From: "Nicolas Escande" <nico.escande@gmail.com>
To: "Baligh Gasmi" <gasmibal@gmail.com>,
"Johannes Berg" <johannes@sipsolutions.net>
Cc: "David S . Miller" <davem@davemloft.net>,
"Eric Dumazet" <edumazet@google.com>,
"Jakub Kicinski" <kuba@kernel.org>,
"Paolo Abeni" <pabeni@redhat.com>,
<linux-wireless@vger.kernel.org>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, "Felix Fietkau" <nbd@nbd.name>,
"Toke Hoiland-Jorgensen" <toke@redhat.com>,
"Linus Lussing" <linus.luessing@c0d3.blue>,
"Kalle Valo" <kvalo@kernel.org>,
"kernel test robot" <lkp@intel.com>
Subject: Re: [RFC/RFT v5 1/4] mac80211: use AQL airtime for expected throughput.
Date: Thu, 25 Aug 2022 15:31:40 +0200 [thread overview]
Message-ID: <CMF5B109JKDQ.R3G4GDYBLZT6@syracuse> (raw)
In-Reply-To: <20220719123525.3448926-2-gasmibal@gmail.com>
Hello Baligh,
On Tue Jul 19, 2022 at 2:35 PM CEST, Baligh Gasmi wrote:
> Since the integration of AQL, packet TX airtime estimation is
> calculated and counted to be used for the dequeue limit.
>
> Use this estimated airtime to compute expected throughput for
> each station.
>
> It will be a generic mac80211 implementation. that can be used if the
> driver do not have get_expected_throughput implementation.
>
> Useful for L2 routing protocols, like B.A.T.M.A.N.
>
> Signed-off-by: Baligh Gasmi <gasmibal@gmail.com>
> Reported-by: kernel test robot <lkp@intel.com>
> CC: Felix Fietkau <nbd@nbd.name>
> ---
> net/mac80211/driver-ops.h | 2 ++
> net/mac80211/sta_info.c | 39 +++++++++++++++++++++++++++++++++++++++
> net/mac80211/sta_info.h | 11 +++++++++++
> net/mac80211/status.c | 2 ++
> net/mac80211/tx.c | 8 +++++++-
> 5 files changed, 61 insertions(+), 1 deletion(-)
>
> diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
> index 4e2fc1a08681..fa9952154795 100644
> --- a/net/mac80211/driver-ops.h
> +++ b/net/mac80211/driver-ops.h
> @@ -1142,6 +1142,8 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local,
> trace_drv_get_expected_throughput(&sta->sta);
> if (local->ops->get_expected_throughput && sta->uploaded)
> ret = local->ops->get_expected_throughput(&local->hw, &sta->sta);
> + else
> + ret = ewma_avg_est_tp_read(&sta->deflink.status_stats.avg_est_tp);
> trace_drv_return_u32(local, ret);
>
> return ret;
> diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
> index e04a0905e941..201aab465234 100644
> --- a/net/mac80211/sta_info.c
> +++ b/net/mac80211/sta_info.c
> @@ -1993,6 +1993,45 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
> tx_pending, 0);
> }
>
> +void ieee80211_sta_update_tp(struct ieee80211_local *local,
> + struct sta_info *sta,
> + struct sk_buff *skb,
> + u16 tx_time_est,
> + bool ack, int retry)
> +{
> + unsigned long diff;
> + struct rate_control_ref *ref = NULL;
> +
> + if (!skb || !sta || !tx_time_est)
> + return;
> +
> + if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
> + ref = sta->rate_ctrl;
> +
> + if (ref && ref->ops->get_expected_throughput)
> + return;
> +
> + if (local->ops->get_expected_throughput)
> + return;
> +
> + tx_time_est += ack ? 4 : 0;
> + tx_time_est += retry ? retry * 2 : 2;
> +
> + sta->deflink.tx_stats.tp_tx_size += (skb->len * 8) * 1000;
> + sta->deflink.tx_stats.tp_tx_time_est += tx_time_est;
> +
> + diff = jiffies - sta->deflink.status_stats.last_tp_update;
> + if (diff > HZ / 10) {
> + ewma_avg_est_tp_add(&sta->deflink.status_stats.avg_est_tp,
> + sta->deflink.tx_stats.tp_tx_size /
> + sta->deflink.tx_stats.tp_tx_time_est);
This needs a div_u64(), the arch may not have native 64 bits div support
> +
> + sta->deflink.tx_stats.tp_tx_size = 0;
> + sta->deflink.tx_stats.tp_tx_time_est = 0;
> + sta->deflink.status_stats.last_tp_update = jiffies;
> + }
> +}
> +
> int sta_info_move_state(struct sta_info *sta,
> enum ieee80211_sta_state new_state)
> {
> diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
> index 35c390bedfba..4200856fefcd 100644
> --- a/net/mac80211/sta_info.h
> +++ b/net/mac80211/sta_info.h
> @@ -123,6 +123,7 @@ enum ieee80211_sta_info_flags {
> #define HT_AGG_STATE_STOP_CB 7
> #define HT_AGG_STATE_SENT_ADDBA 8
>
> +DECLARE_EWMA(avg_est_tp, 8, 16)
> DECLARE_EWMA(avg_signal, 10, 8)
> enum ieee80211_agg_stop_reason {
> AGG_STOP_DECLINED,
> @@ -157,6 +158,12 @@ void ieee80211_register_airtime(struct ieee80211_txq *txq,
>
> struct sta_info;
>
> +void ieee80211_sta_update_tp(struct ieee80211_local *local,
> + struct sta_info *sta,
> + struct sk_buff *skb,
> + u16 tx_time_est,
> + bool ack, int retry);
> +
> /**
> * struct tid_ampdu_tx - TID aggregation information (Tx).
> *
> @@ -549,6 +556,8 @@ struct link_sta_info {
> s8 last_ack_signal;
> bool ack_signal_filled;
> struct ewma_avg_signal avg_ack_signal;
> + struct ewma_avg_est_tp avg_est_tp;
> + unsigned long last_tp_update;
> } status_stats;
>
> /* Updated from TX path only, no locking requirements */
> @@ -558,6 +567,8 @@ struct link_sta_info {
> struct ieee80211_tx_rate last_rate;
> struct rate_info last_rate_info;
> u64 msdu[IEEE80211_NUM_TIDS + 1];
> + u64 tp_tx_size;
> + u64 tp_tx_time_est;
> } tx_stats;
>
> enum ieee80211_sta_rx_bandwidth cur_max_bandwidth;
> diff --git a/net/mac80211/status.c b/net/mac80211/status.c
> index e69272139437..1fb93abc1709 100644
> --- a/net/mac80211/status.c
> +++ b/net/mac80211/status.c
> @@ -1152,6 +1152,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
> ack_signal_valid > !!(info->status.flags & IEEE80211_TX_STATUS_ACK_SIGNAL_VALID);
>
> + ieee80211_sta_update_tp(local, sta, skb, tx_time_est, acked, retry_count);
> +
> if (pubsta) {
> struct ieee80211_sub_if_data *sdata = sta->sdata;
>
> diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
> index c425f4fb7c2e..beb79b04c287 100644
> --- a/net/mac80211/tx.c
> +++ b/net/mac80211/tx.c
> @@ -3617,6 +3617,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
> struct ieee80211_tx_data tx;
> ieee80211_tx_result r;
> struct ieee80211_vif *vif = txq->vif;
> + struct rate_control_ref *ref = NULL;
>
> WARN_ON_ONCE(softirq_count() == 0);
>
> @@ -3775,8 +3776,13 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
> encap_out:
> IEEE80211_SKB_CB(skb)->control.vif = vif;
>
> + if (tx.sta && test_sta_flag(tx.sta, WLAN_STA_RATE_CONTROL))
> + ref = tx.sta->rate_ctrl;
> +
> if (vif &&
> - wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
> + ((!local->ops->get_expected_throughput &&
> + (!ref || !ref->ops->get_expected_throughput)) ||
> + wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL))) {
> bool ampdu = txq->ac != IEEE80211_AC_VO;
> u32 airtime;
>
> --
> 2.37.1
next prev parent reply other threads:[~2022-08-25 13:49 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-19 12:35 [RFC/RFT v5 0/4] expected throughput from AQL airtime Baligh Gasmi
2022-07-19 12:35 ` [RFC/RFT v5 1/4] mac80211: use AQL airtime for expected throughput Baligh Gasmi
2022-08-25 13:31 ` Nicolas Escande [this message]
2022-08-25 14:17 ` Baligh GASMI
2022-07-19 12:35 ` [RFC/RFT v5 2/4] mac80211: add periodic monitor for channel busy time Baligh Gasmi
2022-08-25 8:58 ` Johannes Berg
2022-08-25 9:27 ` Baligh GASMI
2022-08-25 13:35 ` Nicolas Escande
2022-07-19 12:35 ` [RFC/RFT v5 3/4] mac80211: add busy time factor into expected throughput Baligh Gasmi
2022-08-25 13:36 ` Nicolas Escande
2022-07-19 12:35 ` [RFC/RFT v5 4/4] mac80211: extend channel info with average busy time Baligh Gasmi
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CMF5B109JKDQ.R3G4GDYBLZT6@syracuse \
--to=nico.escande@gmail.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gasmibal@gmail.com \
--cc=johannes@sipsolutions.net \
--cc=kuba@kernel.org \
--cc=kvalo@kernel.org \
--cc=linus.luessing@c0d3.blue \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-wireless@vger.kernel.org \
--cc=lkp@intel.com \
--cc=nbd@nbd.name \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=toke@redhat.com \
/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;
as well as URLs for NNTP newsgroup(s).