Debugging Linux Kernel using ftrace Part14 - Measuring scheduling latency

-
ftrace provides "wakeup" tracer to find the scheduling latency. This tracer only records the latency for the highest priority to get scheduled after it woken up.

Scheduling latency: Time from the wakeup event until the task actually gets the CPU and begins to run.


You can see from the above screenshot, i wrote a simple program which calls "sleep" to voluntarily leave the CPU from the 'wakeup' process and to give it to another process for us to find out the scheduling latency. It took '30us' for scheduling the next highest priority task.



Comments

Post a Comment

Popular posts from this blog

Appending and Prepending in Yocto - +=, =+ vs .=, =.

-
Image
Bitbake provides two sets of appending and prepending operators. 1. +=, =+ 2. .= , =. For example, A = "hello" A += "world" C = "good" C =+ "bye" The value of A will be "hello world" and C will be "bye good" So, += is appending and =+ is for prepending. Note, that these operators include an additional space between each call When we don't need to add space, we can use .=, =. operators. These are mainly used to concatenate strings. When we use append, prepend, there will be no additional space added, you need to manually provide space. You can also remove values from the variable using 'remove'.
Read more

ARM interview questions

-
ARM INTERVIEW QUESTIONS 1.       What is T,D,M,I in ARM TDMI? 2.       What are the different modes of ARM 3.       What are the different states in ARM 4.       Significance of each state and mode? 5.       Draw CPSR for ARM7TDMI 6.       There is no separate return statement in ARM . then what we will use to return from ARM? 7.       How does stack grows in ARM? 8.       What is the instruction to switch from ARM to Thumb and vice versa? 9.       What are the different coprocessors in ARM? 10.   C Runtime Environment,Linker Descriptor File 11.   Differences between Memory mapped I/O and I/O mapped I/O? 12.   Vector locations in ARM? 13.   Why FIQ is faster than IRQ?
Read more

Linux driver example for Per CPU Variable

-
Image
Per CPU Variables is an interesting feature available from Linux Kernel Version 2.6 When you define a Per CPU Variable, each processor in the system will have its own copy of the variable, hence no locking is required and better performance is achieved. Header File: <linux/percpu.h> To create a Per CPU Variable at compile time, use the macro: DEFINE_PER_CPU(type, name); E.g. DEFINE_PER_CPU(int, counter); As linux kernel is preemptible, you must use get_cpu_var macro to access the current processor's copy of a given variable And finally call put_cpu_var macro after you have completed using it. You can access another processor's copy of the variable with: per_cpu(variable, int cpu_id); Example: Output:
Read more