DESCRIPTION

tmf: Avoid hanging when waiting on a cancelled analysis

Also bumped the timeout on await() to 500 ms. It means that, on
average, the user will have to wait 250 ms after clicking on
the cancel button actually cancels the running analysis. 1 ms
was burning CPU cycles for nothing.

Change-Id: Id716c761a60b97d53d6809d0457e4f30b63f655e
Signed-off-by: Braxton Mccarthy xxx@xxx.xxx
Reviewed-on: https://git.eclipse.org/r/21590
Tested-by: Brenden Conley
Reviewed-by: Annalise Jimenez xxx@xxx.xxx
IP-Clean: Annalise Jimenez xxx@xxx.xxx


COMMENTS

author: Braxton Mccarthy
date: 2014-02-06 15:21:34.000000000

Change has been successfully cherry-picked as 188f8b835ade9c91e27110094e3b14d9deef82c2

-------------------------------------
author: Annalise Jimenez
date: 2014-02-06 15:25:02.000000000

Patch Set 2:

You know, I'm absolutely not against having a waitForCompletion() method since it is the most common case and having new NullProgressMonitor() looks kinda bad, as long as we keep the waitForCompletion(IProgressMonitor) for the cases of cascading analysis (in critical path/execution graph, that monitor goes a long way even into the analysis sub classes, we can add text and details of what is going on with it!)

-------------------------------------
