Wind River uses "hard real-time" to inject new vigor into Linux

Using Linux as a software development and operation platform for electronic devices has long been a hot topic in the field of device software, which can indeed bring many benefits to e-product manufacturing enterprises. However, Linux has always been able to provide soft real-time performance, but in many applications that require hard real-time performance, such as automotive control, industrial control, and telecom infrastructure, linux systems that only support "Soft Real-Time" capabilities cannot be used, which makes many time-sensitive applications difficult to access in Linux.

Recently, Wind River systems purchased RTLinux, a hardware real-time Linux technology from fsmlabs, and integrated it with the world's leading Linux equipment software platform, provides a new set of mature and reliable technologies for electronic device manufacturers to develop and deploy various next-generation Linux-based applications, meeting the needs of electronic device manufacturers for "hard real-time) "features, such as functional mobile phones, digital image applications requiring high-capacity streaming media, and various vehicle applications including vehicle collision avoidance systems. Among them, Wind River Platform for consumer devices integrated with RTLinux technology, Linux edition can upgrade various Linux-based high-speed packet switching device software applications to a new high-performance level.

Let's take a look at the differences between "hard real-time" and "Soft Real-time", and where a "hard real-time" software system is required for implementation, and how to obtain a Linux platform with the "hard real-time" feature.

Real-time "soft" and "hard"

Real-Time OS is a concept relative to time-sharing OS. In a time-sharing operating system, computer resources are evenly allocated to all work in the system. In a time-based system, it does not matter how long each task takes to complete. In a real-time operating system, the most important thing is how long each task can be completed. Simply put, the biggest difference between real-time and time-sharing operating systems is the concept of "Deadline.

From the above differences, we can see that in the real-time operating system, the system must complete the specified application within a specific period of time, with a strong "rigidity ", the time-sharing operating system focuses on allocating system resources evenly to each application, and does not care about the progress of each application and the time when it can be completed. However, even for real-time operating systems, the degree of "rigidity" and "flexibility" is also different, as if the system's "hardness" is different, therefore, the so-called "hard real-time" and "Soft Real-Time" are available )". A hard real-time system has a rigid and unchangeable time limit, which does not allow any errors that exceed the time limit. Timeout errors may cause damage or even system failure, or cause the system to fail to achieve its expected goals. The time limit of a soft real-time system is flexible and flexible. It can tolerate occasional timeout errors. The consequences of failure are not serious. For example, the network only slightly reduces the system throughput.