ath10k performance, master branch from 20160407

[Michal Kazior]

On 19 April 2016 at 09:31, Roman Yeryomin <leroi.lists at gmail.com> wrote:
> On 19 April 2016 at 08:28, Michal Kazior <michal.kazior at tieto.com> wrote:
>> On 18 April 2016 at 15:00, Roman Yeryomin <leroi.lists at gmail.com> wrote:
>>> So it looks like Michal's patch set "ath10k: implement push-pull tx
>>> model" introduced this regression - after restoring it from reverts
>>> fq_codel_drop is hungry again.
>>> Any ideas how to fix?
>>
>> If my hunch is right there's no easy (and proper) fix for that now.
>>
>> One of the patchset patches (ath10k: implement wake_tx_queue) starts
>> to use mac80211 software queuing. This introduces extra induced
>> latency and I'm guessing it results in fill-in-then-drain sequences in
>> some cases which end up being long enough to make fq_codel_drop more
>> work than normal.
>>
>> This is required for other changes and MU-MIMO performance
>> improvements so this patch can't be removed.
>
> But qca988x doesn't support MU-MIMO, AFAIK.

Correct.


> Can this be made chip dependent?

I guess it could but it'd arguably make the driver more complex and
harder to maintain. What we want is a long-term fix, not a short-term
one.

The long-term fix is a work-in-progress which aims at killing
bufferbloat in general [1][2]. This should, by proxy, improve
everything.

[1]: https://www.spinics.net/lists/linux-wireless/msg149776.html
[2]: https://www.spinics.net/lists/linux-wireless/msg148714.html
[3]: https://www.spinics.net/lists/linux-wireless/msg149039.html

You can try out patchset from [1] (and maybe [3] as well) to see if it
helps you (assuming you have spare time to play around).


Michał