of the stream (so the "chkbfs" functionality is complete now).
Fixed wrong block number report in BlockAllocator::CheckBlockRun(), blocks are
now printed out in absolute numbers (not allocation_group relative anymore).
Use Inode::IsContainer() where necessary instead of Inode::IsDirectory().
Fixed a big and nasty bug in AllocationBlock::SetTo(): the number of bits in
a block could be calculated wrong for a partial allocation group which need
more than one block in the bitmap - hopefully, that was the last remaining
big bug in the block allocator.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2032 a95241bf-73f2-0310-859d-f6bbb57e9c96
inode locked if the _inode parameter is passed.
Makes some more use of the new type identificators.
Symlinks are no longer added to the "size" index (compatibility with BFS, and it also
makes much more sense).
Now sets S_STR_INDEX for directories, if no index type was set (again, compatibility
issue with BFS).
Fixed a bug in the Inode::GrowStream() method in the double indirect region.
Some style updates.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2030 a95241bf-73f2-0310-859d-f6bbb57e9c96
Renamed Inode::IsDirectory() to Inode::IsContainer() (since it is also true
for index/attribute directories).
Introduced a new Inode::IsDirectory() that only checks for real and standard
directories. Let's hope I've fixed more bugs with that than introduced new
ones...
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2029 a95241bf-73f2-0310-859d-f6bbb57e9c96
The only functional change is that bfs_rename() now checks for '/' in the
target name (the VFS should do those things, but you never know as long
you haven't written it yourself :).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2028 a95241bf-73f2-0310-859d-f6bbb57e9c96
via the private ioctls defined in bfs_control.h.
Detects all kinds of errors, and can correct most of them. It doesn't fix
any errors in the b+trees (like the ones created by an earlier version
of the BPlusTree class ;-), and it also can't fix the "blocks are already set"
error, which occurs if more than one file claims a particular block (or
range of blocks) for itself.
The double indirect data range is not yet supported, so use with care, or
run the original chkbfs afterwards to fix any errors because of that.
Might not yet analyze 100% correct (shows way to many errors for my tastes...).
A "chkbfs" command will be made available shortly.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1994 a95241bf-73f2-0310-859d-f6bbb57e9c96
and atomic_test_and_set() for userland testing purposes.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1987 a95241bf-73f2-0310-859d-f6bbb57e9c96
the bug where a block_run could get a zero length after merging it...
Updated a comment in Inode::Remove().
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1986 a95241bf-73f2-0310-859d-f6bbb57e9c96
block_runs can be merged together.
Added a constant for the maximum length of a block_run.
Added a flag constant to the inode that prevents freeing up its space
after it has been removed - this is only useful for the "chkbfs" stuff.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1985 a95241bf-73f2-0310-859d-f6bbb57e9c96
Cache::Read() != B_OK failed if the underlying class used that function.
We can now boot R5 with VM turned on without any problems (what a stupid bug).
As a side effect, you can now also mount volumes on your BFS disk, which was
also broken because of this bug.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1930 a95241bf-73f2-0310-859d-f6bbb57e9c96
had some running live queries.
SimpleLock now allows nesting; added some missing atomic operations to
make its implementation as easy as possible.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1901 a95241bf-73f2-0310-859d-f6bbb57e9c96
weren't moved to the kernel (as owner), so they would be deleted after
the team which almost randomly created them died.
Benaphores are now only used if USE_BENAPHORES is defined - I have renamed
the Benaphore class to Semaphore to take the changed behaviour into account.
Added a Status() method to the Locker class.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1885 a95241bf-73f2-0310-859d-f6bbb57e9c96
could be changed before or during the comparison).
Some style changes.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1861 a95241bf-73f2-0310-859d-f6bbb57e9c96
system folders lowercase naming.
Build print transport add-ons in their own sub-folder, too.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1844 a95241bf-73f2-0310-859d-f6bbb57e9c96
Update the protocols and interfaces modules names prefix to reflect the real
disk hierarchy where they lives.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1809 a95241bf-73f2-0310-859d-f6bbb57e9c96
- net_server_driver now publish a /dev/net/server entry,
- net_stack_driver still publish a /dev/net/stack entry.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1795 a95241bf-73f2-0310-859d-f6bbb57e9c96
and Free() methods which operate on the AllocationBlocks.
BlockAllocator::AllocateBlocks() couldn't correctly reserve space for allocation
groups with more than 2 blocks - AllocationGroup::Allocate() now can, which
is now used by AllocateBlocks() (but it's slightly less fast).
Began implementing functionality for a chkbfs-like command.
Some style changes.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1603 a95241bf-73f2-0310-859d-f6bbb57e9c96
$ COMPILE_FOR_R5=1 jam
will compile the "bfs" version, otherwise the "obfs" version is created.
Note: the final executable will always be called obfs (for now).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1591 a95241bf-73f2-0310-859d-f6bbb57e9c96
merged setup_keyboard() and init_driver().
Added TRACE_KEYBOARD define to easily enable debug output from the keyboard driver.
Also made the escape key dropping into KDL - all special keys (like the
F-keys, etc.) aren't working in BeBochs, so that's a simple work-around
for that problem.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1302 a95241bf-73f2-0310-859d-f6bbb57e9c96
and checking buffer validity when a buffer is received. removed the
downstream latency variable because there is no downstream from this
node. also added helpful comments.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1080 a95241bf-73f2-0310-859d-f6bbb57e9c96
changed start_time to be TimeSource()->Now().
added some helpful comments.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1079 a95241bf-73f2-0310-859d-f6bbb57e9c96
for many classes for the sake of completeness.
Added a Transaction::IsStarted() method to not let it look like as if the
transaction is started more than once.
Changes made after suggestions from Mike Nordell, again :-)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1067 a95241bf-73f2-0310-859d-f6bbb57e9c96
instead of the too shorter "stack", which incidently fix a target dependency issue
with the STL stack header.
Wait. No. It's the reverse! :-)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1063 a95241bf-73f2-0310-859d-f6bbb57e9c96
suggested by Mike Nordell.
Some code cleanups, added a comment in Inode::SetFileSize() to point out
that Stream<Cache>::WriteAt() denies growing the file size its own.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1060 a95241bf-73f2-0310-859d-f6bbb57e9c96
Inode::FillGapWithZeros(), pointed out by Mike Nordell.
Note, that function is currently not used.
Some smaller cleanups.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1058 a95241bf-73f2-0310-859d-f6bbb57e9c96
free anything if it couldn't acquire the semaphore.
That allowed me to get aware of a possible bug in the destructor :-)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1057 a95241bf-73f2-0310-859d-f6bbb57e9c96
Made some robustness improvements to mediareader based on things
that I noticed while doing mediawriter.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1037 a95241bf-73f2-0310-859d-f6bbb57e9c96
Don't bother looking at fileproducer since there are no versions there
beyond the initial commit.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1035 a95241bf-73f2-0310-859d-f6bbb57e9c96
our file system):
- added bfs_wake_vnode(), and bfs_suspend_vnode()
- bumped B_CUR_FS_API_VERSION to 3 as needed for Dano
It should now be able to boot Dano with our BFS, although I haven't tested
it. The information was gained using some degree of reverse engineering...
It won't be part of the BFS implementation for OpenBeOS (that won't run on R5
anymore) :-)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1010 a95241bf-73f2-0310-859d-f6bbb57e9c96
is no only "-O1", since gcc obviously produces bad code if compiled with more.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@996 a95241bf-73f2-0310-859d-f6bbb57e9c96
files anymore (only Inode::WriteAt() denied it before).
Introduced a BFS_NAME define to be able to switch easier between "obfs",
and "bfs".
bfs_write_stat() didn't return the error code if Inode::SetFileSize() failed;
instead, it always reported success.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@995 a95241bf-73f2-0310-859d-f6bbb57e9c96
current/src/add-ons/kernel/drivers/net/Jamfile so the network stack driver
will access to build party.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@992 a95241bf-73f2-0310-859d-f6bbb57e9c96
- the maximum number of blocks a block_run can cover is 65535 not 65536
- allocations over a block boundary in the block bitmap always failed due
to a incorrectly handled status
Both bugs could prevent BFS to create the VM swap file which led BeOS to
stop booting under certain circumstances.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@989 a95241bf-73f2-0310-859d-f6bbb57e9c96
Tested, and works - we are now feature complete (and now for the bugs... :-)).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@974 a95241bf-73f2-0310-859d-f6bbb57e9c96
