<div dir="ltr">> I do keep hoping for pretty pictures. Got any? :-P<br><br>Certainly! I do have some :). Here is the link:<br><a href="https://drive.google.com/corp/drive/folders/14OIuQEHOUiIoNrVnKprj6rBYFNZ0Coif">https://drive.google.com/corp/drive/folders/14OIuQEHOUiIoNrVnKprj6rBYFNZ0Coif</a><br><br>><br>> Is there an ax QCAXXXX platform, m.2 card, or mini-pci card worth<br>> testing at this point?<br><br>It will be great if someone with <a href="http://11.ax">11.ax</a> platform can help give it a try.<br><br>> How are they handling mu-mimo?<br><br>I think it should still work. The queue length in airtime for each individual queue is unchanged, even the multiple queues are allowed to transmit concurrently with mu-mimo.<br><br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">I have a round of tests scheduled for intel's ax200 chips, soon. Not sure<br>what, if any, of this new work might apply.</blockquote><div>It will be very interesting to know how it performance on 802.11ax platforms. Supposedly 802.11ax already fixed the latency problem so the benefit of this patch should be less significant.</div></div><br><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Nov 14, 2019 at 6:07 PM Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">On Thu, Nov 14, 2019 at 6:04 PM Kan Yan <<a href="mailto:kyan@google.com" target="_blank">kyan@google.com</a>> wrote:<br>
><br>
> I have tested it with Toke's patch "[PATCH v6 4/4] mac80211: Use<br>
> Airtime-based Queue Limits (AQL) on packet dequeue", but didn't<br>
> include it here, as it is self contained and Toke has plan to update<br>
> it.<br>
><br>
> The platform (QCA9984) used in my test<br>
<br>
I do keep hoping for pretty pictures. Got any? :-P<br>
<br>
> doesn't support 802.11ax, so I<br>
> was not able to test the HE mode support added in v7 update of "Import<br>
> airtime calculation code from mt76" from Toke.<br>
<br>
Is there an ax QCAXXXX platform, m.2 card, or mini-pci card worth<br>
testing at this point?<br>
<br>
How are they handling mu-mimo?<br>
<br>
I have a round of tests scheduled for intel's ax200 chips, soon. Not sure<br>
what, if any, of this new work might apply.<br>
<br>
> On Thu, Nov 14, 2019 at 5:48 PM Kan Yan <<a href="mailto:kyan@google.com" target="_blank">kyan@google.com</a>> wrote:<br>
> ><br>
> > This patch series port the Airtime Queue Limits concept from the out-of-tree<br>
> > ath10k implementation[0] to mac80211. This version takes my patch to do the<br>
> > throttling in mac80211, and replaces the driver API with the mechanism from<br>
> > Toke's series, which instead calculated the expected airtime at dequeue time<br>
> > inside mac80211, storing it in the SKB cb field.<br>
> ><br>
> > This version has been tested on QCA9984 platform.<br>
> ><br>
> > [0] <a href="https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/1703105/7" rel="noreferrer" target="_blank">https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/1703105/7</a><br>
> ><br>
> > Changelog:<br>
> ><br>
> > v8:<br>
> > - Includes Toke's v7 version of "mac80211: Import airtime calculation code from mt76"<br>
> > - Don't clobber sta's customized queue limit when configuring the default via debugfs<br>
> > - Fix a racing condition when reset aql_tx_pending.<br>
> ><br>
> > v7:<br>
> > - Fix aql_total_pending_airtime underflow due to insufficient locking.<br>
> ><br>
> > v6:<br>
> > - Fix sta lookup in ieee80211_report_used_skb().<br>
> > - Move call to ieee80211_sta_update_pending_airtime() to a bit later in<br>
> > __ieee80211_tx_status()<br>
> > v5:<br>
> > - Add missing export of ieee80211_calc_rx_airtime() and make<br>
> > ieee80211_calc_tx_airtime_rate() static (kbuildbot).<br>
> > - Use skb_get_queue_mapping() to get the AC from the skb.<br>
> > - Take basic rate configuration for the BSS into account when calculating<br>
> > multicast rate.<br>
> > v4:<br>
> > - Fix calculation that clamps the maximum airtime to fit into 10 bits<br>
> > - Incorporate Rich Brown's nits for the commit message in Kan's patch<br>
> > - Add fewer local variables to ieee80211_tx_dequeue()<br>
> > v3:<br>
> > - Move the tx_time_est field so it's shared with ack_frame_id, and use units<br>
> > of 4us for the value stored in it.<br>
> > - Move the addition of the Ethernet header size into ieee80211_calc_expected_tx_airtime()<br>
> > v2:<br>
> > - Integrate Kan's approach to airtime throttling.<br>
> > - Hopefully fix the cb struct alignment on big-endian architectures.<br>
> ><br>
> ><br>
> ><br>
> > Kan Yan (1):<br>
> > mac80211: Implement Airtime-based Queue Limit (AQL)<br>
> ><br>
> > Toke Høiland-Jørgensen (1):<br>
> > mac80211: Import airtime calculation code from mt76<br>
> ><br>
> > include/net/cfg80211.h | 7 +<br>
> > include/net/mac80211.h | 41 +++<br>
> > net/mac80211/Makefile | 3 +-<br>
> > net/mac80211/airtime.c | 597 +++++++++++++++++++++++++++++++++++++<br>
> > net/mac80211/debugfs.c | 85 ++++++<br>
> > net/mac80211/debugfs_sta.c | 43 ++-<br>
> > net/mac80211/ieee80211_i.h | 8 +<br>
> > net/mac80211/main.c | 10 +-<br>
> > net/mac80211/sta_info.c | 38 +++<br>
> > net/mac80211/sta_info.h | 8 +<br>
> > net/mac80211/tx.c | 47 ++-<br>
> > 11 files changed, 872 insertions(+), 15 deletions(-)<br>
> > create mode 100644 net/mac80211/airtime.c<br>
> ><br>
> > --<br>
> > 2.24.0.rc1.363.gb1bccd3e3d-goog<br>
> ><br>
> _______________________________________________<br>
> Make-wifi-fast mailing list<br>
> <a href="mailto:Make-wifi-fast@lists.bufferbloat.net" target="_blank">Make-wifi-fast@lists.bufferbloat.net</a><br>
> <a href="https://lists.bufferbloat.net/listinfo/make-wifi-fast" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/make-wifi-fast</a><br>
<br>
<br>
<br>
-- <br>
<br>
Dave Täht<br>
CTO, TekLibre, LLC<br>
<a href="http://www.teklibre.com" rel="noreferrer" target="_blank">http://www.teklibre.com</a><br>
Tel: <a href="tel:(831)%20205-9740" value="+18312059740" target="_blank">1-831-205-9740</a><br>
</blockquote></div>