Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
* [Cake] Help with the AQM layer
@ 2015-10-12  7:47 Loganaden Velvindron
  2015-10-12  7:51 ` Dave Taht
  2015-10-12  8:12 ` Kevin Darbyshire-Bryant
  0 siblings, 2 replies; 6+ messages in thread
From: Loganaden Velvindron @ 2015-10-12  7:47 UTC (permalink / raw)
  To: cake

[-- Attachment #1: Type: text/plain, Size: 575 bytes --]

Hi folks,

I'm reading about this on the website:

"
The AQM layer has no configuration options. However, it is planned to add
simple tuning options for different prevailing RTTs that may be
significantly different from the Internet-scale 100ms currently assumed.
Satellite links tend to impose longer RTTs, and enclosed LANs tend to have
much shorter RTTs.
"

In Mauritius, and other african countries, we have RTT of around 300-400
ms. Could someone please point me to where I should look for adding a
tunable for this in the source files ?


Kind regards,
//Logan
C-x-C-c

[-- Attachment #2: Type: text/html, Size: 852 bytes --]

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [Cake] Help with the AQM layer
  2015-10-12  7:47 [Cake] Help with the AQM layer Loganaden Velvindron
@ 2015-10-12  7:51 ` Dave Taht
  2015-10-12  8:12 ` Kevin Darbyshire-Bryant
  1 sibling, 0 replies; 6+ messages in thread
From: Dave Taht @ 2015-10-12  7:51 UTC (permalink / raw)
  To: Loganaden Velvindron; +Cc: cake

I passed a partial patch around yestereday that almost but not quite
added support for the rtt parameter.

On Mon, Oct 12, 2015 at 9:47 AM, Loganaden Velvindron
<loganaden@gmail.com> wrote:
> Hi folks,
>
> I'm reading about this on the website:
>
> "
> The AQM layer has no configuration options. However, it is planned to add
> simple tuning options for different prevailing RTTs that may be
> significantly different from the Internet-scale 100ms currently assumed.
> Satellite links tend to impose longer RTTs, and enclosed LANs tend to have
> much shorter RTTs.
> "
>
> In Mauritius, and other african countries, we have RTT of around 300-400 ms.
> Could someone please point me to where I should look for adding a tunable
> for this in the source files ?
>
>
> Kind regards,
> //Logan
> C-x-C-c
>
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake
>



-- 
Dave Täht
Do you want faster, better, wifi? https://www.patreon.com/dtaht

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [Cake] Help with the AQM layer
  2015-10-12  7:47 [Cake] Help with the AQM layer Loganaden Velvindron
  2015-10-12  7:51 ` Dave Taht
@ 2015-10-12  8:12 ` Kevin Darbyshire-Bryant
  2015-10-12  8:17   ` Dave Taht
  1 sibling, 1 reply; 6+ messages in thread
From: Kevin Darbyshire-Bryant @ 2015-10-12  8:12 UTC (permalink / raw)
  To: cake

[-- Attachment #1: Type: text/plain, Size: 1811 bytes --]

Hi Logan,

On 08/10/15  I pushed an 'exposeinterval' feature branch to both mine &
dave's sch_cake & tc-adv repos (so module & user side changes) which
exposed the interval (rtt) parameter.  By the following morning it even
worked!  On Morning of 11th Dave sent an email "adding 'rtt' support
correctly" to which I rather assumed my 'exposeinterval' branch was
superfluous, incorrect and unneeded so I removed them from Dave's repos
in the expectation of great things.

You'll still find my original versions of that branch
https://github.com/kdarbyshirebryant/sch_cake/tree/exposeinterval &
https://github.com/kdarbyshirebryant/tc-adv/tree/exposeinterval

A glance over Dave's patch suggests the only difference to the
'rtt/interval' side of things between his & mine is using nanoseconds in
the pass from user-space to kernel space rather than my use of milliseconds.

If you provide tc with a 'rtt 300ms' parameter it should work a treat.

Kevin


On 12/10/15 08:47, Loganaden Velvindron wrote:
> Hi folks,
>
> I'm reading about this on the website:
>
> "
> The AQM layer has no configuration options. However, it is planned to
> add simple tuning options for different prevailing RTTs that may be
> significantly different from the Internet-scale 100ms currently
> assumed. Satellite links tend to impose longer RTTs, and enclosed LANs
> tend to have much shorter RTTs.
> "
>
> In Mauritius, and other african countries, we have RTT of around
> 300-400 ms. Could someone please point me to where I should look for
> adding a tunable for this in the source files ?
>
>
> Kind regards,
> //Logan
> C-x-C-c
>
>
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake



[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4816 bytes --]

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [Cake] Help with the AQM layer
  2015-10-12  8:12 ` Kevin Darbyshire-Bryant
@ 2015-10-12  8:17   ` Dave Taht
  2015-10-12  8:18     ` Dave Taht
  0 siblings, 1 reply; 6+ messages in thread
From: Dave Taht @ 2015-10-12  8:17 UTC (permalink / raw)
  To: Kevin Darbyshire-Bryant; +Cc: cake

no, I missed your branch and announcement entirely.

On Mon, Oct 12, 2015 at 10:12 AM, Kevin Darbyshire-Bryant
<kevin@darbyshire-bryant.me.uk> wrote:
> Hi Logan,
>
> On 08/10/15  I pushed an 'exposeinterval' feature branch to both mine &
> dave's sch_cake & tc-adv repos (so module & user side changes) which
> exposed the interval (rtt) parameter.  By the following morning it even
> worked!  On Morning of 11th Dave sent an email "adding 'rtt' support
> correctly" to which I rather assumed my 'exposeinterval' branch was
> superfluous, incorrect and unneeded so I removed them from Dave's repos
> in the expectation of great things.
>
> You'll still find my original versions of that branch
> https://github.com/kdarbyshirebryant/sch_cake/tree/exposeinterval &
> https://github.com/kdarbyshirebryant/tc-adv/tree/exposeinterval
>
> A glance over Dave's patch suggests the only difference to the
> 'rtt/interval' side of things between his & mine is using nanoseconds in
> the pass from user-space to kernel space rather than my use of milliseconds.
>
> If you provide tc with a 'rtt 300ms' parameter it should work a treat.
>
> Kevin
>
>
> On 12/10/15 08:47, Loganaden Velvindron wrote:
>> Hi folks,
>>
>> I'm reading about this on the website:
>>
>> "
>> The AQM layer has no configuration options. However, it is planned to
>> add simple tuning options for different prevailing RTTs that may be
>> significantly different from the Internet-scale 100ms currently
>> assumed. Satellite links tend to impose longer RTTs, and enclosed LANs
>> tend to have much shorter RTTs.
>> "
>>
>> In Mauritius, and other african countries, we have RTT of around
>> 300-400 ms. Could someone please point me to where I should look for
>> adding a tunable for this in the source files ?
>>
>>
>> Kind regards,
>> //Logan
>> C-x-C-c
>>
>>
>> _______________________________________________
>> Cake mailing list
>> Cake@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/cake
>
>
>
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake
>



-- 
Dave Täht
Do you want faster, better, wifi? https://www.patreon.com/dtaht

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [Cake] Help with the AQM layer
  2015-10-12  8:17   ` Dave Taht
@ 2015-10-12  8:18     ` Dave Taht
  2015-10-12  8:46       ` Kevin Darbyshire-Bryant
  0 siblings, 1 reply; 6+ messages in thread
From: Dave Taht @ 2015-10-12  8:18 UTC (permalink / raw)
  To: Kevin Darbyshire-Bryant; +Cc: cake

so, awesome, merge it.

On Mon, Oct 12, 2015 at 10:17 AM, Dave Taht <dave.taht@gmail.com> wrote:
> no, I missed your branch and announcement entirely.
>
> On Mon, Oct 12, 2015 at 10:12 AM, Kevin Darbyshire-Bryant
> <kevin@darbyshire-bryant.me.uk> wrote:
>> Hi Logan,
>>
>> On 08/10/15  I pushed an 'exposeinterval' feature branch to both mine &
>> dave's sch_cake & tc-adv repos (so module & user side changes) which
>> exposed the interval (rtt) parameter.  By the following morning it even
>> worked!  On Morning of 11th Dave sent an email "adding 'rtt' support
>> correctly" to which I rather assumed my 'exposeinterval' branch was
>> superfluous, incorrect and unneeded so I removed them from Dave's repos
>> in the expectation of great things.
>>
>> You'll still find my original versions of that branch
>> https://github.com/kdarbyshirebryant/sch_cake/tree/exposeinterval &
>> https://github.com/kdarbyshirebryant/tc-adv/tree/exposeinterval
>>
>> A glance over Dave's patch suggests the only difference to the
>> 'rtt/interval' side of things between his & mine is using nanoseconds in
>> the pass from user-space to kernel space rather than my use of milliseconds.
>>
>> If you provide tc with a 'rtt 300ms' parameter it should work a treat.
>>
>> Kevin
>>
>>
>> On 12/10/15 08:47, Loganaden Velvindron wrote:
>>> Hi folks,
>>>
>>> I'm reading about this on the website:
>>>
>>> "
>>> The AQM layer has no configuration options. However, it is planned to
>>> add simple tuning options for different prevailing RTTs that may be
>>> significantly different from the Internet-scale 100ms currently
>>> assumed. Satellite links tend to impose longer RTTs, and enclosed LANs
>>> tend to have much shorter RTTs.
>>> "
>>>
>>> In Mauritius, and other african countries, we have RTT of around
>>> 300-400 ms. Could someone please point me to where I should look for
>>> adding a tunable for this in the source files ?
>>>
>>>
>>> Kind regards,
>>> //Logan
>>> C-x-C-c
>>>
>>>
>>> _______________________________________________
>>> Cake mailing list
>>> Cake@lists.bufferbloat.net
>>> https://lists.bufferbloat.net/listinfo/cake
>>
>>
>>
>> _______________________________________________
>> Cake mailing list
>> Cake@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/cake
>>
>
>
>
> --
> Dave Täht
> Do you want faster, better, wifi? https://www.patreon.com/dtaht



-- 
Dave Täht
Do you want faster, better, wifi? https://www.patreon.com/dtaht

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [Cake] Help with the AQM layer
  2015-10-12  8:18     ` Dave Taht
@ 2015-10-12  8:46       ` Kevin Darbyshire-Bryant
  0 siblings, 0 replies; 6+ messages in thread
From: Kevin Darbyshire-Bryant @ 2015-10-12  8:46 UTC (permalink / raw)
  To: Dave Taht; +Cc: cake

[-- Attachment #1: Type: text/plain, Size: 2701 bytes --]

They are now merged :-)

The TC code *really* needs looking at, it works but I really was never
any good at user interfaces!

Kevin

On 12/10/15 09:18, Dave Taht wrote:
> so, awesome, merge it.
>
> On Mon, Oct 12, 2015 at 10:17 AM, Dave Taht <dave.taht@gmail.com> wrote:
>> no, I missed your branch and announcement entirely.
>>
>> On Mon, Oct 12, 2015 at 10:12 AM, Kevin Darbyshire-Bryant
>> <kevin@darbyshire-bryant.me.uk> wrote:
>>> Hi Logan,
>>>
>>> On 08/10/15  I pushed an 'exposeinterval' feature branch to both mine &
>>> dave's sch_cake & tc-adv repos (so module & user side changes) which
>>> exposed the interval (rtt) parameter.  By the following morning it even
>>> worked!  On Morning of 11th Dave sent an email "adding 'rtt' support
>>> correctly" to which I rather assumed my 'exposeinterval' branch was
>>> superfluous, incorrect and unneeded so I removed them from Dave's repos
>>> in the expectation of great things.
>>>
>>> You'll still find my original versions of that branch
>>> https://github.com/kdarbyshirebryant/sch_cake/tree/exposeinterval &
>>> https://github.com/kdarbyshirebryant/tc-adv/tree/exposeinterval
>>>
>>> A glance over Dave's patch suggests the only difference to the
>>> 'rtt/interval' side of things between his & mine is using nanoseconds in
>>> the pass from user-space to kernel space rather than my use of milliseconds.
>>>
>>> If you provide tc with a 'rtt 300ms' parameter it should work a treat.
>>>
>>> Kevin
>>>
>>>
>>> On 12/10/15 08:47, Loganaden Velvindron wrote:
>>>> Hi folks,
>>>>
>>>> I'm reading about this on the website:
>>>>
>>>> "
>>>> The AQM layer has no configuration options. However, it is planned to
>>>> add simple tuning options for different prevailing RTTs that may be
>>>> significantly different from the Internet-scale 100ms currently
>>>> assumed. Satellite links tend to impose longer RTTs, and enclosed LANs
>>>> tend to have much shorter RTTs.
>>>> "
>>>>
>>>> In Mauritius, and other african countries, we have RTT of around
>>>> 300-400 ms. Could someone please point me to where I should look for
>>>> adding a tunable for this in the source files ?
>>>>
>>>>
>>>> Kind regards,
>>>> //Logan
>>>> C-x-C-c
>>>>
>>>>
>>>> _______________________________________________
>>>> Cake mailing list
>>>> Cake@lists.bufferbloat.net
>>>> https://lists.bufferbloat.net/listinfo/cake
>>>
>>>
>>> _______________________________________________
>>> Cake mailing list
>>> Cake@lists.bufferbloat.net
>>> https://lists.bufferbloat.net/listinfo/cake
>>>
>>
>>
>> --
>> Dave Täht
>> Do you want faster, better, wifi? https://www.patreon.com/dtaht
>
>



[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4816 bytes --]

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2015-10-12  8:46 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-10-12  7:47 [Cake] Help with the AQM layer Loganaden Velvindron
2015-10-12  7:51 ` Dave Taht
2015-10-12  8:12 ` Kevin Darbyshire-Bryant
2015-10-12  8:17   ` Dave Taht
2015-10-12  8:18     ` Dave Taht
2015-10-12  8:46       ` Kevin Darbyshire-Bryant

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox