* What now when we're [almost] out of ADVERTISED bits?
@ 2015-11-29 13:53 Yuval Mintz
2015-11-29 21:39 ` Or Gerlitz
0 siblings, 1 reply; 6+ messages in thread
From: Yuval Mintz @ 2015-11-29 13:53 UTC (permalink / raw)
To: ben, netdev
[I suspect there was probably some discussion over this,
but I couldn't find it; References would be welcome]
So it appears we're almost out of bits for new advertised speeds;
I'm currently looking at adding 100g.
Assuming we want [and we do want] to have those in the `supported',
`advertising' and `lp_advertising' fields, the 2 reserve fields in
ethtool_cmd would not be sufficient [unless we break them into 4 u16].
Or are we planning something more generic than this for future bits?
Following with a slightly [but related] topic, what's our policy for
non-finalized standards? Specifically, for 25Gb and 50Gb?
Thanks,
Yuval
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: What now when we're [almost] out of ADVERTISED bits?
2015-11-29 13:53 What now when we're [almost] out of ADVERTISED bits? Yuval Mintz
@ 2015-11-29 21:39 ` Or Gerlitz
2015-11-30 0:40 ` Ben Hutchings
0 siblings, 1 reply; 6+ messages in thread
From: Or Gerlitz @ 2015-11-29 21:39 UTC (permalink / raw)
To: Yuval Mintz; +Cc: ben, netdev, David Decotigny
On Sun, Nov 29, 2015 at 3:53 PM, Yuval Mintz <Yuval.Mintz@qlogic.com> wrote:
> [I suspect there was probably some discussion over this,
> but I couldn't find it; References would be welcome]
there was a work by David Decotigny that should have solved the out of
bits problem here [1]. Maybe it should be revived.
[1] https://lkml.org/lkml/2015/1/26/882
> So it appears we're almost out of bits for new advertised speeds;
> I'm currently looking at adding 100g.
>
> Assuming we want [and we do want] to have those in the `supported',
> `advertising' and `lp_advertising' fields, the 2 reserve fields in
> ethtool_cmd would not be sufficient [unless we break them into 4 u16].
> Or are we planning something more generic than this for future bits?
Or.
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: What now when we're [almost] out of ADVERTISED bits?
2015-11-29 21:39 ` Or Gerlitz
@ 2015-11-30 0:40 ` Ben Hutchings
2015-11-30 2:53 ` David Miller
0 siblings, 1 reply; 6+ messages in thread
From: Ben Hutchings @ 2015-11-30 0:40 UTC (permalink / raw)
To: Or Gerlitz, Yuval Mintz; +Cc: netdev, David Decotigny
[-- Attachment #1: Type: text/plain, Size: 980 bytes --]
On Sun, 2015-11-29 at 23:39 +0200, Or Gerlitz wrote:
> On Sun, Nov 29, 2015 at 3:53 PM, Yuval Mintz <Yuval.Mintz@qlogic.com> wrote:
> > [I suspect there was probably some discussion over this,
> > but I couldn't find it; References would be welcome]
>
> there was a work by David Decotigny that should have solved the out of
> bits problem here [1]. Maybe it should be revived.
>
> [1] https://lkml.org/lkml/2015/1/26/882
Yes, it should.
Ben.
> > So it appears we're almost out of bits for new advertised speeds;
> > I'm currently looking at adding 100g.
> >
> > Assuming we want [and we do want] to have those in the `supported',
> > `advertising' and `lp_advertising' fields, the 2 reserve fields in
> > ethtool_cmd would not be sufficient [unless we break them into 4 u16].
> > Or are we planning something more generic than this for future bits?
>
> Or.
--
Ben Hutchings
Who are all these weirdos? - David Bowie, reading IRC for the first time
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 811 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: What now when we're [almost] out of ADVERTISED bits?
2015-11-30 0:40 ` Ben Hutchings
@ 2015-11-30 2:53 ` David Miller
2015-11-30 6:11 ` Yuval Mintz
0 siblings, 1 reply; 6+ messages in thread
From: David Miller @ 2015-11-30 2:53 UTC (permalink / raw)
To: ben; +Cc: gerlitz.or, Yuval.Mintz, netdev, ddecotig
From: Ben Hutchings <ben@decadent.org.uk>
Date: Mon, 30 Nov 2015 00:40:54 +0000
> On Sun, 2015-11-29 at 23:39 +0200, Or Gerlitz wrote:
>> On Sun, Nov 29, 2015 at 3:53 PM, Yuval Mintz <Yuval.Mintz@qlogic.com> wrote:
>> > [I suspect there was probably some discussion over this,
>> > but I couldn't find it; References would be welcome]
>>
>> there was a work by David Decotigny that should have solved the out of
>> bits problem here [1]. Maybe it should be revived.
>>
>> [1] https://lkml.org/lkml/2015/1/26/882
>
> Yes, it should.
A repost would strongly facilitate that.
Just if anyone ever thinks something is being ignored, just don't
even use your brain, simply repost it again.
^ permalink raw reply [flat|nested] 6+ messages in thread
* RE: What now when we're [almost] out of ADVERTISED bits?
2015-11-30 2:53 ` David Miller
@ 2015-11-30 6:11 ` Yuval Mintz
2015-11-30 17:26 ` David Decotigny
0 siblings, 1 reply; 6+ messages in thread
From: Yuval Mintz @ 2015-11-30 6:11 UTC (permalink / raw)
To: ddecotig; +Cc: gerlitz.or, netdev, David Miller, ben
>>> there was a work by David Decotigny that should have solved the out
>>> of bits problem here [1]. Maybe it should be revived.
>>>
>>> [1] https://lkml.org/lkml/2015/1/26/882
>>
>> Yes, it should.
>
> A repost would strongly facilitate that.
>
> Just if anyone ever thinks something is being ignored, just don't even use your
> brain, simply repost it again.
David, are you going to re-post? Or do you want me to take over this one?
Thanks,
Yuval
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: What now when we're [almost] out of ADVERTISED bits?
2015-11-30 6:11 ` Yuval Mintz
@ 2015-11-30 17:26 ` David Decotigny
0 siblings, 0 replies; 6+ messages in thread
From: David Decotigny @ 2015-11-30 17:26 UTC (permalink / raw)
To: Yuval Mintz; +Cc: gerlitz.or, netdev, David Miller, ben
yes, I will update+repost.
On Sun, Nov 29, 2015 at 10:11 PM, Yuval Mintz <Yuval.Mintz@qlogic.com> wrote:
>>>> there was a work by David Decotigny that should have solved the out
>>>> of bits problem here [1]. Maybe it should be revived.
>>>>
>>>> [1] https://lkml.org/lkml/2015/1/26/882
>>>
>>> Yes, it should.
>>
>> A repost would strongly facilitate that.
>>
>> Just if anyone ever thinks something is being ignored, just don't even use your
>> brain, simply repost it again.
>
> David, are you going to re-post? Or do you want me to take over this one?
>
> Thanks,
> Yuval
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2015-11-30 17:26 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-11-29 13:53 What now when we're [almost] out of ADVERTISED bits? Yuval Mintz
2015-11-29 21:39 ` Or Gerlitz
2015-11-30 0:40 ` Ben Hutchings
2015-11-30 2:53 ` David Miller
2015-11-30 6:11 ` Yuval Mintz
2015-11-30 17:26 ` David Decotigny
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.