Now orphan scan worker has no trace log, so it is
very hard to tell whether it is finished or blocked.
So add 2 mlog trace log so that we can tell whether
the current orphan scan worker is blocked or not.
It does help when I analyzed a orphan scan bug.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits)
ext4: Adding error check after calling ext4_mb_regular_allocator()
ext4: Fix dirtying of journalled buffers in data=journal mode
ext4: re-inline ext4_rec_len_(to|from)_disk functions
jbd2: Remove t_handle_lock from start_this_handle()
jbd2: Change j_state_lock to be a rwlock_t
jbd2: Use atomic variables to avoid taking t_handle_lock in jbd2_journal_stop
ext4: Add mount options in superblock
ext4: force block allocation on quota_off
ext4: fix freeze deadlock under IO
ext4: drop inode from orphan list if ext4_delete_inode() fails
ext4: check to make make sure bd_dev is set before dereferencing it
jbd2: Make barrier messages less scary
ext4: don't print scary messages for allocation failures post-abort
ext4: fix EFBIG edge case when writing to large non-extent file
ext4: fix ext4_get_blocks references
ext4: Always journal quota file modifications
ext4: Fix potential memory leak in ext4_fill_super
ext4: Don't error out the fs if the user tries to make a file too big
ext4: allocate stripe-multiple IOs on stripe boundaries
ext4: move aio completion after unwritten extent conversion
...
Fix up conflicts in fs/ext4/inode.c as per Ted.
Fix up xfs conflicts as per earlier xfs merge.
Lockstat reports have shown that j_state_lock is a major source of
lock contention, especially on systems with more than 4 CPU cores. So
change it to be a read/write spinlock.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
OCFS2 uses t_commit trigger to compute and store checksum of the just
committed blocks. When a buffer has b_frozen_data, checksum is computed
for it instead of b_data but this can result in an old checksum being
written to the filesystem in the following scenario:
1) transaction1 is opened
2) handle1 is opened
3) journal_access(handle1, bh)
- This sets jh->b_transaction to transaction1
4) modify(bh)
5) journal_dirty(handle1, bh)
6) handle1 is closed
7) start committing transaction1, opening transaction2
8) handle2 is opened
9) journal_access(handle2, bh)
- This copies off b_frozen_data to make it safe for transaction1 to commit.
jh->b_next_transaction is set to transaction2.
10) jbd2_journal_write_metadata() checksums b_frozen_data
11) the journal correctly writes b_frozen_data to the disk journal
12) handle2 is closed
- There was no dirty call for the bh on handle2, so it is never queued for
any more journal operation
13) Checkpointing finally happens, and it just spools the bh via normal buffer
writeback. This will write b_data, which was never triggered on and thus
contains a wrong (old) checksum.
This patch fixes the problem by calling the trigger at the moment data is
frozen for journal commit - i.e., either when b_frozen_data is created by
do_get_write_access or just before we write a buffer to the log if
b_frozen_data does not exist. We also rename the trigger to t_frozen as
that better describes when it is called.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We used to let orphan scan work in the default work queue,
but there is a corner case which will make the system deadlock.
The scenario is like this:
1. set heartbeat threadshold to 200. this will allow us to have a
great chance to have a orphan scan work before our quorum decision.
2. mount node 1.
3. after 1~2 minutes, mount node 2(in order to make the bug easier
to reproduce, better add maxcpus=1 to kernel command line).
4. node 1 do orphan scan work.
5. node 2 do orphan scan work.
6. node 1 do orphan scan work. After this, node 1 hold the orphan scan
lock while node 2 know node 1 is the master.
7. ifdown eth2 in node 2(eth2 is what we do ocfs2 interconnection).
Now when node 2 begins orphan scan, the system queue is blocked.
The root cause is that both orphan scan work and quorum decision work
will use the system event work queue. orphan scan has a chance of
blocking the event work queue(in dlm_wait_for_node_death) so that there
is no chance for quorum decision work to proceed.
This patch resolve it by moving orphan scan work to ocfs2_wq.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
In ocfs2, we use ocfs2_extend_trans() to extend a journal handle's
blocks. But if jbd2_journal_extend() fails, it will only restart
with the the new number of blocks. This tends to be awkward since
in most cases we want additional reserved blocks. It makes our code
harder to mantain since the caller can't be sure all the original
blocks will not be accessed and dirtied again. There are 15 callers
of ocfs2_extend_trans() in fs/ocfs2, and 12 of them have to add
h_buffer_credits before they call ocfs2_extend_trans(). This makes
ocfs2_extend_trans() really extend atop the original block count.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
jbd[2]_journal_dirty_metadata() only returns 0. It's been returning 0
since before the kernel moved to git. There is no point in checking
this error.
ocfs2_journal_dirty() has been faithfully returning the status since the
beginning. All over ocfs2, we have blocks of code checking this can't
fail status. In the past few years, we've tried to avoid adding these
checks, because they are pointless. But anyone who looks at our code
assumes they are needed.
Finally, ocfs2_journal_dirty() is made a void function. All error
checking is removed from other files. We'll BUG_ON() the status of
jbd2_journal_dirty_metadata() just in case they change it someday. They
won't.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
The next step in divorcing metadata I/O management from struct inode is
to pass struct ocfs2_caching_info to the journal functions. Thus the
journal locks a metadata cache with the cache io_lock function. It also
can compare ci_last_trans and ci_created_trans directly.
This is a large patch because of all the places we change
ocfs2_journal_access..(handle, inode, ...) to
ocfs2_journal_access..(handle, INODE_CACHE(inode), ...).
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We are really passing the inode into the ocfs2_read/write_blocks()
functions to get at the metadata cache. This commit passes the cache
directly into the metadata block functions, divorcing them from the
inode.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
If the mount fails for any reason, ocfs2_dismount_volume calls
ocfs2_orphan_scan_stop. It requires that ocfs2_orphan_scan_init
be called to setup the mutex and work queues, but that doesn't
happen if the mount has failed and we oops accessing an uninitialized
work queue.
This patch splits the init and startup of the orphan scan, eliminating
the oops.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Local and Hard-RO mounts do not need orphan scanning.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We don't access the LVB in our ocfs2_*_lock_res_init() functions.
Since the LVB can become invalid during some cluster recovery
operations, the dlmglue must be able to handle an uninitialized
LVB.
For the orphan scan lock, we initialized an uninitialzed LVB with our
scan sequence number plus one. This starts a normal orphan scan
cycle.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Currently if the orphan scan fires a tick before the user issues the umount,
the umount will wait for the queued orphan scan tasks to complete.
This patch makes the umount stop the orphan scan as early as possible so as
to reduce the probability of the queued tasks slowing down the umount.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
When a dentry is unlinked, the unlinking node takes an EX on the dentry lock
before moving the dentry to the orphan directory. Other nodes that have
this dentry in cache have a PR on the same dentry lock. When the EX is
requested, the other nodes flag the corresponding inode as MAYBE_ORPHANED
during downconvert. The inode is finally deleted when the last node to iput
the inode sees that i_nlink==0 and the MAYBE_ORPHANED flag is set.
A problem arises if a node is forced to free dentry locks because of memory
pressure. If this happens, the node will no longer get downconvert
notifications for the dentries that have been unlinked on another node.
If it also happens that node is actively using the corresponding inode and
happens to be the one performing the last iput on that inode, it will fail
to delete the inode as it will not have the MAYBE_ORPHANED flag set.
This patch fixes this shortcoming by introducing a periodic scan of the
orphan directories to delete such inodes. Care has been taken to distribute
the workload across the cluster so that no one node has to perform the task
all the time.
Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
During recovery, a node recovers orphans in it's slot and the dead node(s). But
if the dead nodes were holding orphans in offline slots, they will be left
unrecovered.
If the dead node is the last one to die and is holding orphans in other slots
and is the first one to mount, then it only recovers it's own slot, which
leaves orphans in offline slots.
This patch queues complete_recovery to clean orphans for all offline slots
during mount and node recovery.
Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Acked-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch makes use of Ocfs2's flexible btree code to add an additional
tree to directory inodes. The new tree stores an array of small,
fixed-length records in each leaf block. Each record stores a hash value,
and pointer to a block in the traditional (unindexed) directory tree where a
dirent with the given name hash resides. Lookup exclusively uses this tree
to find dirents, thus providing us with constant time name lookups.
Some of the hashing code was copied from ext3. Unfortunately, it has lots of
unfixed checkpatch errors. I left that as-is so that tracking changes would
be easier.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Acked-by: Joel Becker <joel.becker@oracle.com>
Move the definition of struct recovery_map from journal.c to journal.h. This
is preparation for the next patch.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Use the db_check field of ocfs2_dir_block_trailer to crc/ecc the
dirblocks.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The per-metadata-type ocfs2_journal_access_*() functions hook up jbd2
commit triggers and allow us to compute metadata ecc right before the
buffers are written out. This commit provides ecc for inodes, extent
blocks, group descriptors, and quota blocks. It is not safe to use
extened attributes and metaecc at the same time yet.
The ocfs2_extent_tree and ocfs2_path abstractions in alloc.c both hide
the type of block at their root. Before, it didn't matter, but now the
root block must use the appropriate ocfs2_journal_access_*() function.
To keep this abstract, the structures now have a pointer to the matching
journal_access function and a wrapper call to call it.
A few places use naked ocfs2_write_block() calls instead of adding the
blocks to the journal. We make sure to calculate their checksum and ecc
before the write.
Since we pass around the journal_access functions. Let's typedef them
in ocfs2.h.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
We create wrappers for ocfs2_journal_access() that are specific to the
type of metadata block. This allows us to associate jbd2 commit
triggers with the block. The triggers will compute metadata ecc in a
future commit.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Enable quota usage tracking on mount and disable it on umount. Also
add support for quota on and quota off quotactls and usrquota and
grpquota mount options. Add quota features among supported ones.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Implement functions for recovery after a crash. Functions just
read local quota file and sync info to global quota file.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
OCFS2 can easily support nested transactions. We just have to
take care and not spoil statistics acquire semaphore unnecessarily.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
JBD2 is fully backwards compatible with JBD and it's been tested enough with
Ocfs2 that we can clean this code up now.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Random places in the code would check a dinode bh to see if it was
valid. Not only did they do different levels of validation, they
handled errors in different ways.
The previous commit unified inode block reads, validating all block
reads in the same place. Thus, these haphazard checks are no longer
necessary. Rather than eliminate them, however, we change them to
BUG_ON() checks. This ensures the assumptions remain true. All of the
code paths to these checks have been audited to ensure they come from a
validated inode read.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The ocfs2 code currently reads inodes off disk with a simple
ocfs2_read_block() call. Each place that does this has a different set
of sanity checks it performs. Some check only the signature. A couple
validate the block number (the block read vs di->i_blkno). A couple
others check for VALID_FL. Only one place validates i_fs_generation. A
couple check nothing. Even when an error is found, they don't all do
the same thing.
We wrap inode reading into ocfs2_read_inode_block(). This will validate
all the above fields, going readonly if they are invalid (they never
should be). ocfs2_read_inode_block_full() is provided for the places
that want to pass read_block flags. Every caller is passing a struct
inode with a valid ip_blkno, so we don't need a separate blkno argument
either.
We will remove the validation checks from the rest of the code in a
later commit, as they are no longer necessary.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Patch sets journal descriptor to NULL after the journal is shutdown.
This ensures that jbd2_journal_release_jbd_inode(), which removes the
jbd2 inode from txn lists, can be called safely from ocfs2_clear_inode()
even after the journal has been shutdown.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
ocfs2_read_blocks() currently requires the CACHED flag for cached I/O.
However, that's the common case. Let's flip it around and provide an
IGNORE_CACHE flag for the special users. This has the added benefit of
cleaning up the code some (ignore_cache takes on its special meaning
earlier in the loop).
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
More than 30 callers of ocfs2_read_block() pass exactly OCFS2_BH_CACHED.
Only six pass a different flag set. Rather than have every caller care,
let's make ocfs2_read_block() take no flags and always do a cached read.
The remaining six places can call ocfs2_read_blocks() directly.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Now that synchronous readers are using ocfs2_read_blocks_sync(), all
callers of ocfs2_read_blocks() are passing an inode. Use it
unconditionally. Since it's there, we don't need to pass the
ocfs2_super either.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The ocfs2_read_blocks() function currently handles sync reads, cached,
reads, and sometimes cached reads. We're going to add some
functionality to it, so first we should simplify it. The uncached,
synchronous reads are much easer to handle as a separate function, so we
instroduce ocfs2_read_blocks_sync().
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
ocfs2 wants JBD2 for many reasons, not the least of which is that JBD is
limiting our maximum filesystem size.
It's a pretty trivial change. Most functions are just renamed. The
only functional change is moving to Jan's inode-based ordered data mode.
It's better, too.
Because JBD2 reads and writes JBD journals, this is compatible with any
existing filesystem. It can even interact with JBD-based ocfs2 as long
as the journal is formated for JBD.
We provide a compatibility option so that paranoid people can still use
JBD for the time being. This will go away shortly.
[ Moved call of ocfs2_begin_ordered_truncate() from ocfs2_delete_inode() to
ocfs2_truncate_for_delete(). --Mark ]
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This fixes a bug introduced with 539d8264093560b917ee3afe4c7f74e5da09d6a5:
[PATCH 2/2] ocfs2: Fix race between mount and recovery
ocfs2_mark_dead_nodes() was reading journal inodes while holding the
spinlock protecting our in-memory recovery state. The fix is very simple -
the disk state is protected by a cluster lock that's already held, so we
just move the spinlock down past the read.
Reviewed-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
As the fs recovery is asynchronous, there is a small chance that another
node can mount (and thus recover) the slot before the recovery thread
gets to it.
If this happens, the recovery thread will block indefinitely on the
journal/slot lock as that lock will be held for the duration of the mount
(by design) by the node assigned to that slot.
The solution implemented is to keep track of the journal replays using
a recovery generation in the journal inode, which will be incremented by the
thread replaying that journal. The recovery thread, before attempting the
blocking lock on the journal/slot lock, will compare the generation on disk
with what it has cached and skip recovery if it does not match.
This bug appears to have been inadvertently introduced during the mount/umount
vote removal by mainline commit 34d024f843. In the
mount voting scheme, the messaging would indirectly indicate that the slot
was being recovered.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
A couple places use OCFS2_DEBUG_FS where they really mean
CONFIG_OCFS2_DEBUG_FS.
Reported-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
if (...) BUG(); should be replaced with BUG_ON(...) when the test has no
side-effects to allow a definition of BUG_ON that drops the code completely.
The semantic patch that makes this change is as follows:
(http://www.emn.fr/x-info/coccinelle/)
// <smpl>
@ disable unlikely @ expression E,f; @@
(
if (<... f(...) ...>) { BUG(); }
|
- if (unlikely(E)) { BUG(); }
+ BUG_ON(E);
)
@@ expression E,f; @@
(
if (<... f(...) ...>) { BUG(); }
|
- if (E) { BUG(); }
+ BUG_ON(E);
)
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The in-memory slot map uses the same magic as the on-disk one. There is
a special value to mark a slot as invalid. It relies on the size of
certain types and so on.
Write a new in-memory map that keeps validity as a separate field. Outside
of the I/O functions, OCFS2_INVALID_SLOT now means what it is supposed to.
It also is no longer tied to the type size.
This also means that only the I/O functions refer to 16bit quantities.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The old recovery map was a bitmap of node numbers. This was sufficient
for the maximum node number of 254. Going forward, we want node numbers
to be UINT32. Thus, we need a new recovery map.
Note that we can't keep track of slots here. We must write down the
node number to recovery *before* we get the locks needed to convert a
node number into a slot number.
The recovery map is now an array of unsigned ints, max_slots in size.
It moves to journal.c with the rest of recovery.
Because it needs to be initialized, we move all of recovery initialization
into a new function, ocfs2_recovery_init(). This actually cleans up
ocfs2_initialize_super() a little as well. Following on, recovery cleaup
becomes part of ocfs2_recovery_exit().
A number of node map functions are rendered obsolete and are removed.
Finally, waiting on recovery is wrapped in a function rather than naked
checks on the recovery_event. This is a cleanup from Mark.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Just use osb_lock around the ocfs2_slot_info data. This allows us to
take the ocfs2_slot_info structure private in slot_info.c. All access
is now via accessors.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
journal.c and dlmglue.c would refresh the slot map by hand. Instead, have
the update and clear functions do the work inside slot_map.c. The eventual
result is to make ocfs2_slot_info defined privately in slot_map.c
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Create separate lockdep lock classes for system file's i_mutexes. They are
used to guard allocations and similar things and thus rank differently
than i_mutex of a regular file or directory.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Mostly taken from ext3. This allows the user to set the jbd commit interval,
in seconds. The default of 5 seconds stays the same, but now users can
easily increase the commit interval. Typically, this would be increased in
order to benefit performance at the expense of data-safety.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Call this the "inode_lock" now, since it covers both data and meta data.
This patch makes no functional changes.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Tao Ma