On Mon, May 21, 2018 at 10:35:58PM +0200, Toke Høiland-Jørgensen wrote:
> +static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff
> *skb)
> +{
> + const struct skb_shared_info *shinfo = skb_shinfo(skb);
> + unsigned int hdr_len, last_len = 0;
> + u32 off = skb_network
[Cc'ing netfilter-devel@ for awareness]
On Mon, May 21, 2018 at 10:35:58PM +0200, Toke Høiland-Jørgensen wrote:
> When CAKE is deployed on a gateway that also performs NAT (which is a
> common deployment mode), the host fairness mechanism cannot distinguish
> internal hosts from each other, and so
On 05/21/2018 01:35 PM, Toke Høiland-Jørgensen wrote:
> +
> + /* 3 reserved flags must be unset to avoid future breakage
> + * ECE/CWR/NS can be safely ignored
> + * ACK must be set
> + * All other flags URG/PSH/RST/SYN/FIN must be unset
> + * 0x0FFF = all TCP flags (
When CAKE is deployed on a gateway that also performs NAT (which is a
common deployment mode), the host fairness mechanism cannot distinguish
internal hosts from each other, and so fails to work correctly.
To fix this, we add an optional NAT awareness mode, which will query the
kernel conntrack me
This commit adds configurable overhead compensation support to the rate
shaper. With this feature, userspace can configure the actual bottleneck
link overhead and encapsulation mode used, which will be used by the shaper
to calculate the precise duration of each packet on the wire.
This feature is
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 presenting an API simple enough that even an ISP can configure it.
Example of use on a cable ISP uplink:
tc qdisc add dev eth0 cake bandwidth 20
At lower bandwidths, the transmission time of a single GSO segment can add
an unacceptable amount of latency due to HOL blocking. Furthermore, with a
software shaper, any tuning mechanism employed by the kernel to control the
maximum size of GSO segments is thrown off by the artificial limit on
ban
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 unfortunately quite prevalent, especially for DSL and cable
subscribers), the downstream throughput can be limited by the number of
ACKs capab
This adds support for DiffServ-based priority queueing to CAKE. If the
shaper is in use, each priority tier gets its own virtual clock, which
limits that tier's rate to a fraction of the overall shaped rate, to
discourage trying to game the priority mechanism.
CAKE defaults to a simple, three-tier
The ingress mode is meant to be enabled when CAKE runs downlink of the
actual bottleneck (such as on an IFB device). The mode changes the shaper
to also account dropped packets to the shaped rate, as these have already
traversed the bottleneck.
Enabling ingress mode will also tune the AQM to alway
This patch series adds the CAKE qdisc, and has been split up to ease
review.
I have attempted to split out each configurable feature into its own patch.
The first commit adds the base shaper and packet scheduler, while
subsequent commits add the optional features. The full userspace API and
most d
On 05/21/2018 11:08 AM, Eric Dumazet wrote:
>
>
> On 05/21/2018 10:35 AM, Toke Høiland-Jørgensen wrote:
>
>> Ah yes, sequence number wrapping. I was thinking I needed to deal with
>> that, and then got sidetracked and forgot about it. Will fix.
>>
>> Other than that, do you agree that this app
On 05/21/2018 10:35 AM, Toke Høiland-Jørgensen wrote:
> Ah yes, sequence number wrapping. I was thinking I needed to deal with
> that, and then got sidetracked and forgot about it. Will fix.
>
> Other than that, do you agree that this approach to SACK and header
> handling can work?
Unfortunat
Eric Dumazet writes:
> On 05/21/2018 09:24 AM, Toke Høiland-Jørgensen wrote:
>
>> +while (oplen_tmp >= 8) {
>> +u32 right_b = get_unaligned_be32(sack_tmp + 4);
>> +u32 left_b = get_unaligned_be32(sack_tmp);
>> +
>> +if (left_
On 05/21/2018 09:24 AM, Toke Høiland-Jørgensen wrote:
> + while (oplen_tmp >= 8) {
> + u32 right_b = get_unaligned_be32(sack_tmp + 4);
> + u32 left_b = get_unaligned_be32(sack_tmp);
> +
> + if (left_b >= right_b)
> +
At lower bandwidths, the transmission time of a single GSO segment can add
an unacceptable amount of latency due to HOL blocking. Furthermore, with a
software shaper, any tuning mechanism employed by the kernel to control the
maximum size of GSO segments is thrown off by the artificial limit on
ban
This patch series adds the CAKE qdisc, and has been split up to ease
review.
I have attempted to split out each configurable feature into its own patch.
The first commit adds the base shaper and packet scheduler, while
subsequent commits add the optional features. The full userspace API and
most d
This adds support for DiffServ-based priority queueing to CAKE. If the
shaper is in use, each priority tier gets its own virtual clock, which
limits that tier's rate to a fraction of the overall shaped rate, to
discourage trying to game the priority mechanism.
CAKE defaults to a simple, three-tier
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 presenting an API simple enough that even an ISP can configure it.
Example of use on a cable ISP uplink:
tc qdisc add dev eth0 cake bandwidth 20
This commit adds configurable overhead compensation support to the rate
shaper. With this feature, userspace can configure the actual bottleneck
link overhead and encapsulation mode used, which will be used by the shaper
to calculate the precise duration of each packet on the wire.
This feature is
When CAKE is deployed on a gateway that also performs NAT (which is a
common deployment mode), the host fairness mechanism cannot distinguish
internal hosts from each other, and so fails to work correctly.
To fix this, we add an optional NAT awareness mode, which will query the
kernel conntrack me
The ingress mode is meant to be enabled when CAKE runs downlink of the
actual bottleneck (such as on an IFB device). The mode changes the shaper
to also account dropped packets to the shaped rate, as these have already
traversed the bottleneck.
Enabling ingress mode will also tune the AQM to alway
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 unfortunately quite prevalent, especially for DSL and cable
subscribers), the downstream throughput can be limited by the number of
ACKs capab
Georgios Amanakis writes:
> Of course you are right. I was using archlinux's build system which
> produces the bug somehow. If I compile directly from the source everything
> works normal.
>
> I am sorry for the mess this caused.
No worries. We are still debugging another issue like it on openwr
Of course you are right. I was using archlinux's build system which
produces the bug somehow. If I compile directly from the source everything
works normal.
I am sorry for the mess this caused.
George
On Mon, May 21, 2018, 10:00 AM Toke Høiland-Jørgensen wrote:
> Georgios Amanakis writes:
>
Georgios Amanakis writes:
> I am well aware of that :)
> On my system though with tc-adv@aa554002 and sch_cake/cobalt@842d7f0
> it doesn't produce any detailed stats:
Hmm, the thing is that I can reproduce your error if I use commit
d52fe0077637caa1e3a4b1242d2bf935929b8275 in tc-adv I can reprod
26 matches
Mail list logo
