Re: [PATCH RFC] mm readahead: Fix the readahead fail in case of emptynuma node

[Raghavendra K T]

On 12/04/2013 02:11 PM, Andrew Morton wrote:
> On Wed, 04 Dec 2013 14:00:09 +0530 Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx> wrote:
>
> > Unfaortunately, from my search, I saw that the code belonged to pre git
> > time, so could not get much information on that.
>
> Here: https://lkml.org/lkml/2004/8/20/242
>
> It seems it was done as a rather thoughtless performance optimisation.
> I'd say it's time to reimplement max_sane_readahead() from scratch.

Ok. Thanks for the link. I think after that,
Here it was changed to pernode:
https://lkml.org/lkml/2004/8/21/9 to avoid iteration all over.

do you think above patch (+comments) with some sanitized nr (thus
avoiding iteration over nodes in remote numa readahead case) does look
better?
or should we iterate all memory.




--
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/