Reto Schneider [off-list ref] writes:
On 8/4/21 17:13, chris.chiu@canonical.com wrote:
quoted
The TX A-MPDU aggregation is not handled in the driver since the
ieee80211_start_tx_ba_session has never been started properly.
Start and stop the TX BA session by tracking the TX aggregation
status of each TID. Fix the ampdu_action and the tx descriptor
accordingly with the given TID.
I'd like to test this but I am not sure what to look for (before and
after applying the patch).
Thanks, testing feedback is always very much appreciated.
What should I look for when looking at the (sniffed) Wireshark traces?
From my (maintainer) point of view most important is that there are no
regressions visible to users, for example no data stalls, crashes or
anything like that.
--
https://patchwork.kernel.org/project/linux-wireless/list/
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
On Fri, Aug 6, 2021 at 8:32 PM Kalle Valo [off-list ref] wrote:
Reto Schneider [off-list ref] writes:
quoted
On 8/4/21 17:13, chris.chiu@canonical.com wrote:
quoted
The TX A-MPDU aggregation is not handled in the driver since the
ieee80211_start_tx_ba_session has never been started properly.
Start and stop the TX BA session by tracking the TX aggregation
status of each TID. Fix the ampdu_action and the tx descriptor
accordingly with the given TID.
I'd like to test this but I am not sure what to look for (before and
after applying the patch).
Thanks, testing feedback is always very much appreciated.
quoted
What should I look for when looking at the (sniffed) Wireshark traces?
If you are able to verify the difference by the air capture, please
refer to https://imgur.com/a/jcFQTc8. You should see more than 1
packet aggregated and sent from your wifi adapter's mac address, and
get the block ack response from the Access Point (also shown in the
image). If TX aggregation is not enabled, you will only see 1 tx
packet from your wifi, and get an ack right after from the AP.
Please also help test if there's any possible regression. Thanks so much.
Chris
From my (maintainer) point of view most important is that there are no
regressions visible to users, for example no data stalls, crashes or
anything like that.
--
https://patchwork.kernel.org/project/linux-wireless/list/
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches