[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: semaphore and spin locks

To: "atul" <atul_info@yahoo.com>,"to_kbies" <kernelnewbies@nl.linux.org>
Subject: Re: semaphore and spin locks
From: Thomas Hofer <th@monochrom.at>
Date: Mon, 6 Aug 2001 13:48:49 +0200
In-Reply-To: <000201c03276$fff5c340$4562d6d2@man>
References: <000201c03276$fff5c340$4562d6d2@man>
Sender: owner-kernelnewbies@nl.linux.org

You wrote (Dienstag, 10. Oktober 2000 07:00):

> Since a process has to busy wait on spin-lock, what if 2 or more
> processes get stuck on the same spin lock, which process will be
> allowed to enter the critical region..??

The lucky one that comes first - the hardware decides. I think there's 
no guarantee for a process not to starve.

Atul, please adjust your system-clock.

Thomas.
-
Kernelnewbies: Help each other learn about the Linux kernel.
Archive:       http://mail.nl.linux.org/kernelnewbies/
IRC Channel:   irc.openprojects.net / #kernelnewbies
Web Page:      http://www.kernelnewbies.org/

Follow-Ups:
- RE: semaphore and spin locks
  - From: "atul" <atul_info@yahoo.com>

References:
- RE: semaphore and spin locks
  - From: "atul" <atul_info@yahoo.com>

Prev by Date: Re: Sending data between kernel module and user process
Next by Date: Re: kernel debugging talk
Prev by thread: RE: semaphore and spin locks
Next by thread: RE: semaphore and spin locks
Index(es):
- Date
- Thread