On Tue, 29 Jun 2004 10:08:34 +0200,
Francois Wellenreiter <Francois.Wellenreiter@xxxxxxxxxxxx> wrote:
>My conclusion is that we should make a global review on kdb working in
>SMP mode.
>We should reconsider spin lock management, protection against IPI, CPU
>state table
>management to be able to run breakpoints correctly in SMP mode.
You are quite corect. This is a known problem with the current design
of kdb, concurrent breakpoints can deadlock. Fixing this requires a
complete redesign of the kdb entry logic and will break all
architectures. Unfortunately my past and current workload has never
left enough time to do this redesign.
---------------------------
Use http://oss.sgi.com/ecartis to modify your settings or to unsubscribe.
|