Take the 2-minute tour ×
Unix & Linux Stack Exchange is a question and answer site for users of Linux, FreeBSD and other Un*x-like operating systems.. It's 100% free, no registration required.

I know that jiffies length is selected at kernel compile time and it is defaulted to 250 (4ms).
Source: man 7 time - The Software Clock, HZ, and Jiffies

I wonder what happens inside a jiffy. What are the conditions to increase the value of utime or stime in /proc/pid/stat? When does it happens?

I have some thoughts but I'm not sure they are true:

  • When a process gets time to run, the jiffy count is incremented instantly.
  • Linux can't tell how many operations have been executed in 1 jiffy.
  • Furthermore Linux can't tell how much time has been used by the current process in 1 jiffy. (Has it used all the 4 milliseconds, or less?)
  • Current process starts in the beginning of the jiffy and never starts later.
  • When a process is done and there is remaining time from current jiffy nothing happens (nop).
  • If a process with higher priority occurs it does not affect the current jiffy.

It would help a lot to understand theese.

share|improve this question

1 Answer 1

When jiffy count is incremented then a process gets time to run. The jiffies are incremented by the timer interrupt that tells the scheduler to reschedule. The jiffy defines the maximum time period for the processes to run without rescheduling. If the process calls yield() or sleep(), for example, then rescheduling takes place immediately. Thus the context switch to a next available running process not necessarily occurs at the jiffy boundary.

However, the actual kernel behavior is defined at kernel compile time, linux/kernel/Kconfig.preempt:

choice
    prompt "Preemption Model"
    default PREEMPT_NONE

config PREEMPT_NONE
    bool "No Forced Preemption (Server)"
    help
      This is the traditional Linux preemption model, geared towards
      throughput. It will still provide good latencies most of the
      time, but there are no guarantees and occasional longer delays
      are possible.

      Select this option if you are building a kernel for a server or
      scientific/computation system, or if you want to maximize the
      raw processing power of the kernel, irrespective of scheduling
      latencies.

config PREEMPT_VOLUNTARY
    bool "Voluntary Kernel Preemption (Desktop)"
    help
      This option reduces the latency of the kernel by adding more
      "explicit preemption points" to the kernel code. These new
      preemption points have been selected to reduce the maximum
      latency of rescheduling, providing faster application reactions,
      at the cost of slightly lower throughput.

      This allows reaction to interactive events by allowing a
      low priority process to voluntarily preempt itself even if it
      is in kernel mode executing a system call. This allows
      applications to run more 'smoothly' even when the system is
      under load.

      Select this if you are building a kernel for a desktop system.

config PREEMPT
    bool "Preemptible Kernel (Low-Latency Desktop)"
    select PREEMPT_COUNT
    select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
    help
      This option reduces the latency of the kernel by making
      all kernel code (that is not executing in a critical section)
      preemptible.  This allows reaction to interactive events by
      permitting a low priority process to be preempted involuntarily
      even if it is in kernel mode executing a system call and would
      otherwise not be about to reach a natural preemption point.
      This allows applications to run more 'smoothly' even when the
      system is under load, at the cost of slightly lower throughput
      and a slight runtime overhead to kernel code.

      Select this if you are building a kernel for a desktop or
      embedded system with latency requirements in the milliseconds
      range.

endchoice

Yes, Linux can't tell how many operations have been executed in 1 jiffy as different instructions takes different times to execute as well as pipelining of the instructions affects the number of instructions executed in a unit of time.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.