linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Nicholas Mc Guire <der.herr@hofr.at>
To: Monica Puig-Pey <puigpeym@unican.es>
Cc: linux-rt-users@vger.kernel.org
Subject: Re: I/O operations priority in RTOS
Date: Sun, 5 Jun 2011 01:42:14 +0200	[thread overview]
Message-ID: <20110604234214.GA30640@opentech.at> (raw)
In-Reply-To: <4DEA1F22.6000603@unican.es>

On Sat, 04 Jun 2011, Monica Puig-Pey wrote:

> Hello,
> I'm studying how to develop drivers in a real time OS and how do they  
> work. I'm using  Ubuntu 10.04 with the 2.6.31-11-rt patch installed.
> I would like to know the priority when executing open(), read(), write()  
> and close() operations.
> In my example the thread which is using the driver runs with 10 RTPRIO,  
> but I don't know what happens in kernel context with the priority when  
> running the I/O operations.
> Thank you for your help, I don't know where to learn about this.
>

Priorities are not associated with functions but rather with processes/threads
so the priority with which the functions open/read/write are executed depend
on the process that invokes these functions.

That said there is an indirect impact of the function on priority as soon as
the funciton needs to share any resources that need protection by locking. The
moment that happens the effective execution priority of the function no longer only depends on the task that calls open but may indirectly depedn on a totally
unrelated task that happens to hold a lock protecting some shared resource.

So the consequence for rt-drivers is that they must ensure that they minimize
critical sections, or prevent them all together (i.e. by using lock free 
methods). Notably this puts restrictions on the use of dynamic resources at 
runtime, that is after the driver was initialized - basically you want all 
resources that the rt-driver needs allocated at driver initialization time. 
Also when using bottom half mechanisms you need to take into account the 
priority of the kernel thread that manages the defered work items, so 
rt-drivers may have a different structure than normal drivers.

hofrat

  parent reply	other threads:[~2011-06-04 23:52 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-04 11:48 One Interrupted Threads per Interrupt line? Monica Puig-Pey
2011-06-04 12:03 ` I/O operations priority in RTOS Monica Puig-Pey
2011-06-04 12:30   ` kernel threads in drivers using the RT patch Monica Puig-Pey
2011-06-06 11:47     ` Changing Kernel thread priorities Monica Puig-Pey
2011-06-06 11:54       ` Rolando Martins
2011-06-06 11:58         ` Monica Puig-Pey
2011-06-06 16:49           ` Mark Hounschell
2011-06-07  8:40             ` Monica Puig-Pey
2011-06-07  9:14               ` Mark Hounschell
2011-06-07  9:46                 ` Mark Hounschell
2011-06-07 18:34                   ` Monica Puig-Pey
2011-06-07 18:55                     ` Mark Hounschell
2011-06-10 10:12                       ` Monica Puig-Pey
2011-06-06 18:20       ` Armin Steinhoff
2011-06-04 23:42   ` Nicholas Mc Guire [this message]
2011-06-05  8:46     ` I/O operations priority in RTOS Armin Steinhoff
2011-06-05  9:25       ` Jan Kiszka
2011-06-05 22:39         ` Armin Steinhoff
2011-06-05 23:09           ` Jan Kiszka
2011-06-05  9:28       ` Nicholas Mc Guire
2011-06-05  9:44         ` Jan Kiszka
2011-06-05 22:29           ` Nicholas Mc Guire
2011-06-05 23:00             ` Jan Kiszka
2011-06-06  0:21               ` Nicholas Mc Guire
2011-06-06 20:35                 ` Jan Kiszka
2011-06-06  7:41           ` Armin Steinhoff
2011-06-06 20:48             ` Jan Kiszka
2011-06-05 22:32         ` Armin Steinhoff

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20110604234214.GA30640@opentech.at \
    --to=der.herr@hofr.at \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=puigpeym@unican.es \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).