From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Received: from mail-qk1-f193.google.com ([209.85.222.193]:41354 "EHLO mail-qk1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725889AbeIJH3N (ORCPT ); Mon, 10 Sep 2018 03:29:13 -0400 MIME-Version: 1.0 References: <20180906035323.GA11337@nems_nctu_lu> <877ejzynz9.fsf@toke.dk> <87sh2mykmt.fsf@toke.dk> In-Reply-To: <87sh2mykmt.fsf@toke.dk> From: Dave Taht Date: Sun, 9 Sep 2018 16:44:53 -0700 Message-ID: (sfid-20180910_043735_764128_54AF44EE) Subject: Re: [PATCH] ath9k: add reset for airtime station debugfs To: =?UTF-8?B?VG9rZSBIw7hpbGFuZC1Kw7hyZ2Vuc2Vu?= Cc: git@louie.lu, Kalle Valo , QCA ath9k Development , "David S. Miller" , linux-wireless , Linux Kernel Network Developers Content-Type: text/plain; charset="UTF-8" Sender: linux-wireless-owner@vger.kernel.org List-ID: On Thu, Sep 6, 2018 at 4:13 AM Toke H=C3=B8iland-J=C3=B8rgensen wrote: > > Louie Lu writes: > > > Toke H=C3=B8iland-J=C3=B8rgensen =E6=96=BC 2018=E5=B9=B4= 9=E6=9C=886=E6=97=A5 =E9=80=B1=E5=9B=9B =E4=B8=8B=E5=8D=885:27=E5=AF=AB=E9= =81=93=EF=BC=9A > > > >> Louie Lu writes: > >> > >> > Let user can reset station airtime status by debugfs, it will > >> > reset all airtime deficit to ATH_AIRTIME_QUANTUM and reset rx/tx > >> > airtime accumulate to 0. > >> > >> No objections to the patch, but I'm curious which issues you were > >> debugging that led you to needing it? :) > >> > > I'm testing to get the packet queue time + airtime in > > ath_tx_process_buffer, > > Right; I've been thinking that it would be useful to make the CoDel > enqueue time available to drivers. And minstrel, for that matter > (lowering the number of retries for packets that has queued for a long > time, for instance). Good to hear that others are looking into something > similar :) Yea! Seeing retransmits scale down would be a goodness. Last I looked ath9k was at, like 10?, when it should be, like, 2, at mcs0 and 10 at mcs15. I can't seem to publish a link to this directly, but it's open access if you search via https://scholar.google.com/: "Resolving Bufferbloat in TCP Communication over IEEE 802.11 n WLAN by Reducing MAC Retransmission Limit at Low Data Rate" even their simple bifurcated model worked well. > > > it would be useful if I can reset the station airtime accumulated > > value, so I can observe in each test round (e.g. 5 ping) airtime > > accumulated > > > > Also to reset the deficit to make sure it run like fresh one. > > Yup, makes sense. > > -Toke --=20 Dave T=C3=A4ht CEO, TekLibre, LLC http://www.teklibre.com Tel: 1-669-226-2619 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dave Taht Subject: Re: [PATCH] ath9k: add reset for airtime station debugfs Date: Sun, 9 Sep 2018 16:44:53 -0700 Message-ID: References: <20180906035323.GA11337@nems_nctu_lu> <877ejzynz9.fsf@toke.dk> <87sh2mykmt.fsf@toke.dk> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Cc: git@louie.lu, Kalle Valo , QCA ath9k Development , "David S. Miller" , linux-wireless , Linux Kernel Network Developers To: =?UTF-8?B?VG9rZSBIw7hpbGFuZC1Kw7hyZ2Vuc2Vu?= Return-path: Received: from mail-qk1-f193.google.com ([209.85.222.193]:41354 "EHLO mail-qk1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725889AbeIJH3N (ORCPT ); Mon, 10 Sep 2018 03:29:13 -0400 In-Reply-To: <87sh2mykmt.fsf@toke.dk> Sender: netdev-owner@vger.kernel.org List-ID: On Thu, Sep 6, 2018 at 4:13 AM Toke H=C3=B8iland-J=C3=B8rgensen wrote: > > Louie Lu writes: > > > Toke H=C3=B8iland-J=C3=B8rgensen =E6=96=BC 2018=E5=B9=B4= 9=E6=9C=886=E6=97=A5 =E9=80=B1=E5=9B=9B =E4=B8=8B=E5=8D=885:27=E5=AF=AB=E9= =81=93=EF=BC=9A > > > >> Louie Lu writes: > >> > >> > Let user can reset station airtime status by debugfs, it will > >> > reset all airtime deficit to ATH_AIRTIME_QUANTUM and reset rx/tx > >> > airtime accumulate to 0. > >> > >> No objections to the patch, but I'm curious which issues you were > >> debugging that led you to needing it? :) > >> > > I'm testing to get the packet queue time + airtime in > > ath_tx_process_buffer, > > Right; I've been thinking that it would be useful to make the CoDel > enqueue time available to drivers. And minstrel, for that matter > (lowering the number of retries for packets that has queued for a long > time, for instance). Good to hear that others are looking into something > similar :) Yea! Seeing retransmits scale down would be a goodness. Last I looked ath9k was at, like 10?, when it should be, like, 2, at mcs0 and 10 at mcs15. I can't seem to publish a link to this directly, but it's open access if you search via https://scholar.google.com/: "Resolving Bufferbloat in TCP Communication over IEEE 802.11 n WLAN by Reducing MAC Retransmission Limit at Low Data Rate" even their simple bifurcated model worked well. > > > it would be useful if I can reset the station airtime accumulated > > value, so I can observe in each test round (e.g. 5 ping) airtime > > accumulated > > > > Also to reset the deficit to make sure it run like fresh one. > > Yup, makes sense. > > -Toke --=20 Dave T=C3=A4ht CEO, TekLibre, LLC http://www.teklibre.com Tel: 1-669-226-2619