Re: [PATCH] Replace timer_bh with tasklet

From: george anzinger (george@mvista.com)
Date: Fri Jun 21 2002 - 09:04:28 EST


"David S. Miller" wrote:
>
> From: george anzinger <george@mvista.com>
> Date: Thu, 20 Jun 2002 16:54:16 -0700
>
> Is the only network issue? Is it possible that the network code
> uses bh_locking to protect against timers? Moveing timers to
> softirqs would invalidate this sort of protection. Is this an
> issue?
>
> It is the whole issue. We have to stop all timers while we run the
> non-SMP safe protocol code.

Thanks. I think this can be done much the same way it is now. I will modify the patch accordingly.

At the same time, I must say that stoping the timers is, IMNSHO, NOT a good thing for the kernel. It can cause unexpected timer latencies which can impact most any task on the system. (But you already knew this :) I understand that it is not seldom used, but still...

-- 
George Anzinger   george@mvista.com
High-res-timers:  http://sourceforge.net/projects/high-res-timers/
Real time sched:  http://sourceforge.net/projects/rtsched/
Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sun Jun 23 2002 - 22:00:24 EST