I've found some information about the Android garbage collector that are contradictions to me.
Android Devevelopers Guide says:
Android 3.0 is the first version of the platform designed to run on either single or multicore processor architectures. A variety of changes in the Dalvik VM, Bionic library, and elsewhere add support for symmetric multiprocessing in multicore environments. These optimizations can benefit all applications, even those that are single-threaded. For example, with two active cores, a single-threaded application might still see a performance boost if the Dalvik garbage collector runs on the second core. The system will arrange for this automatically."
Ok, now the other thing
According to this link: The Dalvik Virtual Machine Architecture android uses mark and sweep aproach.
The current strategy in the Dalvik garbage collector is to keep mark bits, or the bits that indicate that a particular object is “reachable” and therefore should not be garbage collected, separate from other heap memory.
If we check how mark and sweep works on this link: Mark and Sweep Garbage Collection Algorithm , we can see this:
The main disadvantage of the mark-and-sweep approach is the fact that that normal program execution is suspended while the garbage collection algorithm runs. In particular, this can be a problem in a program that interacts with a human user or that must satisfy real-time execution constraints. For example, an interactive application that uses mark-and-sweep garbage collection becomes unresponsive periodically.
So my question now is, how does it really work? Does garbage collector pause everything while he is working, or is he capable of running completely independent on the other active processor core?