Hi!
On 11:58 Wed 15 Sep , Smital Desai wrote:
> Hi everyone,
>
> It's an extract in LDD3 , regarding spink lock. I have put my query in
> brackets.
>
> Spinlocks are, by their nature, intended for use on multiprocessor systems,
> although a uniprocessor workstation running a preemptive kernel behaves like
> SMP, as far as concurrency is concerned.
> ( I need to understand , how this is true with an example preferably )
There is a timer interrupt on every system which causes the cpu to stop
processing whatever it is processing to run the scheduler. The scheduler will
start a different task. This way it looks like all tasks run at the same time.
> If a nonpreemptive uniprocessor system ever went into a spin on a lock, it
> would spin forever; no other thread would ever be able to obtain the CPU to
> release the lock. For this reason, spinlock operations on uniprocessor
> systems without pre-emption enabled are optimized to do nothing, with the
> exception of the ones that change the IRQ masking status.
> ( I don't get the meaning of last sentence "with the exception of ......"
> Please can somebody explain )
There are many variants of spin_(un)lock. Some of them (e.g. spin_lock_irq +
spin_lock_irqsave) turn off interrupts, so that nothing else can get in the
way of critical sections.
-Michi
--
programing a layer 3+4 network protocol for mesh networks
see http://michaelblizek.twilightparadox.com
--
To unsubscribe from this list: send an email with
"unsubscribe kernelnewbies" to [email protected]
Please read the FAQ at http://kernelnewbies.org/FAQ
