From: "Toke Høiland-Jørgensen" <toke@toke.dk>
To: Tim Shepard <shep@alum.mit.edu>
Cc: linux-wireless@vger.kernel.org,
make-wifi-fast@lists.bufferbloat.net,
ath9k-devel@lists.ath9k.org, Felix Fietkau <nbd@nbd.name>
Subject: Re: [Make-wifi-fast] [PATCH] ath9k: Switch to using mac80211 intermediate software queues.
Date: Sun, 19 Jun 2016 15:50:23 +0200 [thread overview]
Message-ID: <87twgpqodc.fsf@toke.dk> (raw)
In-Reply-To: <E1bEcwS-0006jR-00@www.xplot.org> (Tim Shepard's message of "Sun, 19 Jun 2016 09:39:12 -0400")
Tim Shepard <shep@alum.mit.edu> writes:
>>
>> You're right that it doesn't check the max. However, this is less of a
>> problem now that there is no intermediate queueing in the driver; and
>> indeed the utility of haven the qlen_* tunables is somewhat questionable
>> with the patch applied: The only thing this is going to control is the
>> size of the retry queue, and possible limit the size of the retry queue.
>> [....]
>
> The driver queues things up for the hardware to DMA and transmit.
> Something has to limit the amount of packets handed over to the
> hardware. (We lack access to hardware documentation (grrrr!) but it
> appears to me that the hardware has a hard limit on how many packets
> can be handed to it.)
There's a ring buffer eight entries long that the aggregates (or
packets) are put on when actually being handed to the hardware.
This is in ath_txq->txq_fifo.
>> Because there's a second limit in play (which has always been there): in
>> ath_tx_sched_aggr() there is this check:
>>
>> if ((aggr && txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) ||
>> (!aggr && txq->axq_depth >= ATH_NON_AGGR_MIN_QDEPTH)) {
>> __skb_queue_tail(&tid->retry_q, bf->bf_mpdu);
>> *stop = true;
>> return false;
>> }
>>
>> The two constants are 2 and 8 respectively. This means that, with
>> aggregation enabled, no more than two full aggregates will be queued up.
>> The size of the aggregates is dynamically computed from the current
>> rate: they are limited a maximum of four milliseconds of (estimated)
>> airtime (for the BE queue; the others have different limits).
>>
>> So in a sense there's already a dynamic limit on the hardware queues.
>> Now, whether four milliseconds is the right maximum aggregate size might
>> be worth discussing. It is the maximum allowed by the standard. Dave and
>> I have been
>
> Ah that may be the clue that I lacked. There's got to be a dependency
> on processor speed (how quickly the system and driver can get another
> packet hooked up for transmission after completions) but perhaps with
> aggregates being so large in time, with full aggregates even the
> slowest processors are fast enough to avoid starvation.
>
> If there's no aggregation, a limit of some sort is needed (probably to
> prevent malfunction of the hardware/driver, but in any case to limit
> excess latency). And this limit will depend on processor speed (and
> will need to be autotuned at runtime).
ATH_NON_AGGR_MIN_QDEPTH is 8 -- so yeah, the limit is higher if there is
no aggregation.
These are hard-coded values, so presumably they are large enough to keep
the hardware busy on most platforms (or someone would have noticed and
changed them?). So I doubt there is much to be gained to add a mechanism
to dynamically tune them (between 0 and 2?).
The exception being in case pulling from the mac80211 queue is too slow
to keep the hardware busy at the current settings. I see no problems
with this on my hardware, but that's an x86 box. I would probably hold
off on the dynamic tuning until having proven that there's actually a
bottleneck, though... ;)
-Toke
next parent reply other threads:[~2016-06-19 13:50 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <E1bEcwS-0006jR-00@www.xplot.org>
2016-06-19 13:50 ` Toke Høiland-Jørgensen [this message]
[not found] <E1bJYSp-0001M8-00@www.xplot.org>
2016-07-04 17:46 ` Toke Høiland-Jørgensen
2016-07-06 13:23 ` Felix Fietkau
2016-07-06 14:45 ` Toke Høiland-Jørgensen
[not found] <E1bETEY-0000BM-00@www.xplot.org>
2016-06-19 8:52 ` Toke Høiland-Jørgensen
[not found] <20160617090929.31606-2-toke@toke.dk>
2016-06-18 19:05 ` Toke Høiland-Jørgensen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.bufferbloat.net/postorius/lists/make-wifi-fast.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87twgpqodc.fsf@toke.dk \
--to=toke@toke.dk \
--cc=ath9k-devel@lists.ath9k.org \
--cc=linux-wireless@vger.kernel.org \
--cc=make-wifi-fast@lists.bufferbloat.net \
--cc=nbd@nbd.name \
--cc=shep@alum.mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox