I am always interested in flent.org tcp_nup, tcp_ndown, and rrul_be tests on wifi hardware. In AP mode, especially, against a few clients in rtt_fair on the "ending the anomaly" test suite at the bottom of this link: https://www.cs.kau.se/tohojo/airtime-fairness/ . Of these, it's trying to optimize bandwidth more fairly and keep latencies low when 4 or more stations are trying to transmit (in a world with 16 or more stations online), that increasingly bothers me the most. I'm seeing 5+ seconds on some rtt_fair-like tests nowadays. I was also seeing huge simultaneous upload vs download disparities on the latest kernels, on various threads over here: https://forum.openwrt.org/t/aql-and-the-ath10k-is-lovely/59002 and more recently here: https://forum.openwrt.org/t/reducing-multiplexing-latencies-still-further-in-wifi/133605 I don't understand why napi with the default budget (64) is even needed on the ath10k, as a single txop takes a minimum of ~200us, but perhaps your patch will help. Still, measuring the TCP statistics in-band would be nice to see. Some new tools are appearing that can do this, Apple's goresponsiveness, crusader... that are simpler to use than flent. On Tue, Dec 20, 2022 at 12:17 AM Abhishek Kumar <kuabhs@xxxxxxxxxxxx> wrote: > > NAPI poll can be done in threaded context along with soft irq > context. Threaded context can be scheduled efficiently, thus > creating less of bottleneck during Rx processing. This patch is > to enable threaded NAPI on ath10k driver. > > Based on testing, it was observed that on WCN3990, the CPU0 reaches > 100% utilization when napi runs in softirq context. At the same > time the other CPUs are at low consumption percentage. This > does not allow device to reach its maximum throughput potential. > After enabling threaded napi, CPU load is balanced across all CPUs > and following improvments were observed: > - UDP_RX increase by ~22-25% > - TCP_RX increase by ~15% > > Tested-on: WCN3990 hw1.0 SNOC WLAN.HL.3.2.2-00696-QCAHLSWMTPL-1 > Signed-off-by: Abhishek Kumar <kuabhs@xxxxxxxxxxxx> > --- > > drivers/net/wireless/ath/ath10k/core.c | 16 ++++++++++++++++ > drivers/net/wireless/ath/ath10k/hw.h | 2 ++ > drivers/net/wireless/ath/ath10k/snoc.c | 3 +++ > 3 files changed, 21 insertions(+) > > diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c > index 5eb131ab916fd..ee4b6ba508c81 100644 > --- a/drivers/net/wireless/ath/ath10k/core.c > +++ b/drivers/net/wireless/ath/ath10k/core.c > @@ -100,6 +100,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA988X_HW_2_0_VERSION, > @@ -140,6 +141,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9887_HW_1_0_VERSION, > @@ -181,6 +183,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA6174_HW_3_2_VERSION, > @@ -217,6 +220,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA6174_HW_2_1_VERSION, > @@ -257,6 +261,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA6174_HW_2_1_VERSION, > @@ -297,6 +302,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA6174_HW_3_0_VERSION, > @@ -337,6 +343,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA6174_HW_3_2_VERSION, > @@ -381,6 +388,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA99X0_HW_2_0_DEV_VERSION, > @@ -427,6 +435,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9984_HW_1_0_DEV_VERSION, > @@ -480,6 +489,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9888_HW_2_0_DEV_VERSION, > @@ -530,6 +540,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9377_HW_1_0_DEV_VERSION, > @@ -570,6 +581,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9377_HW_1_1_DEV_VERSION, > @@ -612,6 +624,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA9377_HW_1_1_DEV_VERSION, > @@ -645,6 +658,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = QCA4019_HW_1_0_DEV_VERSION, > @@ -692,6 +706,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = false, > .use_fw_tx_credits = true, > .delay_unmap_buffer = false, > + .enable_threaded_napi = false, > }, > { > .id = WCN3990_HW_1_0_DEV_VERSION, > @@ -725,6 +740,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { > .hw_restart_disconnect = true, > .use_fw_tx_credits = false, > .delay_unmap_buffer = true, > + .enable_threaded_napi = true, > }, > }; > > diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h > index 9643031a4427a..adf3076b96503 100644 > --- a/drivers/net/wireless/ath/ath10k/hw.h > +++ b/drivers/net/wireless/ath/ath10k/hw.h > @@ -639,6 +639,8 @@ struct ath10k_hw_params { > bool use_fw_tx_credits; > > bool delay_unmap_buffer; > + > + bool enable_threaded_napi; > }; > > struct htt_resp; > diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c > index cfcb759a87dea..b94150fb6ef06 100644 > --- a/drivers/net/wireless/ath/ath10k/snoc.c > +++ b/drivers/net/wireless/ath/ath10k/snoc.c > @@ -927,6 +927,9 @@ static int ath10k_snoc_hif_start(struct ath10k *ar) > > bitmap_clear(ar_snoc->pending_ce_irqs, 0, CE_COUNT_MAX); > > + if (ar->hw_params.enable_threaded_napi) > + dev_set_threaded(&ar->napi_dev, true); > + > ath10k_core_napi_enable(ar); > ath10k_snoc_irq_enable(ar); > ath10k_snoc_rx_post(ar); > -- > 2.39.0.314.g84b9a713c41-goog > -- This song goes out to all the folk that thought Stadia would work: https://www.linkedin.com/posts/dtaht_the-mushroom-song-activity-6981366665607352320-FXtz Dave Täht CEO, TekLibre, LLC
