transaction since currently there is no way
to know how much metadata space is being reserved by delayed inode stuff.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
I noticed recently that my overcommit patch was causing one of my enospc tests
to fail 25% of the time with early ENOSPC. This is because my overcommit patch
was letting us go way over board, but it wasn't waiting long enough to let the
delalloc shrinker do it's job. The problem is we just start writeback and wait
a little bit hoping we flush enough, but we only free up delalloc space by
having the writes complete all the way. We do this by waiting for ordered
extents, which we do but only if we already free'd enough for the reservation,
which isn't right, we should flush ordered extents if we didn't reclaim enough
in case that will push us over the edge. With this patch I've not seen a
failure in this enospc test after running it in a loop for an hour. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Yeah yeah I know this is how we used to do it and then I changed it, but damnit
I'm changing it back. The fact is that writing out checksums will modify
metadata, which could cause us to dirty a block group we've already written out,
so we have to truncate it and all of it's checksums and re-write it which will
write new checksums which could dirty a blockg roup that has already been
written and you see where I'm going with this? This can cause unmount or really
anything that depends on a transaction to commit to take it's sweet damned time
to happen. So go back to the way it was, only this time we're specifically
setting NODATACOW because we can't go through the COW pathway anyway and we're
doing our own built-in cow'ing by truncating the free space cache. The other
new thing is once we truncate the old cache and preallocate the new space, we
don't need to do that song and dance at all for the rest of the transaction, we
can just overwrite the existing space with the new cache if the block group
changes for whatever reason, and the NODATACOW will let us do this fine. So
keep track of which transaction we last cleared our cache in and if we cleared
it in this transaction just say we're all setup and carry on. This survives
xfstests and stress.sh.
The inode cache will continue to use the normal csum infrastructure since it
only gets written once and there will be no more modifications to the fs tree in
a transaction commit.
Signed-off-by: Josef Bacik <josef@redhat.com>
My overcommit stuff can be a little racy when we're filling up the disk with
fs_mark and we overcommit into things that quickly get used up for data. So use
num_bytes to see if we have enough available space so we're less likely to
overcommit ourselves out of the ability to make reservations. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Some users have requested this and I've found I needed a way to disable cache
loading without actually clearing the cache, so introduce the no_space_cache
option. Before we check the super blocks cache generation field and if it was
populated we always turned space caching on. Now we check this and set the
space cache option on, and then parse the mount options so that if we want it
off it get's turned off. Then we check the mount option all the places we do
the caching work instead of checking the super's cache generation. This makes
things more consistent and lets us turn space caching off. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
One of the things that kills us is the fact that our ENOSPC reservations are
horribly over the top in most normal cases. There isn't too much that can be
done about this because when we are completely full we really need them to work
like this so we don't under reserve. However if there is plenty of unallocated
chunks on the disk we can use that to gauge how much we can overcommit. So this
patch adds chunk free space accounting so we always know how much unallocated
space we have. Then if we fail to make a reservation within our allocated
space, check to see if we can overcommit. In the normal flushing case (like
with delalloc metadata reservations) we'll take the free space and divide it by
2 if our metadata profile is setup for DUP or any of those, and then divide it
by 8 to make sure we don't overcommit too much. Then if we're in a non-flushing
case (we really need this reservation now!) we only limit ourselves to half of
the free space. This makes this fio test
[torrent]
filename=torrent-test
rw=randwrite
size=4g
ioengine=sync
directory=/mnt/btrfs-test
go from taking around 45 minutes to 10 seconds on my freshly formatted 3 TiB
file system. This doesn't seem to break my other enospc tests, but could really
use some more testing as this is a super scary change. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
There is a bug that may lead to early ENOSPC in our reservation code. We've
been checking against num_bytes which may be above and beyond what we want to
actually reserve, which could give us a false ENOSPC. Fix this by making sure
the unused space is above how much we want to reserve and not how much we're
trying to flush. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
I kept getting warnings from evict because we were calling
btrfs_start_transaction() with a transaction already started when doing a
balance. This is because we remove a block group which requires a transaction,
and the put the last reference on the cache inode. Instead of doing this we
need to delay the iput so it is done not within a transaction having started.
This gets rid of our warnings. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
The only thing that we need to have a trans handle for is in
reserve_metadata_bytes and thats to know how much flushing we can do. So
instead of passing it around, just check current->journal_info for a
trans_handle so we know if we can commit a transaction to try and free up space
or not. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Since the durable block rsv stuff has been killed there is no need to get the
block_rsv in btrfs_free_tree_block anymore.
Signed-off-by: Josef Bacik <josef@redhat.com>
The alloc warnings everybody has been seeing is because we have been reserving
space for csums, but we weren't actually using that space. So make
get_block_rsv() return the trans->block_rsv if we're modifying the csum root.
Also set the trans->block_rsv to NULL so that if we modify the csum root when
running delayed ref's that comes out of the global reserve like it's supposed
to. With this patch I'm not seeing those alloc warnings anymore. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Since free space inodes now use normal checksumming we need to make sure to
account for their metadata use. So reserve metadata space, and then if we fail
to write out the metadata we can just release it, otherwise it will be freed up
when the io completes. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
If we have to emergency reserve space we need to not increase the block_rsv
size, otherwise we'll leak space. Take for instance delalloc, say we reserve
4k, and we use that 4k, and then we have to emergency allocate another 4k, we
bump the size up to 8k, however we've only accounted for 4k in reservations in
all of our supporting logic, so we'll go to free the 4k and end up having a size
of 4k, which will cause us to later not free as much space. I saw this doing
testing where I wasn't reserving enough space for something but was still
leaking space, very frustrating. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
When changing back to using a spin_lock to protect the extent counters I decided
that since we would only be dropping our original extent, it was ok to just drop
the extent and return. However since somebody else could have come in and done
a reservation, we need to do the normal song and dance to clear the reservation
out properly. So calculate how much space we need to free, and then subtract
what we just attempted to reserve. If it's more then we know we need to drop
those bytes from the delalloc block rsv. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
If you run xfstest 224 it you will get lots of messages about not being able to
delete inodes and that they will be cleaned up next mount. This is because
btrfs_block_rsv_check was not calling reserve_metadata_bytes with the ability to
flush, so if there was not enough space, it simply failed. But in truncate and
evict case we could easily flush space to try and get enough space to do our
work, so make btrfs_block_rsv_check take a flush argument to pass down to
reserve_metadata_bytes. Now xfstests 224 runs fine without all those
complaints. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We will try and reserve metadata bytes in btrfs_block_rsv_check and if we cannot
because we have a transaction open it will return EAGAIN, so we do not need to
try and commit the transaction again.
Signed-off-by: Josef Bacik <josef@redhat.com>
The priority and refill_used flags are not used anymore, and neither is the
usage counter, so just remove them from btrfs_block_rsv.
Signed-off-by: Josef Bacik <josef@redhat.com>
We have not been reserving enough space for checksums. We were just reserving
bytes for the checksum items themselves, we were not taking into account having
to cow the tree and such. This patch adds a csum_bytes counter to the inode for
keeping track of the number of bytes outstanding we have for checksums. Then we
calculate how many leaves would be required for the checksums we are given and
use that to reserve space. This adds a significant amount of bytes to our
reservations, but we will handle this later. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We have been using bytes_reserved for metadata reservations, which is wrong
since we use that to keep track of outstanding reservations from the allocator.
This resulted in us doing a lot of silly things to make sure we don't allocate a
bunch of metadata chunks since we never had a real view of how much space was
actually in use by metadata.
This passes Arne's enospc test and xfstests as well as my own enospc tests.
Hopefully this will get us moving in the right direction. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
btrfs_bio is a bio abstraction able to split and not complete after the last
bio has returned (like the old btrfs_multi_bio). Additionally, btrfs_bio
tracks the mirror_num used to read data which can be used for error
correction purposes.
Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
This fixes a regression introduced by commit cdcb725c05 ("Btrfs: check
if there is enough space for balancing smarter"). We can't do 64-bit
divides on 32-bit architectures.
In cases where we need to divide/multiply by 2 we should just left/right
shift respectively, and in cases where theres N number of devices use
do_div. Also make the counters u64 to match up with rw_devices.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Acked-and-tested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The filesystem turns readonly instead of returning the error to the
caller when detected error in btrfs_drop_snapshot().
and, because the caller doesn't check the error, the function type is
changed to 'void'.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When checking if there is enough space for balancing a block group,
since we do not take raid types into consideration, we do not account
corrent amounts of space that we needed. This makes us do some extra
work before we get ENOSPC.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We have a problem where if a user specifies discard but doesn't actually support
it we will return EOPNOTSUPP from btrfs_discard_extent. This is a problem
because this gets called (in a fashion) from the tree log recovery code, which
has a nice little BUG_ON(ret) after it, which causes us to fail the tree log
replay. So instead detect wether our devices support discard when we're adding
them and then don't issue discards if we know that the device doesn't support
it. And just for good measure set ret = 0 in btrfs_issue_discard just in case
we still get EOPNOTSUPP so we don't screw anybody up like this again. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In __btrfs_free_extent we will print the leaf if we fail to find the extent we
wanted, but the problem is if we get an error we won't have a leaf so often this
leads to a NULL pointer dereference and we lose the error that actually
occurred. So only print the leaf if ret > 0, which means we didn't find the
item we were looking for but we didn't error either. This way the error is
preserved.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Here I have a two SSD-partitions btrfs, and they are defaultly set to
"data=raid0, metadata=raid1", then I try to fill my btrfs partition
till "No space left on device", via "dd if=/dev/zero of=/mnt/btrfs/tmp".
I get an oops panic from kernel BUG at fs/btrfs/extent-tree.c:5199!, which
refers to find_free_extent's
BUG_ON(index != get_block_group_index(block_group));
In SSD mode, in order to find enough space to alloc, we may check the
block_group cache which has been checked sometime before, but the index is not
updated, where it hits the BUG_ON.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Acked-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The access for ro in btrfs_block_group_cache should be protected
because of the racy lock in relocation.
Signed-off-by: Wu Bo <wu.bo@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When btrfs_unlink_inode() and btrfs_orphan_add() in btrfs_unlink()
are error, the error code is returned to the caller instead of
BUG_ON().
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btrfs transaction code will return any errors that come from
reserve_metadata_bytes. We need to make sure we don't return funny
things like 1 or EAGAIN.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch was originally from Tejun Heo. lockdep complains about the btrfs
locking because we sometimes take btree locks from two different trees at the
same time. The current classes are based only on level in the btree, which
isn't enough information for lockdep to figure out if the lock is safe.
This patch makes a class for each type of tree, and lumps all the FS trees that
actually have files and directories into the same class.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btrfs metadata btree is the source of significant
lock contention, especially in the root node. This
commit changes our locking to use a reader/writer
lock.
The lock is built on top of rw spinlocks, and it
extends the lock tracking to remember if we have a
read lock or a write lock when we go to blocking. Atomics
count the number of blocking readers or writers at any
given time.
It removes all of the adaptive spinning from the old code
and uses only the spinning/blocking hints inside of btrfs
to decide when it should continue spinning.
In read heavy workloads this is dramatically faster. In write
heavy workloads we're still faster because of less contention
on the root node lock.
We suffer slightly in dbench because we schedule more often
during write locks, but all other benchmarks so far are improved.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we balanced the chunks across the devices, BUG_ON() in
__finish_chunk_alloc() was triggered.
------------[ cut here ]------------
kernel BUG at fs/btrfs/volumes.c:2568!
[SNIP]
Call Trace:
[<ffffffffa049525e>] btrfs_alloc_chunk+0x8e/0xa0 [btrfs]
[<ffffffffa04546b0>] do_chunk_alloc+0x330/0x3a0 [btrfs]
[<ffffffffa045c654>] btrfs_reserve_extent+0xb4/0x1f0 [btrfs]
[<ffffffffa045c86b>] btrfs_alloc_free_block+0xdb/0x350 [btrfs]
[<ffffffffa048a8d8>] ? read_extent_buffer+0xd8/0x1d0 [btrfs]
[<ffffffffa04476fd>] __btrfs_cow_block+0x14d/0x5e0 [btrfs]
[<ffffffffa044660d>] ? read_block_for_search+0x14d/0x4d0 [btrfs]
[<ffffffffa0447c9b>] btrfs_cow_block+0x10b/0x240 [btrfs]
[<ffffffffa044dd5e>] btrfs_search_slot+0x49e/0x7a0 [btrfs]
[<ffffffffa044f07d>] btrfs_insert_empty_items+0x8d/0xf0 [btrfs]
[<ffffffffa045e973>] insert_with_overflow+0x43/0x110 [btrfs]
[<ffffffffa045eb0d>] btrfs_insert_dir_item+0xcd/0x1f0 [btrfs]
[<ffffffffa0489bd0>] ? map_extent_buffer+0xb0/0xc0 [btrfs]
[<ffffffff812276ad>] ? rb_insert_color+0x9d/0x160
[<ffffffffa046cc40>] ? inode_tree_add+0xf0/0x150 [btrfs]
[<ffffffffa0474801>] btrfs_add_link+0xc1/0x1c0 [btrfs]
[<ffffffff811dacac>] ? security_inode_init_security+0x1c/0x30
[<ffffffffa04a28aa>] ? btrfs_init_acl+0x4a/0x180 [btrfs]
[<ffffffffa047492f>] btrfs_add_nondir+0x2f/0x70 [btrfs]
[<ffffffffa046af16>] ? btrfs_init_inode_security+0x46/0x60 [btrfs]
[<ffffffffa0474ac0>] btrfs_create+0x150/0x1d0 [btrfs]
[<ffffffff81159c63>] ? generic_permission+0x23/0xb0
[<ffffffff8115b415>] vfs_create+0xa5/0xc0
[<ffffffff8115ce6e>] do_last+0x5fe/0x880
[<ffffffff8115dc0d>] path_openat+0xcd/0x3d0
[<ffffffff8115e029>] do_filp_open+0x49/0xa0
[<ffffffff8116a965>] ? alloc_fd+0x95/0x160
[<ffffffff8114f0c7>] do_sys_open+0x107/0x1e0
[<ffffffff810bcc3f>] ? audit_syscall_entry+0x1bf/0x1f0
[<ffffffff8114f1e0>] sys_open+0x20/0x30
[<ffffffff81484ec2>] system_call_fastpath+0x16/0x1b
[SNIP]
RIP [<ffffffffa049444a>] __finish_chunk_alloc+0x20a/0x220 [btrfs]
The reason is:
Task1 Space balance task
do_chunk_alloc()
__finish_chunk_alloc()
update device info
in the chunk tree
alloc system metadata block
relocate system metadata block group
set system metadata block group
readonly, This block group is the
only one that can allocate space. So
there is no free space that can be
allocated now.
find no space and don't try
to alloc new chunk, and then
return ENOSPC
BUG_ON() in __finish_chunk_alloc()
was triggered.
Fix this bug by allocating a new system metadata chunk before relocating the
old one if we find there is no free space which can be allocated after setting
the old block group to be read-only.
Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Tested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
So I had this brilliant idea to use atomic counters for outstanding and reserved
extents, but this turned out to be a bad idea. Consider this where we have 1
outstanding extent and 1 reserved extent
Reserver Releaser
atomic_dec(outstanding) now 0
atomic_read(outstanding)+1 get 1
atomic_read(reserved) get 1
don't actually reserve anything because
they are the same
atomic_cmpxchg(reserved, 1, 0)
atomic_inc(outstanding)
atomic_add(0, reserved)
free reserved space for 1 extent
Then the reserver now has no actual space reserved for it, and when it goes to
finish the ordered IO it won't have enough space to do it's allocation and you
get those lovely warnings.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Kill the check to see if we have 512mb of reserved space in delalloc and
shrink_delalloc if we do. This causes unexpected latencies and we have other
logic to see if we need to throttle. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
A user reported a deadlock when copying a bunch of files. This is because they
were low on memory and kthreadd got hung up trying to migrate pages for an
allocation when starting the caching kthread. The page was locked by the person
starting the caching kthread. To fix this we just need to use the async thread
stuff so that the threads are already created and we don't have to worry about
deadlocks. Thanks,
Reported-by: Roman Mamedov <rm@romanrm.ru>
Signed-off-by: Josef Bacik <josef@redhat.com>
In addition to properly handling allocation failure from btrfs_alloc_path, I
also fixed up the kzalloc error handling code immediately below it.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
I also removed the BUG_ON from error return of find_next_chunk in
init_first_rw_device(). It turns out that the only caller of
init_first_rw_device() also BUGS on any nonzero return so no actual behavior
change has occurred here.
do_chunk_alloc() also needed an update since it calls btrfs_alloc_chunk()
which can now return -ENOMEM. Instead of setting space_info->full on any
error from btrfs_alloc_chunk() I catch and return every error value _except_
-ENOSPC. Thanks goes to Tsutomu Itoh for pointing that issue out.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch fixes many callers of btrfs_alloc_path() which BUG_ON allocation
failure. All the sites that are fixed in this patch were checked by me to
be fairly trivial to fix because of at least one of two criteria:
- Callers of the function catch errors from it already so bubbling the
error up will be handled.
- Callers of the function might BUG_ON any nonzero return code in which
case there is no behavior changed (but we still got to remove a BUG_ON)
The following functions were updated:
btrfs_lookup_extent, alloc_reserved_tree_block, btrfs_remove_block_group,
btrfs_lookup_csums_range, btrfs_csum_file_blocks, btrfs_mark_extent_written,
btrfs_inode_by_name, btrfs_new_inode, btrfs_symlink,
insert_reserved_file_extent, and run_delalloc_nocow
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
We keep having problems with early enospc, and that's because our method of
making space is inherently racy. The problem is we can have one guy trying to
make space for himself, and in the meantime people come in and steal his
reservation. In order to stop this we make a waitqueue and put anybody who
comes into reserve_metadata_bytes on that waitqueue if somebody is trying to
make more space. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We have to do weird things when handling enospc in the transaction joining code.
Because we've already joined the transaction we cannot commit the transaction
within the reservation code since it will deadlock, so we have to return EAGAIN
and then make sure we don't retry too many times. Instead of doing this, just
do the reservation the normal way before we join the transaction, that way we
can do whatever we want to try and reclaim space, and then if it fails we know
for sure we are out of space and we can return ENOSPC. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
data parameter should be u64 because a full-sized chunk flags field is
passed instead of 0/1 for distinguishing data from metadata. All
underlying functions expect u64.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
I was testing with empty_cluster = 0 to try and reproduce a problem and kept
hitting early enospc panics. This was because our loop logic was a little
confused. So this is what I did
1) Make the loop variable the ultimate decider on wether we should loop again
isntead of checking to see if we had an uncached bg, empty size or empty
cluster.
2) Increment loop before checking to see what we are on to make the loop
definitions make more sense.
3) If we are on the chunk alloc loop don't set empty_size/empty_cluster to 0
unless we didn't actually allocate a chunk. If we did allocate a chunk we
should be able to easily setup a new cluster so clearing
empty_size/empty_cluster makes us less efficient.
This kept me from hitting panics while trying to reproduce the other problem.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
I noticed when running an enospc test that we would get stuck committing the
transaction in check_data_space even though we truly didn't have enough space.
So check to see if bytes_pinned is bigger than num_bytes, if it's not don't
commit the transaction. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Currently, btrfs_truncate_item and btrfs_extend_item returns only 0.
So, the check by BUG_ON in the caller is unnecessary.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Observed as a large delay when --mixed filesystem is filled up.
Test example:
1. create tiny --mixed FS:
$ dd if=/dev/zero of=2G.img seek=$((2048 * 1024 * 1024 - 1)) count=1 bs=1
$ mkfs.btrfs --mixed 2G.img
$ mount -oloop 2G.img /mnt/ut/
2. Try to fill it up:
$ dd if=/dev/urandom of=10M.file bs=10240 count=1024
$ seq 1 256 | while read file_no; do echo $file_no; time cp 10M.file ${file_no}.copy; done
Up to '200.copy' it goes fast, but when disk fills-up each -ENOSPC
message takes 3 seconds to pop-up _every_ ENOSPC (and in usermode linux
it's even more: 30-60 seconds!). (Maybe, time depends on kernel's timer resolution).
No IO, no CPU load, just rescheduling. Some debugging revealed busy spinning
in shrink_delalloc.
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If we have a very large filesystem, we can spend a lot of time in
find_free_extent just trying to allocate from empty block groups. So instead
check to see if the block group even has enough space for the allocation, and if
not go on to the next block group.
Signed-off-by: Josef Bacik <josef@redhat.com>
Our readahead is sort of sloppy, and really isn't always needed. For example if
ls is doing a stating ls (which is the default) it's going to stat in non-disk
order, so if say you have a directory with a stupid amount of files, readahead
is going to do nothing but waste time in the case of doing the stat. Taking the
unconditional readahead out made my test go from 57 minutes to 36 minutes. This
means that everywhere we do loop through the tree we want to make sure we do set
path->reada properly, so I went through and found all of the places where we
loop through the path and set reada to 1. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
When the fs is super full and we unmount the fs, we could get stuck in this
thing where unmount is waiting for the caching kthread to make progress and the
caching kthread keeps scheduling because we're in the middle of a commit. So
instead just let the caching kthread keep going and only yeild if
need_resched(). This makes my horrible umount case go from taking up to 10
minutes to taking less than 20 seconds. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Originally this was going to be used as a way to give hints to the allocator,
but frankly we can get much better hints elsewhere and it's not even used at all
for anything usefull. In addition to be completely useless, when we initialize
an inode we try and find a freeish block group to set as the inodes block group,
and with a completely full 40gb fs this takes _forever_, so I imagine with say
1tb fs this is just unbearable. So just axe the thing altoghether, we don't
need it and it saves us 8 bytes in the inode and saves us 500 microseconds per
inode lookup in my testcase. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
The ceph guys keep running into problems where we have space reserved in our
orphan block rsv when freeing it up. This is because they tend to do snapshots
alot, so their truncates tend to use a bunch of space, so when we go to do
things like update the inode we have to steal reservation space in order to make
the reservation happen. This happens because truncate can use as much space as
it freaking feels like, but we still have to hold space for removing the orphan
item and updating the inode, which will definitely always happen. So in order
to fix this we need to split all of the reservation stuf up. So with this patch
we have
1) The orphan block reserve which only holds the space for deleting our orphan
item when everything is over.
2) The truncate block reserve which gets allocated and used specifically for the
space that the truncate will use on a per truncate basis.
3) The transaction will always have 1 item's worth of data reserved so we can
update the inode normally.
Hopefully this will make the ceph problem go away. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We use trans_mutex for lots of things, here's a basic list
1) To serialize trans_handles joining the currently running transaction
2) To make sure that no new trans handles are started while we are committing
3) To protect the dead_roots list and the transaction lists
Really the serializing trans_handles joining is not too hard, and can really get
bogged down in acquiring a reference to the transaction. So replace the
trans_mutex with a trans_lock spinlock and use it to do the following
1) Protect fs_info->running_transaction. All trans handles have to do is check
this, and then take a reference of the transaction and keep on going.
2) Protect the fs_info->trans_list. This doesn't get used too much, basically
it just holds the current transactions, which will usually just be the currently
committing transaction and the currently running transaction at most.
3) Protect the dead roots list. This is only ever processed by splicing the
list so this is relatively simple.
4) Protect the fs_info->reloc_ctl stuff. This is very lightweight and was using
the trans_mutex before, so this is a pretty straightforward change.
5) Protect fs_info->no_trans_join. Because we don't hold the trans_lock over
the entirety of the commit we need to have a way to block new people from
creating a new transaction while we're doing our work. So we set no_trans_join
and in join_transaction we test to see if that is set, and if it is we do a
wait_on_commit.
6) Make the transaction use count atomic so we don't need to take locks to
modify it when we're dropping references.
7) Add a commit_lock to the transaction to make sure multiple people trying to
commit the same transaction don't race and commit at the same time.
8) Make open_ioctl_trans an atomic so we don't have to take any locks for ioctl
trans.
I have tested this with xfstests, but obviously it is a pretty hairy change so
lots of testing is greatly appreciated. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
I keep forgetting that btrfs_join_transaction() just ignores the num_items
argument, which leads me to sending pointless patches and looking stupid :). So
just kill the num_items argument from btrfs_join_transaction and
btrfs_start_ioctl_transaction, since neither of them use it. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Changelog V5 -> V6:
- Fix oom when the memory load is high, by storing the delayed nodes into the
root's radix tree, and letting btrfs inodes go.
Changelog V4 -> V5:
- Fix the race on adding the delayed node to the inode, which is spotted by
Chris Mason.
- Merge Chris Mason's incremental patch into this patch.
- Fix deadlock between readdir() and memory fault, which is reported by
Itaru Kitayama.
Changelog V3 -> V4:
- Fix nested lock, which is reported by Itaru Kitayama, by updating space cache
inode in time.
Changelog V2 -> V3:
- Fix the race between the delayed worker and the task which does delayed items
balance, which is reported by Tsutomu Itoh.
- Modify the patch address David Sterba's comment.
- Fix the bug of the cpu recursion spinlock, reported by Chris Mason
Changelog V1 -> V2:
- break up the global rb-tree, use a list to manage the delayed nodes,
which is created for every directory and file, and used to manage the
delayed directory name index items and the delayed inode item.
- introduce a worker to deal with the delayed nodes.
Compare with Ext3/4, the performance of file creation and deletion on btrfs
is very poor. the reason is that btrfs must do a lot of b+ tree insertions,
such as inode item, directory name item, directory name index and so on.
If we can do some delayed b+ tree insertion or deletion, we can improve the
performance, so we made this patch which implemented delayed directory name
index insertion/deletion and delayed inode update.
Implementation:
- introduce a delayed root object into the filesystem, that use two lists to
manage the delayed nodes which are created for every file/directory.
One is used to manage all the delayed nodes that have delayed items. And the
other is used to manage the delayed nodes which is waiting to be dealt with
by the work thread.
- Every delayed node has two rb-tree, one is used to manage the directory name
index which is going to be inserted into b+ tree, and the other is used to
manage the directory name index which is going to be deleted from b+ tree.
- introduce a worker to deal with the delayed operation. This worker is used
to deal with the works of the delayed directory name index items insertion
and deletion and the delayed inode update.
When the delayed items is beyond the lower limit, we create works for some
delayed nodes and insert them into the work queue of the worker, and then
go back.
When the delayed items is beyond the upper bound, we create works for all
the delayed nodes that haven't been dealt with, and insert them into the work
queue of the worker, and then wait for that the untreated items is below some
threshold value.
- When we want to insert a directory name index into b+ tree, we just add the
information into the delayed inserting rb-tree.
And then we check the number of the delayed items and do delayed items
balance. (The balance policy is above.)
- When we want to delete a directory name index from the b+ tree, we search it
in the inserting rb-tree at first. If we look it up, just drop it. If not,
add the key of it into the delayed deleting rb-tree.
Similar to the delayed inserting rb-tree, we also check the number of the
delayed items and do delayed items balance.
(The same to inserting manipulation)
- When we want to update the metadata of some inode, we cached the data of the
inode into the delayed node. the worker will flush it into the b+ tree after
dealing with the delayed insertion and deletion.
- We will move the delayed node to the tail of the list after we access the
delayed node, By this way, we can cache more delayed items and merge more
inode updates.
- If we want to commit transaction, we will deal with all the delayed node.
- the delayed node will be freed when we free the btrfs inode.
- Before we log the inode items, we commit all the directory name index items
and the delayed inode update.
I did a quick test by the benchmark tool[1] and found we can improve the
performance of file creation by ~15%, and file deletion by ~20%.
Before applying this patch:
Create files:
Total files: 50000
Total time: 1.096108
Average time: 0.000022
Delete files:
Total files: 50000
Total time: 1.510403
Average time: 0.000030
After applying this patch:
Create files:
Total files: 50000
Total time: 0.932899
Average time: 0.000019
Delete files:
Total files: 50000
Total time: 1.215732
Average time: 0.000024
[1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3
Many thanks for Kitayama-san's help!
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: David Sterba <dave@jikos.cz>
Tested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Tested-by: Itaru Kitayama <kitayama@cl.bb4u.ne.jp>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When a btrfs disk is created by mixed data & metadata option, it will have no
pure data or pure metadata space info.
In btrfs's for-linus branch, commit 78b1ea13838039cd88afdd62519b40b344d6c920
(Btrfs: fix OOPS of empty filesystem after balance) initializes space infos at
the very beginning. The problem is this initialization does not take the mixed
case into account, which will cause btrfs will easily get into ENOSPC in mixed
case.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Remove code which has been #if0-ed out for a very long time and does not
seem to be related to current codebase anymore.
Signed-off-by: David Sterba <dsterba@suse.cz>
parameter tree root it's not used since commit
5f39d397df ("Btrfs: Create extent_buffer
interface for large blocksizes")
Signed-off-by: David Sterba <dsterba@suse.cz>
The check on the return value of kmalloc() is added to some places.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This is similar to block group caching.
We dedicate a special inode in fs tree to save free ino cache.
At the very first time we create/delete a file after mount, the free ino
cache will be loaded from disk into memory. When the fs tree is commited,
the cache will be written back to disk.
To keep compatibility, we check the root generation against the generation
of the special inode when loading the cache, so the loading will fail
if the btrfs filesystem was mounted in an older kernel before.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
There's a potential problem in 32bit system when we exhaust 32bit inode
numbers and start to allocate big inode numbers, because btrfs uses
inode->i_ino in many places.
So here we always use BTRFS_I(inode)->location.objectid, which is an
u64 variable.
There are 2 exceptions that BTRFS_I(inode)->location.objectid !=
inode->i_ino: the btree inode (0 vs 1) and empty subvol dirs (256 vs 2),
and inode->i_ino will be used in those cases.
Another reason to make this change is I'm going to use a special inode
to save free ino cache, and the inode number must be > (u64)-256.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
So we can re-use the code to cache free inode numbers.
The change is quite straightforward. Two new structures are introduced.
- struct btrfs_free_space_ctl
We move those variables that are used for caching free space from
struct btrfs_block_group_cache to this new struct.
- struct btrfs_free_space_op
We do block group specific work (e.g. calculation of extents threshold)
through functions registered in this struct.
And then we can remove references to struct btrfs_block_group_cache.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Everytime we try to allocate disk space we try and see if we can pre-emptively
allocate a chunk, but in the common case we don't allocate anything, so there is
no sense in taking the chunk_mutex at all. So instead if we are allocating a
chunk, mark it in the space_info so we don't get two people trying to allocate
at the same time. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Reviewed-by: Liu Bo <liubo2009@cn.fujitsu.com>
find_free_extent likes to allocate in contiguous clusters,
which makes writeback faster, especially on SSD storage. As
the FS fragments, these clusters become harder to find and we have
to decide between allocating a new chunk to make more clusters
or giving up on the cluster to allocate from the free space
we have.
Right now it creates too many chunks, and you can end up with
a whole FS that is mostly empty metadata chunks. This commit
changes the allocation code to be more strict and only
allocate new chunks when we've made good use of the chunks we
already have.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
btrfs will remove unused block groups after balance.
When a empty filesystem is balanced, the block group with tag "DATA" may be
dropped, and after umount and mount again, it will not find "DATA" space_info
and lead to OOPS.
So we initial the necessary space_infos(DATA, SYSTEM, METADATA) to avoid OOPS.
Reported-by: Daniel J Blueman <daniel.blueman@gmail.com>
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
After Josef's patch(commit 3c14874acc),
btrfs will exclude super bytes when reading block groups(by marking a extent
state UPTODATE). However, these bytes do not get freed while balance remove
unused block groups, and we won't process those removed ones any more, when
we do umount and unload the btrfs module, btrfs hits a memory leak.
This patch add the missing free operation.
Reproduce steps:
$ mkfs.btrfs disk
$ mount disk /mnt/btrfs -o loop
$ btrfs filesystem balance /mnt/btrfs
$ umount /mnt/btrfs
$ rmmod btrfs
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
To make Btrfs code more robust, several return value checks where memory
allocation can fail are introduced. I use BUG_ON where I don't know how
to handle the error properly, which increases the number of using the
notorious BUG_ON, though.
Signed-off-by: Yoshinori Sano <yoshinori.sano@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We take an free extent out from allocator, trim it, then put it back,
but before we trim the block group, we should make sure the block group is
cached, so plus a little change to make cache_block_group() run without a
transaction.
Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Callers of btrfs_discard_extent() should check if we are mounted with -o discard,
as we want to make fitrim to work even the fs is not mounted with -o discard.
Also we should use REQ_DISCARD to map the free extent to get a full mapping,
last we only return errors if
1. the error is not a EOPNOTSUPP
2. no device supports discard
Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Make the function public as we should update the reserved extents calculations
after taking out an extent for trimming.
Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In the filesystem context, we must allocate memory by GFP_NOFS,
or we may start another filesystem operation and make kswap thread hang up.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch is checking return value of read_tree_block(),
and if it is NULL, error processing.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch changes some BUG_ON() to the error return.
(but, most callers still use BUG_ON())
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Tracepoints can provide insight into why btrfs hits bugs and be greatly
helpful for debugging, e.g
dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0
dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0
btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0)
btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0)
btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8
flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA
flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0)
flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0)
flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0)
btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0)
btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0)
Here is what I have added:
1) ordere_extent:
btrfs_ordered_extent_add
btrfs_ordered_extent_remove
btrfs_ordered_extent_start
btrfs_ordered_extent_put
These provide critical information to understand how ordered_extents are
updated.
2) extent_map:
btrfs_get_extent
extent_map is used in both read and write cases, and it is useful for tracking
how btrfs specific IO is running.
3) writepage:
__extent_writepage
btrfs_writepage_end_io_hook
Pages are cirtical resourses and produce a lot of corner cases during writeback,
so it is valuable to know how page is written to disk.
4) inode:
btrfs_inode_new
btrfs_inode_request
btrfs_inode_evict
These can show where and when a inode is created, when a inode is evicted.
5) sync:
btrfs_sync_file
btrfs_sync_fs
These show sync arguments.
6) transaction:
btrfs_transaction_commit
In transaction based filesystem, it will be useful to know the generation and
who does commit.
7) back reference and cow:
btrfs_delayed_tree_ref
btrfs_delayed_data_ref
btrfs_delayed_ref_head
btrfs_cow_block
Btrfs natively supports back references, these tracepoints are helpful on
understanding btrfs's COW mechanism.
8) chunk:
btrfs_chunk_alloc
btrfs_chunk_free
Chunk is a link between physical offset and logical offset, and stands for space
infomation in btrfs, and these are helpful on tracing space things.
9) reserved_extent:
btrfs_reserved_extent_alloc
btrfs_reserved_extent_free
These can show how btrfs uses its space.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Currently if we have corrupted items things will blow up in spectacular ways.
So as we read in blocks and they are leaves, check the entire leaf to make sure
all of the items are correct and point to valid parts in the leaf for the item
data the are responsible for. If the item is corrupt we will kick back EIO and
not read any of the copies since they are likely to not be correct either. This
will catch generic corruptions, it will be up to the individual callers of
btrfs_search_slot to make sure their items are right. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
If we cannot truncate an inode for some reason we will never delete the orphan
item associated with that inode, which means that we will loop forever in
btrfs_orphan_cleanup. Instead of doing this just return error so we fail to
mount. It sucks, but hey it's better than hanging. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
We track delayed allocation per inodes via 2 counters, one is
outstanding_extents and reserved_extents. Outstanding_extents is already an
atomic_t, but reserved_extents is not and is protected by a spinlock. So
convert this to an atomic_t and instead of using a spinlock, use atomic_cmpxchg
when releasing delalloc bytes. This makes our inode 72 bytes smaller, and
reduces locking overhead (albiet it was minimal to begin with). Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: break out of shrink_delalloc earlier
btrfs: fix not enough reserved space
btrfs: fix dip leak
Btrfs: make sure not to return overlapping extents to fiemap
Btrfs: deal with short returns from copy_from_user
Btrfs: fix regressions in copy_from_user handling
Josef had changed shrink_delalloc to exit after three shrink
attempts, which wasn't quite enough because new writers could
race in and steal free space.
But it also fixed deadlocks and stalls as we tried to recover
delalloc reservations. The code was tweaked to loop 1024
times, and would reset the counter any time a small amount
of progress was made. This was too drastic, and with a
lot of writers we can end up stuck in shrink_delalloc forever.
The shrink_delalloc loop is fairly complex because the caller is looping
too, and the caller will go ahead and force a transaction commit to make
sure we reclaim space.
This reworks things to exit shrink_delalloc when we've forced some
writeback and the delalloc reservations have gone down. This means
the writeback has not just started but has also finished at
least some of the metadata changes required to reclaim delalloc
space.
If we've got this wrong, we're returning ENOSPC too early, which
is a big improvement over the current behavior of hanging the machine.
Test 224 in xfstests hammers on this nicely, and with 1000 writers
trying to fill a 1GB drive we get our first ENOSPC at 93% full. The
other writers are able to continue until we get 100%.
This is a worst case test for btrfs because the 1000 writers are doing
small IO, and the small FS size means we don't have a lot of room
for metadata chunks.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: fix fiemap bugs with delalloc
Btrfs: set FMODE_EXCL in btrfs_device->mode
Btrfs: make btrfs_rm_device() fail gracefully
Btrfs: Avoid accessing unmapped kernel address
Btrfs: Fix BTRFS_IOC_SUBVOL_SETFLAGS ioctl
Btrfs: allow balance to explicitly allocate chunks as it relocates
Btrfs: put ENOSPC debugging under a mount option
Btrfs device shrinking and balancing ends up reallocating all the blocks
in order to allow COW to move them to new destinations. It is somewhat
awkward in terms of ENOSPC because most of the enospc code is built
around the idea that some operation on a reference counted tree triggers
allocations in the non-reference counted trees.
This commit changes the balancing code to deal with enospc by trying to
allocate a new chunk. If that allocation succeeds, we go ahead and
retry whatever failed due to enospc.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
ENOSPC in btrfs is getting to the point where the extra debugging isn't
required. I've put it under mount -o enospc_debug just in case someone
is having difficult problems.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
I add the check on the return value of alloc_extent_map() to several places.
In addition, alloc_extent_map() returns only the address or NULL.
Therefore, check by IS_ERR() is unnecessary. So, I remove IS_ERR() checking.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (33 commits)
Btrfs: Fix page count calculation
btrfs: Drop __exit attribute on btrfs_exit_compress
btrfs: cleanup error handling in btrfs_unlink_inode()
Btrfs: exclude super blocks when we read in block groups
Btrfs: make sure search_bitmap finds something in remove_from_bitmap
btrfs: fix return value check of btrfs_start_transaction()
btrfs: checking NULL or not in some functions
Btrfs: avoid uninit variable warnings in ordered-data.c
Btrfs: catch errors from btrfs_sync_log
Btrfs: make shrink_delalloc a little friendlier
Btrfs: handle no memory properly in prepare_pages
Btrfs: do error checking in btrfs_del_csums
Btrfs: use the global block reserve if we cannot reserve space
Btrfs: do not release more reserved bytes to the global_block_rsv than we need
Btrfs: fix check_path_shared so it returns the right value
btrfs: check return value of btrfs_start_ioctl_transaction() properly
btrfs: fix return value check of btrfs_join_transaction()
fs/btrfs/inode.c: Add missing IS_ERR test
btrfs: fix missing break in switch phrase
btrfs: fix several uncheck memory allocations
...
This has been resulting in a BUT_ON(ret) after btrfs_reserve_extent in
btrfs_cow_file_range. The reason is we don't actually calculate the bytes_super
for a block group until we go to cache it, which means that the space_info can
hand out reservations for space that it doesn't actually have, and we can run
out of data space. This is also a problem if you are using space caching since
we don't ever calculate bytes_super for the block groups. So instead everytime
we read a block group call exclude_super_stripes, which calculates the
bytes_super for the block group so it can be left out of the space_info. Then
whenever caching completes we just call free_excluded_extents so that the super
excluded extents are freed up. Also if we are unmounting and we hit any block
groups that haven't been cached we still need to call free_excluded_extents to
make sure things are cleaned up properly. Thanks,
Reported-by: Arne Jansen <sensille@gmx.net>
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The error check of btrfs_start_transaction() is added, and the mistake
of the error check on several places is corrected.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Because NULL is returned when the memory allocation fails,
it is checked whether it is NULL.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Xfstests 224 will just sit there and spin for ever until eventually we give up
flushing delalloc and exit. On my box this took several hours. I could not
interrupt this process either, even though we use INTERRUPTIBLE. So do 2 things
1) Keep us from looping over and over again without reclaiming anything
2) If we get interrupted exit the loop
I tested this and the test now exits in a reasonable amount of time, and can be
interrupted with ctrl+c. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We call use_block_rsv right before we make an allocation in order to make sure
we have enough space. Now normally people have called btrfs_start_transaction()
with the appropriate amount of space that we need, so we just use some of that
pre-reserved space and move along happily. The problem is where people use
btrfs_join_transaction(), which doesn't actually reserve any space. So we try
and reserve space here, but we cannot flush delalloc, so this forces us to
return -ENOSPC when in reality we have plenty of space. The most common symptom
is seeing a bunch of "couldn't dirty inode" messages in syslog. With
xfstests 224 we end up falling back to start_transaction and then doing all the
flush delalloc stuff which causes to hang for a very long time.
So instead steal from the global reserve, which is what this is meant for
anyway. With this patch and the other 2 I have sent xfstests 224 now passes
successfully. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we do btrfs_block_rsv_release, if global_block_rsv is not full we will
release all the extra bytes to global_block_rsv, even if it's only a little
short of the amount of space that we need to reserve. This causes us to starve
ourselves of reservable space during the transaction which will force us to
shrink delalloc bytes and commit the transaction more often than we should. So
instead just add the amount of bytes we need to add to the global reserve so
reserved == size, and then add the rest back into the space_info for general
use. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The error check of btrfs_join_transaction()/btrfs_join_transaction_nolock()
is added, and the mistake of the error check in several places is
corrected.
For more stable Btrfs, I think that we should reduce BUG_ON().
But, I think that long time is necessary for this.
So, I propose this patch as a short-term solution.
With this patch:
- To more stable Btrfs, the part that should be corrected is clarified.
- The panic isn't done by the NULL pointer reference etc. (even if
BUG_ON() is increased temporarily)
- The error code is returned in the place where the error can be easily
returned.
As a long-term plan:
- BUG_ON() is reduced by using the forced-readonly framework, etc.
Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (25 commits)
Btrfs: forced readonly mounts on errors
btrfs: Require CAP_SYS_ADMIN for filesystem rebalance
Btrfs: don't warn if we get ENOSPC in btrfs_block_rsv_check
btrfs: Fix memory leak in btrfs_read_fs_root_no_radix()
btrfs: check NULL or not
btrfs: Don't pass NULL ptr to func that may deref it.
btrfs: mount failure return value fix
btrfs: Mem leak in btrfs_get_acl()
btrfs: fix wrong free space information of btrfs
btrfs: make the chunk allocator utilize the devices better
btrfs: restructure find_free_dev_extent()
btrfs: fix wrong calculation of stripe size
btrfs: try to reclaim some space when chunk allocation fails
btrfs: fix wrong data space statistics
fs/btrfs: Fix build of ctree
Btrfs: fix off by one while setting block groups readonly
Btrfs: Add BTRFS_IOC_SUBVOL_GETFLAGS/SETFLAGS ioctls
Btrfs: Add readonly snapshots support
Btrfs: Refactor btrfs_ioctl_snap_create()
btrfs: Extract duplicate decompress code
...
This patch comes from "Forced readonly mounts on errors" ideas.
As we know, this is the first step in being more fault tolerant of disk
corruptions instead of just using BUG() statements.
The major content:
- add a framework for generating errors that should result in filesystems
going readonly.
- keep FS state in disk super block.
- make sure that all of resource will be freed and released at umount time.
- make sure that fter FS is forced readonly on error, there will be no more
disk change before FS is corrected. For this, we should stop write operation.
After this patch is applied, the conversion from BUG() to such a framework can
happen incrementally.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If we run low on space we could get a bunch of warnings out of
btrfs_block_rsv_check, but this is mostly just called via the transaction code
to see if we need to end the transaction, it expects to see failures, so let's
not WARN and freak everybody out for no reason. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we store data by raid profile in btrfs with two or more different size
disks, df command shows there is some free space in the filesystem, but the
user can not write any data in fact, df command shows the wrong free space
information of btrfs.
# mkfs.btrfs -d raid1 /dev/sda9 /dev/sda10
# btrfs-show
Label: none uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
Total devices 2 FS bytes used 28.00KB
devid 1 size 5.01GB used 2.03GB path /dev/sda9
devid 2 size 10.00GB used 2.01GB path /dev/sda10
# btrfs device scan /dev/sda9 /dev/sda10
# mount /dev/sda9 /mnt
# dd if=/dev/zero of=tmpfile0 bs=4K count=9999999999
(fill the filesystem)
# sync
# df -TH
Filesystem Type Size Used Avail Use% Mounted on
/dev/sda9 btrfs 17G 8.6G 5.4G 62% /mnt
# btrfs-show
Label: none uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
Total devices 2 FS bytes used 3.99GB
devid 1 size 5.01GB used 5.01GB path /dev/sda9
devid 2 size 10.00GB used 4.99GB path /dev/sda10
It is because btrfs cannot allocate chunks when one of the pairing disks has
no space, the free space on the other disks can not be used for ever, and should
be subtracted from the total space, but btrfs doesn't subtract this space from
the total. It is strange to the user.
This patch fixes it by calcing the free space that can be used to allocate
chunks.
Implementation:
1. get all the devices free space, and align them by stripe length.
2. sort the devices by the free space.
3. check the free space of the devices,
3.1. if it is not zero, and then check the number of the devices that has
more free space than this device,
if the number of the devices is beyond the min stripe number, the free
space can be used, and add into total free space.
if the number of the devices is below the min stripe number, we can not
use the free space, the check ends.
3.2. if the free space is zero, check the next devices, goto 3.1
This implementation is just likely fake chunk allocation.
After appling this patch, df can show correct space information:
# df -TH
Filesystem Type Size Used Avail Use% Mounted on
/dev/sda9 btrfs 17G 8.6G 0 100% /mnt
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
- make it return the start position and length of the max free space when it can
not find a suitable free space.
- make it more readability
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We cannot write data into files when when there is tiny space in the filesystem.
Reproduce steps:
# mkfs.btrfs /dev/sda1
# mount /dev/sda1 /mnt
# dd if=/dev/zero of=/mnt/tmpfile0 bs=4K count=1
# dd if=/dev/zero of=/mnt/tmpfile1 bs=4K count=99999999999999
(fill the filesystem)
# umount /mnt
# mount /dev/sda1 /mnt
# rm -f /mnt/tmpfile0
# dd if=/dev/zero of=/mnt/tmpfile0 bs=4K count=1
(failed with nospec)
But if we do the last step again, we can write data successfully. The reason of
the problem is that btrfs didn't try to commit the current transaction and
reclaim some space when chunk allocation failed.
This patch fixes it by committing the current transaction to reclaim some
space when chunk allocation fails.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we read in block groups, we'll set non-redundant groups
readonly if we find a raid1, DUP or raid10 group. But the
ro code has an off by one bug in the math around testing to
make sure out accounting doesn't go wrong.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: prevent RAID level downgrades when space is low
Btrfs: account for missing devices in RAID allocation profiles
Btrfs: EIO when we fail to read tree roots
Btrfs: fix compiler warnings
Btrfs: Make async snapshot ioctl more generic
Btrfs: pwrite blocked when writing from the mmaped buffer of the same page
Btrfs: Fix a crash when mounting a subvolume
Btrfs: fix sync subvol/snapshot creation
Btrfs: Fix page leak in compressed writeback path
Btrfs: do not BUG if we fail to remove the orphan item for dead snapshots
Btrfs: fixup return code for btrfs_del_orphan_item
Btrfs: do not do fast caching if we are allocating blocks for tree_root
Btrfs: deal with space cache errors better
Btrfs: fix use after free in O_DIRECT
The extent allocator has code that allows us to fill
allocations from any available block group, even if it doesn't
match the raid level we've requested.
This was put in because adding a new drive to a filesystem
made with the default mkfs options actually upgrades the metadata from
single spindle dup to full RAID1.
But, the code also allows us to allocate from a raid0 chunk when we
really want a raid1 or raid10 chunk. This can cause big trouble because
mkfs creates a small (4MB) raid0 chunk for data and metadata which then
goes unused for raid1/raid10 installs.
The allocator will happily wander in and allocate from that chunk when
things get tight, which is not correct.
The fix here is to make sure that we provide duplication when the
caller has asked for it. It does all the dups to be any raid level,
which preserves the dup->raid1 upgrade abilities.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we mount in RAID degraded mode without adding a new device to
replace the failed one, we can end up using the wrong RAID flags for
allocations.
This results in strange combinations of block groups (raid1 in a raid10
filesystem) and corruptions when we try to allocate blocks from single
spindle chunks on drives that are actually missing.
The first device has two small 4MB chunks in it that mkfs creates and
these are usually unused in a raid1 or raid10 setup. But, in -o degraded,
the allocator will fall back to these because the mask of desired raid groups
isn't correct.
The fix here is to count the missing devices as we build up the list
of devices in the system. This count is used when picking the
raid level to make sure we continue using the same levels that were
in place before we lost a drive.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Not being able to delete an orphan item isn't a horrible thing. The worst that
happens is the next time around we try and do the orphan cleanup and we can't
find the referenced object and just delete the item and move on.
Signed-off-by: Josef Bacik <josef@redhat.com>
Since the fast caching uses normal tree locking, we can possibly deadlock if we
get to the caching via a btrfs_search_slot() on the tree_root. So just check to
see if the root we are on is the tree root, and just don't do the fast caching.
Reported-by: Sage Weil <sage@newdream.net>
Signed-off-by: Josef Bacik <josef@redhat.com>
Currently if the space cache inode generation number doesn't match the
generation number in the space cache header we will just fail to load the space
cache, but we won't mark the space cache as an error, so we'll keep getting that
error each time somebody tries to cache that block group until we actually clear
the thing. Fix this by marking the space cache as having an error so we only
get the message once. This patch also makes it so that we don't try and setup
space cache for a block group that isn't cached, since we won't be able to write
it out anyway. None of these problems are actual problems, they are just
annoying and sub-optimal. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (24 commits)
Btrfs: don't use migrate page without CONFIG_MIGRATION
Btrfs: deal with DIO bios that span more than one ordered extent
Btrfs: setup blank root and fs_info for mount time
Btrfs: fix fiemap
Btrfs - fix race between btrfs_get_sb() and umount
Btrfs: update inode ctime when using links
Btrfs: make sure new inode size is ok in fallocate
Btrfs: fix typo in fallocate to make it honor actual size
Btrfs: avoid NULL pointer deref in try_release_extent_buffer
Btrfs: make btrfs_add_nondir take parent inode as an argument
Btrfs: hold i_mutex when calling btrfs_log_dentry_safe
Btrfs: use dget_parent where we can UPDATED
Btrfs: fix more ESTALE problems with NFS
Btrfs: handle NFS lookups properly
btrfs: make 1-bit signed fileds unsigned
btrfs: Show device attr correctly for symlinks
btrfs: Set file size correctly in file clone
btrfs: Check if dest_offset is block-size aligned before cloning file
Btrfs: handle the space_cache option properly
btrfs: Fix early enospc because 'unused' calculated with wrong sign.
...
'unused' calculated with wrong sign in reserve_metadata_bytes().
This might have lead to unwanted over-reservations.
Signed-off-by: Arne Jansen <sensille@gmx.net>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (39 commits)
Btrfs: deal with errors from updating the tree log
Btrfs: allow subvol deletion by unprivileged user with -o user_subvol_rm_allowed
Btrfs: make SNAP_DESTROY async
Btrfs: add SNAP_CREATE_ASYNC ioctl
Btrfs: add START_SYNC, WAIT_SYNC ioctls
Btrfs: async transaction commit
Btrfs: fix deadlock in btrfs_commit_transaction
Btrfs: fix lockdep warning on clone ioctl
Btrfs: fix clone ioctl where range is adjacent to extent
Btrfs: fix delalloc checks in clone ioctl
Btrfs: drop unused variable in block_alloc_rsv
Btrfs: cleanup warnings from gcc 4.6 (nonbugs)
Btrfs: Fix variables set but not read (bugs found by gcc 4.6)
Btrfs: Use ERR_CAST helpers
Btrfs: use memdup_user helpers
Btrfs: fix raid code for removing missing drives
Btrfs: Switch the extent buffer rbtree into a radix tree
Btrfs: restructure try_release_extent_buffer()
Btrfs: use the flusher threads for delalloc throttling
Btrfs: tune the chunk allocation to 5% of the FS as metadata
...
Fix up trivial conflicts in fs/btrfs/super.c and fs/fs-writeback.c, and
remove use of INIT_RCU_HEAD in fs/btrfs/extent_io.c (that init macro was
useless and removed in commit 5e8067adfd: "rcu head remove init")
These are all the cases where a variable is set, but not read which are
not bugs as far as I can see, but simply leftovers.
Still needs more review.
Found by gcc 4.6's new warnings
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We have a fairly complex set of loops around walking our list of
delalloc inodes when we find metadata delalloc space running low.
It doesn't work very well, can use large amounts of CPU and doesn't
do very efficient writeback.
This switches us to kick the bdi flusher threads instead. All dirty
data in btrfs is accounted as delalloc data, so this is very similar
in terms of what it writes, but we're able to just kick off the IO
and wait for progress.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
An earlier commit tried to keep us from allocating too many
empty metadata chunks. It was somewhat too restrictive and could
lead to ENOSPC errors on empty filesystems.
This increases the limits to about 5% of the FS size, allowing more
metadata chunks to be preallocated.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If you mount -o space_cache, the option will be persistent across mounts, but to
make sure the user knows that they did this, emit a message telling them if they
didn't mount with -o space_cache but the feature is still used.
Signed-off-by: Josef Bacik <josef@redhat.com>
If something goes wrong with the free space cache we need a way to make sure
it's not loaded on mount and that it's cleared for everybody. When you pass the
clear_cache option it will make it so all block groups are setup to be cleared,
which keeps them from being loaded and then they will be truncated when the
transaction is committed. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
There are just a few things that need to be fixed in the kernel to support mixed
data+metadata block groups. Mostly we just need to make sure that if we are
using mixed block groups that we continue to allocate mixed block groups as we
need them. Also we need to make sure __find_space_info will find our space info
if we search for DATA or METADATA only. Tested this with xfstests and it works
nicely. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
With the free space disk caching we can mark the block group as started with the
caching, but we don't have a caching ctl. This can race with anybody else who
tries to get the caching ctl before we cache (this is very hard to do btw). So
instead check to see if cache->caching_ctl is set, and if not return NULL.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
This patch actually loads the free space cache if it exists. The only thing
that really changes here is that we need to cache the block group if we're going
to remove an extent from it. Previously we did not do this since the caching
kthread would pick it up. With the on disk cache we don't have this luxury so
we need to make sure we read the on disk cache in first, and then remove the
extent, that way when the extent is unpinned the free space is added to the
block group. This has been tested with all sorts of things.
Signed-off-by: Josef Bacik <josef@redhat.com>
This is a simple bit, just dump the free space cache out to our preallocated
inode when we're writing out dirty block groups. There are a bunch of changes
in inode.c in order to account for special cases. Mostly when we're doing the
writeout we're holding trans_mutex, so we need to use the nolock transacation
functions. Also we can't do asynchronous completions since the async thread
could be blocked on already completed IO waiting for the transaction lock. This
has been tested with xfstests and btrfs filesystem balance, as well as my ENOSPC
tests. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
In order to save free space cache, we need an inode to hold the data, and we
need a special item to point at the right inode for the right block group. So
first, create a special item that will point to the right inode, and the number
of extent entries we will have and the number of bitmaps we will have. We
truncate and pre-allocate space everytime to make sure it's uptodate.
This feature will be turned on as soon as you mount with -o space_cache, however
it is safe to boot into old kernels, they will just generate the cache the old
fashion way. When you boot back into a newer kernel we will notice that we
modified and not the cache and automatically discard the cache.
Signed-off-by: Josef Bacik <josef@redhat.com>
Because btrfs_dirty_inode does a btrfs_join_transaction, it doesn't actually
reserve space. It does this so we can try and dirty the inode quickly without
having to deal with the ENOSPC problems. But if it does get back ENOSPC it
handles it properly. The problem is use_block_rsv does a WARN_ON whenever this
case happens, even tho btrfs_dirty_inode takes it into account and actually
expects to get -ENOSPC if things are particularly tight. So instead just remove
the warning. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
btrfs_commit_transaction will free our trans, but because we pass trans to
shrink_delalloc we could possibly have a use after free situation. So instead
if we commit the transaction, set trans to null and set committed to true so we
don't keep trying to commit a transaction. This fixes a panic I could reproduce
at will. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
With multi-threaded writes we were getting ENOSPC early because somebody would
come in, start flushing delalloc because they couldn't make their reservation,
and in the meantime other threads would come in and use the space that was
getting freed up, so when the original thread went to check to see if they had
space they didn't and they'd return ENOSPC. So instead if we have some free
space but not enough for our reservation, take the reservation and then start
doing the flushing. The only time we don't take reservations is when we've
already overcommitted our space, that way we don't have people who come late to
the party way overcommitting ourselves. This also moves all of the retrying and
flushing code into reserve_metdata_bytes so it's all uniform. This keeps my
fs_mark test from returning -ENOSPC as soon as it starts and actually lets me
fill up the disk. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Because the ENOSPC code over reserves super aggressively we end up allocating
chunks way more often than we should. For example with my fs_mark tests on a
2gb fs I can end up reserved 1gb just for metadata, when only 34mb of that is
being used. So instead check to see if the amount of space actually used is
less than 30% of the total space, and if so don't allocate a chunk, but only if
we have at least 256mb of free space to make sure we don't put too much pressure
on free space.
Signed-off-by: Josef Bacik <josef@redhat.com>
Currently we try and flush delalloc, but we only do that in a sort of weak way,
which works fine in most cases but if we're under heavy pressure we need to be
able to wait for flushing to happen. Also instead of checking the bytes
reserved in the block_rsv, check the space info since it is more accurate. The
sync option will be used in a future patch.
Signed-off-by: Josef Bacik <josef@redhat.com>
The global reservation stuff tries to add together DATA and METADATA used in
order to figure out how much to reserve for everything, but this doesn't work
right for mixed block groups. Instead if we have mixed block groups just set
data used to 0. Also with mixed block groups we will use bytes_may_use for
keeping track of delalloc bytes, so we need to take that into account in our
reservation calculations.
Signed-off-by: Josef Bacik <josef@redhat.com>
The new ENOSPC stuff breaks out the raid types which breaks the way we were
reporting df to the system. This fixes it back so that Available is the total
space available to data and used is the actual bytes used by the filesystem.
This means that Available is Total - data used - all of the metadata space.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
In very severe ENOSPC cases we can run out of inodes to do delalloc on, which
means we'll just keep looping trying to shrink delalloc. Instead, if we fail to
shrink delalloc 3 times in a row break out since we're not likely to make any
progress. Tested this with a 100mb fs an xfstests test 13. Before the patch it
would hang the box, with the patch we get -ENOSPC like we should. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
All the blkdev_issue_* helpers can only sanely be used for synchronous
caller. To issue cache flushes or barriers asynchronously the caller needs
to set up a bio by itself with a completion callback to move the asynchronous
state machine ahead. So drop the BLKDEV_IFL_WAIT flag that is always
specified when calling blkdev_issue_* and also remove the now unused flags
argument to blkdev_issue_flush and blkdev_issue_zeroout. For
blkdev_issue_discard we need to keep it for the secure discard flag, which
gains a more descriptive name and loses the bitops vs flag confusion.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Switch to the WRITE_FLUSH_FUA flag for log writes, remove the EOPNOTSUPP
detection for barriers and stop setting the barrier flag for discards.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: The file argument for fsync() is never null
Btrfs: handle ERR_PTR from posix_acl_from_xattr()
Btrfs: avoid BUG when dropping root and reference in same transaction
Btrfs: prohibit a operation of changing acl's mask when noacl mount option used
Btrfs: should add a permission check for setfacl
Btrfs: btrfs_lookup_dir_item() can return ERR_PTR
Btrfs: btrfs_read_fs_root_no_name() returns ERR_PTRs
Btrfs: unwind after btrfs_start_transaction() errors
Btrfs: btrfs_iget() returns ERR_PTR
Btrfs: handle kzalloc() failure in open_ctree()
Btrfs: handle error returns from btrfs_lookup_dir_item()
Btrfs: Fix BUG_ON for fs converted from extN
Btrfs: Fix null dereference in relocation.c
Btrfs: fix remap_file_pages error
Btrfs: uninitialized data is check_path_shared()
Btrfs: fix fallocate regression
Btrfs: fix loop device on top of btrfs
Tree blocks can live in data block groups in FS converted from extN.
So it's easy to trigger the BUG_ON.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (27 commits)
Btrfs: add more error checking to btrfs_dirty_inode
Btrfs: allow unaligned DIO
Btrfs: drop verbose enospc printk
Btrfs: Fix block generation verification race
Btrfs: fix preallocation and nodatacow checks in O_DIRECT
Btrfs: avoid ENOSPC errors in btrfs_dirty_inode
Btrfs: move O_DIRECT space reservation to btrfs_direct_IO
Btrfs: rework O_DIRECT enospc handling
Btrfs: use async helpers for DIO write checksumming
Btrfs: don't walk around with task->state != TASK_RUNNING
Btrfs: do aio_write instead of write
Btrfs: add basic DIO read/write support
direct-io: do not merge logically non-contiguous requests
direct-io: add a hook for the fs to provide its own submit_bio function
fs: allow short direct-io reads to be completed via buffered IO
Btrfs: Metadata ENOSPC handling for balance
Btrfs: Pre-allocate space for data relocation
Btrfs: Metadata ENOSPC handling for tree log
Btrfs: Metadata reservation for orphan inodes
Btrfs: Introduce global metadata reservation
...
This patch adds metadata ENOSPC handling for the balance code.
It is consisted by following major changes:
1. Avoid COW tree leave in the phrase of merging tree.
2. Handle interaction with snapshot creation.
3. make the backref cache can live across transactions.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Reserve metadata space for extent tree, checksum tree and root tree
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Introduce metadata reservation context for delayed allocation
and update various related functions.
This patch also introduces EXTENT_FIRST_DELALLOC control bit for
set/clear_extent_bit. It tells set/clear_bit_hook whether they
are processing the first extent_state with EXTENT_DELALLOC bit
set. This change is important if set/clear_extent_bit involves
multiple extent_state.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Besides simplify the code, this change makes sure all metadata
reservation for normal metadata operations are released after
committing transaction.
Changes since V1:
Add code that check if unlink and rmdir will free space.
Add ENOSPC handling for clone ioctl.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Introducing metadata reseravtion contexts has two major advantages.
First, it makes metadata reseravtion more traceable. Second, it can
reclaim freed space and re-add them to the itself after transaction
committed.
Besides add btrfs_block_rsv structure and related helper functions,
This patch contains following changes:
Move code that decides if freed tree block should be pinned into
btrfs_free_tree_block().
Make space accounting more accurate, mainly for handling read only
block groups.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Shrink delayed allocation space in a synchronized manner is more
controllable than flushing all delay allocated space in an async
thread.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We already have fs_info->chunk_mutex to avoid concurrent
chunk creation.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The size of reserved space is stored in space_info. If block groups
of different raid types are linked to separate space_info, changing
allocation profile will corrupt reserved space accounting.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The patch just convert all blkdev_issue_xxx function to common
set of flags. Wait/allocation semantics preserved.
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: make sure the chunk allocator doesn't create zero length chunks
Btrfs: fix data enospc check overflow
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: add check for changed leaves in setup_leaf_for_split
Btrfs: create snapshot references in same commit as snapshot
Btrfs: fix small race with delalloc flushing waitqueue's
Btrfs: use add_to_page_cache_lru, use __page_cache_alloc
Btrfs: fix chunk allocate size calculation
Btrfs: kill max_extent mount option
Btrfs: fail to mount if we have problems reading the block groups
Btrfs: check btrfs_get_extent return for IS_ERR()
Btrfs: handle kmalloc() failure in inode lookup ioctl
Btrfs: dereferencing freed memory
Btrfs: Simplify num_stripes's calculation logical for __btrfs_alloc_chunk()
Btrfs: Add error handle for btrfs_search_slot() in btrfs_read_chunk_tree()
Btrfs: Remove unnecessary finish_wait() in wait_current_trans()
Btrfs: add NULL check for do_walk_down()
Btrfs: remove duplicate include in ioctl.c
Fix trivial conflict in fs/btrfs/compression.c due to slab.h include
cleanups.
Because we account for reserved space we get from the allocator before we
actually account for allocating delalloc space, we can have a small window where
the amount of "used" space in a space_info is more than the total amount of
space in the space_info. This will cause a overflow in our check, so it will
seem like we have _tons_ of free space, and we'll allow reservations to occur
that will end up larger than the amount of space we have. I've seen users
report ENOSPC panic's in cow_file_range a few times recently, so I tried to
reproduce this problem and found I could reproduce it if I ran one of my tests
in a loop for like 20 minutes. With this patch my test ran all night without
issues. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Everytime we start a new flushing thread, we init the waitqueue if there isn't a
flushing thread running. The problem with this is we check
space_info->flushing, which we clear right before doing a wake_up on the
flushing waitqueue, which causes problems if we init the waitqueue in the middle
of clearing the flushing flagh and calling wake_up. This is hard to hit, but
the code is wrong anyway, so init the flushing/allocating waitqueue when
creating the space info and let it be. I haven't seen the panic since I've been
using this patch. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
As Yan pointed out, theres not much reason for all this complicated math to
account for file extents being split up into max_extent chunks, since they are
likely to all end up in the same leaf anyway. Since there isn't much reason to
use max_extent, just remove the option altogether so we have one less thing we
need to test.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We don't actually check the return value of btrfs_read_block_groups, so we can
possibly succeed to mount, but then fail to say read the superblock xattr for
selinux which will cause the vfs code to deactivate the super.
This is a problem because in find_free_extent we just assume that we
will find the right space_info for the allocation we want. But if we
failed to read the block groups, we won't have setup any space_info's,
and we'll hit a NULL pointer deref in find_free_extent.
This patch fixes that problem by checking the return value of
btrfs_read_block_groups, and failing out properly. I've also added a
check in find_free_extent so if for some reason we don't find an
appropriate space_info, we just return -ENOSPC.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
btrfs_find_create_tree_block() may return NULL, so we must check the returned
value, or we will access a NULL pointer.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
This patch just goes through and fixes everybody that does
lock_extent()
blah
unlock_extent()
to use
lock_extent_bits()
blah
unlock_extent_cached()
and pass around a extent_state so we only have to do the searches once per
function. This gives me about a 3 mb/s boots on my random write test. I have
not converted some things, like the relocation and ioctl's, since they aren't
heavily used and the relocation stuff is in the middle of being re-written. I
also changed the clear_extent_bit() to only unset the cached state if we are
clearing EXTENT_LOCKED and related stuff, so we can do things like this
lock_extent_bits()
clear delalloc bits
unlock_extent_cached()
without losing our cached state. I tested this thoroughly and turned on
LEAK_DEBUG to make sure we weren't leaking extent states, everything worked out
fine.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When dropping a empty tree, walk_down_tree() skips checking
extent information for the tree root. This will triggers a
BUG_ON in walk_up_proc().
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We can race with the unmount of an fs and the stopping of a kthread where we
will free the block group before we're done using it. The reason for this is
because we do not hold a reference on the block group while its caching, since
the allocator drops its reference once it exits or moves on to the next block
group. This patch fixes the problem by taking a reference to the block group
before we start caching and dropping it when we're done to make sure all
accesses to the block group are safe. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch makes us a bit less zealous about making sure we have enough free
metadata space by pearing down the size of new metadata chunks to 256mb instead
of 1gb. Also, we used to try an allocate metadata chunks when allocating data,
but that sort of thing is done elsewhere now so we can just remove it. With my
-ENOSPC test I used to have 3gb reserved for metadata out of 75gb, now I have
1.7gb. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If block group 0 is completely free, btrfs_read_block_groups will
add extent [0, BTRFS_SUPER_INFO_OFFSET) to the free space cache.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The bytes_used field in root item was originally planned to
trace the amount of used data and tree blocks. But it never
worked right since we can't trace freeing of data accurately.
This patch changes it to only trace the amount of tree blocks.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
iput() can trigger new transactions if we are dropping the
final reference, so calling it in btrfs_commit_transaction
may end up deadlock. This patch adds delayed iput to avoid
the issue.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We allow two log transactions at a time, but use same flag
to mark dirty tree-log btree blocks. So we may flush dirty
blocks belonging to newer log transaction when committing a
log transaction. This patch fixes the issue by using two
flags to mark dirty tree-log btree blocks.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: fix panic when trying to destroy a newly allocated
Btrfs: allow more metadata chunk preallocation
Btrfs: fallback on uncompressed io if compressed io fails
Btrfs: find ideal block group for caching
Btrfs: avoid null deref in unpin_extent_cache()
Btrfs: skip btrfs_release_path in btrfs_update_root and btrfs_del_root
Btrfs: fix some metadata enospc issues
Btrfs: fix how we set max_size for free space clusters
Btrfs: cleanup transaction starting and fix journal_info usage
Btrfs: fix data allocation hint start
On an FS where all of the space has not been allocated into chunks yet,
the enospc can return enospc just because the existing metadata chunks
are full.
We get around this by allowing more metadata chunks to be allocated up
to a certain limit, and finding the right limit is a little fuzzy. The
problem is the reservations for delalloc would preallocate way too much
of the FS as metadata. We need to start saying no and just force some
IO to happen.
But we also need to let a reasonable amount of the FS become metadata.
This bumps the hard limit up, later releases will have a better system.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch changes a few things. Hopefully the comments are helpfull, but
I'll try and be as verbose here.
Problem:
My fedora box was taking 1 minute and 21 seconds to boot with btrfs as root.
Part of this problem was we pick the first block group we can find and start
caching it, even if it may not have enough free space. The other problem is
we only search for cached block groups the first time around, which we won't
find any cached block groups because this is a newly mounted fs, so we end up
caching several block groups during bootup, which with alot of fragmentation
takes around 30-45 seconds to complete, which bogs down the system. So
Solution:
1) Don't cache block groups willy-nilly at first. Instead try and figure out
which block group has the most free, and therefore will take the least amount
of time to cache.
2) Don't be so picky about cached block groups. The other problem is once
we've filled up a cluster, if the block group isn't finished caching the next
time we try and do the allocation we'll completely ignore the cluster and
start searching from the beginning of the space, which makes us cache more
block groups, which slows us down even more. So instead of skipping block
groups that are not finished caching when we have a hint, only skip the block
group if it hasn't started caching yet.
There is one other tweak in here. Before if we allocated a chunk and still
couldn't find new space, we'd end up switching the space info to force another
chunk allocation. This could make us end up with way too many chunks, so keep
track of this particular case.
With this patch and my previous cluster fixes my fedora box now boots in 43
seconds, and according to the bootchart is not held up by our block group
caching at all.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: always pin metadata in discard mode
Btrfs: enable discard support
Btrfs: add -o discard option
Btrfs: properly wait log writers during log sync
Btrfs: fix possible ENOSPC problems with truncate
Btrfs: fix btrfs acl #ifdef checks
Btrfs: streamline tree-log btree block writeout
Btrfs: avoid tree log commit when there are no changes
Btrfs: only write one super copy during fsync
We have an optimization in btrfs to allow blocks to be
immediately freed if they were allocated in this transaction and never
written. Otherwise they are pinned and freed when the transaction
commits.
This isn't optimal for discard mode because immediately freeing
them means immediately discarding them. It is better to give the
block to the pinning code and letting the (slow) discard happen later.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The discard support code in btrfs currently is guarded by ifdefs for
BIO_RW_DISCARD, which is never defines as it's the name of an enum
memeber. Just remove the useless ifdefs to actually enable the code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Enable discard by default is not a good idea given the the trim speed
of SSD prototypes we've seen, and the carecteristics for many high-end
arrays. Turn of discards by default and require the -o discard option
to enable them on.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: fix file clone ioctl for bookend extents
Btrfs: fix uninit compiler warning in cow_file_range_nocow
Btrfs: constify dentry_operations
Btrfs: optimize back reference update during btrfs_drop_snapshot
Btrfs: remove negative dentry when deleting subvolumne
Btrfs: optimize fsync for the single writer case
Btrfs: async delalloc flushing under space pressure
Btrfs: release delalloc reservations on extent item insertion
Btrfs: delay clearing EXTENT_DELALLOC for compressed extents
Btrfs: cleanup extent_clear_unlock_delalloc flags
Btrfs: fix possible softlockup in the allocator
Btrfs: fix deadlock on async thread startup
This patch reading level 0 tree blocks that already use full backrefs.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch moves the delalloc flushing that occurs when we are under space
pressure off to a async thread pool. This helps since we only free up
metadata space when we actually insert the extent item, which means it takes
quite a while for space to be free'ed up if we wait on all ordered extents.
However, if space is freed up due to inline extents being inserted, we can
wake people who are waiting up early, and they can finish their work.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch fixes an issue with the delalloc metadata space reservation
code. The problem is we used to free the reservation as soon as we
allocated the delalloc region. The problem with this is if we are not
inserting an inline extent, we don't actually insert the extent item until
after the ordered extent is written out. This patch does 3 things,
1) It moves the reservation clearing stuff into the ordered code, so when
we remove the ordered extent we remove the reservation.
2) It adds a EXTENT_DO_ACCOUNTING flag that gets passed when we clear
delalloc bits in the cases where we want to clear the metadata reservation
when we clear the delalloc extent, in the case that we do an inline extent
or we invalidate the page.
3) It adds another waitqueue to the space info so that when we start a fs
wide delalloc flush, anybody else who also hits that area will simply wait
for the flush to finish and then try to make their allocation.
This has been tested thoroughly to make sure we did not regress on
performance.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Like the cluster allocating stuff, we can lockup the box with the normal
allocation path. This happens when we
1) Start to cache a block group that is severely fragmented, but has a decent
amount of free space.
2) Start to commit a transaction
3) Have the commit try and empty out some of the delalloc inodes with extents
that are relatively large.
The inodes will not be able to make the allocations because they will ask for
allocations larger than a contiguous area in the free space cache. So we will
wait for more progress to be made on the block group, but since we're in a
commit the caching kthread won't make any more progress and it already has
enough free space that wait_block_group_cache_progress will just return. So,
if we wait and fail to make the allocation the next time around, just loop and
go to the next block group. This keeps us from getting stuck in a softlockup.
Thanks,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If an ioctl-initiated transaction is open, we can't force a commit during
the free space checks in order to free up pinned extents or else we
deadlock. Just ENOSPC instead.
A more satisfying solution that reserves space for the entire user
transaction up front is forthcoming...
Signed-off-by: Sage Weil <sage@newdream.net>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
At the start of a transaction we do a btrfs_reserve_metadata_space() and
specify how many items we plan on modifying. Then once we've done our
modifications and such, just call btrfs_unreserve_metadata_space() for
the same number of items we reserved.
For keeping track of metadata needed for data I've had to add an extent_io op
for when we merge extents. This lets us track space properly when we are doing
sequential writes, so we don't end up reserving way more metadata space than
what we need.
The only place where the metadata space accounting is not done is in the
relocation code. This is because Yan is going to be reworking that code in the
near future, so running btrfs-vol -b could still possibly result in a ENOSPC
related panic. This patch also turns off the metadata_ratio stuff in order to
allow users to more efficiently use their disk space.
This patch makes it so we track how much metadata we need for an inode's
delayed allocation extents by tracking how many extents are currently
waiting for allocation. It introduces two new callbacks for the
extent_io tree's, merge_extent_hook and split_extent_hook. These help
us keep track of when we merge delalloc extents together and split them
up. Reservations are handled prior to any actually dirty'ing occurs,
and then we unreserve after we dirty.
btrfs_unreserve_metadata_for_delalloc() will make the appropriate
unreservations as needed based on the number of reservations we
currently have and the number of extents we currently have. Doing the
reservation outside of doing any of the actual dirty'ing lets us do
things like filemap_flush() the inode to try and force delalloc to
happen, or as a last resort actually start allocation on all delalloc
inodes in the fs. This has survived dbench, fs_mark and an fsx torture
test.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We now do extra checks before a balance to make sure
there is room for the balance to take place. One of
the checks was testing to see if we were trying to
balance away the last block group of a given type.
If there is no space available for new chunks, we
should not try and balance away the last block group
of a give type. But, the code wasn't checking for
available chunk space, and so it was exiting too soon.
The fix here is to combine some of the checks and make
sure we try to allocate new chunks when we're balancing
the last block group.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
After a balance it is briefly possible for the space info
field in the inode to be NULL. This adds some checks
to make sure things properly deal with the NULL value.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
As we get closer to proper -ENOSPC handling in btrfs, we need more accurate
space accounting for the space info's. Currently we exclude the free space for
the super mirrors, but the space they take up isn't accounted for in any of the
counters. This patch introduces bytes_super, which keeps track of the amount
of bytes used for a super mirror in the block group cache and space info. This
makes sure that our free space caclucations will be completely accurate.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch removes a bunch of dead code from the snapshot removal stuff. It
was confusing me when doing the metadata ENOSPC stuff so I killed it.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The box can get locked up in the allocator if we happen upon a block group
under these conditions:
1) During a commit, so caching threads cannot make progress
2) Our block group currently is in the middle of being cached
3) Our block group currently has plenty of free space in it
4) Our block group is so fragmented that it ends up having no free space chunks
larger than min_bytes calculated by btrfs_find_space_cluster.
What happens is we try and do btrfs_find_space_cluster, which fails because it
is unable to find enough free space chunks that are large than min_bytes and
are close enough together. Since the block group is not cached we do a
wait_block_group_cache_progress, which waits for the number of bytes we need,
except the block group already has _plenty_ of free space, its just severely
fragmented, so we loop and try again, ad infinitum. This patch keeps us from
waiting on the block group to finish caching if we failed to find a free space
cluster before. It also makes sure that we don't even try to find a free space
cluster if we are on our last loop in the allocator, since we will have tried
everything at this point at it is futile.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Currently, we can panic the box if the first block group we go to move is of a
type where there is no space left to move those extents. For example, if we
fill the disk up with data, and then we try to balance and we have no room to
move the data nor room to allocate new chunks, we will panic. Change this by
checking to see if we have room to move this chunk around, and if not, return
-ENOSPC and move on to the next chunk. This will make sure we remove block
groups that are moveable, like if we have alot of empty metadata block groups,
and then that way we make room to be able to balance our data chunks as well.
Tested this with an fs that would panic on btrfs-vol -b normally, but no longer
panics with this patch.
V1->V2:
-actually search for a free extent on the device to make sure we can allocate a
chunk if need be.
-fix btrfs_shrink_device to make sure we actually try to relocate all the
chunks, and then if we can't return -ENOSPC so if we are doing a btrfs-vol -r
we don't remove the device with data still on it.
-check to make sure the block group we are going to relocate isn't the last one
in that particular space
-fix a bug in btrfs_shrink_device where we would change the device's size and
not fix it if we fail to do our relocate
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch adds snapshot/subvolume destroy ioctl. A subvolume that isn't being
used and doesn't contains links to other subvolumes can be destroyed.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch contains two changes to avoid unnecessary tree block reads during
snapshot dropping.
First, check tree block's reference count and flags before reading the tree
block. if reference count > 1 and there is no need to update backrefs, we can
avoid reading the tree block.
Second, save when snapshot was created in root_key.offset. we can compare block
pointer's generation with snapshot's creation generation during updating
backrefs. If a given block was created before snapshot was created, the
snapshot can't be the tree block's owner. So we can avoid reading the block.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch gets rid of two limitations of async block group caching.
The old code delays handling pinned extents when block group is in
caching. To allocate logged file extents, the old code need wait
until block group is fully cached. To get rid of the limitations,
This patch introduces a data structure to track the progress of
caching. Base on the caching progress, we know which extents should
be added to the free space cache when handling the pinned extents.
The logged file extents are also handled in a similar way.
This patch also changes how pinned extents are tracked. The old
code uses one tree to track pinned extents, and copy the pinned
extents tree at transaction commit time. This patch makes it use
two trees to track pinned extents. One tree for extents that are
pinned in the running transaction, one tree for extents that can
be unpinned. At transaction commit time, we swap the two trees.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
blk_ioctl_discard duplicates large amounts of code from blkdev_issue_discard,
the only difference between the two is that blkdev_issue_discard needs to
send a barrier discard request and blk_ioctl_discard a non-barrier one,
and blk_ioctl_discard needs to wait on the request. To facilitates this
add a flags argument to blkdev_issue_discard to control both aspects of the
behaviour. This will be very useful later on for using the waiting
funcitonality for other callers.
Based on an earlier patch from Matthew Wilcox <matthew@wil.cx>.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
There are two main users of the extent_map tree. The
first is regular file inodes, where it is evenly spread
between readers and writers.
The second is the chunk allocation tree, which maps blocks from
logical addresses to phyiscal ones, and it is 99.99% reads.
The mapping tree is a point of lock contention during heavy IO
workloads, so this commit switches things to a rw lock.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The async caching thread can end up looping forever if a given
search puts it at the last key in a leaf. It will end up calling
btrfs_next_leaf and then checking if it needs to politely drop
the read semaphore.
Most of the time this looping isn't noticed because it is able to
make progress the next time around. But, during log replay,
we wait on the async caching thread to finish, and the async thread
is waiting on the commit, and no progress is really made.
The fix used here is to copy the key out of the next leaf,
that way our search lands there properly.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The semaphore used by the async caching threads can prevent a
transaction commit, which can make the FS appear to stall. This
releases the semaphore more often when a transaction commit is
in progress.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The async block group caching code uses the commit_root pointer
to get a stable version of the extent allocation tree for scanning.
This copy of the tree root isn't going to change and it significantly
reduces the complexity of the scanning code.
During a commit, we have a loop where we update the extent allocation
tree root. We need to loop because updating the root pointer in
the tree of tree roots may allocate blocks which may change the
extent allocation tree.
Right now the commit_root pointer is changed inside this loop. It
is more correct to change the commit_root pointer only after all the
looping is done.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
- don't stop the caching thread until btrfs_commit_super return.
- if caching is interrupted by umount, set last to (u64)-1.
otherwise the un-scanned range of block group will be considered
as free extent.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
We are racy with async block caching and unpinning extents. This patch makes
things much less complicated by only unpinning the extent if the block group is
cached. We check the block_group->cached var under the block_group->lock spin
lock. If it is set to BTRFS_CACHE_FINISHED then we update the pinned counters,
and unpin the extent and add the free space back. If it is not set to this, we
start the caching of the block group so the next time we unpin extents we can
unpin the extent. This keeps us from racing with the async caching threads,
lets us kill the fs wide async thread counter, and keeps us from having to set
DELALLOC bits for every extent we hit if there are caching kthreads going.
One thing that needed to be changed was btrfs_free_super_mirror_extents. Now
instead of just looking for LOCKED extents, we also look for DIRTY extents,
since we could have left some extents pinned in the previous transaction that
will never get freed now that we are unmounting, which would cause us to leak
memory. So btrfs_free_super_mirror_extents has been changed to
btrfs_free_pinned_extents, and it will clear the extents locked for the super
mirror, and any remaining pinned extents that may be present. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs allocates individual extents from block groups, and each
block group has a specific type. It may hold metadata, data
mirrored or striped etc.
When we balance space (btrfs-vol -b) or remove a drive (btrfs-vol -r)
we free block groups. Once a block group is freed, the space it was
using on the device may be available for use by new block groups.
btrfs_remove_block_group was clearing the flag that said
'our devices are full, don't even try to allocate new block groups',
but it was only clearing that flag for a specific type of block group.
This commit clears the full flag for all of the types of block groups,
making it much more likely that we'll be able to balance space when
the drive is close to full.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch moves the caching of the block group off to a kthread in order to
allow people to allocate sooner. Instead of blocking up behind the caching
mutex, we instead kick of the caching kthread, and then attempt to make an
allocation. If we cannot, we wait on the block groups caching waitqueue, which
the caching kthread will wake the waiting threads up everytime it finds 2 meg
worth of space, and then again when its finished caching. This is how I tested
the speedup from this
mkfs the disk
mount the disk
fill the disk up with fs_mark
unmount the disk
mount the disk
time touch /mnt/foo
Without my changes this took 11 seconds on my box, with these changes it now
takes 1 second.
Another change thats been put in place is we lock the super mirror's in the
pinned extent map in order to keep us from adding that stuff as free space when
caching the block group. This doesn't really change anything else as far as the
pinned extent map is concerned, since for actual pinned extents we use
EXTENT_DIRTY, but it does mean that when we unmount we have to go in and unlock
those extents to keep from leaking memory.
I've also added a check where when we are reading block groups from disk, if the
amount of space used == the size of the block group, we go ahead and mark the
block group as cached. This drastically reduces the amount of time it takes to
cache the block groups. Using the same test as above, except doing a dd to a
file and then unmounting, it used to take 33 seconds to umount, now it takes 3
seconds.
This version uses the commit_root in the caching kthread, and then keeps track
of how many async caching threads are running at any given time so if one of the
async threads is still running as we cross transactions we can wait until its
finished before handling the pinned extents. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Currently btrfs has a problem where it can use a ridiculous amount of RAM simply
tracking free space. As free space gets fragmented, we end up with thousands of
entries on an rb-tree per block group, which usually spans 1 gig of area. Since
we currently don't ever flush free space cache back to disk this gets to be a
bit unweildly on large fs's with lots of fragmentation.
This patch solves this problem by using PAGE_SIZE bitmaps for parts of the free
space cache. Initially we calculate a threshold of extent entries we can
handle, which is however many extent entries we can cram into 16k of ram. The
maximum amount of RAM that should ever be used to track 1 gigabyte of diskspace
will be 32k of RAM, which scales much better than we did before.
Once we pass the extent threshold, we start adding bitmaps and using those
instead for tracking the free space. This patch also makes it so that any free
space thats less than 4 * sectorsize we go ahead and put into a bitmap. This is
nice since we try and allocate out of the front of a block group, so if the
front of a block group is heavily fragmented and then has a huge chunk of free
space at the end, we go ahead and add the fragmented areas to bitmaps and use a
normal extent entry to track the big chunk at the back of the block group.
I've also taken the opportunity to revamp how we search for free space.
Previously we indexed free space via an offset indexed rb tree and a bytes
indexed rb tree. I've dropped the bytes indexed rb tree and use only the offset
indexed rb tree. This cuts the number of tree operations we were doing
previously down by half, and gives us a little bit of a better allocation
pattern since we will always start from a specific offset and search forward
from there, instead of searching for the size we need and try and get it as
close as possible to the offset we want.
I've given this a healthy amount of testing pre-new format stuff, as well as
post-new format stuff. I've booted up my fedora box which is installed on btrfs
with this patch and ran with it for a few days without issues. I've not seen
any performance regressions in any of my tests.
Since the last patch Yan Zheng fixed a problem where we could have overlapping
entries, so updating their offset inline would cause problems. Thanks,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Write dirty block groups may allocate new block, and so may add new delayed
back ref. btrfs_run_delayed_refs may make some block groups dirty.
commit_cowonly_roots does not handle the recursion properly, and some dirty
blocks can be left unwritten at commit time. This patch moves
btrfs_run_delayed_refs into the loop that writes dirty block groups, and makes
the code not break out of the loop until there are no dirty block groups or
delayed back refs.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Make an error msg look nicer by inserting a space between number and word.
Signed-off-by: Hu Tao <hu.taoo@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The new backref format has restriction on type of backref item. If a tree
block isn't referenced by its owner tree, full backrefs must be used for the
pointers in it. When a tree block loses its owner tree's reference, backrefs
for the pointers in it should be updated to full backrefs. Current
btrfs_drop_snapshot misses the code that updates backrefs, so it's unsafe for
general use.
This patch adds backrefs update code to btrfs_drop_snapshot. It isn't a
problem in the restricted form btrfs_drop_snapshot is used today, but for
general snapshot deletion this update is required.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
lookup_inline_extent_backref only checks for duplicate backref for data
extents. It assumes backrefs for tree block never conflict.
This patch makes lookup_inline_extent_backref check for duplicate backrefs
for both data and tree block, so that we can detect potential bug earlier.
This is a safety check, strictly speaking it is not required.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
There's no need to preserve this abstraction; it used to let us use
hardware crc32c support directly, but libcrc32c is already doing that for us
through the crypto API -- so we're already using the Intel crc32c
acceleration where appropriate.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Some SSDs perform best when reusing block numbers often, while
others perform much better when clustering strictly allocates
big chunks of unused space.
The default mount -o ssd will find rough groupings of blocks
where there are a bunch of free blocks that might have some
allocated blocks mixed in.
mount -o ssd_spread will make sure there are no allocated blocks
mixed in. It should perform better on lower end SSDs.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btrfs allocator uses list_for_each to walk the available block
groups when searching for free blocks. It starts off with a hint
to help find the best block group for a given allocation.
The hint is resolved into a block group, but we don't properly check
to make sure the block group we find isn't in the middle of being
freed due to filesystem shrinking or balancing. If it is being
freed, the list pointers in it are bogus and can't be trusted. But,
the code happily goes along and uses them in the list_for_each loop,
leading to all kinds of fun.
The fix used here is to check to make sure the block group we find really
is on the list before we use it. list_del_init is used when removing
it from the list, so we can do a proper check.
The allocation clustering code has a similar bug where it will trust
the block group in the current free space cluster. If our allocation
flags have changed (going from single spindle dup to raid1 for example)
because the drives in the FS have changed, we're not allowed to use
the old block group any more.
The fix used here is to check the current cluster against the
current allocation flags.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Just happened to notice a bunch of %llu vs u64 warnings. Here's a patch
to cast them all.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch makes the chunk allocator keep a good ratio of metadata vs data
block groups. By default for every 8 data block groups, we'll allocate 1
metadata chunk, or about 12% of the disk will be allocated for metadata. This
can be changed by specifying the metadata_ratio mount option.
This is simply the number of data block groups that have to be allocated to
force a metadata chunk allocation. By making sure we allocate metadata chunks
more often, we are less likely to get into situations where the whole disk
has been allocated as data block groups.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Because btrfs is copy-on-write, we end up picking new locations for
blocks very often. This makes it fairly difficult to maintain perfect
read patterns over time, but we can at least do some optimizations
for writes.
This is done today by remembering the last place we allocated and
trying to find a free space hole big enough to hold more than just one
allocation. The end result is that we tend to write sequentially to
the drive.
This happens all the time for metadata and it happens for data
when mounted -o ssd. But, the way we record it is fairly racey
and it tends to fragment the free space over time because we are trying
to allocate fairly large areas at once.
This commit gets rid of the races by adding a free space cluster object
with dedicated locking to make sure that only one process at a time
is out replacing the cluster.
The free space fragmentation is somewhat solved by allowing a cluster
to be comprised of smaller free space extents. This part definitely
adds some CPU time to the cluster allocations, but it allows the allocator
to consume the small holes left behind by cow.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch removes the pinned_mutex. The extent io map has an internal tree
lock that protects the tree itself, and since we only copy the extent io map
when we are committing the transaction we don't need it there. We also don't
need it when caching the block group since searching through the tree is also
protected by the internal map spin lock.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
This patch removes the block group alloc mutex used to protect the free space
tree for allocations and replaces it with a spin lock which is used only to
protect the free space rb tree. This means we only take the lock when we are
directly manipulating the tree, which makes us a touch faster with
multi-threaded workloads.
This patch also gets rid of btrfs_find_free_space and replaces it with
btrfs_find_space_for_alloc, which takes the number of bytes you want to
allocate, and empty_size, which is used to indicate how much free space should
be at the end of the allocation.
It will return an offset for the allocator to use. If we don't end up using it
we _must_ call btrfs_add_free_space to put it back. This is the tradeoff to
kill the alloc_mutex, since we need to make sure nobody else comes along and
takes our space.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
I've replaced the strange looping constructs with a list_for_each_entry on
space_info->block_groups. If we have a hint we just jump into the loop with
the block group and start looking for space. If we don't find anything we
start at the beginning and start looking. We never come out of the loop with a
ref on the block_group _unless_ we found space to use, then we drop it after we
set the trans block_group.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
This patch cleans up the free space cache code a bit. It better documents the
idiosyncrasies of tree_search_offset and makes the code make a bit more sense.
I took out the info allocation at the start of __btrfs_add_free_space and put it
where it makes more sense. This was left over cruft from when alloc_mutex
existed. Also all of the re-searches we do to make sure we inserted properly.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
COW means we cycle though blocks fairly quickly, and once we
free an extent on disk, it doesn't make much sense to keep the pages around.
This commit tries to immediately free the page when we free the extent,
which lowers our memory footprint significantly.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The tree logging code allows individual files or directories to be logged
without including operations on other files and directories in the FS.
It tries to commit the minimal set of changes to disk in order to
fsync the single file or directory that was sent to fsync or O_SYNC.
The tree logging code was allowing files and directories to be unlinked
if they were part of a rename operation where only one directory
in the rename was in the fsync log. This patch adds a few new rules
to the tree logging.
1) on rename or unlink, if the inode being unlinked isn't in the fsync
log, we must force a full commit before doing an fsync of the directory
where the unlink was done. The commit isn't done during the unlink,
but it is forced the next time we try to log the parent directory.
Solution: record transid of last unlink/rename per directory when the
directory wasn't already logged. For renames this is only done when
renaming to a different directory.
mkdir foo/some_dir
normal commit
rename foo/some_dir foo2/some_dir
mkdir foo/some_dir
fsync foo/some_dir/some_file
The fsync above will unlink the original some_dir without recording
it in its new location (foo2). After a crash, some_dir will be gone
unless the fsync of some_file forces a full commit
2) we must log any new names for any file or dir that is in the fsync
log. This way we make sure not to lose files that are unlinked during
the same transaction.
2a) we must log any new names for any file or dir during rename
when the directory they are being removed from was logged.
2a is actually the more important variant. Without the extra logging
a crash might unlink the old name without recreating the new one
3) after a crash, we must go through any directories with a link count
of zero and redo the rm -rf
mkdir f1/foo
normal commit
rm -rf f1/foo
fsync(f1)
The directory f1 was fully removed from the FS, but fsync was never
called on f1, only its parent dir. After a crash the rm -rf must
be replayed. This must be able to recurse down the entire
directory tree. The inode link count fixup code takes care of the
ugly details.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
btrfs_mark_buffer dirty would set dirty bits in the extent_io tree
for the buffers it was dirtying. This may require a kmalloc and it
was not atomic. So, anyone who called btrfs_mark_buffer_dirty had to
set any btree locks they were holding to blocking first.
This commit changes dirty tracking for extent buffers to just use a flag
in the extent buffer. Now that we have one and only one extent buffer
per page, this can be safely done without losing dirty bits along the way.
This also introduces a path->leave_spinning flag that callers of
btrfs_search_slot can use to indicate they will properly deal with a
path returned where all the locks are spinning instead of blocking.
Many of the btree search callers now expect spinning paths,
resulting in better btree concurrency overall.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
To avoid deadlocks and reduce latencies during some critical operations, some
transaction writers are allowed to jump into the running transaction and make
it run a little longer, while others sit around and wait for the commit to
finish.
This is a bit unfair, especially when the callers that jump in do a bunch
of IO that makes all the others procs on the box wait. This commit
reduces the stalls this produces by pre-reading file extent pointers
during btrfs_finish_ordered_io before the transaction is joined.
It also tunes the drop_snapshot code to politely wait for transactions
that have started writing out their delayed refs to finish. This avoids
new delayed refs being flooded into the queue while we're trying to
close off the transaction.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The delayed reference queue maintains pending operations that need to
be done to the extent allocation tree. These are processed by
finding records in the tree that are not currently being processed one at
a time.
This is slow because it uses lots of time searching through the rbtree
and because it creates lock contention on the extent allocation tree
when lots of different procs are running delayed refs at the same time.
This commit changes things to grab a cluster of refs for processing,
using a cursor into the rbtree as the starting point of the next search.
This way we walk smoothly through the rbtree.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When extents are freed, it is likely that we've removed the last
delayed reference update for the extent. This checks the delayed
ref tree when things are freed, and if no ref updates area left it
immediately processes the delayed ref.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The extent allocation tree maintains a reference count and full
back reference information for every extent allocated in the
filesystem. For subvolume and snapshot trees, every time
a block goes through COW, the new copy of the block adds a reference
on every block it points to.
If a btree node points to 150 leaves, then the COW code needs to go
and add backrefs on 150 different extents, which might be spread all
over the extent allocation tree.
These updates currently happen during btrfs_cow_block, and most COWs
happen during btrfs_search_slot. btrfs_search_slot has locks held
on both the parent and the node we are COWing, and so we really want
to avoid IO during the COW if we can.
This commit adds an rbtree of pending reference count updates and extent
allocations. The tree is ordered by byte number of the extent and byte number
of the parent for the back reference. The tree allows us to:
1) Modify back references in something close to disk order, reducing seeks
2) Significantly reduce the number of modifications made as block pointers
are balanced around
3) Do all of the extent insertion and back reference modifications outside
of the performance critical btrfs_search_slot code.
#3 has the added benefit of greatly reducing the btrfs stack footprint.
The extent allocation tree modifications are done without the deep
(and somewhat recursive) call chains used in the past.
These delayed back reference updates must be done before the transaction
commits, and so the rbtree is tied to the transaction. Throttling is
implemented to help keep the queue of backrefs at a reasonable size.
Since there was a similar mechanism in place for the extent tree
extents, that is removed and replaced by the delayed reference tree.
Yan Zheng <yan.zheng@oracle.com> helped review and fixup this code.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Storage allocated to different raid levels in btrfs is tracked by
a btrfs_space_info structure, and all of the current space_infos are
collected into a list_head.
Most filesystems have 3 or 4 of these structs total, and the list is
only changed when new raid levels are added or at unmount time.
This commit adds rcu locking on the list head, and properly frees
things at unmount time. It also clears the space_info->full flag
whenever new space is added to the FS.
The locking for the space info list goes like this:
reads: protected by rcu_read_lock()
writes: protected by the chunk_mutex
At unmount time we don't need special locking because all the readers
are gone.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
btrfs_tree_locked was being used to make sure a given extent_buffer was
properly locked in a few places. But, it wasn't correct for UP compiled
kernels.
This switches it to using assert_spin_locked instead, and renames it to
btrfs_assert_tree_locked to better reflect how it was really being used.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This fixes a problem where we could return -ENOSPC when we may actually have
plenty of space, the space is just pinned. Instead of returning -ENOSPC
immediately, commit the transaction first and then try and do the allocation
again.
This patch also does chunk allocation for metadata if we pass the 80%
threshold for metadata space. This will help with stack usage since the chunk
allocation will happen early on, instead of when the allocation is happening.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
This is a step in the direction of better -ENOSPC handling. Instead of
checking the global bytes counter we check the space_info bytes counters to
make sure we have enough space.
If we don't we go ahead and try to allocate a new chunk, and then if that fails
we return -ENOSPC. This patch adds two counters to btrfs_space_info,
bytes_delalloc and bytes_may_use.
bytes_delalloc account for extents we've actually setup for delalloc and will
be allocated at some point down the line.
bytes_may_use is to keep track of how many bytes we may use for delalloc at
some point. When we actually set the extent_bit for the delalloc bytes we
subtract the reserved bytes from the bytes_may_use counter. This keeps us from
not actually being able to allocate space for any delalloc bytes.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
btrfs_record_root_in_trans needs the trans_mutex held to make sure two
callers don't race to setup the root in a given transaction. This adds
it to all the places that were missing it.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Btrfs is currently using spin_lock_nested with a nested value based
on the tree depth of the block. But, this doesn't quite work because
the max tree depth is bigger than what spin_lock_nested can deal with,
and because locks are sometimes taken before the level field is filled in.
The solution here is to use lockdep_set_class_and_name instead, and to
set the class before unlocking the pages when the block is read from the
disk and just after init of a freshly allocated tree block.
btrfs_clear_path_blocking is also changed to take the locks in the proper
order, and it also makes sure all the locks currently held are properly
set to blocking before it tries to retake the spinlocks. Otherwise, lockdep
gets upset about bad lock orderin.
The lockdep magic cam from Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Larger metadata clusters can significantly improve writeback performance
on ssd drives with large erasure blocks. The larger clusters make it
more likely a given IO will completely overwrite the ssd block, so it
doesn't have to do an internal rwm cycle.
On spinning media, lager metadata clusters end up spreading out the
metadata more over time, which makes fsck slower, so we don't want this
to be the default.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Theres a slight problem with finish_current_insert, if we set all to 1 and then
go through and don't actually skip any of the extents on the pending list, we
could exit right after we've added new extents.
This is a problem because by inserting the new extents we could have gotten new
COW's to happen and such, so we may have some pending updates to do or even
more inserts to do after that.
So this patch will only exit if we have never skipped any of the extents in the
pending list, and we have no extents to insert, this will make sure that all of
the pending work is truly done before we return. I've been running with this
patch for a few days with all of my other testing and have not seen issues.
Thanks,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Every transaction in btrfs creates a new snapshot, and then schedules the
snapshot from the last transaction for deletion. Snapshot deletion
works by walking down the btree and dropping the reference counts
on each btree block during the walk.
If if a given leaf or node has a reference count greater than one,
the reference count is decremented and the subtree pointed to by that
node is ignored.
If the reference count is one, walking continues down into that node
or leaf, and the references of everything it points to are decremented.
The old code would try to work in small pieces, walking down the tree
until it found the lowest leaf or node to free and then returning. This
was very friendly to the rest of the FS because it didn't have a huge
impact on other operations.
But it wouldn't always keep up with the rate that new commits added new
snapshots for deletion, and it wasn't very optimal for the extent
allocation tree because it wasn't finding leaves that were close together
on disk and processing them at the same time.
This changes things to walk down to a level 1 node and then process it
in bulk. All the leaf pointers are sorted and the leaves are dropped
in order based on their extent number.
The extent allocation tree and commit code are now fast enough for
this kind of bulk processing to work without slowing the rest of the FS
down. Overall it does less IO and is better able to keep up with
snapshot deletions under high load.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When a block goes through cow, we update the reference counts of
everything that block points to. The internal pointers of the block
can be in just about any order, and it is likely to have clusters of
things that are close together and clusters of things that are not.
To help reduce the seeks that come with updating all of these reference
counts, sort them by byte number before actual updates are done.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
To improve performance, btrfs_sync_log merges tree log sync
requests. But it wrongly merges sync requests for different
tree logs. If multiple tree logs are synced at the same time,
only one of them actually gets synced.
This patch has following changes to fix the bug:
Move most tree log related fields in btrfs_fs_info to
btrfs_root. This allows merging sync requests separately
for each tree log.
Don't insert root item into the log root tree immediately
after log tree is allocated. Root item for log tree is
inserted when log tree get synced for the first time. This
allows syncing the log root tree without first syncing all
log trees.
At tree-log sync, btrfs_sync_log first sync the log tree;
then updates corresponding root item in the log root tree;
sync the log root tree; then update the super block.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
replace_one_extent searches tree leaves for references to a given extent. It
stops searching if it goes beyond the last possible position.
The last possible position is computed by adding the starting offset of a found
file extent to the full size of the extent. The code uses physical size of the
extent as the full size. This is incorrect when compression is used.
The fix is get the full size from ram_bytes field of file extent item.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
btrfs_extent_post_op calls finish_current_insert and del_pending_extents. They
both may enter infinite loops.
finish_current_insert enters infinite loop if it only finds some backrefs to
update. The fix is to check for pending backref updates before restarting the
loop.
The infinite loop in del_pending_extents is due to a the skipped variable
not being properly reset before looping around.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Merge list_for_each* and list_entry to list_for_each_entry*
Signed-off-by: Qinghuang Feng <qhfeng.kernel@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch contains following things.
1) Limit the max size of btrfs_ordered_sum structure to PAGE_SIZE. This
struct is kmalloced so we want to keep it reasonable.
2) Replace copy_extent_csums by btrfs_lookup_csums_range. This was
duplicated code in tree-log.c
3) Remove replay_one_csum. csum items are replayed at the same time as
replaying file extents. This guarantees we only replay useful csums.
4) nbytes accounting fix.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This is a patch to fix discard semantic to make Btrfs work with FTL and SSD.
We can improve FTL's performance by telling it which sectors are freed by file
system. But if we don't tell FTL the information of free sectors in proper
time, the transaction mechanism of Btrfs will be destroyed and Btrfs could not
roll back the previous transaction under the power loss condition.
There are some problems in the old implementation:
1, In __free_extent(), the pinned down extents should not be discarded.
2, In free_extents(), the free extents are all pinned, so they need to
be discarded in transaction committing time instead of free_extents().
3, The reserved extent used by log tree should be discard too.
This patch change discard behavior as follows:
1, For the extents which need to be free at once,
we discard them in update_block_group().
2, Delay discarding the pinned extent in btrfs_finish_extent_commit()
when committing transaction.
3, Remove discarding from free_extents() and __free_extent()
4, Add discard interface into btrfs_free_reserved_extent()
5, Discard sectors before updating the free space cache, otherwise,
FTL will destroy file system data.
There is a race in relocate_inode_pages, it happens when
find_delalloc_range finds the delalloc extent before the
boundary bit is set. Thank you,
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This adds the missing block accounting code to finish_current_insert and makes
block accounting for root item properly protected by the delalloc spin lock.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Btrfs maintains a cache of blocks available for allocation in ram. The
code that frees extents was marking the extents free and then deleting
the checksum items.
This meant it was possible the extent would be reallocated before the
checksum item was actually deleted, leading to races and other
problems as the checksums were updated for the newly allocated extent.
The fix is to delete the checksum before marking the extent free.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The delalloc lock doesn't need to have irqs disabled, nobody that
changes the number of delalloc bytes in the FS is running with irqs off.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Checksums on data can be disabled by mount option, so it's
possible some data extents don't have checksums or have
invalid checksums. This causes trouble for data relocation.
This patch contains following things to make data relocation
work.
1) make nodatasum/nodatacow mount option only affects new
files. Checksums and COW on data are only controlled by the
inode flags.
2) check the existence of checksum in the nodatacow checker.
If checksums exist, force COW the data extent. This ensure that
checksum for a given block is either valid or does not exist.
3) update data relocation code to properly handle the case
of checksum missing.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This patch makes seed device possible to be shared by
multiple mounted file systems. The sharing is achieved
by cloning seed device's btrfs_fs_devices structure.
Thanks you,
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
The block group structs are referenced in many different
places, and it's not safe to free while balancing. So, those block
group structs were simply leaked instead.
This patch replaces the block group pointer in the inode with the starting byte
offset of the block group and adds reference counting to the block group
struct.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This finishes off the new checksumming code by removing csum items
for extents that are no longer in use.
The trick is doing it without racing because a single csum item may
hold csums for more than one extent. Extra checks are added to
btrfs_csum_file_blocks to make sure that we are using the correct
csum item after dropping locks.
A new btrfs_split_item is added to split a single csum item so it
can be split without dropping the leaf lock. This is used to
remove csum bytes from the middle of an item.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch implements superblock duplication. Superblocks
are stored at offset 16K, 64M and 256G on every devices.
Spaces used by superblocks are preserved by the allocator,
which uses a reverse mapping function to find the logical
addresses that correspond to superblocks. Thank you,
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Shut up various sparse warnings about symbols that should be either
static or have their declarations in scope.
Signed-off-by: Christoph Hellwig <hch@lst.de>
This the lockdep complaint by having a different mutex to gaurd caching the
block group, so you don't end up with this backwards dependancy. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
The btrfs git kernel trees is used to build a standalone tree for
compiling against older kernels. This commit makes the standalone tree
work with 2.6.27
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* open/close_bdev_excl -> open/close_bdev_exclusive
* blkdev_issue_discard takes a GFP mask now
* Fix blkdev_issue_discard usage now that it is enabled
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch fixes what I hope is the last early ENOSPC bug left. I did not know
that pinned extents would merge into one big extent when inserted on to the
pinned extent tree, so I was adding free space to a block group that could
possibly span multiple block groups.
This is a big issue because first that space doesn't exist in that block group,
and second we won't actually use that space because there are a bunch of other
checks to make sure we're allocating within the constraints of the block group.
This patch fixes the problem by adding the btrfs_add_free_space to
btrfs_update_pinned_extents which makes sure we are adding the appropriate
amount of free space to the appropriate block group. Thanks much to Lee Trager
for running my myriad of debug patches to help me track this problem down.
Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
In insert_extents(), when ret==1 and last is not zero, it should
check if the current inserted item is the last item in this batching
inserts. If so, it should just break from loop. If not, 'cur =
insert_list->next' will make no sense because the list is empty now,
and 'op' will point to an unexpectable place.
There are also some trivial fixs in this patch including one comment
typo error and deleting two redundant lines.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In my batch delete/update/insert patch I introduced a free space leak. The
extent that we do the original search on in free_extents is never pinned, so we
always update the block saying that it has free space, but the free space never
actually gets added to the free space tree, since op->del will always be 0 and
it's never actually added to the pinned extents tree.
This patch fixes this problem by making sure we call pin_down_bytes on the
pending extent op and set op->del to the return value of pin_down_bytes so
update_block_group is called with the right value. This seems to fix the case
where we were getting ENOSPC when there was plenty of space available.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Seed device is a special btrfs with SEEDING super flag
set and can only be mounted in read-only mode. Seed
devices allow people to create new btrfs on top of it.
The new FS contains the same contents as the seed device,
but it can be mounted in read-write mode.
This patch does the following:
1) split code in btrfs_alloc_chunk into two parts. The first part does makes
the newly allocated chunk usable, but does not do any operation that modifies
the chunk tree. The second part does the the chunk tree modifications. This
division is for the bootstrap step of adding storage to the seed device.
2) Update device management code to handle seed device.
The basic idea is: For an FS grown from seed devices, its
seed devices are put into a list. Seed devices are
opened on demand at mounting time. If any seed device is
missing or has been changed, btrfs kernel module will
refuse to mount the FS.
3) make btrfs_find_block_group not return NULL when all
block groups are read-only.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This patch adds mount ro and remount support. The main
changes in patch are: adding btrfs_remount and related
helper function; splitting the transaction related code
out of close_ctree into btrfs_commit_super; updating
allocator to properly handle read only block group.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
While profiling the allocator I noticed a good amount of time was being spent in
finish_current_insert and del_pending_extents, and as the filesystem filled up
more and more time was being spent in those functions. This patch aims to try
and reduce that problem. This happens two ways
1) track if we tried to delete an extent that we are going to update or insert.
Once we get into finish_current_insert we discard any of the extents that were
marked for deletion. This saves us from doing unnecessary work almost every
time finish_current_insert runs.
2) Batch insertion/updates/deletions. Instead of doing a btrfs_search_slot for
each individual extent and doing the needed operation, we instead keep the leaf
around and see if there is anything else we can do on that leaf. On the insert
case I introduced a btrfs_insert_some_items, which will take an array of keys
with an array of data_sizes and try and squeeze in as many of those keys as
possible, and then return how many keys it was able to insert. In the update
case we search for an extent ref, update the ref and then loop through the leaf
to see if any of the other refs we are looking to update are on that leaf, and
then once we are done we release the path and search for the next ref we need to
update. And finally for the deletion we try and delete the extent+ref in pairs,
so we will try to find extent+ref pairs next to the extent we are trying to free
and free them in bulk if possible.
This along with the other cluster fix that Chris pushed out a bit ago helps make
the allocator preform more uniformly as it fills up the disk. There is still a
slight drop as we fill up the disk since we start having to stick new blocks in
odd places which results in more COW's than on a empty fs, but the drop is not
nearly as severe as it was before.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
When we fail to allocate a new block group, we should still do the
checks to make sure allocations try again with the minimum requested
allocation size.
This also fixes a deadlock that come from a missed down_read in
the chunk allocation failure handling.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The allocator wasn't catching all of the cases where it needed to do
extra loops because the check to enforce them wasn't happening early
enough.
When the allocator decided to increase the size of the allocation
for metadata clustering, it wasn't always setting the empty_size to
include the extra (optional) bytes. This also fixes the empty_size field
to be correct.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The loop searching for free space would exit out too soon when
metadata clustering was trying to allocate a large extent. This makes
sure a full scan of the free space is done searching for only the
minimum extent size requested by the higher layers.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When metadata allocation clustering has to fall back to unclustered
allocs because large free areas could not be found, it was sometimes
substracting too much from the total bytes to allocate. This would
make it wrap below zero.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In comes cases the empty cluster was added twice to the total number of
bytes the allocator was trying to find.
With empty clustering on, the hint byte was sometimes outside of the
block group. Add an extra goto to find the correct block group.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This lowers the empty cluster target for metadata allocations. The lower
target makes it easier to do allocations and still seems to perform well.
It also fixes the allocator loop to drop the empty cluster when things
start getting difficult, avoiding false enospc warnings.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The allocator uses the last allocation as a starting point for metadata
allocations, and tries to allocate in clusters of at least 256k.
If the search for a free block fails to find the expected block, this patch
forces a new cluster to be found in the free list.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When reading compressed extents, try to put pages into the page cache
for any pages covered by the compressed extent that readpages didn't already
preload.
Add an async work queue to handle transformations at delayed allocation processing
time. Right now this is just compression. The workflow is:
1) Find offsets in the file marked for delayed allocation
2) Lock the pages
3) Lock the state bits
4) Call the async delalloc code
The async delalloc code clears the state lock bits and delalloc bits. It is
important this happens before the range goes into the work queue because
otherwise it might deadlock with other work queue items that try to lock
those extent bits.
The file pages are compressed, and if the compression doesn't work the
pages are written back directly.
An ordered work queue is used to make sure the inodes are written in the same
order that pdflush or writepages sent them down.
This changes extent_write_cache_pages to let the writepage function
update the wbc nr_written count.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch updates btrfs-progs for fallocate support.
fallocate is a little different in Btrfs because we need to tell the
COW system that a given preallocated extent doesn't need to be
cow'd as long as there are no snapshots of it. This leverages the
-o nodatacow checks.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This patch simplifies the nodatacow checker. If all references
were created after the latest snapshot, then we can avoid COW
safely. This patch also updates run_delalloc_nocow to do more
fine-grained checking.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
When dropping middle part of an extent, btrfs_drop_extents truncates
the extent at first, then inserts a bookend extent.
Since truncation and insertion can't be done atomically, there is a small
period that the bookend extent isn't in the tree. This causes problem for
functions that search the tree for file extent item. The way to fix this is
lock the range of the bookend extent before truncation.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
finish_current_insert and del_pending_extents process extent tree modifications
that build up while we are changing the extent tree. It is a confusing
bit of code that prevents recursion.
Both functions run through a list of pending operations and both funcs
add to the list of pending operations. If you have two procs in either
one of them, they can end up looping forever making more work for each other.
This patch makes them walk forward through the list of pending changes instead
of always trying to process the entire list. At transaction commit
time, we catch any changes that were left over.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch adds transaction IDs to root tree pointers.
Transaction IDs in tree pointers are compared with the
generation numbers in block headers when reading root
blocks of trees. This can detect some types of IO errors.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This patch removes the giant fs_info->alloc_mutex and replaces it with a bunch
of little locks.
There is now a pinned_mutex, which is used when messing with the pinned_extents
extent io tree, and the extent_ins_mutex which is used with the pending_del and
extent_ins extent io trees.
The locking for the extent tree stuff was inspired by a patch that Yan Zheng
wrote to fix a race condition, I cleaned it up some and changed the locking
around a little bit, but the idea remains the same. Basically instead of
holding the extent_ins_mutex throughout the processing of an extent on the
extent_ins or pending_del trees, we just hold it while we're searching and when
we clear the bits on those trees, and lock the extent for the duration of the
operations on the extent.
Also to keep from getting hung up waiting to lock an extent, I've added a
try_lock_extent so if we cannot lock the extent, move on to the next one in the
tree and we'll come back to that one. I have tested this heavily and it does
not appear to break anything. This has to be applied on top of my
find_free_extent redo patch.
I tested this patch on top of Yan's space reblancing code and it worked fine.
The only thing that has changed since the last version is I pulled out all my
debugging stuff, apparently I forgot to run guilt refresh before I sent the
last patch out. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
So there is an odd case where we can possibly return -ENOSPC when there is in
fact space to be had. It only happens with Metadata writes, and happens _very_
infrequently. What has to happen is we have to allocate have allocated out of
the first logical byte on the disk, which would set last_alloc to
first_logical_byte(root, 0), so search_start == orig_search_start. We then
need to allocate for normal metadata, so BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DUP. We will do a block lookup for the given search_start,
block_group_bits() won't match and we'll go to choose another block group.
However because search_start matches orig_search_start we go to see if we can
allocate a chunk.
If we are in the situation that we cannot allocate a chunk, we fail and ENOSPC.
This is kind of a big flaw of the way find_free_extent works, as it along with
find_free_space loop through _all_ of the block groups, not just the ones that
we want to allocate out of. This patch completely kills find_free_space and
rolls it into find_free_extent. I've introduced a sort of state machine into
this, which will make it easier to get cache miss information out of the
allocator, and will work well with my locking changes.
The basic flow is this: We have the variable loop which is 0, meaning we are
in the hint phase. We lookup the block group for the hint, and lookup the
space_info for what we want to allocate out of. If the block group we were
pointed at by the hint either isn't of the correct type, or just doesn't have
the space we need, we set head to space_info->block_groups, so we start at the
beginning of the block groups for this particular space info, and loop through.
This is also where we add the empty_cluster to total_needed. At this point
loop is set to 1 and we just loop through all of the block groups for this
particular space_info looking for the space we need, just as find_free_space
would have done, except we only hit the block groups we want and not _all_ of
the block groups. If we come full circle we see if we can allocate a chunk.
If we cannot of course we exit with -ENOSPC and we are good. If not we start
over at space_info->block_groups and loop through again, with loop == 2. If we
come full circle and haven't found what we need then we exit with -ENOSPC.
I've been running this for a couple of days now and it seems stable, and I
haven't yet hit a -ENOSPC when there was plenty of space left.
Also I've made a groups_sem to handle the group list for the space_info. This
is part of my locking changes, but is relatively safe and seems better than
holding the space_info spinlock over that entire search time. Thanks,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
This patch improves the space balancing code to keep more sharing
of tree blocks. The only case that breaks sharing of tree blocks is
data extents get fragmented during balancing. The main changes in
this patch are:
Add a 'drop sub-tree' function. This solves the problem in old code
that BTRFS_HEADER_FLAG_WRITTEN check breaks sharing of tree block.
Remove relocation mapping tree. Relocation mappings are stored in
struct btrfs_ref_path and updated dynamically during walking up/down
the reference path. This reduces CPU usage and simplifies code.
This patch also fixes a bug. Root items for reloc trees should be
updated in btrfs_free_reloc_root.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Due to the optimization for truncate, tree leaves only containing
checksum items can be deleted without being COW'ed first. This causes
reference cache misses. The way to fix the miss is create cache
entries for tree leaves only contain checksum.
This patch also fixes a -EEXIST issue in shared reference cache.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
The offset field in struct btrfs_extent_ref records the position
inside file that file extent is referenced by. In the new back
reference system, tree leaves holding references to file extent
are recorded explicitly. We can scan these tree leaves very quickly, so the
offset field is not required.
This patch also makes the back reference system check the objectid
when extents are in deleting.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
This patch makes btrfs count space allocated to file in bytes instead
of 512 byte sectors.
Everything else in btrfs uses a byte count instead of sector sizes or
blocks sizes, so this fits better.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
The tree logging code was trying to separate tree log allocations
from normal metadata allocations to improve writeback patterns during
an fsync.
But, the code was not effective and ended up just mixing tree log
blocks with regular metadata. That seems to be working fairly well,
so the last_log_alloc code can be removed.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This fixes a deadlock that happens between the alloc_mutex and chunk_mutex.
Process A comes in, decides to do a do_chunk_alloc, which takes the
chunk_mutex, and is holding the alloc_mutex because the only way you get to
do_chunk_alloc is by holding the alloc_mutex. btrfs_alloc_chunk does its thing
and goes to insert a new item, which results in a cow of the block.
We get into del_pending_extents from there, where if we need to be rescheduled
we drop the alloc_mutex and schedule. At this point process B comes in to do
an allocation and gets the alloc_mutex, and because process A did not do the
chunk allocation completely it thinks its a good time to do a chunk allocation
as well, and hangs on the chunk_mutex.
Process A wakes up and tries to take the alloc_mutex and cannot. The way to
fix this is do a mutex_trylock() on chunk_mutex. If we return 0 we didn't get
the lock, and if this is just a "hey it may be a good time to allocate a chunk"
then we just exit. If we are trying to force an allocation then we reschedule
and keep trying to acquire the chunk_mutex. If once we acquire it the space is
already full then we can just exit, otherwise we can continue with the chunk
allocation. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
When reading in block groups, a global mask of the available raid policies
should be adjusted based on the types of block groups found on disk. This
global mask is then used to decide which raid policy to use for new
block groups.
The recent allocator changes dropped the call that updated the global
mask, making all the block groups allocated at run time single striped
onto a single drive.
This also fixes the async worker threads to set any thread that uses
the requeue mechanism as busy. This allows us to avoid blocking
on get_request_wait for the async bio submission threads.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch fixes a problem where we end up seeking too much when *last_ptr is
valid. This happens because btrfs_lookup_first_block_group only returns a
block group that starts on or after the given search start, so if the
search_start is in the middle of a block group it will return the block group
after the given search_start, which is suboptimal.
This patch fixes that by doing a btrfs_lookup_block_group, which will return
the block group that contains the given search start. If we fail to find a
block group, we fall back on btrfs_lookup_first_block_group so we can find the
next block group, not sure if this is absolutely needed, but better safe than
sorry.
Also if we can't find the block group that we need, or it happens to not be of
the right type, we need to add empty_cluster since *last_ptr could point to a
mismatched block group, which means we need to start over with empty_cluster
added to total needed. Thank you,
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch updates the space balancing code to utilize the new
backref format. Before, btrfs-vol -b would break any COW links
on data blocks or metadata. This was slow and caused the amount
of space used to explode if a large number of snapshots were present.
The new code can keeps the sharing of all data extents and
most of the tree blocks.
To maintain the sharing of data extents, the space balance code uses
a seperate inode hold data extent pointers, then updates the references
to point to the new location.
To maintain the sharing of tree blocks, the space balance code uses
reloc trees to relocate tree blocks in reference counted roots.
There is one reloc tree for each subvol, and all reloc trees share
same root key objectid. Reloc trees are snapshots of the latest
committed roots of subvols (root->commit_root).
To relocate a tree block referenced by a subvol, there are two steps.
COW the block through subvol's reloc tree, then update block pointer in
the subvol to point to the new block. Since all reloc trees share
same root key objectid, doing special handing for tree blocks
owned by them is easy. Once a tree block has been COWed in one
reloc tree, we can use the resulting new block directly when the
same block is required to COW again through other reloc trees.
In this way, relocated tree blocks are shared between reloc trees,
so they are also shared between subvols.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs has a cache of reference counts in leaves, allowing it to
avoid reading tree leaves while deleting snapshots. To reduce
contention with multiple subvolumes, this cache is private to each
subvolume.
This patch adds shared reference cache support. The new space
balancing code plays with multiple subvols at the same time, So
the old per-subvol reference cache is not well suited.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* Reserved extent accounting: reserved extents have been
allocated in the rbtrees that track free space but have not
been allocated on disk. They were never properly accounted for
in the past, making it hard to know how much space was really free.
* btrfs_find_block_group used to return NULL for block groups that
had been removed by the space balancing code. This made it hard
to account for space during the final stages of a balance run.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The code to free block groups needs to drop the space info spin lock
before calling btrfs_remove_free_space_cache (which can schedule).
This is safe because at unmount time, nobody else is going to play
with the block groups.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch makes the back reference system to explicit record the
location of parent node for all types of extents. The location of
parent node is placed into the offset field of backref key. Every
time a tree block is balanced, the back references for the affected
lower level extents are updated.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Tree log blocks are only reserved, and should not ever get fully
allocated on disk. This check makes sure they stay out of the
extent tree.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
1) replace the per fs_info extent_io_tree that tracked free space with two
rb-trees per block group to track free space areas via offset and size. The
reason to do this is because most allocations come with a hint byte where to
start, so we can usually find a chunk of free space at that hint byte to satisfy
the allocation and get good space packing. If we cannot find free space at or
after the given offset we fall back on looking for a chunk of the given size as
close to that given offset as possible. When we fall back on the size search we
also try to find a slot as close to the size we want as possible, to avoid
breaking small chunks off of huge areas if possible.
2) remove the extent_io_tree that tracked the block group cache from fs_info and
replaced it with an rb-tree thats tracks block group cache via offset. also
added a per space_info list that tracks the block group cache for the particular
space so we can lookup related block groups easily.
3) cleaned up the allocation code to make it a little easier to read and a
little less complicated. Basically there are 3 steps, first look from our
provided hint. If we couldn't find from that given hint, start back at our
original search start and look for space from there. If that fails try to
allocate space if we can and start looking again. If not we're screwed and need
to start over again.
4) small fixes. there were some issues in volumes.c where we wouldn't allocate
the rest of the disk. fixed cow_file_range to actually pass the alloc_hint,
which has helped a good bit in making the fs_mark test I run have semi-normal
results as we run out of space. Generally with data allocations we don't track
where we last allocated from, so everytime we did a data allocation we'd search
through every block group that we have looking for free space. Now searching a
block group with no free space isn't terribly time consuming, it was causing a
slight degradation as we got more data block groups. The alloc_hint has fixed
this slight degredation and made things semi-normal.
There is still one nagging problem I'm working on where we will get ENOSPC when
there is definitely plenty of space. This only happens with metadata
allocations, and only when we are almost full. So you generally hit the 85%
mark first, but sometimes you'll hit the BUG before you hit the 85% wall. I'm
still tracking it down, but until then this seems to be pretty stable and make a
significant performance gain.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
cache block group had a few bugs in the error handling code,
this makes sure paths get properly released and the correct return value
goes out.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This is the same way the transaction code makes sure that all the
other tree blocks are safely on disk. There's an extent_io tree
for each root, and any blocks allocated to the tree logs are
recorded in that tree.
At tree-log sync, the extent_io tree is walked to flush down the
dirty pages and wait for them.
The main benefit is less time spent walking the tree log and skipping
clean pages, and getting sequential IO down to the drive.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Since tree log blocks get freed every transaction, they never really
need to be written to disk. This skips the step where we update
metadata to record they were allocated.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* Pin down data blocks to prevent them from being reallocated like so:
trans 1: allocate file extent
trans 2: free file extent
trans 3: free file extent during old snapshot deletion
trans 3: allocate file extent to new file
trans 3: fsync new file
Before the tree logging code, this was legal because the fsync
would commit the transation that did the final data extent free
and the transaction that allocated the extent to the new file
at the same time.
With the tree logging code, the tree log subtransaction can commit
before the transaction that freed the extent. If we crash,
we're left with two different files using the extent.
* Don't wait in start_transaction if log replay is going on. This
avoids deadlocks from iput while we're cleaning up link counts in the
replay code.
* Don't deadlock in replay_one_name by trying to read an inode off
the disk while holding paths for the directory
* Hold the buffer lock while we mark a buffer as written. This
closes a race where someone is changing a buffer while we write it.
They are supposed to mark it dirty again after they change it, but
this violates the cow rules.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
File syncs and directory syncs are optimized by copying their
items into a special (copy-on-write) log tree. There is one log tree per
subvolume and the btrfs super block points to a tree of log tree roots.
After a crash, items are copied out of the log tree and back into the
subvolume. See tree-log.c for all the details.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Far from the perfect fix, but these structs are small. TODO for the
next release. The block group cache structs are referenced in many
different places, and it isn't safe to just free them while resizing.
A real fix will be a larger change to the allocator so that it doesn't
have to carry about the block group cache structs to find good places
to search for free blocks.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* Make walk_down_tree wake up throttled tasks more often
* Make walk_down_tree call cond_resched during long loops
* As the size of the ref cache grows, wait longer in throttle
* Get rid of the reada code in walk_down_tree, the leaves don't get
read anymore, thanks to the ref cache.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
A btree block cow has two parts, the first is to allocate a destination
block and the second is to copy the old bock over.
The first part needs locks in the extent allocation tree, and may need to
do IO. This changeset splits that into a separate function that can be
called without any tree locks held.
btrfs_search_slot is changed to drop its path and start over if it has
to COW a contended block. This often means that many writers will
pre-alloc a new destination for a the same contended block, but they
cache their prealloc for later use on lower levels in the tree.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
While dropping snapshots, walk_down_tree does most of the work of checking
reference counts and limiting tree traversal to just the blocks that
we are freeing.
It dropped and held the allocation mutex in strange and confusing ways,
this commit changes it to only hold the mutex while actually freeing a block.
The rest of the checks around reference counts should be safe without the lock
because we only allow one process in btrfs_drop_snapshot at a time. Other
processes dropping reference counts should not drop it to 1 because
their tree roots already have an extra ref on the block.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This avoids waiting for transactions with pages locked by breaking out
the code to wait for the current transaction to close into a function
called by btrfs_throttle.
It also lowers the limits for where we start throttling.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The memory reclaiming issue happens when snapshot exists. In that
case, some cache entries may not be used during old snapshot dropping,
so they will remain in the cache until umount.
The patch adds a field to struct btrfs_leaf_ref to record create time. Besides,
the patch makes all dead roots of a given snapshot linked together in order of
create time. After a old snapshot was completely dropped, we check the dead
root list and remove all cache entries created before the oldest dead root in
the list.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
To check whether a given file extent is referenced by multiple snapshots, the
checker walks down the fs tree through dead root and checks all tree blocks in
the path.
We can easily detect whether a given tree block is directly referenced by other
snapshot. We can also detect any indirect reference from other snapshot by
checking reference's generation. The checker can always detect multiple
references, but can't reliably detect cases of single reference. So btrfs may
do file data cow even there is only one reference.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
A large reference cache is directly related to a lot of work pending
for the cleaner thread. This throttles back new operations based on
the size of the reference cache so the cleaner thread will be able to keep
up.
Overall, this actually makes the FS faster because the cleaner thread will
be more likely to find things in cache.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This changes the reference cache to make a single cache per root
instead of one cache per transaction, and to key by the byte number
of the disk block instead of the keys inside.
This makes it much less likely to have cache misses if a snapshot
or something has an extra reference on a higher node or a leaf while
the first transaction that added the leaf into the cache is dropping.
Some throttling is added to functions that free blocks heavily so they
wait for old transactions to drop.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Much of the IO done while dropping snapshots is done looking up
leaves in the filesystem trees to see if they point to any extents and
to drop the references on any extents found.
This creates a cache so that IO isn't required.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Before setting an extent to delalloc, the code needs to wait for
pending ordered extents.
Also, the relocation code needs to wait for ordered IO before scanning
the block group again. This is because the extents are not removed
until the IO for the new extents is finished
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This releases the alloc_mutex in a few places that hold it for over long
operations. btrfs_lookup_block_group is changed so that it doesn't need
the mutex at all.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This replaces the use of the page cache lock bit for locking, which wasn't
suitable for block size < page size and couldn't be used recursively.
The mutexes alone don't fix either problem, but they are the first step.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* In btrfs_delete_inode, wait for ordered extents after calling
truncate_inode_pages. This is much faster, and more correct
* Properly clear our the PageChecked bit everywhere we redirty the page.
* Change the writepage fixup handler to lock the page range and check to
see if an ordered extent had been inserted since the improperly dirtied
page was discovered
* Wait for ordered extents outside the transaction. This isn't required
for locking rules but does improve transaction latencies
* Reduce contention on the alloc_mutex by dropping it while incrementing
refs on a node/leaf and while dropping refs on a leaf.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
btrfs_drop_extents is always called with a range lock held on the inode.
But, it may operate on extents outside that range as it drops and splits
them.
This patch adds a per-inode mutex that is held while calling
btrfs_drop_extents and while inserting new extents into the tree. It
prevents races from two procs working against adjacent ranges in the tree.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The old data=ordered code would force commit to wait until
all the data extents from the transaction were fully on disk. This
introduced large latencies into the commit and stalled new writers
in the transaction for a long time.
The new code changes the way data allocations and extents work:
* When delayed allocation is filled, data extents are reserved, and
the extent bit EXTENT_ORDERED is set on the entire range of the extent.
A struct btrfs_ordered_extent is allocated an inserted into a per-inode
rbtree to track the pending extents.
* As each page is written EXTENT_ORDERED is cleared on the bytes corresponding
to that page.
* When all of the bytes corresponding to a single struct btrfs_ordered_extent
are written, The previously reserved extent is inserted into the FS
btree and into the extent allocation trees. The checksums for the file
data are also updated.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btree defragger wasn't making forward progress because the new key wasn't
being saved by the btrfs_search_forward function.
This also disables the automatic btree defrag, it wasn't scaling well to
huge filesystems. The auto-defrag needs to be done differently.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This makes it possible for callers to check for extent_buffers in cache
without deadlocking against any btree locks held.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The online btree defragger is simplified and rewritten to use
standard btree searches instead of a walk up / down mechanism.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This creates one kthread for commits and one kthread for
deleting old snapshots. All the work queues are removed.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Allocations may need to read in block groups from the extent allocation tree,
which will require a tree search and take locks on the extent allocation
tree. But, those locks might already be held in other places, leading
to deadlocks.
Since the alloc_mutex serializes everything right now, it is safe to
skip the btree locking while caching block groups. A better fix will be
to either create a recursive lock or find a way to back off existing
locks while caching block groups.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
One lock per btree block can make for significant congestion if everyone
has to wait for IO at the high levels of the btree. This drops
locks held by a path when doing reads during a tree search.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Extent alloctions are still protected by a large alloc_mutex.
Objectid allocations are covered by a objectid mutex
Other btree operations are protected by a lock on individual btree nodes
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The allocation trees and the chunk trees are serialized via their own
dedicated mutexes. This means allocation location is still not very
fine grained.
The main FS btree is protected by locks on each block in the btree. Locks
are taken top / down, and as processing finishes on a given level of the
tree, the lock is released after locking the lower level.
The end result of a search is now a path where only the lowest level
is locked. Releasing or freeing the path drops any locks held.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* Force chunk allocation when find_free_extent has to do a full scan
* Record the max key at the start of defrag so it doesn't run forever
* Block groups might not be contiguous, make a forward search for the
next block group in extent-tree.c
* Get rid of extra checks for total fs size
* Fix relocate_one_reference to avoid relocating the same file data block
twice when referenced by an older transaction
* Use the open device count when allocating chunks so that we don't
try to allocate from devices that don't exist
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When duplicate copies exist, writes are allowed to fail to one of those
copies. This changeset includes a few changes that allow the FS to
continue even when some IOs fail.
It also adds verification of the parent generation number for btree blocks.
This generation is stored in the pointer to a block, and it ensures
that missed writes to are detected.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Once part of a delalloc request fails the cow checks, just cow the
entire range
It is possible for the back references to all be from the same root,
but still have snapshots against an extent. The checks are now more strict,
forcing cow any time there are multiple refs against the data extent.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Before, nodatacow only checked to make sure multiple roots didn't have
references on a single extent. This check makes sure that multiple
inodes don't have references.
nodatacow needed an extra check to see if the block group was currently
readonly. This way cows forced by the chunk relocation code are honored.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This required a few structural changes to the code that manages bdev pointers:
The VFS super block now gets an anon-bdev instead of a pointer to the
lowest bdev. This allows us to avoid swapping the super block bdev pointer
around at run time.
The code to read in the super block no longer goes through the extent
buffer interface. Things got ugly keeping the mapping constant.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
balance level starts by trying to empty the middle block, and then
pushes from the right to the middle. This might empty the right block
and leave a small number of pointers in the middle.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The data read retry code needs to find the logical disk block before it
can resubmit new bios. But, finding this block isn't allowed to take
the fs_mutex because that will deadlock with a number of different callers.
This changes the retry code to use the extent map cache instead, but
that requires the extent map cache to have the extent we're looking for.
This is a problem because btrfs_drop_extent_cache just drops the entire
extent instead of the little tiny part it is invalidating.
The bulk of the code in this patch changes btrfs_drop_extent_cache to
invalidate only a portion of the extent cache, and changes btrfs_get_extent
to deal with the results.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This isn't required anymore because we don't reallocate blocks that
have already been written in this transaction.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Block headers now store the chunk tree uuid
Chunk items records the device uuid for each stripes
Device extent items record better back refs to the chunk tree
Block groups record better back refs to the chunk tree
The chunk tree format has also changed. The objectid of BTRFS_CHUNK_ITEM_KEY
used to be the logical offset of the chunk. Now it is a chunk tree id,
with the logical offset being stored in the offset field of the key.
This allows a single chunk tree to record multiple logical address spaces,
upping the number of bytes indexed by a chunk tree from 2^64 to
2^128.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
On huge machines, delayed allocation may try to allocate massive extents.
This change allows btrfs_alloc_extent to return something smaller than
the caller asked for, and the data allocation routines will loop over
the allocations until it fills the whole delayed alloc.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Fix for a endianess BUG when using btrfs v0.13 with kernels older than 2.6.23
Problem:
Has of v0.13, btrfs-progs is using crc32c.c equivalent to the one found on
linux-2.6.23/lib/libcrc32c.c Since crc32c_le() changed in linux-2.6.23, when
running btrfs v0.13 with older kernels we have a missmatch between the versions
of crc32c_le() from btrfs-progs and libcrc32c in the kernel. This missmatch
causes a bug when using btrfs on big endian machines.
Solution:
btrfs_crc32c() macro that when compiling for kernels older than 2.6.23, does
endianess conversion to parameters and return value of crc32c().
This endianess conversion nullifies the differences in implementation
of crc32c_le().
If kernel 2.6.23 or better, it calls crc32c().
Signed-off-by: Miguel Sousa Filipe <miguel.filipe@gmail.com>
---
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Before, metadata checksumming was done by the callers of read_tree_block,
which would set EXTENT_CSUM bits in the extent tree to show that a given
range of pages was already checksummed and didn't need to be verified
again.
But, those bits could go away via try_to_releasepage, and the end
result was bogus checksum failures on pages that never left the cache.
The new code validates checksums when the page is read. It is a little
tricky because metadata blocks can span pages and a single read may
end up going via multiple bios.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When a block is freed, it can be immediately reused if it is from
the current transaction. But, an extra check is required to make sure
the block had not been written yet. If it were reused after being written,
the transid in the block header might match the transid of the
next time the block was allocated.
The parent node records the transaction ID of the block it is pointing to,
and this is used as part of validating the block on reads. So, there
can only be one version of a block per transaction.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Checksums were only verified by btrfs_read_tree_block, which meant the
functions to probe the page cache for blocks were not validating checksums.
Normally this is fine because the buffers will only be in cache if they
have already been validated.
But, there is a window while the buffer is being read from disk where
it could be up to date in the cache but not yet verified. This patch
makes sure all buffers go through checksum verification before they
are used.
This is safer, and it prevents modification of buffers before they go
through the csum code.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
There was an optimization to drop the fs_mutex when doing snapshot deletion
reads, but this can lead to false positives on checksumming errors. Keep
the lock for now.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
