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
