The last log entry was never added to the list (if there were more than one), and
thus, it's blocks were never unlocked nor written back (after some minutes of
makehdimage an empty image would greet you).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14427 a95241bf-73f2-0310-859d-f6bbb57e9c96
though, so it's not really ready to be used in a real file system.
Found an off-by-one/some error in Be's BFS implementation: it doesn't use the log
array to its full extent.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14423 a95241bf-73f2-0310-859d-f6bbb57e9c96
- removed profiles, ppp_up, and some TODOs
- simplified KPPPReportManager and reports API, KPPPInterface::Up()+Down(), and PPPInterfaceListener (also removed some features from the last one)
- KPPPInterface now sends the last PPP_CONNECTION_REPORT message to every newly registered report receiver
- added net_server to the build, but removed old net_server testing-stuff
all changes are completely untested
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14338 a95241bf-73f2-0310-859d-f6bbb57e9c96
in read-only mode, but only wrote to it (which erroneously worked before that change).
Only a white screen appeared, no prompt, nothing.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13918 a95241bf-73f2-0310-859d-f6bbb57e9c96
For a comparison see: http://haiku.mlotz.ch/messagespeed.html
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13912 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added libmessagetest.so to test specifically the BMessage implementation.
Fixing some other unit tests along the way - quite many of them are borken.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13911 a95241bf-73f2-0310-859d-f6bbb57e9c96
src/tests/servers/app/Jamfile. This makes the original Jamfile much cleaner.
Note that you now have to maintain two Jamfiles when adding/removing sources.
The test app server is called haiku_app_server, its library
libhaikuappserver.so. I adjusted a few paths in scripts accordingly, but
I may have missed something elsewhere.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13858 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Moved setting the default cursor from ServerScreen to Desktop
* Getting the default cursor is now done using the CursorManager
* Removed outdated setcursor from SysCursor.cpp (we have a new implementation by now)
* Renamed SysCursor.cpp to CursorSet.cpp as that's what it is
* Moved headers/private/app/SysCursor.h to headers/private/servers/app/CursorSet.h
* Removed some unneeded header includes along the way
There remains {set|get}_syscursor now in CursorSet.cpp. Serverside for these are not implemented
and they are obvious hacks. Do we need to keep them?
Also this commit _would_ break Appearance, but 1) all the related code is currently commented out
with the comment "cursor set management belongs in another app" and 2) it is already broken
because of ColorSet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13726 a95241bf-73f2-0310-859d-f6bbb57e9c96
specified via options -l and -s. An arbitrary program can be run in the
terminal instead of a shell.
* Console::fState was never initialized which could cause the terminal to
not print anything.
* stdin, -out, and -err were set in MiniView::Start() and in
MiniView::ExecuteShell(). Thus resetting them in the latter method after
executing the shell had no effect. Removed it in the former method and
now reset them after loading, but before resuming the shell.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13676 a95241bf-73f2-0310-859d-f6bbb57e9c96
user_shutdown_reply reliably crashes the app server when pressing one
of its buttons (during the shutdown process at least).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13540 a95241bf-73f2-0310-859d-f6bbb57e9c96
the registrar no longer depends on the app_server to be running.
Added a "run_haiku_registrar" tool that is now used in the various "run" scripts.
It only start the registrar on demand, ie. if it's not yet running.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13493 a95241bf-73f2-0310-859d-f6bbb57e9c96
the super block was written back. This had a big race condition when all
blocks in the transaction were written back before the super block was
written. In that case, the log info part of the super block got out of
sync and was plain wrong (eventually causing the disk to be unmountable).
Also moved the list code over to the kernel's DoublyLinkedList.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13366 a95241bf-73f2-0310-859d-f6bbb57e9c96
