Re: [Cake] Diffserv LLT mode

Y via Cake writes: > From: Y > Subject: Re: [Cake] Diffserv LLT mode > To: cake@lists.bufferbloat.net > Date: Sat, 21 Apr 2018 21:40:48 +0900 > > Hi. > > mine stat doen't inclued more. > sad. Did you upgrade the kernel module without

Re: [Cake] Fwd: net-next is OPEN...

Dave Taht writes: > do we consider cake ready this time? I'm not aware of anything outstanding, at least... -Toke ___ Cake mailing list Cake@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/cake

Re: [Cake] A few puzzling Cake results

Jonathan Morton writes: your solution significantly hurts performance in the common case >>> >>> I'm sorry - did someone actually describe such a case? I must have >>> missed it. >> >> I started this whole thread by pointing out that this behaviour results >> in

[Cake] Diffserv LLT mode

Is anyone actually using the LLT diffserv setting? The draft describing it seems to have expired ages ago: https://datatracker.ietf.org/doc/draft-you-tsvwg-latency-loss-tradeoff/ -Toke ___ Cake mailing list Cake@lists.bufferbloat.net

Re: [Cake] net-next is OPEN...

Pete Heist writes: >> On Apr 18, 2018, at 7:43 AM, Pete Heist wrote: >> >> I also think I saw this happen at lower bandwidths as well, when the CPU >> wasn’t loaded. What I’ll do is re-test on the current version I have at, >> say, 50Mbit (or to where load

Re: [Cake] [PATCH net-next v2] Add Common Applications Kept Enhanced (cake) qdisc

Georgios Amanakis writes: > On Tue, Apr 24, 2018 at 11:47 AM, Georgios Amanakis > wrote: >>> >>> Does anyone know if there is a way to do this so the module/builtin >>> split doesn't bite us? >>> >> #ifdef CONFIG_NF_CONNTRACK ?? That is basically what

Re: [Cake] Testing wanted: Statistics API rework

Pete Heist <p...@eventide.io> writes: >> On Apr 24, 2018, at 11:30 PM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >> If someone has time to test it (especially on mips!), that would be >> great; I think we still have a few days left of net-next being o

[Cake] [PATCH ipruote2-next v4] Add support for cake qdisc

. 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 v3] Add Common Applications Kept Enhanced (cake) qdisc

, 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

[Cake] Pre-print of Cake paper available

Last week we submitted an academic paper describing Cake. A pre-print is now available on arXiv: https://arxiv.org/abs/1804.07617 Comments welcome, of course :) -Toke ___ Cake mailing list Cake@lists.bufferbloat.net

[Cake] SKB queue API usage

I've started looking at what changes are needed before Cake can be submitted upstream (see the upstream-4.18 branch of the repo). While looking over the data structures I noticed that struct cake_flow contains pointers to struct sk_buff instread of using the in-kernel struct sk_buff_head queueing

Re: [Cake] Testing variants of the MTU latency scaling

Jonathan Morton writes: >> Based on all this, I propose we change the scaling mechanism so that it >> is only active in egress mode, and change it from 4 MTUs to 2. I'll >> merge Kevin's patch to do this unless someone complains loudly :) > > I suppose that makes enough

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

Sebastian Moeller <moell...@gmx.de> writes: > Hi Toke, > > > >> On Apr 24, 2018, at 10:47, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >> Sebastian Moeller <moell...@gmx.de> writes: >> >>>> On Apr 24, 2018, at 01:01, Pete

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

Sebastian Moeller writes: >> Looking at those threads, they seem to be increasing the number of >> queues. Not sure they need to, but, well, there's nothing in principle >> that says this couldn't be configurable (it is in FQ-CoDel). It would >> need a bit of a reorg of the

Re: [Cake] [PATCH] Remove plain pkt_sched.h dependency

Georgios Amanakis writes: > I just tried an in-tree built using net-next. Aside from that line it > compiles on x86_64 successfully. I will give it a try on my router > later on. Yeah, I was getting to that; but removing that include means the changes have to be imported

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

Pete Heist writes: >> On Apr 24, 2018, at 10:50 AM, Jonathan Morton wrote: >> >>> I think, if we wanted to support the ISP case, that a per-customer *shaper* >>> is more useful. >> >> Yes, I think the technology can be recoded to better suit a >>

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

Sebastian Moeller <moell...@gmx.de> writes: >> On Apr 24, 2018, at 01:01, Pete Heist <p...@eventide.io> wrote: >> >> >>> On Apr 23, 2018, at 10:39 AM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >>> >>> Last week we submitted an a

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

Pete Heist <p...@eventide.io> writes: >> On Apr 23, 2018, at 10:39 AM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >> Last week we submitted an academic paper describing Cake. A pre-print is >> now available on arXiv: https://arxiv.org/abs/1804.0761

Re: [Cake] Testing variants of the MTU latency scaling

Jonas Mårtensson writes: > One thing that is still not clear to me from these results: if I run > cake on an IFB without ingress mode (i.e. the default?), does the MTU > scaling have any impact on TCP download throughput? Odds are that not using ingress mode will

[Cake] [PATCH net-next v2] Add Common Applications Kept Enhanced (cake) qdisc

, 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

[Cake] [PATCH iproute2-next v2] Add support for cake qdisc

r 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 Heist, Georgios Amanakis, and the many other members of the cake@lists.bufferbloat.net m

[Cake] [PATCH iproute2-next v3] Add support for cake qdisc

. 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 iproute2-next v3] Add support for cake qdisc

Stephen Hemminger <step...@networkplumber.org> writes: > On Tue, 24 Apr 2018 14:30:46 +0200 > Toke Høiland-Jørgensen <t...@toke.dk> wrote: > >> +static void cake_print_json_tin(struct tc_cake_tin_stats *tst, uint version) >> +{ >> +open_json_obje

Re: [Cake] [PATCH iproute2-next v3] Add support for cake qdisc

Stephen Hemminger <step...@networkplumber.org> writes: > On Tue, 24 Apr 2018 16:52:57 +0200 > Toke Høiland-Jørgensen <t...@toke.dk> wrote: > >> Well, this is leftover from keeping track of different versions of the >> out-of-tree patch, and we already brok

Re: [Cake] [PATCH net-next v2] Add Common Applications Kept Enhanced (cake) qdisc

Georgios Amanakis <gamana...@gmail.com> writes: > On Tue, 24 Apr 2018 13:44:06 +0200 > Toke Høiland-Jørgensen <t...@toke.dk> wrote: > >> +config NET_SCH_CAKE >> + tristate "Common Applications Kept Enhanced (CAKE)" >> + help >

Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc

Eric Dumazet <eric.duma...@gmail.com> writes: > On 04/25/2018 06:42 AM, Toke Høiland-Jørgensen wrote: >> sch_cake targets the home router use case and is intended to squeeze the >> most bandwidth and latency out of even the slowest ISP links and routers, >> while pres

Re: [Cake] Testing wanted: Statistics API rework

Pete Heist <p...@eventide.io> writes: >> On Apr 25, 2018, at 11:15 AM, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >> >> Pete Heist <p...@eventide.io> writes: >> >>> I requested a re-build over in the Ubiquiti EdgeOS forums. Between >

Re: [Cake] gcc 7.3.1 issue on arch

Jonathan Morton writes: >> On 29 Mar, 2018, at 1:30 am, Bret Towe wrote: >> >> ./include/linux/kernel.h:6:10: fatal error: stdarg.h: No such file or >> directory > > I've started seeing the same error on my PowerPC box, running Gentoo. > It seemed

Re: [Cake] bufferbloat still misunderstood & ignored

Jonathan Morton writes: >> On 30 Mar, 2018, at 11:05 am, Pete Heist wrote: >> >> So this mapping from member (subscriber) to their MACs or IPs would need to >> be configurable somewhere > > Yes, I assumed something like that would be required to assign

Re: [Cake] gcc 7.3.1 issue on arch

Bret Towe writes: > for anyone seeing a compile error like the below on Arch Linux > > CC [M] /root/sch_cake/sch_cake.o > In file included from ./include/linux/list.h:9:0, > from ./include/linux/module.h:9, > from

Re: [Cake] bufferbloat still misunderstood & ignored

Kevin Darbyshire-Bryant via Cake writes: > From: Kevin Darbyshire-Bryant > Subject: bufferbloat still misunderstood & ignored > To: Cake List > Date: Wed, 28 Mar 2018 15:46:47 + > >

Re: [Cake] Compiling under net-next

Toke Høiland-Jørgensen <t...@toke.dk> writes: > George Amanakis <gamana...@gmail.com> writes: > >> It seems the change was introduced here: >> https://patchwork.kernel.org/patch/9671147/ >> >> I drafted the following very simplistic patch, could someb

Re: [Cake] [PATCH 1/2] cake: print_uint format fixes

Kevin Darbyshire-Bryant <ke...@darbyshire-bryant.me.uk> writes: >> On 12 Mar 2018, at 15:11, Stephen Hemminger <step...@networkplumber.org> >> wrote: >> >> On Mon, 12 Mar 2018 10:56:09 +0100 >> Toke Høiland-Jørgensen <t...@toke.dk> wrote: &

Re: [Cake] Compiling under net-next

George Amanakis writes: > It seems the change was introduced here: > https://patchwork.kernel.org/patch/9671147/ > > I drafted the following very simplistic patch, could somebody take a > look at it? LGTM. We may want to actually use the extack feature at some point, but

Re: [Cake] Fwd: Compiling under net-next

Georgios Amanakis writes: > #if LINUX_VERSION_CODE < KERNEL_VERSION(4, 12, 0) > err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy); > -#else > +#elif LINUX_VERSION_CODE < KERNEL_VERSION(4, 16, 0) > err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy,

Re: [Cake] eliminating link_ms and increasing packets to 64 bits

Dave Taht writes: > fprintf(f, " pkts"); > FOR_EACH_TIN(stnc, tst, i) > - fprintf(f, " %12u", tst->sent.packets); > + fprintf(f, " %12llu", tst->sent.packets); > fprintf(f, "\n"); Presumably this can potentially break column

Re: [Cake] eliminating link_ms and increasing packets to 64 bits

Dave Taht writes: > the preceding space handles column alignment. the %12 is probably > going to be misleading. The space separates columns, the %12 aligns them. So it will break alignment. But as I said, mostly a cosmetic issue, so probably not something we should spend a

Re: [Cake] [PATCH] q_cake: Update xstats format to use per-tin structure

Toke Høiland-Jørgensen <t...@toke.dk> writes: > Jonathan Morton <chromati...@gmail.com> writes: > >>> On 11 Feb, 2018, at 7:26 pm, Toke Høiland-Jørgensen <t...@toke.dk> wrote: >>> >>> This updates tc to understand the updated cake x

Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc

David Miller <da...@davemloft.net> writes: > From: Toke Høiland-Jørgensen <t...@toke.dk> > Date: Wed, 25 Apr 2018 15:42:48 +0200 > >> +static void *cake_zalloc(size_t sz) >> +{ >> +void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); >> + >&

Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc

Eric Dumazet <eric.duma...@gmail.com> writes: > On 04/25/2018 11:34 AM, Toke Høiland-Jørgensen wrote: >> Eric Dumazet <eric.duma...@gmail.com> writes: >> >>> On 04/25/2018 09:52 AM, Jonathan Morton wrote: >>>>> We can see here the high

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

David Lang <da...@lang.hm> writes: > On Tue, 24 Apr 2018, Toke Høiland-Jørgensen wrote: > >> Pete Heist <p...@eventide.io> writes: >> >>>> On Apr 24, 2018, at 7:58 AM, Jonathan Morton <chromati...@gmail.com> wrote: >>>> >>>&g

Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc

Eric Dumazet writes: > On 04/25/2018 09:52 AM, Jonathan Morton wrote: >>> We can see here the high cost of forcing software GSO :/ >>> >>> Really, this should be done only : >>> 1) If requested by the admin ( tc gso ) >>> >>> 2) If packet size is above a

[Cake] CAKE upstreaming - testers wanted, ACK filtering rescuers needed

For those who have not been following the discussion on the upstreaming patches, here's an update: - I've just pushed patches to only split GSO packets when shaping below one gigabit; and hopefully made the overhead compensation code deal gracefully with GSO packets if someone for some reason

[Cake] Linux 4.19 released...

...which means that CAKE is now officially in upstream Linux. Woohoo! It's even listed at the top of the "Coolest features" list on the kernelnewbies overview: https://kernelnewbies.org/Linux_4.19#Better_networking_experience_with_the_CAKE_queue_management_algorithm Congratulations, and thanks,

Re: [Cake] [Cerowrt-devel] apu2 sqm/htb issue + a minor win for speeding up fq_codel itself

Dave Taht writes: > Well, fq_codel does use a lot less cpu but everything seems slower I don't suppose 18.06 enables any of the SPECTRE mitigations (was that an issue on ARM)? -Toke ___ Cake mailing list Cake@lists.bufferbloat.net

Re: [Cake] [Cerowrt-devel] apu2 sqm/htb issue + a minor win for speeding up fq_codel itself

Jonathan Morton writes: > I'm not familiar with precisely what mitigations are now in use on > ARM. I am however certain that, on a device running only trustworthy > code (ie. not running a Web browser), mitigating Spectre is > unnecessary. If an attacker gets into a position to exploit it, he's

Re: [Cake] arp flow dissector

Jonathan Morton writes: >> On 2 Sep, 2018, at 10:37 pm, Dave Taht wrote: >> >> Didn't know we had this now. >> >> https://www.spinics.net/lists/netdev/msg413986.html > > Does that automagically give Cake an idea of the IP addresses > associated with the packet, for host-fairness purposes? If

[Cake] [PATCH] MAINTAINERS: Add entry for CAKE qdisc

We would like the existing community to be kept in the loop for any new developments on CAKE; and I certainly plan to keep maintaining it. Reflect this in MAINTAINERS. Signed-off-by: Toke Høiland-Jørgensen --- MAINTAINERS | 6 ++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 4, 2019, at 11:34 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >> This basically means that we can't use CAKE as a leaf qdisc with GSO >> splitting as it stands currently. I *think* the solution is for CAKE to

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

> Jon, is there anything I can check by instrumenting the code somewhere > specific? Is there any way you could test with a bulk UDP flow? I'm wondering whether this is a second-order effect where TCP ACKs are limited in a way that cause the imbalance? Are you using ACK compression? -Toke

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > Ok, that fixes the compiler warnings, but I get this now. Same as > before it’s repeated until reboot, stack sometimes changes but I > always see sch_hfsc.c:1427 at the beginning: Hmm, that's odd. Could you try adding this debugging line in adjust_parent_qlen(), right

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

On 5 January 2019 11:44:44 CET, Jonathan Morton wrote: >> On 5 Jan, 2019, at 12:34 am, Toke Høiland-Jørgensen >wrote: >> >> This basically means that we can't use CAKE as a leaf qdisc with GSO >> splitting as it stands currently. I *think* the solution is for CAK

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 5, 2019, at 2:35 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >>>> On Jan 5, 2019, at 2:10 PM, Toke Høiland-Jørgensen wrote: >>>> >>>> Hmm, that's odd. Could you try adding this debug

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > Quick update to the trace because I had to apply the patch manually > and missed one line to remove (qdisc_tree_reduce_backlog...), just so > it doesn’t through off the addresses for you, but it still does the > same thing: Ah, my bad; you need to replace

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 5, 2019, at 2:10 PM, Toke Høiland-Jørgensen wrote: >> >> Hmm, that's odd. Could you try adding this debugging line in >> adjust_parent_qlen(), right before the sch->q.qlen += n line: >> >> net_info_ratelimited(&q

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > That first bug report looks decidedly similar to mine, but Toke would > have to comment on the specifics. So far I see the patch to > sch_codel.c you mentioned and another two-liner to remove the warning > in hfsc.c (https://patchwork.ozlabs.org/patch/933611/). It would be >

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 5, 2019, at 9:10 PM, Toke Høiland-Jørgensen wrote: >> >> Well, it's the same WARN_ON(), and if that patch had been applied, >> debugging our issue would have been a lot harder, I think. > > Yikes, this is what I mean. I’d

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 5, 2019, at 11:27 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >>>> On Jan 5, 2019, at 9:10 PM, Toke Høiland-Jørgensen wrote: >>>> >>>> Well, it's the same WARN_ON(), and if that patc

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > Lastly, is using cake as a leaf to htb risky until a fix is made? I’ve > been doing that for a while without any apparent issues, though I’m > hesitating now to try that in a production environment. Hmm, that's a good question. I would expect so; but I would also expect the

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

Jonathan Morton writes: >>> Yes, exactly. Would be interesting to hear what Jonathan, Toke and >>> others think. I want to see if fairness is preserved in this case with >>> sparse flows only. Could flent do this? >> >> Well, sparse flows are (by definition) not building a queue, so it >>

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

Sebastian Moeller writes: > Hi Toke, > >> On Jan 18, 2019, at 14:33, Toke Høiland-Jørgensen wrote: >> >> Georgios Amanakis writes: >> >>> Yes, exactly. Would be interesting to hear what Jonathan, Toke and >>> others think. I want to see if fa

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

George Amanakis writes: > A better version of the patch for testing. So basically, you're changing the host fairness algorithm to only consider bulk flows instead of all active flows to that host, right? Seems reasonable to me. Jonathan, any opinion? -Toke

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

Georgios Amanakis writes: > Yes, exactly. Would be interesting to hear what Jonathan, Toke and > others think. I want to see if fairness is preserved in this case with > sparse flows only. Could flent do this? Well, sparse flows are (by definition) not building a queue, so it doesn't really

[Cake] Defending my thesis on Friday - live stream available

Hey everyone I'm defending my PhD thesis this Friday (Nov 23rd), which contains content relevant to all three lists (hence the three-way cross post). In case anyone is interested in watching, I'm setting up a live stream on Youtube, see link below. The defence starts at 09:15 CET (UTC+1), but

Re: [Cake] Defending my thesis on Friday - live stream available

Georgios Amanakis writes: > Thank you very much for doing this, Toke! All the best of luck on > Friday!!! Thanks! :) -Toke ___ Cake mailing list Cake@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/cake

Re: [Cake] Emulating Bufferbloat

Fabian Ruffy writes: > Hello, > > this is a somewhat esoteric question. I am trying to actually force > bufferbloat > in an emulation setup I am using. I set up a dumbbell topology and push > traffic > through it, causing congestion at the central link. I use this setup to > compare >

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > Your patch in the latest kernels looks simpler. Bringing the patch > back to prior kernel versions would be appreciated, but I can > understand how 3.16 becomes less and less relevant as time goes on, > although, it’s not at end of life yet. :) Could you try the latest git

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 6, 2019, at 9:56 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >>> Lastly, is using cake as a leaf to htb risky until a fix is made? I’ve >>> been doing that for a while without any apparent is

[Cake] [PATCH 1/4] sched: Avoid dereferencing skb pointer after child enqueue

From: Toke Høiland-Jørgensen Parent qdiscs may dereference the pointer to the enqueued skb after enqueue. However, both CAKE and TBF call consume_skb() on the original skb when splitting GSO packets, leading to a potential use-after-free in the parent. Fix this by avoiding dereferencing the skb

[Cake] [PATCH 4/4] sch_cake: Correctly update parent qlen when splitting GSO packets

From: Toke Høiland-Jørgensen To ensure parent qdiscs have the same notion of the number of enqueued packets even after splitting a GSO packet, update the qdisc tree with the number of packets that was added due to the split. Signed-off-by: Toke Høiland-Jørgensen --- net/sched/sch_cake.c | 5

[Cake] [PATCH 3/4] sch_api: Allow reducing queue backlog by a negative value

From: Toke Høiland-Jørgensen With GSO splitting in sch_cake, we can decrease as well as increase the qlen. To make it possible to signal this up the qdisc tree, change qdisc_tree_reduce_backlog() to accept signed integer values as the number of packets and bytes to reduce the backlog by. Signed

[Cake] [PATCH 0/4] sched: Fix qdisc interactions exposed by using sch_cake as a leaf qdisc

the report, I also noticed that several qdiscs would dereference the skb pointer after dequeue, which is potentially problematic since the GSO splitting code also frees the original skb. See the individual patches in the series for details. Toke Høiland-Jørgensen (4): sched: Avoid dereferencing skb

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 4, 2019, at 10:34 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >>> Ok, the lockup goes away if you use no-split-gso on the cake qdiscs for the >>> default traffic (noted below in the drr and hfsc cases

Re: [Cake] dual-src/dsthost unfairness, only with bi-directional traffic

Pete Heist writes: >> On Jan 3, 2019, at 12:03 PM, Toke Høiland-Jørgensen wrote: >> >>> Jon, is there anything I can check by instrumenting the code somewhere >>> specific? >> >> Is there any way you could test with a bulk UDP flow? I'm wondering >

Re: [Cake] [PATCH 0/4] sched: Fix qdisc interactions exposed by using sch_cake as a leaf qdisc

David Miller writes: > From: Toke Høiland-Jørgensen > Date: Mon, 7 Jan 2019 20:47:29 +0100 > >> This series fixes a couple of issues exposed by running sch_cake as a >> leaf qdisc in an HFSC tree, which were discovered and reported by Pete >> Heist. The interaction b

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: >> On Jan 8, 2019, at 11:27 PM, Toke Høiland-Jørgensen wrote: >> >> Pete Heist writes: >> >>> Your patch in the latest kernels looks simpler. Bringing the patch >>> back to prior kernel versions would be appreciated, but I can >

Re: [Cake] [PATCH 1/4] sched: Avoid dereferencing skb pointer after child enqueue

Cong Wang writes: > On Mon, Jan 7, 2019 at 11:50 AM Toke Høiland-Jørgensen wrote: >> @@ -1254,7 +1256,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct >> Qdisc *sch, >> if (cl->qdisc->q.qlen != 1) { >> if (unlikely(skb

Re: [Cake] cake infinite loop(?) with hfsc on one-armed router

Pete Heist writes: > Ok, the lockup goes away if you use no-split-gso on the cake qdiscs for the > default traffic (noted below in the drr and hfsc cases with "!!! must use > no-split-gso here !!!"). Only I’d like my 600 μs back. :) > > This smells of a bug Toke fixed on Sep 12, 2018 in >

Re: [Cake] Munin-Plugins

Ruben writes: > Hey guys, > > I've already mentioned this in a response to dtaht on GitHub, but here > again for everyone: > > I was wondering if it's possible to extend the tin statistics by > packets for backlog. Why do you need packets when there's already bytes? > Also I haven't found

Re: [Cake] [PATCH net] gso_segment: Reset skb->mac_len after modifying network header

On 13 September 2018 16:11:18 CEST, Eric Dumazet wrote: > > >On 09/11/2018 03:19 PM, Toke Høiland-Jørgensen wrote: >> When splitting a GSO segment that consists of encapsulated packets, >the >> skb->mac_len of the segments can end up being set wrong, causing >pack

[Cake] [PATCH net v2] gso_segment: Reset skb->mac_len after modifying network header

Pv4 and IPv6 gso_segment handlers, after they modify the network_header. Many thanks to Eric Dumazet for his help in identifying the cause of the bug. Acked-by: Dave Taht Reviewed-by: Eric Dumazet Signed-off-by: Toke Høiland-Jørgensen --- v2: - Properly credit Eric for his help - Add review and

[Cake] [PATCH iproute2] q_cake: Also print nonat, nowash and no-ack-filter keywords

Similar to the previous patch for no-split-gso, the negative keywords for 'nat', 'wash' and 'ack-filter' were not printed either. Add those well. Signed-off-by: Toke Høiland-Jørgensen --- tc/q_cake.c | 6 +- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tc/q_cake.c b/tc

Re: [Cake] Munin-Plugins

Ruben writes: > Hey Toke, > > Am 13.09.2018 21:12 schrieb Toke Høiland-Jørgensen : > > > Ruben writes: > > > Hey Toke, > > > > Thanks for your fast response! > > > > Am 13.09.2018 12:27 schrieb Toke Høiland-Jø

Re: [Cake] Munin-Plugins

Ruben writes: > Hey Toke, > > Thanks for your fast response! > > Am 13.09.2018 12:27 schrieb Toke Høiland-Jørgensen : > > > Ruben writes: > > > Hey guys, > > > > I've already mentioned this in a response to dtaht on GitHub, but here

Re: [Cake] SCE/CAKE coding curiosities

Kevin Darbyshire-Bryant writes: > Ahoy there team Bufferboat :-) > > I’ve been looking at the new SCE related code and a few questions have fallen > out of the brain cell. > > 1) > https://github.com/dtaht/sch_cake/blob/47d821f89f39c1b2216d6f65b014f609e46fc57c/sce.h#L50 > Curious as to why

[Cake] [PATCH iproute2] q_cake: Add support for setting the fwmark option

This adds support for the newly added fwmark option to CAKE, which allows overriding the tin selection from the per-packet firewall marks. The fwmark field is a bitmask that is applied to the fwmark to select the tin. Signed-off-by: Toke Høiland-Jørgensen --- man/man8/tc-cake.8 | 16

[Cake] [PATCH net 1/2] sch_cake: Use tc_skb_protocol() helper for getting packet protocol

We shouldn't be using skb->protocol directly as that will miss cases with hardware-accelerated VLAN tags. Use the helper instead to get the right protocol number. Reported-by: Kevin Darbyshire-Bryant Signed-off-by: Toke Høiland-Jørgensen --- net/sched/sch_cake.c |2 +- 1 file changed

[Cake] [PATCH net 2/2] sch_cake: Make sure we can write the IP header before changing DSCP bits

There is not actually any guarantee that the IP headers are valid before we access the DSCP bits of the packets. Fix this using the same approach taken in sch_dsmark. Reported-by: Kevin Darbyshire-Bryant Signed-off-by: Toke Høiland-Jørgensen --- net/sched/sch_cake.c | 11 +++ 1 file

[Cake] [PATCH net 0/2] sched: A few small fixes for sch_cake

if that's OK with you? -Toke --- Toke Høiland-Jørgensen (2): sch_cake: Use tc_skb_protocol() helper for getting packet protocol sch_cake: Make sure we can write the IP header before changing DSCP bits net/sched/sch_cake.c | 13 - 1 file changed, 12 insertions(+), 1

Re: [Cake] [PATCH net 2/2] sch_cake: Make sure we can write the IP header before changing DSCP bits

Stephen Hemminger writes: > On Thu, 04 Apr 2019 22:44:33 +0200 > Toke Høiland-Jørgensen wrote: > >> Stephen Hemminger writes: >> >> > On Thu, 04 Apr 2019 15:01:33 +0200 >> > Toke Høiland-Jørgensen wrote: >> > >> >>

[Cake] [PATCH for-4.19 2/3] sch_cake: Use tc_skb_protocol() helper for getting packet protocol

Commit bbd669a868bba591ffd38b7bc75a7b361bb54b04 upstream. We shouldn't be using skb->protocol directly as that will miss cases with hardware-accelerated VLAN tags. Use the helper instead to get the right protocol number. Reported-by: Kevin Darbyshire-Bryant Signed-off-by: Toke Høiland-Jørgen

[Cake] [PATCH for-4.19 0/3] Backport of series: 'sched: A few small fixes for sch_cake' from 5.1

Hi Greg This series contains backports for a couple of fixes to sch_cake that was just merged for 5.1. This series backports an earlier refactoring commit, which makes the fixes themselves apply cleanly from upstream. -Toke --- Toke Høiland-Jørgensen (3): sch_cake: Simplify logic

Re: [Cake] [PATCH for-4.19 0/3] Backport of series: 'sched: A few small fixes for sch_cake' from 5.1

Greg Kroah-Hartman writes: > On Fri, Apr 05, 2019 at 02:13:18PM +0200, Toke Høiland-Jørgensen wrote: >> Greg Kroah-Hartman writes: >> >> > On Fri, Apr 05, 2019 at 12:28:21PM +0200, Toke Høiland-Jørgensen wrote: >> >> Hi Greg >> >> >> &

Re: [Cake] [PATCH net 2/2] sch_cake: Make sure we can write the IP header before changing DSCP bits

Stephen Hemminger writes: > On Thu, 04 Apr 2019 15:01:33 +0200 > Toke Høiland-Jørgensen wrote: > >> static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) >> { >> +int wlen = skb_network_offset(skb); > > In theory this could be negative, you

Re: [Cake] Using firewall connmarks as tin selectors

> I also equally aware that this is ‘creeping featuritis’ and doing > nothing to speed cake up… Yeah, this is the crux of the issue, really: it's a tradeoff between ease of use and featuritis. Now in this case the actual impact is a single check it might actually be acceptable > actually I may

Re: [Cake] Using firewall connmarks as tin selectors

Kevin Darbyshire-Bryant writes: > How unpopular would the idea of having cake look at skb->mark directly be? > > https://github.com/ldir-EDB0/sch_cake/commit/64d0e6ac9368a271221db888ab91a367fcd37ae1 > > https://github.com/ldir-EDB0/tc-adv/commit/4f16ae5d588d44f8a5c83fe2f2b7dcad97843cbc Hmm, not

Re: [Cake] Using firewall connmarks as tin selectors

Kevin Darbyshire-Bryant writes: >> On 28 Feb 2019, at 09:54, Toke Høiland-Jørgensen wrote: >> >>> I also equally aware that this is ‘creeping featuritis’ and doing >>> nothing to speed cake up… >> >> Yeah, this is the crux of the issue, real

Re: [Cake] Using firewall connmarks as tin selectors

Kevin Darbyshire-Bryant writes: >> On 3 Mar 2019, at 12:22, John Sager wrote: >> >> If you are going to do that, I would suggest using a few of the upper bits >> of the 32-bit fwmark/connmark space available, rather than the lowest bits. >> Then that would allow to use fwmarks other purposes,

Re: [Cake] Using firewall connmarks as tin selectors

Kevin Darbyshire-Bryant writes: >> On 4 Mar 2019, at 08:39, Pete Heist wrote: >> >> >>> On Mar 3, 2019, at 12:52 PM, Kevin Darbyshire-Bryant >>> wrote: >>> >>> The very bad idea: >>> >>> And it’s bad ‘cos it’s sort of incompatible with the existing fwmark >>> implementation as described

Re: [Cake] Using firewall connmarks as tin selectors

Kevin Darbyshire-Bryant writes: >> On 4 Mar 2019, at 11:17, Toke Høiland-Jørgensen wrote: >> >> Kevin Darbyshire-Bryant writes: >> >>>> On 4 Mar 2019, at 08:39, Pete Heist wrote: >>>> >>>> >>>>> On Mar 3, 2019, at

<    1   2   3   4   5   6   >