From: Dave Taht <dave.taht@gmail.com>
To: Michael Yartys <michael.yartys@protonmail.com>
Cc: Bob McMahon <bob.mcmahon@broadcom.com>,
Make-Wifi-fast <make-wifi-fast@lists.bufferbloat.net>
Subject: Re: [Make-wifi-fast] Weird periodic latency
Date: Sat, 16 Jan 2021 10:20:31 -0800 [thread overview]
Message-ID: <CAA93jw4adi-Vw37czCmSZ9nerRTBXvS2CwuQ+Qw4BCKKehYuEA@mail.gmail.com> (raw)
In-Reply-To: <nPlLbqjVDbaaO57GXZVtru2T2un1kLVAlBli1-WrLed-_otFzbvv4_SL-Ufg-DtXeeaVEUK6Q5647lribJeojtzkymmyB9-sLHLD9-KQaaw=@protonmail.com>
On Sat, Jan 16, 2021 at 10:15 AM Michael Yartys
<michael.yartys@protonmail.com> wrote:
>
> On Saturday, January 16th, 2021 at 19:06, Dave Taht <dave.taht@gmail.com> wrote:
>
> > thxz for the clarification.
>
> No worries! =)
>
> >
> > Also, I would really like the codel target reduced to 10ms on the
> >
> > upcoming release of openwrt.
>
> I ran the 10ms target for a while but don't really remember whether I noticed that much of a difference. Maybe I should try it again? =)
you've got some good reference data now.
>
> Right now I'm planning to try out Toke's virtual time-based scheduler: https://github.com/tohojo/openwrt/blob/virtual-airtime/package/kernel/mac80211/patches/subsys/346-mac80211-Switch-to-a-virtual-time-based-airtime-sche.patch
>
> >
> > On Sat, Jan 16, 2021 at 10:01 AM Michael Yartys
> >
> > michael.yartys@protonmail.com wrote:
> >
> > > On Saturday, January 16th, 2021 at 18:48, Dave Taht dave.taht@gmail.com wrote:
> > >
> > > > That implies it is doing a channel scan. Dumb.
> > > >
> > > > https://blog.cerowrt.org/post/disabling_channel_scans/
> > > >
> > > > but what you encountered seemed more disabling than that, and the
> > > >
> > > > ath10k is supposed to be able to do background channel scans.
> > >
> > > The tests where I experienced the roller-coaster high latency were the result of a fluke I believe. It went away after a reboot and I wasn't readily able to reproduce it. Also, I believe there's some confusion here since my laptop, which was doing the background scans, has an Intel 7260AC card. ath10k is not at fault here (might have been during the fluke, but who knows).
> > >
> > > > On Sat, Jan 16, 2021 at 6:47 AM Michael Yartys
> > > >
> > > > michael.yartys@protonmail.com wrote:
> > > >
> > > > > I'm pretty sure I've managed to figure out what causes the short sharp periodic latency spikes. The Gnome location service uses the surrounding wireless networks as one of the methods to determine your location. When it's turned on I get the following results:
> > > > >
> > > > > https://imgur.com/a/pNXuVRe
> > > > >
> > > > > When it's disabled the latency spikes are gone (and notice that AQL is working here as there is some background traffic from other clients):
> > > > >
> > > > > https://imgur.com/a/v4wWkAC
> > > > >
> > > > > Now, I wasn't able to reproduce the weird roller coaster like latency that I saw previously. I rebooted the laptop before I did these tests, so I guess that solved it.
> > > > >
> > > > > Michael
> > > >
> > > > --
> > > >
> > > > "For a successful technology, reality must take precedence over public
> > > >
> > > > relations, for Mother Nature cannot be fooled" - Richard Feynman
> > > >
> > > > dave@taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729
> >
> > --
> >
> > "For a successful technology, reality must take precedence over public
> >
> > relations, for Mother Nature cannot be fooled" - Richard Feynman
> >
> > dave@taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729
--
"For a successful technology, reality must take precedence over public
relations, for Mother Nature cannot be fooled" - Richard Feynman
dave@taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729
next prev parent reply other threads:[~2021-01-16 18:20 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-15 16:02 Michael Yartys
2021-01-15 16:23 ` Toke Høiland-Jørgensen
2021-01-15 16:59 ` Michael Yartys
2021-01-15 18:55 ` Toke Høiland-Jørgensen
2021-01-15 19:22 ` Michael Yartys
2021-01-15 19:28 ` Toke Høiland-Jørgensen
[not found] ` <CAA93jw6uLUC9b-vuPrEcL_VqXWPOtqUo=ek2G0x=XmvJ-GfLKw@mail.gmail.com>
2021-01-15 19:10 ` Dave Taht
2021-01-15 19:33 ` Michael Yartys
2021-01-15 21:44 ` Bob McMahon
2021-01-16 14:46 ` Michael Yartys
2021-01-16 17:48 ` Dave Taht
2021-01-16 18:01 ` Michael Yartys
2021-01-16 18:06 ` Dave Taht
2021-01-16 18:14 ` Michael Yartys
2021-01-16 18:20 ` Dave Taht [this message]
2021-01-16 21:01 ` Bob McMahon
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
List information: https://lists.bufferbloat.net/postorius/lists/make-wifi-fast.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAA93jw4adi-Vw37czCmSZ9nerRTBXvS2CwuQ+Qw4BCKKehYuEA@mail.gmail.com \
--to=dave.taht@gmail.com \
--cc=bob.mcmahon@broadcom.com \
--cc=make-wifi-fast@lists.bufferbloat.net \
--cc=michael.yartys@protonmail.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