Changed the whole way locking was done. What was I thinking?
Many changes and cleanup ideas from Ingo (thanks!).
Not perfect yet, but much better. Still a few things left to implement
in the COW arena - mmap doesn't use it. Also need to finish the vpageManager
which will cause mmap and cacheManager to use the same vnodes where possible.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1042 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
also initialize newly allocated memory with non zero (0xCC)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1014 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
+ Modified BMimeType::SetSupportedTypes functionality so it keeps track of
stranded types (i.e. previously supported types that have not had the now
unsupporting app signature removed from their supporting apps list yet due
to a false fullSync parameter) over consecutive SetSupportedTypes(...,
false) calls and updates all appropriate stranded types on the next
SetSupportedTypes(..., true) call.
+ Added fullSync parameter to BMimeType::DeleteSupportedTypes
+ Made BMimeType::Delete() do a DeleteSupportedTypes(..., true) call to
properly update the supporting apps lists when a mime type is deleted.
+ Added initial BMimeType::Get/SetSnifferRule
+ Updated BMimeType::CheckSnifferRule() to return B_BAD_VALUE when passed
a NULL rule string.
+ Brought CheckSnifferRule() tests up to date
+ Added lots of Mime::Database doxygen
+ Added any missing mime monitor notifications in Mime::Database
+ Possibly made some other changes as well... :-)
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1004 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added SetSupportedTypes() documentation
Removed a few unnecessary BMessage copies in a couple of functions
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1003 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
