Re: IRQ off latency of printk is very high

[Tim Bird <tim.bird@am.sony.com>]

Mathieu Desnoyers wrote:
> It might help to read this thread I posted on LKML in January 2006
> explaining the problem, which led to some discussion about the issue.
> 
> http://lkml.org/lkml/2006/6/3/48

This is very helpful.  Jon Smirl's answer seems to give the
rationale for supporting printk output in interrupt context.
I'm not sure, however, if extending the interrupt off period
to cover the console output is required.  It didn't until
Ingo changed it in 2.6.17. Maybe this was intentional to
allow printk output to drain before another (printk in
interrupt context) could even possibly be generated, but it
seems like overkill.

I'll continue looking at this.  It helps a lot to know about
the issues discussed in the prior thread.

Thanks,
 -- Tim

=============================
Tim Bird
Architecture Group Chair, CE Linux Forum
Senior Staff Engineer, Sony Corporation of America
=============================