diff options
| -rw-r--r-- | docs/configuration/interfaces/ethernet.rst | 28 | ||||
| -rw-r--r-- | docs/configuration/trafficpolicy/index.rst | 69 |
2 files changed, 91 insertions, 6 deletions
diff --git a/docs/configuration/interfaces/ethernet.rst b/docs/configuration/interfaces/ethernet.rst index bbf52112..a1151fd4 100644 --- a/docs/configuration/interfaces/ethernet.rst +++ b/docs/configuration/interfaces/ethernet.rst @@ -61,6 +61,22 @@ Offloading Enable different types of hardware offloading on the given NIC. + :abbr:`LRO (Large Receive Offload)` is a technique designed to boost the + efficiency of how your computer's network interface card (NIC) processes + incoming network traffic. Typically, network data arrives in smaller chunks + called packets. Processing each packet individually consumes CPU (central + processing unit) resources. Lots of small packets can lead to a performance + bottleneck. Instead of handing the CPU each packet as it comes in, LRO + instructs the NIC to combine multiple incoming packets into a single, larger + packet. This larger packet is then passed to the CPU for processing. + + .. note:: Under some circumstances, LRO is known to modify the packet headers + of forwarded traffic, which breaks the end-to-end principle of computer + networking. LRO is also only able to offload TCP segments encapsulated in + IPv4 packets. Due to these limitations, it is recommended to use GRO + (Generic Receive Offload) where possible. More information on the + limitations of LRO can be found here: https://lwn.net/Articles/358910/ + :abbr:`GSO (Generic Segmentation Offload)` is a pure software offload that is meant to deal with cases where device drivers cannot perform the offloads described above. What occurs in GSO is that a given skbuff will have its data @@ -87,13 +103,13 @@ Offloading placing the packet on the desired CPU's backlog queue and waking up the CPU for processing. RPS has some advantages over RSS: - - it can be used with any NIC, - - software filters can easily be added to hash over new protocols, - - it does not increase hardware device interrupt rate (although it does - introduce inter-processor interrupts (IPIs)). + - it can be used with any NIC + - software filters can easily be added to hash over new protocols + - it does not increase hardware device interrupt rate, although it does + introduce inter-processor interrupts (IPIs) - .. note:: In order to use TSO/LRO with VMXNET3 adaters one must also enable - the SG offloading option. + .. note:: In order to use TSO/LRO with VMXNET3 adapters, the SG offloading + option must also be enabled. Authentication (EAPoL) ---------------------- diff --git a/docs/configuration/trafficpolicy/index.rst b/docs/configuration/trafficpolicy/index.rst index 3463592f..ed63b21f 100644 --- a/docs/configuration/trafficpolicy/index.rst +++ b/docs/configuration/trafficpolicy/index.rst @@ -1145,6 +1145,74 @@ A simple example of Shaper using priorities. set qos policy shaper MY-HTB default priority '7' set qos policy shaper MY-HTB default queue-type 'fair-queue' +.. _CAKE: + +CAKE +------ + +| **Queueing discipline:** Deficit mode. +| **Applies to:** Outbound traffic. + +`Common Applications Kept Enhanced`_ (CAKE) is a comprehensive queue management +system, implemented as a queue discipline (qdisc) for the Linux kernel. It is +designed to replace and improve upon the complex hierarchy of simple qdiscs +presently required to effectively tackle the bufferbloat problem at the network +edge. + +.. cfgcmd:: set qos policy cake <text> bandwidth <value> + + Set the shaper bandwidth, either as an explicit bitrate or a percentage + of the interface bandwidth. + +.. cfgcmd:: set qos policy cake <text> description + + Set a description for the shaper. + +.. cfgcmd:: set qos policy cake <text> flow-isolation blind + + Disables flow isolation, all traffic passes through a single queue. + +.. cfgcmd:: set qos policy cake <text> flow-isolation dst-host + + Flows are defined only by destination address. + +.. cfgcmd:: set qos policy cake <text> flow-isolation dual-dst-host + + Flows are defined by the 5-tuple. Fairness is applied first over destination + addresses, then over individual flows. + +.. cfgcmd:: set qos policy cake <text> flow-isolation dual-src-host + + Flows are defined by the 5-tuple. Fairness is applied first over source + addresses, then over individual flows. + +.. cfgcmd:: set qos policy cake <text> flow-isolation flow + + Flows are defined by the entire 5-tuple (source IP address, source port, + destination IP address, destination port, transport protocol). + +.. cfgcmd:: set qos policy cake <text> flow-isolation host + + Flows are defined by source-destination host pairs. + +.. cfgcmd:: set qos policy cake <text> flow-isolation nat + + Perform NAT lookup before applying flow-isolation rules. + +.. cfgcmd:: set qos policy cake <text> flow-isolation src-host + + Flows are defined only by source address. + +.. cfgcmd:: set qos policy cake <text> flow-isolation triple-isolate + + **(Default)** Flows are defined by the 5-tuple, fairness is applied over source and + destination addresses and also over individual flows. + +.. cfgcmd:: set qos policy cake <text> rtt + + Defines the round-trip time used for active queue management (AQM) in + milliseconds. The default value is 100. + Applying a traffic policy ========================= @@ -1220,5 +1288,6 @@ That is how it is possible to do the so-called "ingress shaping". .. _tocken bucket: https://en.wikipedia.org/wiki/Token_bucket .. _HFSC: https://en.wikipedia.org/wiki/Hierarchical_fair-service_curve .. _Intermediate Functional Block: https://www.linuxfoundation.org/collaborate/workgroups/networking/ifb +.. _Common Applications Kept Enhanced: https://www.bufferbloat.net/projects/codel/wiki/Cake/ .. start_vyoslinter |