On Wed, May 7, 2014 at 4:14 AM, Ingo Molnar wrote:
>
> * Andy Lutomirski wrote:
>
>> > Whatever. I got enough profile data to say that it seems to have
>> > cut 'iret' overhead by at least two thirds. So it may not *work*,
>> > but from a "hey look, some random numbers" standpoint it is worth
>>
* Andy Lutomirski wrote:
> > Whatever. I got enough profile data to say that it seems to have
> > cut 'iret' overhead by at least two thirds. So it may not *work*,
> > but from a "hey look, some random numbers" standpoint it is worth
> > playing with.
>
> :)
>
> Is there actual interest in
Steven Rostedt writes:
> On Tue, 6 May 2014 14:48:50 -0700
> Linus Torvalds wrote:
>
>> Yeah, it's disgusting. I think it is worth fixing to get better
>> numbers (it *would* be very interesting to hear whether this plus the
>> kernel 'retq' thing actually makes real device interrupt overhead
>>
On Tue, 6 May 2014 14:48:50 -0700
Linus Torvalds wrote:
> Yeah, it's disgusting. I think it is worth fixing to get better
> numbers (it *would* be very interesting to hear whether this plus the
> kernel 'retq' thing actually makes real device interrupt overhead
> lower), but I'd be very wary of
On Tue, May 6, 2014 at 2:34 PM, Andy Lutomirski wrote:
>
> I don't think that's enough to fix this -- interrupts may not have
> been on in the first place, I think. I wonder if __put_user_inatomic
> would work here.
That might be the way to go, yes.
And in addition to the CS value you should pr
On Tue, May 6, 2014 at 2:25 PM, Linus Torvalds
wrote:
>
> Whatever. I got enough profile data to say that it seems to have cut
> 'iret' overhead by at least two thirds. So it may not *work*, but from
> a "hey look, some random numbers" standpoint it is worth playing with.
Just to clarify: that's
On Tue, May 6, 2014 at 2:25 PM, Linus Torvalds
wrote:
> On Tue, May 6, 2014 at 2:00 PM, Linus Torvalds
> wrote:
>>
>> I'll do profiles and test the kernel compile too, but the raw timings
>> are certainly promising. The "sysret" hack is pretty disgusting, and
>> it's broken too. sysret doesn't do
On Tue, May 6, 2014 at 2:00 PM, Linus Torvalds
wrote:
>
> I'll do profiles and test the kernel compile too, but the raw timings
> are certainly promising. The "sysret" hack is pretty disgusting, and
> it's broken too. sysret doesn't do some things iret does (like TF flag
> etc), so it's not comple
On Tue, May 6, 2014 at 1:35 PM, Linus Torvalds
wrote:
>
> Heh. That is pretty disgusting. But I guess it could be interesting
> for timing. BRB.
Ooh. That's friggin impressive.
Guys, see if you can recreate these numbers. This is my totally
disgusting test-case, which really is just stress-testi
On Tue, May 6, 2014 at 1:29 PM, Andy Lutomirski wrote:
>
> The only reason it's Signed-off-by is that I agree to the DCO.
> That should not be construed to mean that anyone should apply
> this patch. It's an abomination and it will do terrible,
> terrible things.
Heh. That is pretty disgusting.
This could be even faster if it were written in assembler :)
The only reason it's Signed-off-by is that I agree to the DCO.
That should not be construed to mean that anyone should apply
this patch. It's an abomination and it will do terrible,
terrible things.
It boots, though :) I haven't teste
11 matches
Mail list logo