Re: [Patch] sched: new sched domain for representing multi-core

[Siddha, Suresh B]

On Tue, Jan 31, 2006 at 05:12:16PM -0800, Andrew Morton wrote:
> It's still not clear what's supposed to be happening here.
> 
> In build_sched_domains() we still have code which does:
> 
> 
> 	for_each_cpu_mask(...) {
> 		...
> #ifdef CONFIG_SCHED_MC
> 		...
> #endif
> #ifdef CONFIG_SCHED_SMT
> 		...
> #endif
> 		...
> 	}
> 	...
> #ifdef CONFIG_SCHED_SMT
> 	...
> #endif
> 	...
> #ifdef CONFIG_SCHED_MC
> 	...
> #endif
> 
> So in the first case the SCHED_SMT code will win and in the second case the
> SCHED_MC code will win.  I think.  

I am not sure what you mean here. At all the above pointed places, both 
MC and SMT will win if both are configured.

>  The code is so repetitive in there that
> `patch' may have put the hunks in the wrong place.

I will check your -mm tree.

> 
> What is the design intention here?  What do we _want_ to happen if both MC
> and SMT are enabled?

If both MC and SMT are enabled(and available on the system), then there will 
be two domain levels one for MC and another one for SMT.

> Also the path tests CONFIG_SCHED_MT in a few places where it meant to use
> CONFIG_SCHED_SMT, which rather casts doubt upon the testing quality.

:( Got introduced in my last version of the patch. Thanks for fixing it.

suresh
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/