“Real Time Linux,” which guarantees response within a certain period of time, will be officially integrated into the kernel – Livedoor News

Real Time Linux, which guarantees response within a certain period of time, has been officially integrated into the kernel.

On September 20, 2024, Linus Torvalds, the creator of Linux, announced the release of Linux, known as Real Time Linux.Expect_RTIt is officially integrated into the Linux kernel.

Merge tag 'sched-rt-2024-09-17' from git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip – kernel/git/torvalds/linux.git – Linux kernel source tree

https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=baeb9a7d8b60b021d907127509c44507539c15e5

Linux Real-Time Becomes Officially Part of the Kernel After Decades of Controversy | Ars Technica

https://arstechnica.com/gadgets/2024/09/real-time-linux-is-officially-part-of-the-kernel-after-decades-of-debate/

Real Time Linux is a system that ensures Linux responds to events within a certain time period when used in time-sensitive systems such as industrial control systems, medical equipment, and aerospace equipment. PREEMPT_RT is a patch package created in 2005 that modifies the kernel to integrate real-time functionality into Linux.

“It’s crazy to control a laser using Linux,” Mr. Torvalds said in 2006, but his position is “But if you want to control an industrial welding laser using Linux, there’s nothing wrong with using PREEMPT_RT.” PREEMPT_RT was never part of the Linux kernel, but it has been used in various fields for many years.

So, even if PREEMPT_RT is officially integrated into the Linux kernel, nothing will change immediately, but by officially integrating PREEMPT_RT into the kernel, the dependencies of systems that use PREEMPT_RT will be reduced and maintenance will be easier.

Additionally, on the news site “Hacker News” where engineers gather, an example of a build of the Cyclictest utility was published as a way to demonstrate the power of real-time performance in a single shot. According to the post, when we measured the interrupt latency of each CPU core during the build, we found that in the worst case on regular Linux it can reach double-digit milliseconds, but in Real Time Linux even in the worst case it is said that it can respond in single-digit microseconds.