Re: [Cake] [Bloat] bufferbloat.net is sorely missed.

2016-06-10 Thread Toke Høiland-Jørgensen
Kevin Darbyshire-Bryant writes: > Possibly/probably as a result of CAKE getting into LEDE I note a few people > saying 'bufferbloat.net' is down. This is unfortunate just at a time when a > hoped for uptick in interest factor may well be upon us. Interest has

Re: [Cake] cake separate qos for lan

2016-03-29 Thread Toke Høiland-Jørgensen
Jonathan Morton writes: > But maybe u32, in the hashing configuration, scales better. I did a similar setup for a small ISP quite some time ago that used HTB as the classful qdisc and a hashing u32 filter to divide traffic. This was pre-FQ-CoDel, so it used SFQ on the

Re: [Cake] [Make-wifi-fast] flent testers wanted prior to next release

2017-01-31 Thread Toke Høiland-Jørgensen
Stephen Hemminger writes: > On Tue, 20 Dec 2016 11:02:44 -0800 > Dave Taht wrote: > >> Toke has been busy adding new features to the flent network test tool. >> I consider it *almost* stable enough for a new release. Some of the >> development

Re: [Cake] [Make-wifi-fast] flent testers wanted prior to next release

2017-01-31 Thread Toke Høiland-Jørgensen
Stephen Hemminger <step...@networkplumber.org> writes: > On Tue, 31 Jan 2017 17:35:40 +0100 > Toke Høiland-Jørgensen <t...@toke.dk> wrote: > >> Stephen Hemminger <step...@networkplumber.org> writes: >> >> > On Tue, 20 Dec 2016 11:02:44

Re: [Cake] [Make-wifi-fast] flent testers wanted prior to next release

2017-01-31 Thread Toke Høiland-Jørgensen
"Klatsky, Carl" writes: > Finally had some time to get to this request. I downloaded the current git > version of Flent and was able to launch the flent-gui on Windows. I had some > old > test *.flent.gz results files which loaded just fine. I tried to open the test >

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-02-01 Thread Toke Høiland-Jørgensen
Aaron Wood writes: > - Yeah, as you note Flent has a batch facility. Did you not use this >simply because you couldn't find it, or was there some other reason? >Would love some feedback on what I can do to make that more useful to >people... While I have no doubt

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-02-01 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: > On Jan 30, 2017, at 10:44 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: > > Oh my, this is quite a lot of tests. Nice :) > > It’s also a thumbs up for the ath9k driver changes that nothing went > wrong during the te

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-01-30 Thread Toke Høiland-Jørgensen
Pete Heist writes: > Hi, I’ve posted some Flent results and analysis for point-to-point Wi-Fi > using LEDE on OM2P-HS (ath9k): > > http://www.drhleny.cz/bufferbloat/wifi_bufferbloat.html Oh my, this is quite a lot of tests. Nice :) Few general points on running tests: -

Re: [Cake] diffserv3 tin 2 target 50% of interval?

2017-02-22 Thread Toke Høiland-Jørgensen
Jonathan Morton writes: >> On 22 Feb, 2017, at 13:12, Pete Heist wrote: >> >> Ok, but for what it’s worth, so far I’m not seeing this confer any benefit as >> far as latency is concerned. I will make full results available later, but >> for >> now,

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-02-09 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: >> On Feb 8, 2017, at 5:11 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >>> >>> That reminds me, is there any way to disable fq-codel in the ath9k >>> driver, and revert to being able to use the qdis

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-02-09 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: > On Feb 9, 2017, at 2:51 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: > > Also, could the queue management code be abstracted into a separate > module, so it can be replaced, like a qdisc? I don’t know if the > dispa

Re: [Cake] [Make-wifi-fast] Flent results for point-to-point Wi-Fi on LEDE/OM2P-HS available

2017-02-17 Thread Toke Høiland-Jørgensen
Pete Heist writes: > On Feb 16, 2017, at 10:03 PM, Sebastian Moeller wrote: > > On Feb 16, 2017, at 18:19, Jonathan Morton wrote: > > In a sense if there are thresholds for permissible VO/VI traffic fractions > below which the AP

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-05 Thread Toke Høiland-Jørgensen
"Jason A. Donenfeld" <ja...@zx2c4.com> writes: > On Sun, Oct 2, 2016 at 1:31 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> You don't need a timer. You already have a signal for when more queue >> space is available in the encryption step: When a packet

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-01 Thread Toke Høiland-Jørgensen
"Jason A. Donenfeld" writes: > Hi all, > > On Fri, Sep 30, 2016 at 9:18 PM, Dave Taht wrote: >> All: I've always dreamed of a vpn that could fq and - when it was >> bottlenecking on cpu - throw away packets intelligently. Wireguard, >> which is what jason &

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-01 Thread Toke Høiland-Jørgensen
Dave Taht writes: > My thought - given that at least on some platforms - encrypting 1000 > packets at a time is a bad idea - would be something regulating the > amount of data being crypted at a time, an equivalent to byte queue > limits - BQL - BCL? byte crypto limits - to

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-02 Thread Toke Høiland-Jørgensen
"Jason A. Donenfeld" <ja...@zx2c4.com> writes: > Hey Toke, > > On Sun, Oct 2, 2016 at 1:40 AM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> I assumed that there probably was, but was not sure where. Thanks for >> clearing this up

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-01 Thread Toke Høiland-Jørgensen
Dave Taht <dave.t...@gmail.com> writes: > On Sat, Oct 1, 2016 at 8:51 AM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> Dave Taht <dave.t...@gmail.com> writes: >> >>> My thought - given that at least on some platforms - encrypting 1000 >>> p

Re: [Cake] WireGuard Queuing, Bufferbloat, Performance, Latency, and related issues

2016-10-01 Thread Toke Høiland-Jørgensen
"Jason A. Donenfeld" <ja...@zx2c4.com> writes: > Thanks a lot for your responses. This is steering me in the right direction (I > hope!). Responses are inline below. > > Regards, > Jason > > On Sat, Oct 1, 2016 at 1:51 PM, Toke Høiland-Jørgensen <t...@tok

Re: [Cake] [Make-wifi-fast] Airtime fairness patch merged upstream, and the Turris Omnia debloated

2016-12-25 Thread Toke Høiland-Jørgensen
Valent Turkovic writes: > Please send just a short notification as soon as Lede with airfairness > has been released, I have really good real world location that can > test how effective it works... It should be in the nightly LEDE builds by now :) -Toke

[Cake] Airtime fairness patch merged upstream, and the Turris Omnia debloated

2016-12-19 Thread Toke Høiland-Jørgensen
The airtime fairness patch for ath9k has been accepted into the mainline Linux kernel, and is queued to be merged for 4.11 (i.e. the next merge window after the current 4.10 cycle completes). The patch has also been accepted into LEDE and is currently in Felix' staging tree at

Re: [Cake] Current status and recommendations for APU2C*/ArcherC7 and ath10k platforms?

2017-03-30 Thread Toke Høiland-Jørgensen
leetminiwheat writes: > Apologies I haven't had time to follow recent developments but are there > any recent bufferbloat/CAKE related news/recommendations for the APU2 > platform? Specifically the APU2C (previous was marvell I believe) > > Hardware: > APU2C4 (AMD

Re: [Cake] flow isolation for ISPs

2017-04-06 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: > On Apr 6, 2017, at 2:14 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: > > Pete Heist <petehe...@gmail.com> writes: > > but I’m still a little confused. Is fq_codel actually a classful > qdisc? > > Yup. T

Re: [Cake] Cake] Current status and recommendations for APU2C*/ArcherC7 and ath10k platforms?

2017-04-20 Thread Toke Høiland-Jørgensen
Jon Pike writes: > Thought this might be a good place to ask a question or two abt the > wifi fast stuff... while Toke's listening. > > 1. What's the status of make wifi fast on the ath10k now, or did it > make it there yet? Well, the queue rework is in there, but only

Re: [Cake] flow isolation for ISPs

2017-04-06 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: > On Apr 6, 2017, at 12:50 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: > > Pete Heist <petehe...@gmail.com> writes: > > The fq_codel qdisc does have support for arbitrary tc filters to replace > the default hash

Re: [Cake] ER-X now running cake, thanks for the help. :)

2017-05-05 Thread Toke Høiland-Jørgensen
On 5 May 2017 16:30:38 GMT+02:00, erik.tarald...@telenor.com wrote: > >> Den 5. mai 2017 kl. 15.59 skrev Toke Høiland-Jørgensen ><t...@toke.dk>: >> >> How are you measuring latency in this case? > >I use nuttcp with the option -o. It uses syst

Re: [Cake] ER-X now running cake, thanks for the help. :)

2017-05-05 Thread Toke Høiland-Jørgensen
writes: > Just a follow-up from the great support I got here. I am now running ER-X > with cake with the precompiled binaries from Nils. I need to do some tuning > and get it properly into the lab. Currently I'm dogfooding it at home. > > Any other suggestions in

Re: [Cake] ER-X now running cake, thanks for the help. :)

2017-05-05 Thread Toke Høiland-Jørgensen
writes: >> Fra: Sebastian Moeller > >> .. snip >> One problem with the unelastic load is that as far as I can tell no flow on >> the open internet is >> allows/assumed to behave like that (isn’t the default tcp-friendly, and >> inelastic DOS

Re: [Cake] cake flenter results round 1

2017-11-27 Thread Toke Høiland-Jørgensen
Pete Heist writes: > * I wonder if the UDP flood tests really work at 900mbit: Did you set the UDP bandwidth? --test-parameter udp_bandwidth=1000M for instance -Toke ___ Cake mailing list Cake@lists.bufferbloat.net

Re: [Cake] new patchset for upstream net-next

2017-11-26 Thread Toke Høiland-Jørgensen
gamana...@gmail.com writes: > Just finished building, setting both sch_cake and nf_conntrack as > integral succeeds. Setting nf_conntrack as module fails with sch_cake > as integral (makes sense). So this probably needs either a Kconfig dependency or an ifdef? -Toke

Re: [Cake] new patchset for upstream net-next

2017-11-26 Thread Toke Høiland-Jørgensen
On 26 November 2017 19:22:35 CET, Dave Taht <d...@taht.net> wrote: >Toke Høiland-Jørgensen <t...@toke.dk> writes: > >> gamana...@gmail.com writes: >> >>> Just finished building, setting both sch_cake and nf_conntrack as >>> integral succeeds. Set

Re: [Cake] [PATCH 2/3] Add Common Applications Kept Enhanced (sch_cake) qdisc

2017-11-21 Thread Toke Høiland-Jørgensen
years behind mainline Linux. A stable version has been >> generally available on lede-17.01 and later. >> >> sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in >> the sqm-scripts, with sane defaults and vastly easier configuration.

Re: [Cake] Cake tree unreadable

2017-11-29 Thread Toke Høiland-Jørgensen
Dave Taht writes: > A flag day here is feasible. I will fiddle along the lines you > describe. FWIW I don't think the history is that bad. Sure, there are a bunch of merge commits, but picking out the real ones is not that difficult (unless you are using the github web interface,

Re: [Cake] cake flenter results round 2

2017-11-29 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > I am troubled by the number of data points flent reports for some pings and > uploads in this setup. A typical ack-filter result, similar to rrul2 I > posted before, looks like this: > Summary of rrul test run 'rrul_cakeeth_ds3_900mbit_45mbit_ack'

Re: [Cake] cake flenter results round 2

2017-11-29 Thread Toke Høiland-Jørgensen
> (That was also informative for me about how netperf decides when to > emit a data point…) In that case I can add that the stated reason for this way of doing things is performance (i.e., emitting data points should not interfere with transfer performance). This is mostly an issue on systems

Re: [Cake] cake flenter results round 2

2017-11-29 Thread Toke Høiland-Jørgensen
Pete Heist <petehe...@gmail.com> writes: >> On Nov 29, 2017, at 4:44 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >>> (That was also informative for me about how netperf decides when to >>> emit a data point…) >> >> In that case

Re: [Cake] cake flenter results round 2

2017-11-29 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > Results with irtt/flent-git. Same setup as before: Looks like that is still using netperf for the UDP measurements. Flent does some sanity checks on irtt before using it, which may be failing. Running flent with -v should give some hints...

Re: [Cake] cake flenter results round 2

2017-11-29 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > @Pete @Toke just saw your responses. Thank you very much for the > explanation. I will give irtt and flent-git a try, and maybe build an > aur package for archlinux. There's already an AUR package for flent-git; haven't gotten around to making

Re: [Cake] 1Gbit/20Mbit D/L with ack-filtering

2017-11-29 Thread Toke Høiland-Jørgensen
dpr...@reed.com writes: > BTW, one annoying thing about flent is that netperf is not available > in fedora, rhel, centos as a package. So I have to install it and it > doesn't just plug in smoothly. That's just my convenience issue. I > don't use netperf myself on any of my systems. iperf and

Re: [Cake] cake flenter results round 3

2017-11-30 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > I had to run flent with "-s 0.61" in order to avoid errors with fping dying > prematurely. When did fping die, and did you still get results? There's a watchdog timer to keep it from running too long, but maybe that is a bit too aggressive?

Re: [Cake] cake flenter results round 3

2017-11-30 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > I still got results but did not trust them. > The error occurred at the end of the run. > > ===8<=== > NetperfDemoRunner TCP upload CS5 finished > NetperfDemoRunner TCP upload EF finished > TimerRunner Watchdog [Ping (ms) ICMP]

Re: [Cake] [RFC PATCH 3/3] Add support for building the new cake qdisc

2017-11-17 Thread Toke Høiland-Jørgensen
Dave Taht writes: > --- > net/sched/Kconfig | 11 +++ > net/sched/Makefile | 1 + > 2 files changed, 12 insertions(+) > > diff --git a/net/sched/Kconfig b/net/sched/Kconfig > index c03d86a..3ea22e5 100644 > --- a/net/sched/Kconfig > +++ b/net/sched/Kconfig > @@

Re: [Cake] [Bloat] Update Cake page on bufferbloat.net?

2017-11-03 Thread Toke Høiland-Jørgensen
Jonathan Morton writes: > I think "mostly true but incomplete" is the best way to describe the > current pages. Patches welcome :) https://github.com/tohojo/bufferbloat-net -Toke ___ Cake mailing list

Re: [Cake] cake flenter results round 3

2017-12-01 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > I don't really know. When I ran "ping 10.10.0.1" it just worked. fping > -p250 didn't. What about ping -i0.2? -Toke ___ Cake mailing list Cake@lists.bufferbloat.net

Re: [Cake] Hopefully fixed ACK filter for v6

2018-05-06 Thread Toke Høiland-Jørgensen
Jonathan Morton writes: >>> I certainly am thankful for your work, and believe you deserve $CAKE >>> and $BEVERAGE, I am also leaf to believe 'the cake is a lie' >>> https://m.youtube.com/watch?v=qdrs3gr_GAs ;) >> >> Haha, yes, of course I am aware that the cake really is

Re: [Cake] [PATCH net-next v8 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-04 Thread Toke Høiland-Jørgensen
Thank you for the review! A few comments below, I'll fix the rest. > [...] > > So sch_cake doesn't accept normal tc filters? Is this intentional? > If so, why? For two reasons: - The two-level scheduling used in CAKE (tins / diffserv classes, and flow hashing) does not map in an obvious way

[Cake] Merged the simplified ACK filter...

2018-05-04 Thread Toke Høiland-Jørgensen
...since no one complained. If no one continues to complain, I'll resubmit to net-next with that version later today :) -Toke ___ Cake mailing list Cake@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/cake

Re: [Cake] [PATCH net-next v9 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-14 Thread Toke Høiland-Jørgensen
David Miller <da...@davemloft.net> writes: > From: Toke Høiland-Jørgensen <t...@toke.dk> > Date: Tue, 08 May 2018 16:34:19 +0200 > >> +struct cake_flow { >> +/* this stuff is all needed per-flow at dequeue time */ >> +struct sk_buff*head; >>

Re: [Cake] [PATCH net-next v9 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-14 Thread Toke Høiland-Jørgensen
David Miller <da...@davemloft.net> writes: > From: Toke Høiland-Jørgensen <t...@toke.dk> > Date: Mon, 14 May 2018 11:08:28 +0200 > >> David Miller <da...@davemloft.net> writes: >> >>> From: Toke Høiland-Jørgensen <t...@toke.dk> >>> D

[Cake] [PATCH net-next v10 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-14 Thread Toke Høiland-Jørgensen
s and vastly simpler configuration. CAKE's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht, and Loganaden Velvindron. Testing from Pete Heis

[Cake] [PATCH net-next v10 4/7] sch_cake: Add NAT awareness to packet classifier

2018-05-14 Thread Toke Høiland-Jørgensen
at higher bandwidths. For this reason, the feature is turned off by default. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 72 ++ 1 file changed, 72 insertions(+) diff --git a/net/sched/sch_cake.c b/net

[Cake] [PATCH net-next v10 3/7] sch_cake: Add optional ACK filter

2018-05-14 Thread Toke Høiland-Jørgensen
). Finally, even though we consider the ACK filter to be safer than most, we do not recommend turning it on everywhere: on more symmetrical link bandwidths the effect is negligible at best. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c

[Cake] [PATCH net-next v10 5/7] sch_cake: Add DiffServ handling

2018-05-14 Thread Toke Høiland-Jørgensen
number of configured priority tiers. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 408 +- 1 file changed, 401 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 2802bb2

[Cake] [PATCH net-next v10 2/7] sch_cake: Add ingress mode

2018-05-14 Thread Toke Høiland-Jørgensen
by an EWMA filter. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 78 +++--- 1 file changed, 74 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index e22c712602fa..179bfa

[Cake] [PATCH net-next v10 0/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-14 Thread Toke Høiland-Jørgensen
riting the paper. --- Toke Høiland-Jørgensen (7): sched: Add Common Applications Kept Enhanced (cake) qdisc sch_cake: Add ingress mode sch_cake: Add optional ACK filter sch_cake: Add NAT awareness to packet classifier sch_cake: Add DiffServ handling sch_cake: Add ov

[Cake] [PATCH net-next v10 6/7] sch_cake: Add overhead compensation support to the rate shaper

2018-05-14 Thread Toke Høiland-Jørgensen
reported by the kernel is used. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 123 ++ 1 file changed, 122 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index ccc6f2

[Cake] [PATCH net-next v10 7/7] sch_cake: Conditionally split GSO segments

2018-05-14 Thread Toke Høiland-Jørgensen
on bandwidth. For this reason, we split GSO segments into their individual packets iff the shaper is active and configured to a bandwidth <= 1 Gbps. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 99 +- 1 fil

[Cake] [PATCH net-next v4] Add Common Applications Kept Enhanced (cake) qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht, and Loganaden Velvindron. Testing from Pete Heist, Georgios Amanakis, and the many other members of the cake@lists.bufferbloat.net

Re: [Cake] [PATCH net-next v4] Add Common Applications Kept Enhanced (cake) qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
Eric Dumazet <eric.duma...@gmail.com> writes: > On 04/27/2018 06:38 AM, Toke Høiland-Jørgensen wrote: >> >> Ah, right. Will fix. >> >> Is it safe to dereference the iph pointer before calling >> pskb_may_pull()? > > No, please take a look at ip_r

Re: [Cake] Pre-print of Cake paper available

2018-04-27 Thread Toke Høiland-Jørgensen
Pete Heist <p...@eventide.io> writes: >> On Apr 25, 2018, at 10:28 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >> Hmm, actually it looks like just compiling against the conntrack code >> adds a module dependency on conntrack. And as far as I can tell,

[Cake] [PATCH iproute2-next v5] Add support for cake qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
. sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in the sqm-scripts, with sane defaults and vastly simpler configuration. Cake's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido S

Re: [Cake] [PATCH net-next v4] Add Common Applications Kept Enhanced (cake) qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
Eric Dumazet <eric.duma...@gmail.com> writes: > On 04/27/2018 05:17 AM, Toke Høiland-Jørgensen wrote: > > ... > >> + >> +static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, >> + struct cake_flow *flow) >

[Cake] [PATCH iproute2-next v7] Add support for cake qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
. sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in the sqm-scripts, with sane defaults and vastly simpler configuration. Cake's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido S

[Cake] [PATCH iproute2-next v6] Add support for cake qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
. sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in the sqm-scripts, with sane defaults and vastly simpler configuration. Cake's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido S

[Cake] [PATCH net-next v5] Add Common Applications Kept Enhanced (cake) qdisc

2018-04-27 Thread Toke Høiland-Jørgensen
, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht, and Loganaden Velvindron. Testing from Pete Heist, Georgios Amanakis, and the many other members of the cake@lists.bufferbloat.net

Re: [Cake] Thanks to Toke

2018-04-27 Thread Toke Høiland-Jørgensen
Kevin Darbyshire-Bryant via Cake writes: > Thank you Toke for your continued and continuing efforts in submitting > CAKE to upstream kernel land. I am at least one person who greatly > values and appreciates your time and efforts in doing so…. and > wrangling the

Re: [Cake] [PATCH net-next v5] Add Common Applications Kept Enhanced (cake) qdisc

2018-04-28 Thread Toke Høiland-Jørgensen
Toke Høiland-Jørgensen <t...@toke.dk> writes: > +static inline struct tcphdr *cake_get_tcphdr(struct sk_buff *skb) > +{ > + struct ipv6hdr *ipv6h; > + struct iphdr *iph; > + struct tcphdr *th; > + > + > + switch (skb->protocol) { > + cas

Re: [Cake] Thanks to Toke

2018-04-28 Thread Toke Høiland-Jørgensen
On 28 April 2018 10:48:17 CEST, Kevin Darbyshire-Bryant <ke...@darbyshire-bryant.me.uk> wrote: > > >> On 27 Apr 2018, at 16:06, Toke Høiland-Jørgensen <t...@toke.dk> >wrote: >> >> Kevin Darbyshire-Bryant via Cake <cake@lists.bufferbloat.net> writ

Re: [Cake] [PATCH iproute2-next v7] Add support for cake qdisc

2018-04-28 Thread Toke Høiland-Jørgensen
Stephen Hemminger <step...@networkplumber.org> writes: > On Fri, 27 Apr 2018 21:57:20 +0200 > Toke Høiland-Jørgensen <t...@toke.dk> wrote: > >> sch_cake is intended to squeeze the most bandwidth and latency out of even >> the slowest ISP links and routers, whil

Re: [Cake] [PATCH net-next v8 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-07 Thread Toke Høiland-Jørgensen
Cong Wang <xiyou.wangc...@gmail.com> writes: > On Fri, May 4, 2018 at 12:10 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> Thank you for the review! A few comments below, I'll fix the rest. >> >>> [...] >>> >>> So sch_cake doesn't accept

[Cake] [PATCH net-next v9 0/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-08 Thread Toke Høiland-Jørgensen
sation style. v2: - Fix kbuild test bot complaint - Clean up the netlink ABI - Fix checkpatch complaints - A few tweaks to the behaviour of cake based on testing carried out while writing the paper. --- Toke Høiland-Jørgensen (7): sched: Add Common Applications Kept Enhanced

[Cake] [PATCH net-next v9 3/7] sch_cake: Add optional ACK filter

2018-05-08 Thread Toke Høiland-Jørgensen
). Finally, even though we consider the ACK filter to be safer than most, we do not recommend turning it on everywhere: on more symmetrical link bandwidths the effect is negligible at best. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c

[Cake] [PATCH net-next v9 5/7] sch_cake: Add DiffServ handling

2018-05-08 Thread Toke Høiland-Jørgensen
number of configured priority tiers. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 408 +- 1 file changed, 401 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a227a68

[Cake] [PATCH net-next v9 4/7] sch_cake: Add NAT awareness to packet classifier

2018-05-08 Thread Toke Høiland-Jørgensen
at higher bandwidths. For this reason, the feature is turned off by default. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 73 ++ 1 file changed, 73 insertions(+) diff --git a/net/sched/sch_cake.c b/net

[Cake] [PATCH net-next v9 2/7] sch_cake: Add ingress mode

2018-05-08 Thread Toke Høiland-Jørgensen
by an EWMA filter. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 78 +++--- 1 file changed, 74 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c3446a99341f..aeafbb

[Cake] [PATCH net-next v9 7/7] sch_cake: Conditionally split GSO segments

2018-05-08 Thread Toke Høiland-Jørgensen
on bandwidth. For this reason, we split GSO segments into their individual packets iff the shaper is active and configured to a bandwidth <= 1 Gbps. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 99 +- 1 fil

[Cake] [PATCH net-next v9 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-08 Thread Toke Høiland-Jørgensen
Signed-off-by: Dave Taht <dave.t...@gmail.com> Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- include/uapi/linux/pkt_sched.h | 105 ++ net/sched/Kconfig | 11 net/sched/Makefile |1 net/sched/sch_cake.c | 1729 +++

[Cake] [PATCH net-next v9 6/7] sch_cake: Add overhead compensation support to the rate shaper

2018-05-08 Thread Toke Høiland-Jørgensen
reported by the kernel is used. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 123 ++ 1 file changed, 122 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 6f9980

Re: [Cake] Merged the simplified ACK filter...

2018-05-04 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > There is a plain "n" (probably leftover) at line 1026 and it doesn't > compile. Ah, right, didn't realise that had made it into the github version as well; fixed! :) > Thank you for all the effort you are putting in! You're welcome; testing

[Cake] [PATCH net-next v8 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-04 Thread Toke Høiland-Jørgensen
Signed-off-by: Dave Taht <dave.t...@gmail.com> Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- include/uapi/linux/pkt_sched.h | 105 ++ net/sched/Kconfig | 11 net/sched/Makefile |1 net/sched/sch_cake.c | 1683 +++

[Cake] [PATCH net-next v8 7/7] sch_cake: Conditionally split GSO segments

2018-05-04 Thread Toke Høiland-Jørgensen
on bandwidth. For this reason, we split GSO segments into their individual packets iff the shaper is active and configured to a bandwidth <= 1 Gbps. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 95 -- 1 fil

[Cake] [PATCH net-next v8 2/7] sch_cake: Add ingress mode

2018-05-04 Thread Toke Høiland-Jørgensen
by an EWMA filter. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 70 +++--- 1 file changed, 66 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 8e2f2ba2ed5d..7ca86e

[Cake] [PATCH net-next v8 3/7] sch_cake: Add optional ACK filter

2018-05-04 Thread Toke Høiland-Jørgensen
). Finally, even though we consider the ACK filter to be safer than most, we do not recommend turning it on everywhere: on more symmetrical link bandwidths the effect is negligible at best. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c

[Cake] [PATCH net-next v8 4/7] sch_cake: Add NAT awareness to packet classifier

2018-05-04 Thread Toke Høiland-Jørgensen
at higher bandwidths. For this reason, the feature is turned off by default. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 70 ++ 1 file changed, 70 insertions(+) diff --git a/net/sched/sch_cake.c b/net

[Cake] [PATCH net-next v8 5/7] sch_cake: Add DiffServ handling

2018-05-04 Thread Toke Høiland-Jørgensen
e other DiffServ-handling code. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 394 +- 1 file changed, 387 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index cc45a56d35d6.

[Cake] [PATCH net-next v8 6/7] sch_cake: Add overhead compensation support to the rate shaper

2018-05-04 Thread Toke Høiland-Jørgensen
reported by the kernel is used. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 110 ++ 1 file changed, 109 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 1e5951

[Cake] [PATCH net-next v11 4/7] sch_cake: Add NAT awareness to packet classifier

2018-05-15 Thread Toke Høiland-Jørgensen
at higher bandwidths. For this reason, the feature is turned off by default. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 73 ++ 1 file changed, 73 insertions(+) diff --git a/net/sched/sch_cake.c b/net

[Cake] [PATCH net-next v11 1/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-15 Thread Toke Høiland-Jørgensen
s and vastly simpler configuration. CAKE's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht, and Loganaden Velvindron. Testing from Pete Heis

[Cake] [PATCH net-next v11 6/7] sch_cake: Add overhead compensation support to the rate shaper

2018-05-15 Thread Toke Høiland-Jørgensen
reported by the kernel is used. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 124 ++ 1 file changed, 123 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 4b1334

[Cake] [PATCH net-next v11 2/7] sch_cake: Add ingress mode

2018-05-15 Thread Toke Høiland-Jørgensen
by an EWMA filter. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 78 +++--- 1 file changed, 74 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 9d7fc1848778..8d0823

[Cake] [PATCH net-next v11 3/7] sch_cake: Add optional ACK filter

2018-05-15 Thread Toke Høiland-Jørgensen
). Finally, even though we consider the ACK filter to be safer than most, we do not recommend turning it on everywhere: on more symmetrical link bandwidths the effect is negligible at best. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c

[Cake] [PATCH net-next v11 5/7] sch_cake: Add DiffServ handling

2018-05-15 Thread Toke Høiland-Jørgensen
number of configured priority tiers. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 408 +- 1 file changed, 401 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 14622c1

[Cake] [PATCH v8] Add support for cake qdisc

2018-05-15 Thread Toke Høiland-Jørgensen
. sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in the sqm-scripts, with sane defaults and vastly simpler configuration. Cake's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Guido S

[Cake] [PATCH net-next v11 0/7] sched: Add Common Applications Kept Enhanced (cake) qdisc

2018-05-15 Thread Toke Høiland-Jørgensen
e. v2: - Fix kbuild test bot complaint - Clean up the netlink ABI - Fix checkpatch complaints - A few tweaks to the behaviour of cake based on testing carried out while writing the paper. --- Toke Høiland-Jørgensen (7): sched: Add Common Applications Kept Enhanced (cake)

[Cake] [PATCH net-next v11 7/7] sch_cake: Conditionally split GSO segments

2018-05-15 Thread Toke Høiland-Jørgensen
on bandwidth. For this reason, we split GSO segments into their individual packets iff the shaper is active and configured to a bandwidth <= 1 Gbps. Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk> --- net/sched/sch_cake.c | 99 +- 1 fil

Re: [Cake] tc not showing detailed stats

2018-05-20 Thread Toke Høiland-Jørgensen
Toke Høiland-Jørgensen <t...@toke.dk> writes: > Georgios Amanakis <gamana...@gmail.com> writes: > >> This is on x86_64 running 4.16.9. > > OK, that is decidedly odd. I have just spent the last several hours > debugging this, and I'm starting to lean towa

Re: [Cake] tc not showing detailed stats

2018-05-20 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > I am running everything on 4.16.9. > It seems the culprit is sch-cake. > tc-adv@d52fe00 and sch-cake@66e5d6 : detailed stats are printed > tc-adv@d52fe00 and sch-cake@842d7f : details not printed anymore. > > Could it be that the culprit is

Re: [Cake] tc not showing detailed stats

2018-05-20 Thread Toke Høiland-Jørgensen
Georgios Amanakis writes: > This is on x86_64 running 4.16.9. OK, that is decidedly odd. I have just spent the last several hours debugging this, and I'm starting to lean towards this being an unrelated bug in openwrt, or something triggering such a bug. It seems tc doesn't

Re: [Cake] [PATCH net-next v12 3/7] sch_cake: Add optional ACK filter

2018-05-17 Thread Toke Høiland-Jørgensen
Eric Dumazet <eric.duma...@gmail.com> writes: > On 05/16/2018 01:29 PM, Toke Høiland-Jørgensen wrote: >> The ACK filter is an optional feature of CAKE which is designed to improve >> performance on links with very asymmetrical rate limits. On such links >> (which are un

Re: [Cake] [PATCH net-next v12 3/7] sch_cake: Add optional ACK filter

2018-05-17 Thread Toke Høiland-Jørgensen
Eric Dumazet <eric.duma...@gmail.com> writes: > On 05/17/2018 04:23 AM, Toke Høiland-Jørgensen wrote: > >> >> We don't do full parsing of SACKs, no; we were trying to keep things >> simple... We do detect the presence of SACK options, though, and the >>

Re: [Cake] Does the latest cake support "tc filter"?

2018-05-17 Thread Toke Høiland-Jørgensen
Fushan Wen writes: > Hello developers, > I've seen the mail in the netdev mailing list, saying "other tc > filters supported". So can I use "tc filter" to attach specified > traffic to a specified tin without DSCP marks? It's helpful when > dealing with ingress traffic

  1   2   3   4   5   >