Re: [PATCH] sched: fix constructing the span cpu mask of sched domain

[Andreas Herrmann]

On Sun, May 15, 2011 at 01:50:42AM -0400, Hillf Danton wrote:
> On Wed, May 11, 2011 at 9:54 PM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> > On Wed, 2011-05-11 at 21:26 +0800, Hillf Danton wrote:
> >> Your work for rewriting NUMA support, published at
> >>          http://marc.info/?l=linux-kernel&m=130218515520540
> >> is patched by changing how level is computed and by changing how it is
> >> used to build the mask.
> >>
> >> When computing, some valid levels are lost in your work.
> >>
> >> When building mask, nodes are selected only if they have same distance,
> >> thus nodes of less distance are also masked out since the computation of
> >> level now is tough.
> >>
> >> Without MUNA hardware, I did not test the patch:(
> >
> > I do have a (tiny) NUMA box (2 nodes) but that actually booted with the
> > old code too, Andreas Hermann from AMD (CC'ed) is usually willing to
> > test such patches on somewhat larger systems. Please send a full patch
> > against tip/master for him to apply.
> >
> 
> Hi Peter
> 
> With the guiding from Ingo on git fetch the tip/master, the work is
> now finished:)
> 
> Hopely it is not too late for Andreas.
> 
> In the following, the concern is also added for distances not covered by level,
> please review again.

Sorry, can't test your stuff. What git-tree and branch did you use to
build this patch?

Your patch seems to be corrupted/broken:

  # scripts/checkpatch.pl your_patch.diff 
  ERROR: patch seems to be corrupt (line wrapped?)
  #175: FILE: kernel/sched.c:6822:
  *(*sched_domain_mask_f)(int cpu);
  
  WARNING: line over 80 characters
  #222: FILE: kernel/sched.c:7088:
  +     return per_cpu_ptr(sched_domains_numa_masks[sched_domains_curr_level], cpu);
  
  WARNING: printk() should include KERN_ facility level
  #239: FILE: kernel/sched.c:7105:
  +     	    printk("distance(0,%d): %d\n", j, distance);
  
  ERROR: need consistent spacing around '-' (ctx:WxV)
  #253: FILE: kernel/sched.c:7119:
  +     	    for (k = level -1; k >= i; k--)
 	    	               ^
  ...

(I assume that it wasn't corrupted on my end.)


Andreas


--
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/