Frequently Asked Questions
FAQ for realtime support in Linux Kernel
Questions are given by:
Answers are given by:
Luotao Fu (l.fu AT pengutronix DOT de), Pengutronix e.K., Kernel Development Group
Robert Schwebel (r.schwebel AT pengutronix DOT de), Pengutronix e.K., Kernel Development Group
Q1: What is realtime support
Q2: How does realtime work?
A2: The RT-Preempt patch converts Linux into a fully preemptible kernel. The magic is done with:
- Making in-kernel locking-primitives (using spinlocks) preemptible though reimplementation with rtmutexes:
- Critical sections protected by i.e. spinlock_t and rwlock_t are now preemptible. The creation of non-preemptible sections (in kernel) is still possible with raw_spinlock_t (same APIs like spinlock_t)
- Implementing priority inheritance for in-kernel spinlocks and semaphores. For more information on priority inversion and priority inheritance please consult Introduction to Priority Inversion
- Converting interrupt handlers into preemptible kernel threads: The RT-Preempt patch treats soft interrupt handlers in kernel thread context, which is represented by a task_struct like a common userspace process. However it is also possible to register an IRQ in kernel context.
- Converting the old Linux timer API into separate infrastructures for high resolution kernel timers plus one for timeouts, leading to userspace POSIX timers with high resolution.
more information: RT PREEMPT HOWTO
Q3: What is the procedure to add realtime support?
A3: Download latest realtime preemption patch from http://www.kernel.org/pub/linux/kernel/projects/rt/ then get related vanilla kernel from http://kernel.org/ then patch, configure and compile
Q1: Which Architecture are supporting realtime and who is maintainer?
Q2: What is the procedure to support realtime in new architecture?
Q1: realtime mailing list and archives
Q2: If I have some doubts or problems regarding realtime, do I need to send mail in realtime mailing list or linux kernel mailing list or both?
Realtime Patches questions
Q1: Why I need to download realtime patches, If realtime support is in Linux kernel?
Q2: Where can I download latest realtime patches?
Q3: Where can I post my realtime patches?
A3: Please send patches for the CONFIG_PREEMPT_RT Patch Set to LKML and put Ingo Molnar and Thomas Gleixner on CC.
Please do not send clocksource and clockevents related patches against the -rt patch. Make sure they apply against the latest -hrt-dyntick patch. -hrt-dyntick might be a bit ahead of -rt at times, but the -rt patch pulls -hrt-dyntick on a regular base.
more information: CONFIG_PREEMPT_RT Patch
Q1: How to enable/disable realtime support?
Q2: Change realtime support run time or statically?
Q3: Required parameters for configuring realtime kernel?
Q4: Optional parameters for configuring realtime kernel, but they effect realtime performance?
Realtime samples/Performance questions
Q1: What effects by realtime support and how much and samples to test it and who maintains these samples?
a. scheduling, task switching time
b. Interrupt latency
c. Interprocess communication
e. Device drivers
|Area||Effected by Realtime(%)||Samples||Contact(s)|
Realtime Applications questions
Q1: List of realtime APIs?
Q2: How to write realtime applications?
Q3: Which programming languages are suitable for writing realtime applications?
A3: It depends on your latency requirements, but usually these are advisable:
- C is preferred;
- C++ is possible if some constraints are taken into account (see Q4)
Q4: Keep following things in mind while writing realtime applications?
A4: Taking care of the following during the initial startup phase:
- Call directly from the main() entry the mlockall() call.
- Create all threads at startup time of the application, and touch each page of the entire stack of each thread. Never start threads dynamically during RT show time, this will ruin RT behavior.
- Never use system calls that are known to generate pagefaults, such as fopen(). (Opening of files does the mmap() system call, which generates a page-fault).
- Do not use 'compile time static arrays' without initializing them directly after startup, before RT show time.
more information: HOWTO: Build an RT-application
Q5: Do I need to recompile my applications to get realtime performance?
A5: Recompile is not necessary. Userland does not notice any difference if it is running on RT or not, except for a much better RT-responsiveness, only changing the kernel is enough.
But, usually, locking bugs in userland applications become much more visible due the more dynamic and fine grained scheduling of the kernel. These are not new bugs, but bugs already existing in the applications, which only become visible on RT (Notice that these bugs are also likely to occur on SMP systems).
- A bad designed application on non-RT will never behave realtime on RT. See also Q4.
- Never protect shared/global data in userland processes with semaphores (yes, many people do that...), but use PTHREAD_PRIO_INHERIT mutexes instead. (PTHREAD_PRIO_INHERIT mutexes are only supported in Glibc 2.5 and higher. uClibc based filesystems do not support this)
Q1: Who are the Maintainers of realtime kernel patch?