The fixes include:
1. some endian problems.
2. we should use bit/bpc in ocfs2_block_group_grow_discontig to
allocate clusters.
3. set num_clusters properly in __ocfs2_claim_clusters.
4. change name from ocfs2_supports_discontig_bh to
ocfs2_supports_discontig_bg.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
If we cannot get a contiguous region for a block group, allocate a
discontiguous one when the filesystem supports it.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Tao Ma <tao.ma@oracle.com>
The default behavior for directory reservations stays the same, but we add a
mount option so people can tweak the size of directory reservations
according to their workloads.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
I have observed that the current size of 8M gives us pretty poor
fragmentation on multi-threaded workloads which do lots of writes.
Generally, I can increase the size of local alloc windows and observe a
marked decrease in fragmentation, even up and beyond window sizes of 512
megabytes. This makes sense for a couple reasons - larger local alloc means
more room for reservation windows. On multi-node workloads the larger local
alloc helps as well because we don't have to do window slides as often.
Also, I removed the OCFS2_DEFAULT_LOCAL_ALLOC_SIZE constant as it is no
longer used and the comment above it was out of date.
To test fragmentation, I used a workload which launched 4 threads that did
4k writes into a series of about 140 alternating files.
With resv_level=2, and a 4k/4k file system I observed the following average
fragmentation for various localalloc= parameters:
localalloc= avg. fragmentation
8 48
32 16
64 10
120 7
On larger cluster sizes, the difference is more dramatic.
The new default size top out at 256M, which we'll only get for cluster
sizes of 32K and above.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
This patch pulls the local alloc sizing code into localalloc.c and provides
a callout to it from ocfs2_fill_super(). Behavior is essentially unchanged
except that I correctly calculate the maximum local alloc size. The old code
in ocfs2_parse_options() calculated the max size as:
ocfs2_local_alloc_size(sb) * 8
which is correct, in bits. Unfortunately though the option passed in is in
megabytes. Ultimately, this bug made no real difference - the shrink code
would catch a too-large size and bring it down to something reasonable.
Still, it's less than efficient as-is.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
This patch improves Ocfs2 allocation policy by allowing an inode to
reserve a portion of the local alloc bitmap for itself. The reserved
portion (allocation window) is advisory in that other allocation
windows might steal it if the local alloc bitmap becomes
full. Otherwise, the reservations are honored and guaranteed to be
free. When the local alloc window is moved to a different portion of
the bitmap, existing reservations are discarded.
Reservation windows are represented internally by a red-black
tree. Within that tree, each node represents the reservation window of
one inode. An LRU of active reservations is also maintained. When new
data is written, we allocate it from the inodes window. When all bits
in a window are exhausted, we allocate a new one as close to the
previous one as possible. Should we not find free space, an existing
reservation is pulled off the LRU and cannibalized.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
When the local alloc file changes windows, unused bits are freed back to the
global bitmap. By defnition, those bits can not be in use by any file. Also,
the local alloc will never have been able to allocate those bits if they
were part of a previous truncate. Therefore it makes sense that we should
clear unused local alloc bits in the undo buffer so that they can be used
immediatly.
[ Modified to call it ocfs2_release_clusters() -- Joel ]
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Currently we were adding ioctl cmds/structures for ocfs2 into ocfs2_fs.h
which was used for define ocfs2 on-disk layout. That sounds a little bit
confusing, and it may be quickly polluted espcially when growing the
ocfs2_info_request ioctls afterwards(it will grow i bet).
As a result, such OCFS2 IOCs do need to be placed somewhere other than
ocfs2_fs.h, a separated ocfs2_ioctl.h will be added to store such ioctl
structures and definitions which could also be used from userspace to
invoke ioctls call.
Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We're going to want it in the ast functions, so we convert union
ocfs2_dlm_lksb to struct ocfs2_dlm_lksb and let it carry the connection.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
This patch add extent block (metadata) stealing mechanism for
extent allocation. This mechanism is same as the inode stealing.
if no room in slot specific extent_alloc, we will try to
allocate extent block from the next slot.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Acked-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
There is possibility of a livelock in __ocfs2_cluster_lock(). If a node were
to get an ast for an upconvert request, followed immediately by a bast,
there is a small window where the fs may downconvert the lock before the
process requesting the upconvert is able to take the lock.
This patch adds a new flag to indicate that the upconvert is still in
progress and that the dc thread should not downconvert it right now.
Wengang Wang <wen.gang.wang@oracle.com> and Joel Becker
<joel.becker@oracle.com> contributed heavily to this patch.
Reported-by: David Teigland <teigland@redhat.com>
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2:
ocfs2/trivial: Use le16_to_cpu for a disk value in xattr.c
ocfs2/trivial: Use proper mask for 2 places in hearbeat.c
Ocfs2: Let ocfs2 support fiemap for symlink and fast symlink.
Ocfs2: Should ocfs2 support fiemap for S_IFDIR inode?
ocfs2: Use FIEMAP_EXTENT_SHARED
fiemap: Add new extent flag FIEMAP_EXTENT_SHARED
ocfs2: replace u8 by __u8 in ocfs2_fs.h
ocfs2: explicit declare uninitialized var in user_cluster_connect()
ocfs2-devel: remove redundant OCFS2_MOUNT_POSIX_ACL check in ocfs2_get_acl_nolock()
ocfs2: return -EAGAIN instead of EAGAIN in dlm
ocfs2/cluster: Make fence method configurable - v2
ocfs2: Set MS_POSIXACL on remount
ocfs2: Make acl use the default
ocfs2: Always include ACL support
Mainline commit 53ef99cad9 removed the
JBD compatibility layer from OCFS2. This patch removes the last remaining
remnants of that.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Change acl mount options handling to match the one of XFS and BTRFS and
hopefully it is also easier to use now. When admin does not specify any
acl mount option, acls are enabled if and only if the filesystem has
xattr feature enabled. If admin specifies 'acl' mount option, we fail
the mount if the filesystem does not have xattr feature and thus acls
cannot be enabled.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Implement locking around struct ocfs2_refcount_tree. This protects
all read/write operations on refcount trees. ocfs2_refcount_tree
has its own lock and its own caching_info, protecting buffers among
multiple nodes.
User must call ocfs2_lock_refcount_tree before his operation on
the tree and unlock it after that.
ocfs2_refcount_trees are referenced by the block number of the
refcount tree root block, So we create an rb-tree on the ocfs2_super
to look them up.
Signed-off-by: Tao Ma <tao.ma@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>
Similar ip_last_trans, ip_created_trans tracks the creation of a journal
managed inode. This specifically tracks what transaction created the
inode. This is so the code can know if the inode has ever been written
to disk.
This behavior is desirable for any journal managed object. We move it
to struct ocfs2_caching_info as ci_created_trans so that any object
using ocfs2_caching_info can rely on this behavior.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We have the read side of metadata caching isolated to struct
ocfs2_caching_info, now we need the write side. This means the journal
functions. The journal only does a couple of things with struct inode.
This change moves the ip_last_trans field onto struct
ocfs2_caching_info as ci_last_trans. This field tells the journal
whether a pending journal flush is required.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We don't really want to cart around too many new fields on the
ocfs2_caching_info structure. So let's wrap all our access of the
parent object in a set of operations. One pointer on caching_info, and
more flexibility to boot.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
We want to use the ocfs2_caching_info structure in places that are not
inodes. To do that, it can no longer rely on referencing the inode
directly.
This patch moves the flags to ocfs2_caching_info->ci_flags, stores
pointers to the parent's locks on the ocfs2_caching_info, and renames
the constants and flags to reflect its independant state.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
In commit ea455f8ab6, we moved the dentry lock
put process into ocfs2_wq. This causes problems during umount because ocfs2_wq
can drop references to inodes while they are being invalidated by
invalidate_inodes() causing all sorts of nasty things (invalidate_inodes()
ending in an infinite loop, "Busy inodes after umount" messages etc.).
We fix the problem by stopping ocfs2_wq from doing any further releasing of
inode references on the superblock being unmounted, wait until it finishes
the current round of releasing and finally cleaning up all the references in
dentry_lock_list from ocfs2_put_super().
The issue was tracked down by Tao Ma <tao.ma@oracle.com>.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Add lockdep support to OCFS2. The support also covers all of the cluster
locks except for open locks, journal locks, and local quotafile locks. These
are special because they are acquired for a node, not for a particular process
and lockdep cannot deal with such type of locking.
Signed-off-by: Jan Kara <jack@suse.cz>
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>
It would be nice to know how often we get checksum failures. Even
better, how many of them we can fix with the single bit ecc. So, we add
a statistics structure. The structure can be installed into debugfs
wherever the user wants.
For ocfs2, we'll put it in the superblock-specific debugfs directory and
pass it down from our higher-level functions. The stats are only
registered with debugfs when the filesystem supports metadata ecc.
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>
For nfs exporting, ocfs2_get_dentry() returns the dentry for fh.
ocfs2_get_dentry() may read from disk when the inode is not in memory,
without any cross cluster lock. this leads to the file system loading a
stale inode.
This patch fixes above problem.
Solution is that in case of inode is not in memory, we get the cluster
lock(PR) of alloc inode where the inode in question is allocated from (this
causes node on which deletion is done sync the alloc inode) before reading
out the inode itsself. then we check the bitmap in the group (the inode in
question allcated from) to see if the bit is clear. if it's clear then it's
stale. if the bit is set, we then check generation as the existing code
does.
We have to read out the inode in question from disk first to know its alloc
slot and allot bit. And if its not stale we read it out using ocfs2_iget().
The second read should then be from cache.
And also we have to add a per superblock nfs_sync_lock to cover the lock for
alloc inode and that for inode in question. this is because ocfs2_get_dentry()
and ocfs2_delete_inode() lock on them in reverse order. nfs_sync_lock is locked
in EX mode in ocfs2_get_dentry() and in PR mode in ocfs2_delete_inode(). so
that mutliple ocfs2_delete_inode() can run concurrently in normal case.
[mfasheh@suse.com: build warning fixes and comment cleanups]
Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Acked-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
In ocfs2, the block group search looks for the "emptiest" group
to allocate from. So if the allocator has many equally(or almost
equally) empty groups, new block group will tend to get spread
out amongst them.
So we add osb_inode_alloc_group in ocfs2_super to record the last
used inode allocation group.
For more details, please see
http://oss.oracle.com/osswiki/OCFS2/DesignDocs/InodeAllocationStrategy.
I have done some basic test and the results are a ten times improvement on
some cold-cache stat workloads.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
ocfs2_dx_dir_rebalance() is passed the block offset of a dx leaf which needs
rebalancing. Since we rebalance an entire cluster at a time however, this
function needs to calculate the beginning of that cluster, in blocks. The
calculation was wrong, which would result in a read of non-leaf blocks. Fix
the calculation by adding ocfs2_block_to_cluster_start() which is a more
straight-forward way of determining this.
Reported-by: Tristan Ye <tristan.ye@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Since we've now got a directory format capable of handling a large number of
entries, we can increase the maximum link count supported. This only gets
increased if the directory indexing feature is turned on.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Acked-by: Joel Becker <joel.becker@oracle.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>
This patch removes the debugfs file local_alloc_stats as that information
is now included in the fs_state debugfs file.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch creates a per mount debugfs file, fs_state, which exposes
information like, cluster stack in use, states of the downconvert, recovery
and commit threads, number of journal txns, some allocation stats, list of
all slots, etc.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
For other metadata in ocfs2, metaecc is checked in ocfs2_read_blocks
with io_mutex held. While for xattr bucket, it is calculated by
the whole buckets. So we have to add a spin_lock to prevent multiple
processes calculating metaecc.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Tested-by: Tristan Ye <tristan.ye@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Dropping of last reference to dentry lock is a complicated operation involving
dropping of reference to inode. This can get complicated and quota code in
particular needs to obtain some quota locks which leads to potential deadlock.
Thus we defer dropping of inode reference to ocfs2_wq.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Future ocfs2 features metaecc and indexed directories need to store a
little bit of data in each dirblock. For compatibility, we place this
in a trailer at the end of the dirblock. The trailer plays itself as an
empty dirent, so that if the features are turned off, it can be reused
without requiring a tunefs scan.
This code adds the trailer and validates it when the block is read in.
[ Mark is the original author, but I reinserted this code before his
dir index work. -- Joel ]
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>
This is the code that computes crc32 and ecc for ocfs2 metadata blocks.
There are high-level functions that check whether the filesystem has the
ecc feature, mid-level functions that work on a single block or array of
buffer_heads, and the low-level ecc hamming code that can handle
multiple buffers like crc32_le().
It's not hooked up to the filesystem yet.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
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>
We weren't consistently checking extent blocks after we read them.
Most places checked the signature, but none checked h_blkno or
h_fs_signature. Create a toplevel ocfs2_read_extent_block() that does
the read and the validation.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Random places in the code would check a group descriptor bh to see if it
was valid. The previous commit unified descriptor block reads,
validating all block reads in the same place. Thus, these 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 descriptor read.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
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>
This patch adds POSIX ACL(access control lists) APIs in ocfs2. We convert
struct posix_acl to many ocfs2_acl_entry and regard them as an extended
attribute entry.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The xattr.c code is currently memcmp()ing naking buffer pointers.
Create the OCFS2_IS_VALID_XATTR_BLOCK() macro to match its peers and use
that.
In addition, failed signature checks were returning -EFAULT, which is
completely wrong. Return -EIO.
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>
Now that ocfs2 limits inode numbers to 32bits, add a mount option to
disable the limit. This parallels XFS. 64bit systems can handle the
larger inode numbers.
[ Added description of inode64 mount option in ocfs2.txt. --Mark ]
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch adds the s_incompat flag for extended attribute support. This
helps us ensure that older versions of Ocfs2 or ocfs2-tools will not be able
to mount a volume with xattr support.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch implements storing extended attributes both in inode or a single
external block. We only store EA's in-inode when blocksize > 512 or that
inode block has free space for it. When an EA's value is larger than 80
bytes, we will store the value via b-tree outside inode or block.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Add the structures and helper functions we want for handling inline extended
attributes. We also update the inline-data handlers so that they properly
function in the event that we have both inline data and inline attributes
sharing an inode block.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
A per-mount debugfs file, "local_alloc" is created which when read will
expose live state of the nodes local alloc file. Performance impact is
minimal, only a bit of memory overhead per mount point. Still, the code is
hidden behind CONFIG_OCFS2_FS_STATS. This feature will help us debug
local alloc performance problems on a live system.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Ocfs2's local allocator disables itself for the duration of a mount point
when it has trouble allocating a large enough area from the primary bitmap.
That can cause performance problems, especially for disks which were only
temporarily full or fragmented. This patch allows for the allocator to
shrink it's window first, before being disabled. Later, it can also be
re-enabled so that any performance drop is minimized.
To do this, we allow the value of osb->local_alloc_bits to be shrunk when
needed. The default value is recorded in a mostly read-only variable so that
we can re-initialize when required.
Locking had to be updated so that we could protect changes to
local_alloc_bits. Mostly this involves protecting various local alloc values
with the osb spinlock. A new state is also added, OCFS2_LA_THROTTLED, which
is used when the local allocator is has shrunk, but is not disabled. If the
available space dips below 1 megabyte, the local alloc file is disabled. In
either case, local alloc is re-enabled 30 seconds after the event, or when
an appropriate amount of bits is seen in the primary bitmap.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Do this instead of tracking absolute local alloc size. This avoids
needless re-calculatiion of bits from bytes in localalloc.c. Additionally,
the value is now in a more natural unit for internal file system bitmap
work.
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>
This patch adds code to track the number of times the fs takes
various cluster locks as well as the times associated with it.
The information is made available to users via debugfs.
This patch was originally written by Jan Kara <jack@suse.cz>.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Inode allocation is modified to look in other nodes allocators during
extreme out of space situations. We retry our own slot when space is freed
back to the global bitmap, or whenever we've allocated more than 1024 inodes
from another slot.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The filesystem gains the USERSPACE_STACK incomat bit and the
s_cluster_info field on the superblock. When a userspace stack is in
use, the name of the stack is stored on-disk for mount-time
verification.
The "cluster_stack" option is added to mount(2) processing. The mount
process needs to pass the matching stack name. If the passed name and
the on-disk name do not match, the mount is failed.
When using the classic o2cb stack, the incompat bit is *not* set and no
mount option is used other than the usual heartbeat=local. Thus, the
filesystem is compatible with older tools.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
o2dlm has the non-standard behavior of providing a cancel callback
(unlock_ast) even when the cancel has failed (the locking operation
succeeded without canceling). This is called CANCELGRANT after the
status code sent to the callback. fs/dlm does not provide this
callback, so dlmglue must be changed to live without it.
o2dlm_unlock_ast_wrapper() in stackglue now ignores CANCELGRANT calls.
Because dlmglue no longer sees CANCELGRANT, ocfs2_unlock_ast() no longer
needs to check for it. ocfs2_locking_ast() must catch that a cancel was
tried and clear the cancel state.
Making these changes opens up a locking race. dlmglue uses the the
OCFS2_LOCK_BUSY flag to ensure only one thread is calling the dlm at any
one time. But dlmglue must unlock the lockres before calling into the
dlm. In the small window of time between unlocking the lockres and
calling the dlm, the downconvert thread can try to cancel the lock. The
downconvert thread is checking the OCFS2_LOCK_BUSY flag - it doesn't
know that ocfs2_dlm_lock() has not yet been called.
Because ocfs2_dlm_lock() has not yet been called, the cancel operation
will just be a no-op. There's nothing to cancel. With CANCELGRANT,
dlmglue uses the CANCELGRANT callback to clear up the cancel state.
When it comes around again, it will retry the cancel. Eventually, the
first thread will have called into ocfs2_dlm_lock(), and either the
lock or the cancel will succeed. The downconvert thread can then do its
downconvert.
Without CANCELGRANT, there is nothing to clean up the cancellation
state. The downconvert thread does not know to retry its operations.
More importantly, the original lock may be blocking on the other node
that is trying to cancel us. With neither able to make progress, the
ast is never called and the cancellation state is never cleaned up that
way. dlmglue is deadlocked.
The OCFS2_LOCK_PENDING flag is introduced to remedy this window. It is
set at the same time OCFS2_LOCK_BUSY is. Thus, the downconvert thread
can check whether the lock is cancelable. If not, it just loops around
to try again. Once ocfs2_dlm_lock() is called, the thread then clears
OCFS2_LOCK_PENDING and wakes the downconvert thread. Now, if the
downconvert thread finds the lock BUSY, it can safely try to cancel it.
Whether the cancel works or not, the state will be properly set and the
lock processing can continue.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The last bit of classic stack used directly in ocfs2 code is o2hb.
Specifically, the check for heartbeat during mount and the call to
ocfs2_hb_ctl during unmount.
We create an extra API, ocfs2_cluster_hangup(), to encapsulate the call
to ocfs2_hb_ctl. Other stacks will just leave hangup() empty.
The check for heartbeat is moved into ocfs2_cluster_connect(). It will
be matched by a similar check for other stacks.
With this change, only stackglue.c includes cluster/ headers.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
ocfs2 asks the cluster stack for the local node's node number for two
reasons; to fill the slot map and to print it. While the slot map isn't
necessary for userspace cluster stacks, the printing is very nice for
debugging. Thus we add ocfs2_cluster_this_node() as a generic API to get
this value. It is anticipated that the slot map will not be used under a
userspace cluster stack, so validity checks of the node num only need to
exist in the slot map code. Otherwise, it just gets used and printed as an
opaque value.
[ Fixed up some "int" versus "unsigned int" issues and made osb->node_num
truly opaque. --Mark ]
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This step introduces a cluster stack agnostic API for initializing and
exiting. fs/ocfs2/dlmglue.c no longer uses o2cb/o2dlm knowledge to
connect to the stack. It is all handled in stackglue.c.
heartbeat.c no longer needs to know how it gets called.
ocfs2_do_node_down() is now a clean recovery trigger.
The big gotcha is the ordering of initializations and de-initializations done
underneath ocfs2_cluster_connect(). ocfs2_dlm_init() used to do all
o2dlm initialization in one block. Thus, the o2dlm functionality of
ocfs2_cluster_connect() is very straightforward. ocfs2_dlm_shutdown(),
however, did a few things between de-registration of the eviction
callback and actually shutting down the domain. Now de-registration and
shutdown of the domain are wrapped within the single
ocfs2_cluster_disconnect() call. I've checked the code paths to make
sure we can safely tear down things in ocfs2_dlm_shutdown() before
calling ocfs2_cluster_disconnect(). The filesystem has already set
itself to ignore the callback.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Wrap the lock status block (lksb) in a union. Later we will add a union
element for the fs/dlm lksb. Create accessors for the status and lvb
fields.
Other than a debugging function, dlmglue.c does not directly reference
the o2dlm locking path anymore.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
The old slot map had a few limitations:
- It was limited to one block, so the maximum slot count was 255.
- Each slot was signed 16bits, limiting node numbers to INT16_MAX.
- An empty slot was marked by the magic 0xFFFF (-1).
The new slot map format provides 32bit node numbers (UINT32_MAX), a
separate space to mark a slot in use, and extra room to grow. The slot
map is now bounded by i_size, not a block.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
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>
This patchset moves le*_add_cpu and be*_add_cpu functions from OCFS2 to core
header (1st), converts ext3 filesystem to this API (2nd) and replaces XFS
different named functions with new ones (3rd).
There are many places where these functions will be useful. Just look at:
grep -r 'cpu_to_[ble12346]*([ble12346]*_to_cpu.*[-+]' linux-src/ Patch for
ext3 is an example how conversions will probably look like.
This patch:
- move inline functions which add native byte order variable to
little/big endian variable to core header
* le16_add_cpu(__le16 *var, u16 val)
* le32_add_cpu(__le32 *var, u32 val)
* le64_add_cpu(__le64 *var, u64 val)
* be32_add_cpu(__be32 *var, u32 val)
- add for completeness:
* be16_add_cpu(__be16 *var, u16 val)
* be64_add_cpu(__be64 *var, u64 val)
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Acked-by: Mark Fasheh <mark.fasheh@oracle.com>
Cc: David Chinner <dgc@sgi.com>
Cc: Timothy Shimmin <tes@sgi.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently, when ocfs2 nodes connect via TCP, they advertise their
compatibility level. If the versions do not match, two nodes cannot speak
to each other and they disconnect. As a result, this provides no forward or
backwards compatibility.
This patch implements a simple protocol negotiation at the dlm level by
introducing a major/minor version number scheme for entities that
communicate. Specifically, o2dlm has a major/minor version for interaction
with o2dlm on other nodes, and ocfs2 itself has a major/minor version for
interacting with the filesystem on other nodes.
This will allow rolling upgrades of ocfs2 clusters when changes to the
locking or network protocols can be done in a backwards compatible manner.
In those cases, only the minor number is changed and the negotatied protocol
minor is returned from dlm join. In the far less likely event that a
required protocol change makes backwards compatibility impossible, we simply
bump the major number.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
ocfs2_super->blocked_lock_list and ocfs2_super->blocked_lock_count have some
usage restrictions which aren't immediately obvious to anyone reading the
code. It's a good idea to document this so that we avoid making costly
mistakes in the future.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Hook up ocfs2_flock(), using the new flock lock type in dlmglue.c. A new
mount option, "localflocks" is added so that users can revert to old
functionality as need be.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This adds a new dlmglue lock type which is intended to back flock()
requests.
Since these locks are driven from userspace, usage rules are much more
liberal than the typical Ocfs2 internal cluster lock. As a result, we can't
make use of most dlmglue features - lock caching and lock level
optimizations in particular. Additionally, userspace is free to deadlock
itself, so we have to deal with that in the same way as the rest of the
kernel - by allowing a signal to abort a lock request.
In order to keep ocfs2_cluster_lock() complexity down, ocfs2_file_lock()
does it's own dlm coordination. We still use the same helper functions
though, so duplicated code is kept to a minimum.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Local alloc is a performance optimization in ocfs2 in which a node
takes a window of bits from the global bitmap and then uses that for
all small local allocations. This window size is fixed to 8MB currently.
This patch allows users to specify the window size in MB including
disabling it by passing in 0. If the number specified is too large,
the fs will use the default value of 8MB.
mount -o localalloc=X /dev/sdX /mntpoint
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
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>
The node maps that are set/unset by these votes are no longer relevant, thus
we can remove the mount and umount votes. Since those are the last two
remaining votes, we can also remove the entire vote infrastructure.
The vote thread has been renamed to the downconvert thread, and the small
amount of functionality related to managing it has been moved into
fs/ocfs2/dlmglue.c. All references to votes have been removed or updated.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Add the disk, network and memory structures needed to support data in inode.
Struct ocfs2_inline_data is defined and embedded in ocfs2_dinode for storing
inline data.
A new inode field, i_dyn_features, is added to facilitate tracking of
dynamic inode state. Since it will be used often, we want to mirror it on
ocfs2_inode_info, and transfer it via the meta data lvb.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Reviewed-by: Joel Becker <joel.becker@oracle.com>
ocfs2_align_clusters_to_page_index() needs to cast the clusters shift to
pgoff_t and ocfs2_file_buffered_write() needs loff_t when calculating
destination start for memcpy.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Writes to a region marked as unwritten might result in a record split or
merge. We can support splits by making minor changes to the existing insert
code. Merges require left rotations which mostly re-use right rotation
support functions.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
ocfs2 will attempt to assign the node the slot# provided in the mount
option. Failure to assign the preferred slot is not an error. This small
feature can be useful for automated testing.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Since we don't zero on extend anymore, truncate needs to be fixed up to zero
the part of a file between i_size and and end of it's cluster. Otherwise a
subsequent extend could expose bad data.
This introduced a new helper, which can be used in ocfs2_write().
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Unfortunately, ocfs2 can no longer make use of generic_file_aio_write_nlock()
because allocating writes will require zeroing of pages adjacent to the I/O
for cluster sizes greater than page size.
Implement a custom file write here, which can order page locks for zeroing.
This also has the advantage that cluster locks can easily be ordered outside
of the page locks.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The code in extent_map.c is not prepared to deal with a subtree being
rotated between lookups. This can happen when filling holes in sparse files.
Instead of a lengthy patch to update the code (which would likely lose the
benefit of caching subtree roots), we remove most of the algorithms and
implement a simple path based lookup. A less ambitious extent caching scheme
will be added in a later patch.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Introduce tree rotations into the b-tree code. This will allow ocfs2 to
support sparse files. Much of the added code is designed to be generic (in
the ocfs2 sense) so that it can later be re-used to implement large
extended attributes.
This patch only adds the rotation code and does minimal updates to callers
of the extent api.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This allows users to format an ocfs2 file system with a special flag,
OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT. When the file system sees this flag, it
will not use any cluster services, nor will it require a cluster
configuration, thus acting like a 'local' file system.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Conflicts:
drivers/ata/libata-scsi.c
include/linux/libata.h
Futher merge of Linus's head and compilation fixups.
Signed-Off-By: David Howells <dhowells@redhat.com>
This patch adds the core routines for updating atime in ocfs2.
Signed-off-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This is mostly a search and replace as ocfs2_journal_handle is now no more
than a container for a handle_t pointer.
ocfs2_commit_trans() becomes very straight forward, and we remove some out
of date comments / code.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Record the most recently used allocation group on the allocation context, so
that subsequent allocations can attempt to optimize for contiguousness.
Local alloc especially should benefit from this as the current chain search
tends to let it spew across the disk.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
We were storing cluster count on the ocfs2_super structure, but never
actually using it so remove that. Also, we don't want to populate the
uptodate cache with the unlocked block read - it is technically safe as is,
but we should change it for correctness.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Get rid of osb->uuid, osb->proc_sub_dir, and osb->osb_id. Those fields were
unused, or could easily be removed. As a result, we also no longer need
MAX_OSB_ID or ocfs2_globals_lock.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Orphan dir recovery can deadlock with another process in
ocfs2_delete_inode() in some corner cases. Fix this by tracking recovery
state more closely and allowing it to handle inode wipes which might
deadlock.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Semaphore to mutex conversion.
The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
