lkml.org 
[lkml]   [2012]   [Jun]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 13/40] autonuma: CPU follow memory algorithm


On 2012年07月01日 07:55, Benjamin Herrenschmidt wrote:
> On Sat, 2012-06-30 at 14:58 +0800, Nai Xia wrote:
>> If you insist on ignoring any constructive suggestions from others,
>
> But there is nothing constructive about your criticism.
>
> You are basically saying that the whole thing cannot work unless it's
> based on 20 years of research. Duh !

1. You quote me wrong: I said "group all pages to one node" is correct,
and highly possible to play the major role in your benchmarks.
Sampling is completely broken from my point of view. PZ's patch also
has similar idea of "group all pages to one node" which I think
is also correct.

2. My suggestion to Andrea: Do some more comparative benchmarks to
see what's really happening inside, instead of only macro benchmarks.
You need to have 20 hours of carefully designed survey research
for a new algorithm, instead of reading my mail and spending 20min
to give a conclusion.

If you cannot see the constructiveness of my suggestion. That's
your problem, not mine.

I understand the hard feelings of seeing the possible brokenness of a
thing you've already spend a lot of time. But that's the way people
seeking for truth.

You see, you guys has spent quite sometime to defend your points,
if this time were used to follow my advise doing some further
analysis maybe you've already got some valuable information.

Dor was right, we all made our points. And we are all busy.
Let's stop it. Thanks.

>
> Ben.
>
>
--
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/

\
 
 \ /
  Last update: 2012-07-01 06:01    [from the cache]
©2003-2011 Jasper Spaans