Re: [PATCH v5 0/8] vDSO time changes for 2.6.40

From: Andrew Lutomirski
Date: Mon May 23 2011 - 11:28:32 EST


On Mon, May 23, 2011 at 11:23 AM, Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Mon, May 23, 2011 at 6:31 AM, Andy Lutomirski <luto@xxxxxxx> wrote:
>> [Patch 8/8 is brand-new and optional.  If anyone objects to it,
>>  please just drop it for 2.6.40 and I'll fix it for 2.6.41.]
>
> Hmm. I would just put it into 7/8 immediately, and never have the
> stupid read-lock loop in the first place.
>
> Or I would just say "the time() system call just isn't that critical,
> let's not even bother".

I have no particular preference. The only argument I can make is that
the change deletes code and it lets us tell the glibc people "not only
can you stop using a silly old interface but you can make your code
0.4ns faster."

--Andy
--
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/