I'm working on a project that contains a real-time software component, using the RT PREEMPT patch on Linux.
During "idle" operation the software just sits waiting for incoming TCP connections and requests. Depending on the request, the software may create a real-time thread that runs for a period of time. So the entire application doesn't need to operate in real-time, only this one thread from time to time.
My question is this: I'm well aware that dynamic memory allocation is non-deterministic and is detrimental to real-time code. However, is accessing existing memory on the heap also detrimental to real-time constraints?
I ask because I'm considering a situation where the program starts up, allocates any required structures on the heap, then triggers a real-time thread that accesses the heap.
EDIT: Once the real-time thread has started, other threads are prevented from writing to variables the real-time thread needs to access using locks (well, except for one variable that must be updated, but access is still restricted using a separate lock).
EDIT2: I forgot to mention that the program will ultimately be deployed on a system that doesn't have any swap space, so I don't think the paging of memory should be an issue. (Though of course this doesn't avoid the issue of page-faults through memory that hasn't yet been provisioned by the OS.)
is accessing existing memory on the heap also detrimental to real-time constraints?
No, unless your system is thrashing.
BTW, you could consider writing your own allocation (e.g. above mmap(2)...) and using mlock(2) for the memory that ought to be in RAM.