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
1. Realtime Support questions
2. Architecture questions
3. Mailing list questions
4. Realtime Patches questions
5. Configuring/compiling questions
6. Realtime samples/Performance questions
7. Realtime Applications questions
8. Maintainers questions
Section 1 - Realtime Support questions
Q1: What is realtime support
Q2: How realtime works
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
Section 2 - Architecture questions
Q1: Which Architecture are supporting realtime and who is maintainer
Q2: What is the procedure to support realtime in new architecture
Section 3 - Mailing list questions
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
Section 4 - Realtime Patches questions
Q1: Why I need to download realtime patches, If realtime support is in Linux kernel
Q2: 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
Section 5 - Configuring/compiling questions
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
Section 6 - 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)|
Section 7 - Realtime Applications questions
Q1: List of realtime APIs
Q2: How to write realtime applications
Q3: Which programming languages are suitable for writing realtime applications
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
Section 8 - Maintainers questions
Q1: Maintainers of realtime kernel patch