one alert, when two threads of a team crash. Now we have a per team queue
of debug messages and a thread per team that processes them (that is
usually only the first one). The application class does nothing anymore.
* Implemented debugger handover:
- In case of normal apps, when the relevant servers needed for GUI are
running, we show an alert and, if requested, start a MiniTerminal with
gdb for the crashed team. I couldn't really test it, since alerts don't
seem to work, respectively crash the app server (usually both ;-).
- In case the app server crashes, we always start a consoled with gdb.
This does indeed seem to work.
A gdb attached to a team is not really useful yet, since the shared object
relocations seem to be incorrect, so "bt" is not giving any useful info.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13684 a95241bf-73f2-0310-859d-f6bbb57e9c96
shutdown (input, app, debug server, and registrar).
* Fixed crashing bug, if the shutdown was aborted before the window was
created.
* The text of the confirmation alert depends on whether we reboot or
shut down.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13643 a95241bf-73f2-0310-859d-f6bbb57e9c96
* When an application aborts the shutdown process by refusing to quit, the
shutdown window says so for 3 seconds before closing.
* Fixed the height of the normal buttons in the shutdown window. They
accidentially got the size of a default button.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13564 a95241bf-73f2-0310-859d-f6bbb57e9c96
fonts are now installed as part of other data files
we still install some host fonts if found
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13557 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented handling of apps blocking on modal windows.
* Fixed a few bugs.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13539 a95241bf-73f2-0310-859d-f6bbb57e9c96
Now handles it gracefully if someone deletes its message port (it will try to close
the client and quit).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13511 a95241bf-73f2-0310-859d-f6bbb57e9c96
the focus border, and therefore, I probably broke floating windows (but that's
not that important right now).
Workspace::HideWinBorder() now sets focus to the next WinBorder, not always
the top one.
Workspace::MoveToFront() no longer changes focus, no longer calls ShowWinBorder()
when the window doesn't have to be moved (ie. for the desktop window).
Added Workspace::SetFocus() to change the focus explicetly.
Some other cleanup. This is an ugly patch, but refactoring/rewriting is coming
soon.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13509 a95241bf-73f2-0310-859d-f6bbb57e9c96
asked to quit in parallel. Instead they are asked one after the other.
Played with the window to look more like the one in BeOS. The "shadow" on
the left side is still missing, but otherwise it's close.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13496 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
busy loop of the MessageDeliverer when the port was deleted while there
were still messages to send.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13489 a95241bf-73f2-0310-859d-f6bbb57e9c96
in parallel, it displays the mini icons of all still running apps. Doesn't
look that great, though. Also, quitting the apps in parallel speeds up the
shutdown process, but has the disadvantage, that all apps will throw their
"Save changes...?" alerts at the user at once, which might not be a
desirable experience. I'll probably revert to the way Be did it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13488 a95241bf-73f2-0310-859d-f6bbb57e9c96
them if they didn't listen to B_QUIT_REQUESTED. This works much better
as how it was done before.
Now uses exit() instead of exit_thread() which makes sure no thread survives.
Note, there still is a race condition in case an application quits immediately
before shutting down the server - in that case, it doesn't participate in
the fShutdownSemaphore stuff, and therefore, the app_server could quit it
too early. Maybe I'll fix that one day, as well :)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13481 a95241bf-73f2-0310-859d-f6bbb57e9c96
(but should still have their own look that includes the bevel, I think).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13469 a95241bf-73f2-0310-859d-f6bbb57e9c96
Basic support for the desktop window feel: WinBorder will now resize
a window with kDesktopWindowFeel to span over the whole screen.
Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13462 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixed handling in ServerWindow as stippi's latest commit broke it.
It's now properly done with a separate ServerWindow::SetTitle() method,
that will also take care to rename the window's thread.
Changed naming the window thread in the app_server to "w:<team>:<title>".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13461 a95241bf-73f2-0310-859d-f6bbb57e9c96
Renamed Desktop::FindWinBorderByServerWindowTokenAndTeamID() to FindWinBorderByClientToken().
Every ServerWindow now gets a server token.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13455 a95241bf-73f2-0310-859d-f6bbb57e9c96
and that put apps that used it to sleep (for example, Tracker is using it).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13433 a95241bf-73f2-0310-859d-f6bbb57e9c96
any public header.
* Replaced a good deal of the MessageDeliverer's DeliverMessage() versions
by more general ones using the new interface MessagingTargetSet to represent
a set of targets. This simplifies the usage in cases where the caller doesn't
already have the targets in a supported representation.
* Implemented a first approximation of the shutdown process. There is no
GUI yet. Only superficially tested under R5.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13417 a95241bf-73f2-0310-859d-f6bbb57e9c96
are different. Therefore, workspace changes should work on real hardware as
well now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13387 a95241bf-73f2-0310-859d-f6bbb57e9c96
But since every single cursor is owned by a team - why the cursor manager?
I must overlook something...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13385 a95241bf-73f2-0310-859d-f6bbb57e9c96
windows that wouldn't quit on demand, the app_server would have gotten
the kShutdownServer message anyway already (as the last app was quit).
Since that one removed things like gDesktop/gBitmapManager, it liked
crashing.
Now, there is a semaphore that will be send to each app on quit. Only
when this semaphore can be acquired, the shutdown message will be sent.
Removed unused semaphores (decorator, active app).
Replaced fAppListLock with a BLocker (just calling acquire_sem() without
error checking is very unsafe in userland, and should never be done).
BTW the bug was triggered by broken menu code that only sometimes
really quit the window; it leaves a whole lot of zombies around - Stefano,
any quick idea? :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13384 a95241bf-73f2-0310-859d-f6bbb57e9c96
The ServerWindow did not even have such a mechanism anyway... (it now has).
Minor cleanup, replaced some "delete" with "delete[]" where appropriate.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13382 a95241bf-73f2-0310-859d-f6bbb57e9c96
handle the case at all to give the server the possibility to send a
failure response - ifdef'd some code out.
Added comment to ServerApp::PingTarget(), because what it currently does
does not make any sense.
Minor cleanup (replaced fSignature.String() with Signature()).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13381 a95241bf-73f2-0310-859d-f6bbb57e9c96
bitmap manager do the job.
This fixes a possible crashing bug on quit, a giant memory hole, and
probably also a possible crash during runtime.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13380 a95241bf-73f2-0310-859d-f6bbb57e9c96
order to flicker less (which works, but it's not really that nice yet, as
it currently only works for the background).
The workspaces layer is now also invalidated if a new window appears on the
screen or goes away (also when this happens in another workspace).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13379 a95241bf-73f2-0310-859d-f6bbb57e9c96
A view-only workspaces window support (with lots of drawing flicker) - this
means you see what happens in the workspaces, but it doesn't do anything if
you click on it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13378 a95241bf-73f2-0310-859d-f6bbb57e9c96
- it now seems to work finally correctly
- renamed ViewAttr to ViewState and put it into the BPrivate namespace
- some refactoring (moved some private BView methods to ViewState)
- renamed AS_LAYER_MOVETO/RESIZETO to *_TO (note the underscore)
- exchanged BView::originX/Y with fParentOffset (BPoint)
- divided AS_LAYER_GET_COLORS into separate ones for high/low/view color
- BView::SetPattern() now actually works as expected (ie. updates
only if necessary)
- exchanged the ViewAttr::flags with ViewState::valid_flags which inverses
the previous logic (which wasn't even used consistently)
- fState was initialized twice (incorrectly by the ViewAttr constructor,
and then again correctly by initCachedState()) - now the ViewState
constructor does the job alone, but correctly
- BView::PushState() no longer resets the state (it did so only locally
anyway...)
- cleanup
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13325 a95241bf-73f2-0310-859d-f6bbb57e9c96
say hello to RootLayer.
Adi will probably not like this, but that's definitely only a temporary solution :-)
This little fix greatly increases app_server stability under Haiku - ie. menus
are working now, the team monitor comes up regularly, etc. - how great is that?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13305 a95241bf-73f2-0310-859d-f6bbb57e9c96
test application now works as it should.
DefaultDecorator::GetSizeLimits() did work correctly, there was no need
to have extra protection limits.
Enabled Stephan's automatic resize code on BWindow::SetSizeLimits() again, and
added a short comment why I think R5's behaviour is just a bug/leftover.
Moved guts of ResizeBy() into _ResizeBy() that doesn't send the update message
to the client, and is now called in the constructor to make sure the border
size is within limits. Also made it work there, as fTopLayer is NULL in that
environment.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13304 a95241bf-73f2-0310-859d-f6bbb57e9c96
the window on server side - ie. if the app_server could not create a
window of the size requested, BWindow::fFrame will still be correct
(and the size limits will mirror actual decorator limits).
Renamed fMinWindHeight and friends to fMinHeight and so on.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13302 a95241bf-73f2-0310-859d-f6bbb57e9c96
a valid size on construction; DefaultDecorator should do that as well.
ServerApp AS_CREATE_WINDOW now makes sure it passes a valid rectangle to
ServerWindow's constructor.
Smaller default size for Layers that have been created with an invalid frame.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13291 a95241bf-73f2-0310-859d-f6bbb57e9c96
- moved part of the update code from Layer to WinBorder. Fits better
there.
- renamed a couple members.
- some cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13273 a95241bf-73f2-0310-859d-f6bbb57e9c96
used for new area.
MemPool::AddToPool() now gracefully deals with NULL pointers (or a size of 0).
BitmapManager was deleting the area it transferred to AreaPool before - it
no longer needs an extra area, though.
Minor other cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13260 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also applied our style guide on that class.
Renamed some public globals to match our style guide.
Made BitmapManager inherit from BLocker instead of duplicating its
functionality (incorrectly, did not check for B_INTERRUPTED) locally.
Some more cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13259 a95241bf-73f2-0310-859d-f6bbb57e9c96
area_for() is not the cheapest call; the user better knows the area and deletes it directly.
Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13257 a95241bf-73f2-0310-859d-f6bbb57e9c96
application and bitmaps are removed, the team's windows are now removed
as well.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13251 a95241bf-73f2-0310-859d-f6bbb57e9c96
- replaced fMsgSender/Receiver with a BPortLink fLink
- moved message loop into non-static method _MessageLooper()
- renamed Zoom()/Minimize()/Quit()/ScreenModeChanged() to Notify*(), and
Quit() to NotfiyQuitRequested() to make more clear what they do (they
don't operate on ServerWindow, they just notify its client)
- less insane way to init a window: there is no longer the constructor
and a separate method Init(); now there is the constructor (which
fully sets up the window), InitCheck(), and Run() which runs the
window's message loop
- moved the quitting stuff into a separate method Quit() and made
it callable from other threads.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13247 a95241bf-73f2-0310-859d-f6bbb57e9c96
will update it automatically.
Renamed ServerWindow::fName to fTitle, made it a pointer - it will now just
adopt the title pointer that came from AS_CREATE_WINDOW.
Just another cleanup round: renamed Layer::GetName() to Name(), no
more layer->fName->String() accesses.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13239 a95241bf-73f2-0310-859d-f6bbb57e9c96
can now quit instantly.
AppServer must no longer call ServerApp's destructor once it's running - it now
has to call Quit() in this case. The ServerApp is now destructed in its own thread.
Some cleanup (like renaming ServerApp::MonitorThreadID() to Thread()).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13238 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixed broken ViewHWInterface::GetModeList() - it did not correctly write into
the allocated memory. Also extended it to be more flexible, has better timing
values, and more resolutions.
ViewHWInterface::SetMode() will now check if the requested mode is in its
list of supported modes.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13226 a95241bf-73f2-0310-859d-f6bbb57e9c96
Updated a couple headers
Moved all decorator code to ServerApp where it belongs
Modified AppServer::Broadcast to allow ServerApps send messages to all apps without having to have a global AppServer instance
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13204 a95241bf-73f2-0310-859d-f6bbb57e9c96
fCurrentLayer was used to determine to which layer a new one would be
added to, but BView::AddChild() would only set this correctly for the
current view, ie. all children of the new child were added to the
wrong layer in the app_server.
Now, AS_LAYER_CREATE sends the parent's token to the server, and the
server relies on this to build the layer hierarchy.
All of a sudden a lot of hidden views are visible now. I noticed the
bug while refactoring the task manager, but a lot of apps were affected.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13164 a95241bf-73f2-0310-859d-f6bbb57e9c96
to LinkReceiver, LinkMsgSender to LinkSender, and put everything into the
BPrivate namespace.
Made AppServerLink a cheap object - it will use the applications receiver/sender
and not create its own buffers.
Fixed broken communication stuff here and there (mostly Font.cpp).
Put the newly introduced set|get_system_colors() into the BPrivate namespace -
please don't introduce private functions into the public namespace!!!
Also fixed their broken communication use, as Darkwyrm obviously forgot about
it again: the sequence Flush(); GetNextMessage() without error checking is
purely wrong and can make the app hang and/or crash! :-)
Other minor cleanup.
The input_server used some test mode with the haiku build target which is
probably wrong.
Hopefully I did not forget anything this time.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13128 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also fixed _AllocateBuffer() to handle out of memory situations gracefully.
It should probably also have upper limits with regard to the bitmap size.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13109 a95241bf-73f2-0310-859d-f6bbb57e9c96
as required by the interface.
Unfortunately, this doesn't help the slow window moving with Rudolf's drivers.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13099 a95241bf-73f2-0310-859d-f6bbb57e9c96
Note that the inversion_map and the index_map aren't the same as in Beos, due to bugs (or different behaviour) in color_distance.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13086 a95241bf-73f2-0310-859d-f6bbb57e9c96
Hack workaround: enlarged the text width a bit, because the title often appeared
truncated for no apparent reason.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13012 a95241bf-73f2-0310-859d-f6bbb57e9c96
(Incorrectly) implemented AS_GET_DESKTOP_COLOR - works for now.
Minor cleanup.
Is AS_SET_SCREEN_MODE used at all?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13010 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added LinkMsgReader::NeedsReply() method.
Completely redone ServerApp messaging: no more "replyport" from BAppServerLink; instead,
the registered client reply port is used. Fixed some more weak messaging stuff.
ServerApp now recognizes if an unknown message needs a reply, and sends it - for example,
the "Screen" preferences app no longer hangs, but crashes on start :)
Made LinkMsgReader::Read() virtual again, since it's needed by RAMLinkMsgReader.cpp.
Renamed BPortLink::GetNextReply() to GetNextMessage().
Some more cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13004 a95241bf-73f2-0310-859d-f6bbb57e9c96
Note, the special case can go as soon as we've moved the driver over to the new
driver architecture.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13001 a95241bf-73f2-0310-859d-f6bbb57e9c96
BPortLink::AttachString() now accepts a length argument, and will no longer
send a terminating null byte; LinkMsgReader::ReadString(), however, will
make sure the string read is null terminated.
Changed client communication code to use FlushWithReply() instead of Flush()
and GetNextReply() - there were many bugs and shortcomings in the code, I
hope I've fixed them all.
Converted ClientFontList.cpp to our coding style (but not completely, the
class members are missing).
Some more cleanup - I hope Adi will adopt our coding style one day!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12998 a95241bf-73f2-0310-859d-f6bbb57e9c96
to enable debug output in the runtime linker and still have to compute the offsets
manually.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12900 a95241bf-73f2-0310-859d-f6bbb57e9c96
- extended libdebug.so functionality to be able to get stack frames,
current instruction pointer, etc.
- changed the debug_server to be able to run as a simple BLooper - this
saves some trouble when the app_server dies
- the debug_server now prints out a stack crawl for the crashed team
(without symbols, though - for that data to be helpful you should
have a look at the loaded images (ie. where they start))
- the debug_server now also prints the team name when it kills it
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12882 a95241bf-73f2-0310-859d-f6bbb57e9c96
port is now transferred to the client, so that it goes away automatically.
Unfortunately, this doesn't seem to work. This code is truly a big mess :-/
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12846 a95241bf-73f2-0310-859d-f6bbb57e9c96
has to care about refresh rates. Also changed Screen::GetMode() (formerly
Resolution()) to return all interesting values, so that hopefully no one
will call it anymore like RootLayer::SetScreens() did.
Greatly improved the horrible RootLayer::SetScreens().
The app_server is now able to deal with failing HWInterface::SetMode() calls;
in this case, it will fall back to the hardware's current mode. This now
also works correctly in combination with the vesa driver, so that you don't
have to compile the app_server with the same resolution you boot in anymore.
SetMode() now always returns if it succeeded or not.
Renamed RootLayer::fScreenXYResolution to fScreenWidth/Height respectively.
Removed the useless DisplayDriver::DisplayMode() method.
Added B_GET_DISPLAY_MODE to the required accelerant hooks.
Some minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12831 a95241bf-73f2-0310-859d-f6bbb57e9c96
missing required hooks, it's now unloaded (and uninitialized if necessary)
correctly, the device is closed, and the next one will be examined.
Not deeply tested, but seems to work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12804 a95241bf-73f2-0310-859d-f6bbb57e9c96
communication, the port's reply port is no longer sent to the app_server (as it
knows where to reply to, anyway).
Also made sure the view's looper is locked while getting the coords - I guess
BPortLink doesn't like to be written to from two different threads :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12742 a95241bf-73f2-0310-859d-f6bbb57e9c96
Uncomment in Jamfile "#APPSERVER_TEST_MODE = 1 ;" to test app_server with input_server
Uncomment in InputServer.h "//#define R5_CURSOR_COMM" to enable cursor comm when appserver BPortlink comm is used
Default mode is R5 comm if TARGET != haiku
and appserver BPortLink comm when TARGET = haiku
For APPSERVER_TEST_MODE, make sure to change the ViewInputDevice path in AddOnManager.cpp
To test with app_server, enable LaunchCursorThread() in AppServer.cpp and uncomment "#define INPUTSERVER_TEST_MODE 1" in ViewHWInterface.cpp
Also make sure to change the input_server path in AppServer.cpp
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12493 a95241bf-73f2-0310-859d-f6bbb57e9c96
we write view events to a port so that the ViewInputDevice gets them and have them processed by input_server, and then app_server
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12489 a95241bf-73f2-0310-859d-f6bbb57e9c96
