From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lj1-x232.google.com (mail-lj1-x232.google.com [IPv6:2a00:1450:4864:20::232]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 0120A3B29E for ; Thu, 29 Dec 2022 00:54:28 -0500 (EST) Received: by mail-lj1-x232.google.com with SMTP id u12so14789873ljj.11 for ; Wed, 28 Dec 2022 21:54:28 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=+/KXiMBrRZyavYEEOBJk/mAOrHdopW7Ju0+mEhcLu2I=; b=hIs31zRBmKDr68RufUNSYO6J5M+lMI2yS3jZeE3N9ygz40XCkXiPkVLyEP0cnIkZrU R/6yN/tkd/B70oSSQIc8sFd10XaK8o8dGi9I3GFNM/geSWRAugPBkXpAHW/92UFwEfnM sy3aQbZouUreytlAh9CBMaV77khYI3Cyv8I9I= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=+/KXiMBrRZyavYEEOBJk/mAOrHdopW7Ju0+mEhcLu2I=; b=qqypaiC/Y6HPuiC+ZdXZXzM3HsnoA0FiOsS4qaoPwfB6Y2nZt9ISopaxPNgPbs7mgd Wc4R9tMUyV9pksAJP00bcz7nZyUFcj5ETNZepS68GF0C6eXakCVnC9dI8RTscZlHkn/2 Y5AE4uWYWAOaPxvWtnHsbYMos9JlSbaaobFNJHLNveAFa27AEg8VJjF+n0OIpwm4udgh UY1DKOTqJPW5laWu0Y0kO1LIlDCMFc45Ik8fTdSOnu3APV1XGZHblqOmHs5L2KL93UPI ugfn2rJA4RWYVMUWkmKDvQhA5ZpDmH1hr9OjG++8siZYnTxr0RGuVYfxgnslI+/Y4x7L FxiA== X-Gm-Message-State: AFqh2kp5pOlpcRzc2HepUZ5O9n0t+tG5Av1Dqq8UTSZf62z/hMJHdiiL 5BPYZJhGD9R2/hh+z1A/hKJTHzmqXwBDNvPN8KmtZRkVJC/s9PlFvAs96vtfx9lUcaJiL9n1+xe QWJK/ydz5CsgsnZPkKJ1f/dd+8DPFCG1YLbPMEdw7+Q== X-Google-Smtp-Source: AMrXdXtsuFZDdEONu7RrPd2m1imeZUv8AqTLqsucV9xq2SAW73nAkd36QPDlneRuJGl7uZdu4Mr5rQKAhDEnmHBm97k= X-Received: by 2002:a2e:9987:0:b0:26d:e38f:7e21 with SMTP id w7-20020a2e9987000000b0026de38f7e21mr1107551lji.273.1672293267130; Wed, 28 Dec 2022 21:54:27 -0800 (PST) MIME-Version: 1.0 References: <20221220075215.1.Ic12e347e0d61a618124b742614e82bbd5d770173@changeid> In-Reply-To: From: Bob McMahon Date: Wed, 28 Dec 2022 21:54:15 -0800 Message-ID: To: Dave Taht Cc: Abhishek Kumar , netdev@vger.kernel.org, kvalo@kernel.org, linux-wireless@vger.kernel.org, linux-kernel@vger.kernel.org, ath10k@lists.infradead.org, Eric Dumazet , Make-Wifi-fast , Jakub Kicinski , Paolo Abeni , "David S. Miller" Content-Type: multipart/alternative; boundary="00000000000026830a05f0f11e5e" Subject: Re: [Make-wifi-fast] [PATCH] ath10k: snoc: enable threaded napi on WCN3990 X-BeenThere: make-wifi-fast@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Dec 2022 05:54:29 -0000 --00000000000026830a05f0f11e5e Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable A bit of a tangent but iperf 2's enhanced option provides sampled RTT and CWND in the interval output. I requires -e. It also provide the connect time, the icwnd, irtt and the mss per the connect. [rjmcmahon@rjm-nas ~]$ iperf -c 192.168.1.85 -i 1 -e ------------------------------------------------------------ Client connecting to 192.168.1.85, TCP port 5001 with pid 20041 (1 flows) Write buffer size: 131072 Byte TOS set to 0x0 (Nagle on) TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.73%eno1 port 38822 connected with 192.168.1.85 port 5001 (sock=3D3) (icwnd/mss/irtt=3D14/1448/246) (ct=3D0.32 ms) on 2022-12-28 21:51:13 (PST) [ ID] Interval Transfer Bandwidth Write/Err Rtry Cwnd/RTT(var) NetPwr [ 1] 0.00-1.00 sec 114 MBytes 952 Mbits/sec 908/0 3 353K/1901(59) us 62606 [ 1] 1.00-2.00 sec 111 MBytes 932 Mbits/sec 889/0 0 354K/2029(115) us 57429 [ 1] 2.00-3.00 sec 112 MBytes 937 Mbits/sec 894/0 3 354K/2061(84) us 56855 [ 1] 3.00-4.00 sec 112 MBytes 938 Mbits/sec 895/0 3 354K/2027(115) us 57873 [ 1] 4.00-5.00 sec 112 MBytes 938 Mbits/sec 895/0 6 354K/2046(68) us 57336 [ 1] 5.00-6.00 sec 112 MBytes 937 Mbits/sec 894/0 0 374K/2160(109) us 54249 [ 1] 6.00-7.00 sec 111 MBytes 933 Mbits/sec 890/0 2 374K/2155(115) us 54132 [ 1] 7.00-8.00 sec 111 MBytes 934 Mbits/sec 891/0 2 374K/2139(120) us 54598 [ 1] 8.00-9.00 sec 112 MBytes 938 Mbits/sec 895/0 0 374K/2129(126) us 55101 [ 1] 9.00-10.00 sec 112 MBytes 935 Mbits/sec 892/0 1 374K/2200(102) us 53144 [ 1] 0.00-10.03 sec 1.09 GBytes 935 Mbits/sec 8944/0 20 374K/4082(4010) us 28632 Bob On Wed, Dec 28, 2022 at 4:49 PM Dave Taht via Make-wifi-fast < make-wifi-fast@lists.bufferbloat.net> wrote: > On Wed, Dec 28, 2022 at 3:53 PM Abhishek Kumar > wrote: > > > > Apologies for the late reply, Thanks Dave for your comment. My answer i= s > inline. > > > > On Tue, Dec 20, 2022 at 7:10 AM Dave Taht wrote: > > > > > > 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 used testing using iperf and conductive setup and fetched the > > throughput data(mentioned below). > > > > > > 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 > > Interesting, thanks for the pointer and probably the Qualcomm team is > > aware of it. > > > > > > 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 d= o > > > this, Apple's goresponsiveness, crusader... that are simpler to use > > > than flent. > > Here are some of the additional raw data with and without threaded napi= : > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D > > udp_rx(Without threaded NAPI) > > 435.98+-5.16 : Channel 44 > > 439.06+-0.66 : Channel 157 > > > > udp_rx(With threaded NAPI) > > 509.73+-41.03 : Channel 44 > > 549.97+-7.62 : Channel 157 > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D > > udp_tx(Without threaded NAPI) > > 461.31+-0.69 : Channel 44 > > 461.46+-0.78 : Channel 157 > > > > udp_tx(With threaded NAPI) > > 459.20+-0.77 : Channel 44 > > 459.78+-1.08 : Channel 157 > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D > > tcp_rx(Without threaded NAPI) > > 472.63+-2.35 : Channel 44 > > 469.29+-6.31 : Channel 157 > > > > tcp_rx(With threaded NAPI) > > 498.49+-2.44 : Channel 44 > > 541.14+-40.65 : Channel 157 > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D > > tcp_tx(Without threaded NAPI) > > 317.34+-2.37 : Channel 44 > > 317.01+-2.56 : Channel 157 > > > > tcp_tx(With threaded NAPI) > > 371.34+-2.36 : Channel 44 > > 376.95+-9.40 : Channel 157 > > My concern is primarily with the induced tcp latency on this test. A > way to check that is to run wireshark on your test client driving the > test, capture the iperf traffic, and then plot the "Statistics->TCP > stream statistics for both throughput and rtt. Would it be possible > for you to do that and put up those plots somewhere? > > The worst case test is a tcp bidirectional test which I don't know if > older iperfs can do. (iperf2 has new bounceback and bidir tests) > > Ideally stuff going in either direction, would not look as horrible, > as it did, back in 2016, documented in this linuxplumbers presentation > here: > https://blog.linuxplumbersconf.org/2016/ocw/system/presentations/3963/ori= ginal/linuxplumbers_wifi_latency-3Nov.pdf > and discussed on lwn, here: https://lwn.net/Articles/705884/ > > I worry about folk achieving slightly better tcp throughput at the > expense of clobbering in-tcp-stream latency. Back then we were > shooting for no more than 40ms extra latency under load on this chip, > down from (unusable) seconds. Presently elsewhere, on other chips, > we're getting 8ms with stuff that's not in tree for the ath10k, there > is a slight cost in single stream throughput but when multiple streams > are in use, on multiple stations, things like web pages fly, > irrespective of load. > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D > > > > > > > > On Tue, Dec 20, 2022 at 12:17 AM Abhishek Kumar > 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 > > > > --- > > > > > > > > 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[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA988X_HW_2_0_VERSION, > > > > @@ -140,6 +141,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9887_HW_1_0_VERSION, > > > > @@ -181,6 +183,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA6174_HW_3_2_VERSION, > > > > @@ -217,6 +220,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA6174_HW_2_1_VERSION, > > > > @@ -257,6 +261,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA6174_HW_2_1_VERSION, > > > > @@ -297,6 +302,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA6174_HW_3_0_VERSION, > > > > @@ -337,6 +343,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA6174_HW_3_2_VERSION, > > > > @@ -381,6 +388,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA99X0_HW_2_0_DEV_VERSION, > > > > @@ -427,6 +435,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9984_HW_1_0_DEV_VERSION, > > > > @@ -480,6 +489,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9888_HW_2_0_DEV_VERSION, > > > > @@ -530,6 +540,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9377_HW_1_0_DEV_VERSION, > > > > @@ -570,6 +581,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9377_HW_1_1_DEV_VERSION, > > > > @@ -612,6 +624,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA9377_HW_1_1_DEV_VERSION, > > > > @@ -645,6 +658,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D QCA4019_HW_1_0_DEV_VERSION, > > > > @@ -692,6 +706,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D false, > > > > .use_fw_tx_credits =3D true, > > > > .delay_unmap_buffer =3D false, > > > > + .enable_threaded_napi =3D false, > > > > }, > > > > { > > > > .id =3D WCN3990_HW_1_0_DEV_VERSION, > > > > @@ -725,6 +740,7 @@ static const struct ath10k_hw_params > ath10k_hw_params_list[] =3D { > > > > .hw_restart_disconnect =3D true, > > > > .use_fw_tx_credits =3D false, > > > > .delay_unmap_buffer =3D true, > > > > + .enable_threaded_napi =3D 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-698136666= 5607352320-FXtz > > > Dave T=C3=A4ht CEO, TekLibre, LLC > > > > -- > This song goes out to all the folk that thought Stadia would work: > > https://www.linkedin.com/posts/dtaht_the-mushroom-song-activity-698136666= 5607352320-FXtz > Dave T=C3=A4ht CEO, TekLibre, LLC > _______________________________________________ > Make-wifi-fast mailing list > Make-wifi-fast@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/make-wifi-fast --=20 This electronic communication and the information and any files transmitted= =20 with it, or attached to it, are confidential and are intended solely for=20 the use of the individual or entity to whom it is addressed and may contain= =20 information that is confidential, legally privileged, protected by privacy= =20 laws, or otherwise restricted from disclosure to anyone else. If you are=20 not the intended recipient or the person responsible for delivering the=20 e-mail to the intended recipient, you are hereby notified that any use,=20 copying, distributing, dissemination, forwarding, printing, or copying of= =20 this e-mail is strictly prohibited. If you received this e-mail in error,= =20 please return the e-mail to the sender, delete it from your computer, and= =20 destroy any printed copy of it. --00000000000026830a05f0f11e5e Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
A bit of a tangent but iperf 2's enhanced option provi= des sampled RTT and CWND in the interval output. I requires -e. It also pro= vide the connect time, the icwnd, irtt and the mss per the connect.

= [rjmcmahon@rjm-nas ~]$ iperf -c 192.168.1.85 -i 1 -e
-------------------= -----------------------------------------
Client connecting to 192.168.1= .85, TCP port 5001 with pid 20041 (1 flows)
Write buffer size: 131072 By= te
TOS set to 0x0 (Nagle on)
TCP window size: 16.0 KByte (default)------------------------------------------------------------
[ =C2=A01]= local 192.168.1.73%eno1 port 38822 connected with 192.168.1.85 port 5001 (= sock=3D3) (icwnd/mss/irtt= =3D14/1448/246) (ct=3D0.32 ms) on 2022-12-28 21:51:13 (PST)
[ ID]= Interval =C2=A0 =C2=A0 =C2=A0 =C2=A0Transfer =C2=A0 =C2=A0Bandwidth =C2=A0= =C2=A0 =C2=A0 Write/Err =C2=A0Rtry =C2=A0 =C2=A0 Cwnd/RTT(var) =C2=A0 =C2= =A0 =C2=A0 =C2=A0NetPwr
[ =C2=A01] 0.00-1.00 sec =C2=A0 114 MBytes =C2= =A0 952 Mbits/sec =C2=A0908/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 3 =C2=A0 =C2=A0 = =C2=A0353K/1901(59) = us =C2=A062606
[ =C2=A01] 1.00-2.00 sec =C2=A0 111 MBytes =C2=A0 932 Mbi= ts/sec =C2=A0889/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 0 =C2=A0 =C2=A0 =C2=A0354K/2= 029(115) us =C2=A057429
[ =C2=A01] 2.00-3.00 sec =C2=A0 112 MBytes =C2= =A0 937 Mbits/sec =C2=A0894/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 3 =C2=A0 =C2=A0 = =C2=A0354K/2061(84) us =C2=A056855
[ =C2=A01] 3.00-4.00 sec =C2=A0 112 M= Bytes =C2=A0 938 Mbits/sec =C2=A0895/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 3 =C2=A0= =C2=A0 =C2=A0354K/2027(115) us =C2=A057873
[ =C2=A01] 4.00-5.00 sec =C2= =A0 112 MBytes =C2=A0 938 Mbits/sec =C2=A0895/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= 6 =C2=A0 =C2=A0 =C2=A0354K/2046(68) us =C2=A057336
[ =C2=A01] 5.00-6.00= sec =C2=A0 112 MBytes =C2=A0 937 Mbits/sec =C2=A0894/0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 0 =C2=A0 =C2=A0 =C2=A0374K/2160(109) us =C2=A054249
[ =C2=A01= ] 6.00-7.00 sec =C2=A0 111 MBytes =C2=A0 933 Mbits/sec =C2=A0890/0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 2 =C2=A0 =C2=A0 =C2=A0374K/2155(115) us =C2=A054132[ =C2=A01] 7.00-8.00 sec =C2=A0 111 MBytes =C2=A0 934 Mbits/sec =C2=A0891/= 0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 2 =C2=A0 =C2=A0 =C2=A0374K/2139(120) us =C2= =A054598
[ =C2=A01] 8.00-9.00 sec =C2=A0 112 MBytes =C2=A0 938 Mbits/sec= =C2=A0895/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 0 =C2=A0 =C2=A0 =C2=A0374K/2129(12= 6) us =C2=A055101
[ =C2=A01] 9.00-10.00 sec =C2=A0 112 MBytes =C2=A0 935= Mbits/sec =C2=A0892/0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 1 =C2=A0 =C2=A0 =C2=A037= 4K/2200(102) us =C2=A053144
[ =C2=A01] 0.00-10.03 sec =C2=A01.09 GBytes = =C2=A0 935 Mbits/sec =C2=A08944/0 =C2=A0 =C2=A0 =C2=A0 =C2=A020 =C2=A0 =C2= =A0 =C2=A0374K/4082(4010) us =C2=A028632


Bob

On Wed, Dec 28, 2022= at 4:49 PM Dave Taht via Make-wifi-fast <make-wifi-fast@lists.bufferbloat.net> wrot= e:
On Wed, Dec 2= 8, 2022 at 3:53 PM Abhishek Kumar <kuabhs@chromium.org> wrote:
>
> Apologies for the late reply, Thanks Dave for your comment. My answer = is inline.
>
> On Tue, Dec 20, 2022 at 7:10 AM Dave Taht <dave.taht@gmail.com> wrote:
> >
> > 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 cli= ents
> > in rtt_fair on the "ending the anomaly" test suite at t= he bottom of
> > this link: https://www.cs.kau.se/tohojo/airt= ime-fairness/ . Of these,
> > it's trying to optimize bandwidth more fairly and keep latenc= ies low
> > when 4 or more stations are trying to transmit (in a world with 1= 6 or
> > more stations online), that increasingly bothers me the most. I&#= 39;m
> > seeing 5+ seconds on some rtt_fair-like tests nowadays.
> I used testing using iperf and conductive setup and fetched the
> throughput data(mentioned below).
> >
> > I was also seeing huge simultaneous upload vs download disparitie= s 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:
> > ht= tps://forum.openwrt.org/t/reducing-multiplexing-latencies-still-further-in-= wifi/133605
> Interesting, thanks for the pointer and probably the Qualcomm team is<= br> > aware of it.
> >
> > I don't understand why napi with the default budget (64) is e= ven
> > 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 c= an do
> > this, Apple's goresponsiveness, crusader... that are simpler = to use
> > than flent.
> Here are some of the additional raw data with and without threaded nap= i:
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D
> udp_rx(Without threaded NAPI)
> 435.98+-5.16 : Channel 44
> 439.06+-0.66 : Channel 157
>
> udp_rx(With threaded NAPI)
> 509.73+-41.03 : Channel 44
> 549.97+-7.62 : Channel 157
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D
> udp_tx(Without threaded NAPI)
> 461.31+-0.69=C2=A0 : Channel 44
> 461.46+-0.78 : Channel 157
>
> udp_tx(With threaded NAPI)
> 459.20+-0.77 : Channel 44
> 459.78+-1.08 : Channel 157
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D
> tcp_rx(Without threaded NAPI)
> 472.63+-2.35 : Channel 44
> 469.29+-6.31 : Channel 157
>
> tcp_rx(With threaded NAPI)
> 498.49+-2.44 : Channel 44
> 541.14+-40.65 : Channel 157
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D
> tcp_tx(Without threaded NAPI)
> 317.34+-2.37 : Channel 44
> 317.01+-2.56 : Channel 157
>
> tcp_tx(With threaded NAPI)
> 371.34+-2.36 : Channel 44
> 376.95+-9.40 : Channel 157

My concern is primarily with the induced tcp latency on this test. A
way to check that is to run wireshark on your test client driving the
test, capture the iperf traffic, and then plot the "Statistics->TCP=
stream statistics for both throughput and rtt. Would it be possible
for you to do that and put up those plots somewhere?

The worst case test is a tcp bidirectional test which I don't know if older iperfs can do. (iperf2 has new bounceback and bidir tests)

Ideally stuff going in either direction, would not look as horrible,
as it did, back in 2016, documented in this linuxplumbers presentation
here: https://blog.linuxplumbersconf.org/2016/ocw/system/pres= entations/3963/original/linuxplumbers_wifi_latency-3Nov.pdf
and discussed on lwn, here: https://lwn.net/Articles/705884/

I worry about folk achieving slightly better tcp throughput at the
expense of clobbering in-tcp-stream latency. Back then we were
shooting for no more than 40ms extra latency under load on this chip,
down from (unusable) seconds. Presently elsewhere, on other chips,
we're getting 8ms with stuff that's not in tree for the ath10k, the= re
is a slight cost in single stream throughput but when multiple streams
are in use, on multiple stations, things like web pages fly,
irrespective of load.


> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D
>
> >
> > On Tue, Dec 20, 2022 at 12:17 AM Abhishek Kumar <kuabhs@chromium.org> wro= te:
> > >
> > > NAPI poll can be done in threaded context along with soft ir= q
> > > 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 s= ame
> > > time the other CPUs are at low consumption percentage. This<= br> > > > does not allow device to reach its maximum throughput potent= ial.
> > > After enabling threaded napi, CPU load is balanced across al= l 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-QCAHLSWMTP= L-1
> > > Signed-off-by: Abhishek Kumar <kuabhs@chromium.org>
> > > ---
> > >
> > >=C2=A0 drivers/net/wireless/ath/ath10k/core.c | 16 ++++++++++= ++++++
> > >=C2=A0 drivers/net/wireless/ath/ath10k/hw.h=C2=A0 =C2=A0|=C2= =A0 2 ++
> > >=C2=A0 drivers/net/wireless/ath/ath10k/snoc.c |=C2=A0 3 +++ > > >=C2=A0 3 files changed, 21 insertions(+)
> > >
> > > diff --git a/drivers/net/wireless/ath/ath10k/core.c b/driver= s/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 ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA988X_HW_2_0_VERSION,
> > > @@ -140,6 +141,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9887_HW_1_0_VERSION,
> > > @@ -181,6 +183,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA6174_HW_3_2_VERSION,
> > > @@ -217,6 +220,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA6174_HW_2_1_VERSION,
> > > @@ -257,6 +261,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA6174_HW_2_1_VERSION,
> > > @@ -297,6 +302,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA6174_HW_3_0_VERSION,
> > > @@ -337,6 +343,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA6174_HW_3_2_VERSION,
> > > @@ -381,6 +388,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA99X0_HW_2_0_DEV_VERSION,
> > > @@ -427,6 +435,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9984_HW_1_0_DEV_VERSION,
> > > @@ -480,6 +489,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9888_HW_2_0_DEV_VERSION,
> > > @@ -530,6 +540,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9377_HW_1_0_DEV_VERSION,
> > > @@ -570,6 +581,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9377_HW_1_1_DEV_VERSION,
> > > @@ -612,6 +624,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA9377_HW_1_1_DEV_VERSION,
> > > @@ -645,6 +658,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D QCA4019_HW_1_0_DEV_VERSION,
> > > @@ -692,6 +706,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D false,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0{
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.id =3D WCN3990_HW_1_0_DEV_VERSION,
> > > @@ -725,6 +740,7 @@ static const struct ath10k_hw_params ath= 10k_hw_params_list[] =3D {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.hw_restart_disconnect =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.use_fw_tx_credits =3D false,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0.delay_unmap_buffer =3D true,
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0.ena= ble_threaded_napi =3D true,
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0},
> > >=C2=A0 };
> > >
> > > 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 {
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0bool use_fw_tx_credits;
> > >
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0bool delay_unmap_buffer; > > > +
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0bool enable_threaded_napi;
> > >=C2=A0 };
> > >
> > >=C2=A0 struct htt_resp;
> > > diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/driver= s/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)
> > >
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0bitmap_clear(ar_snoc->pe= nding_ce_irqs, 0, CE_COUNT_MAX);
> > >
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0if (ar->hw_params.enable_thre= aded_napi)
> > > +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dev_= set_threaded(&ar->napi_dev, true);
> > > +
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0ath10k_core_napi_enable(ar)= ;
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0ath10k_snoc_irq_enable(ar);=
> > >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0ath10k_snoc_rx_post(ar); > > > --
> > > 2.39.0.314.g84b9a713c41-goog
> > >
> >
> >
> > --
> > This song goes out to all the folk that thought Stadia would work= :
> > ht= tps://www.linkedin.com/posts/dtaht_the-mushroom-song-activity-6981366665607= 352320-FXtz
> > Dave T=C3=A4ht CEO, TekLibre, LLC



--
This song goes out to all the folk that thought Stadia would work:
https://www.= linkedin.com/posts/dtaht_the-mushroom-song-activity-6981366665607352320-FXt= z
Dave T=C3=A4ht CEO, TekLibre, LLC
_______________________________________________
Make-wifi-fast mailing list
M= ake-wifi-fast@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/make-wif= i-fast

This ele= ctronic communication and the information and any files transmitted with it= , or attached to it, are confidential and are intended solely for the use o= f the individual or entity to whom it is addressed and may contain informat= ion that is confidential, legally privileged, protected by privacy laws, or= otherwise restricted from disclosure to anyone else. If you are not the in= tended recipient or the person responsible for delivering the e-mail to the= intended recipient, you are hereby notified that any use, copying, distrib= uting, dissemination, forwarding, printing, or copying of this e-mail is st= rictly prohibited. If you received this e-mail in error, please return the = e-mail to the sender, delete it from your computer, and destroy any printed= copy of it. --00000000000026830a05f0f11e5e--