--- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -934,4 +934,118 @@ enum { #define TCA_CBS_MAX (__TCA_CBS_MAX - 1) +/* CAKE */ +enum { + TCA_CAKE_UNSPEC, + TCA_CAKE_PAD, + TCA_CAKE_BASE_RATE64, + TCA_CAKE_DIFFSERV_MODE, + TCA_CAKE_ATM, + TCA_CAKE_FLOW_MODE, + TCA_CAKE_OVERHEAD, + TCA_CAKE_RTT, + TCA_CAKE_TARGET, + TCA_CAKE_AUTORATE, + TCA_CAKE_MEMORY, + TCA_CAKE_NAT, + TCA_CAKE_RAW, // was _ETHERNET + TCA_CAKE_WASH, + TCA_CAKE_MPU, + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, + __TCA_CAKE_MAX +}; +#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) + +enum { + __TCA_CAKE_STATS_INVALID, + TCA_CAKE_STATS_PAD, + TCA_CAKE_STATS_CAPACITY_ESTIMATE64, + TCA_CAKE_STATS_MEMORY_LIMIT, + TCA_CAKE_STATS_MEMORY_USED, + TCA_CAKE_STATS_AVG_NETOFF, + TCA_CAKE_STATS_MIN_NETLEN, + TCA_CAKE_STATS_MAX_NETLEN, + TCA_CAKE_STATS_MIN_ADJLEN, + TCA_CAKE_STATS_MAX_ADJLEN, + TCA_CAKE_STATS_TIN_STATS, + TCA_CAKE_STATS_DEFICIT, + TCA_CAKE_STATS_COBALT_COUNT, + TCA_CAKE_STATS_DROPPING, + TCA_CAKE_STATS_DROP_NEXT_US, + TCA_CAKE_STATS_P_DROP, + TCA_CAKE_STATS_BLUE_TIMER_US, + __TCA_CAKE_STATS_MAX +}; +#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) + +enum { + __TCA_CAKE_TIN_STATS_INVALID, + TCA_CAKE_TIN_STATS_PAD, + TCA_CAKE_TIN_STATS_SENT_PACKETS, + TCA_CAKE_TIN_STATS_SENT_BYTES64, + TCA_CAKE_TIN_STATS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS, + TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64, + TCA_CAKE_TIN_STATS_BACKLOG_PACKETS, + TCA_CAKE_TIN_STATS_BACKLOG_BYTES, + TCA_CAKE_TIN_STATS_THRESHOLD_RATE64, + TCA_CAKE_TIN_STATS_TARGET_US, + TCA_CAKE_TIN_STATS_INTERVAL_US, + TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS, + TCA_CAKE_TIN_STATS_WAY_MISSES, + TCA_CAKE_TIN_STATS_WAY_COLLISIONS, + TCA_CAKE_TIN_STATS_PEAK_DELAY_US, + TCA_CAKE_TIN_STATS_AVG_DELAY_US, + TCA_CAKE_TIN_STATS_BASE_DELAY_US, + TCA_CAKE_TIN_STATS_SPARSE_FLOWS, + TCA_CAKE_TIN_STATS_BULK_FLOWS, + TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS, + TCA_CAKE_TIN_STATS_MAX_SKBLEN, + TCA_CAKE_TIN_STATS_FLOW_QUANTUM, + __TCA_CAKE_TIN_STATS_MAX +}; +#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1) +#define TC_CAKE_MAX_TINS (8) + +enum { + CAKE_FLOW_NONE = 0, + CAKE_FLOW_SRC_IP, + CAKE_FLOW_DST_IP, + CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */ + CAKE_FLOW_FLOWS, + CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */ + CAKE_FLOW_MAX, +}; + +enum { + CAKE_DIFFSERV_DIFFSERV3 = 0, + CAKE_DIFFSERV_DIFFSERV4, + CAKE_DIFFSERV_DIFFSERV8, + CAKE_DIFFSERV_BESTEFFORT, + CAKE_DIFFSERV_PRECEDENCE, + CAKE_DIFFSERV_MAX +}; + +enum { + CAKE_ACK_NONE = 0, + CAKE_ACK_FILTER, + CAKE_ACK_AGGRESSIVE, + CAKE_ACK_MAX +}; + +enum { + CAKE_ATM_NONE = 0, + CAKE_ATM_ATM, + CAKE_ATM_PTM, + CAKE_ATM_MAX +}; + + #endif --- /dev/null +++ b/man/man8/tc-cake.8 @@ -0,0 +1,710 @@ +.TH CAKE 8 "19 July 2018" "iproute2" "Linux" +.SH NAME +CAKE \- Common Applications Kept Enhanced (CAKE) +.SH SYNOPSIS +.B tc qdisc ... cake +.br +[ +.BR bandwidth +RATE | +.BR unlimited* +| +.BR autorate-ingress +] +.br +[ +.BR rtt +TIME | +.BR datacentre +| +.BR lan +| +.BR metro +| +.BR regional +| +.BR internet* +| +.BR oceanic +| +.BR satellite +| +.BR interplanetary +] +.br +[ +.BR besteffort +| +.BR diffserv8 +| +.BR diffserv4 +| +.BR diffserv3* +] +.br +[ +.BR flowblind +| +.BR srchost +| +.BR dsthost +| +.BR hosts +| +.BR flows +| +.BR dual-srchost +| +.BR dual-dsthost +| +.BR triple-isolate* +] +.br +[ +.BR nat +| +.BR nonat* +] +.br +[ +.BR wash +| +.BR nowash* +] +.br +[ +.BR split-gso* +| +.BR no-split-gso +] +.br +[ +.BR ack-filter +| +.BR ack-filter-aggressive +| +.BR no-ack-filter* +] +.br +[ +.BR memlimit +LIMIT ] +.br +[ +.BR ptm +| +.BR atm +| +.BR noatm* +] +.br +[ +.BR overhead +N | +.BR conservative +| +.BR raw* +] +.br +[ +.BR mpu +N ] +.br +[ +.BR ingress +| +.BR egress* +] +.br +(* marks defaults) + + +.SH DESCRIPTION +CAKE (Common Applications Kept Enhanced) is a shaping-capable queue discipline +which uses both AQM and FQ. It combines COBALT, which is an AQM algorithm +combining Codel and BLUE, a shaper which operates in deficit mode, and a variant +of DRR++ for flow isolation. 8-way set-associative hashing is used to virtually +eliminate hash collisions. Priority queuing is available through a simplified +diffserv implementation. Overhead compensation for various encapsulation +schemes is tightly integrated. + +All settings are optional; the default settings are chosen to be sensible in +most common deployments. Most people will only need to set the +.B bandwidth +parameter to get useful results, but reading the +.B Overhead Compensation +and +.B Round Trip Time +sections is strongly encouraged. + +.SH SHAPER PARAMETERS +CAKE uses a deficit-mode shaper, which does not exhibit the initial burst +typical of token-bucket shapers. It will automatically burst precisely as much +as required to maintain the configured throughput. As such, it is very +straightforward to configure. +.PP +.B unlimited +(default) +.br + No limit on the bandwidth. +.PP +.B bandwidth +RATE +.br + Set the shaper bandwidth. See +.BR tc(8) +or examples below for details of the RATE value. +.PP +.B autorate-ingress +.br + Automatic capacity estimation based on traffic arriving at this qdisc. +This is most likely to be useful with cellular links, which tend to change +quality randomly. A +.B bandwidth +parameter can be used in conjunction to specify an initial estimate. The shaper +will periodically be set to a bandwidth slightly below the estimated rate. This +estimator cannot estimate the bandwidth of links downstream of itself. + +.SH OVERHEAD COMPENSATION PARAMETERS +The size of each packet on the wire may differ from that seen by Linux. The +following parameters allow CAKE to compensate for this difference by internally +considering each packet to be bigger than Linux informs it. To assist users who +are not expert network engineers, keywords have been provided to represent a +number of common link technologies. + +.SS Manual Overhead Specification +.B overhead +BYTES +.br + Adds BYTES to the size of each packet. BYTES may be negative; values +between -64 and 256 (inclusive) are accepted. +.PP +.B mpu +BYTES +.br + Rounds each packet (including overhead) up to a minimum length +BYTES. BYTES may not be negative; values between 0 and 256 (inclusive) +are accepted. +.PP +.B atm +.br + Compensates for ATM cell framing, which is normally found on ADSL links. +This is performed after the +.B overhead +parameter above. ATM uses fixed 53-byte cells, each of which can carry 48 bytes +payload. +.PP +.B ptm +.br + Compensates for PTM encoding, which is normally found on VDSL2 links and +uses a 64b/65b encoding scheme. It is even more efficient to simply +derate the specified shaper bandwidth by a factor of 64/65 or 0.984. See +ITU G.992.3 Annex N and IEEE 802.3 Section 61.3 for details. +.PP +.B noatm +.br + Disables ATM and PTM compensation. + +.SS Failsafe Overhead Keywords +These two keywords are provided for quick-and-dirty setup. Use them if you +can't be bothered to read the rest of this section. +.PP +.B raw +(default) +.br + Turns off all overhead compensation in CAKE. The packet size reported +by Linux will be used directly. +.PP + Other overhead keywords may be added after "raw". The effect of this is +to make the overhead compensation operate relative to the reported packet size, +not the underlying IP packet size. +.PP +.B conservative +.br + Compensates for more overhead than is likely to occur on any +widely-deployed link technology. +.br + Equivalent to +.B overhead 48 atm. + +.SS ADSL Overhead Keywords +Most ADSL modems have a way to check which framing scheme is in use. Often this +is also specified in the settings document provided by the ISP. The keywords in +this section are intended to correspond with these sources of information. All +of them implicitly set the +.B atm +flag. +.PP +.B pppoa-vcmux +.br + Equivalent to +.B overhead 10 atm +.PP +.B pppoa-llc +.br + Equivalent to +.B overhead 14 atm +.PP +.B pppoe-vcmux +.br + Equivalent to +.B overhead 32 atm +.PP +.B pppoe-llcsnap +.br + Equivalent to +.B overhead 40 atm +.PP +.B bridged-vcmux +.br + Equivalent to +.B overhead 24 atm +.PP +.B bridged-llcsnap +.br + Equivalent to +.B overhead 32 atm +.PP +.B ipoa-vcmux +.br + Equivalent to +.B overhead 8 atm +.PP +.B ipoa-llcsnap +.br + Equivalent to +.B overhead 16 atm +.PP +See also the Ethernet Correction Factors section below. + +.SS VDSL2 Overhead Keywords +ATM was dropped from VDSL2 in favour of PTM, which is a much more +straightforward framing scheme. Some ISPs retained PPPoE for compatibility with +their existing back-end systems. +.PP +.B pppoe-ptm +.br + Equivalent to +.B overhead 30 ptm + +.br + PPPoE: 2B PPP + 6B PPPoE + +.br + ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence + +.br + PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS) +.br +.PP +.B bridged-ptm +.br + Equivalent to +.B overhead 22 ptm +.br + ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence + +.br + PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS) +.br +.PP +See also the Ethernet Correction Factors section below. + +.SS DOCSIS Cable Overhead Keyword +DOCSIS is the universal standard for providing Internet service over cable-TV +infrastructure. + +In this case, the actual on-wire overhead is less important than the packet size +the head-end equipment uses for shaping and metering. This is specified to be +an Ethernet frame including the CRC (aka FCS). +.PP +.B docsis +.br + Equivalent to +.B overhead 18 mpu 64 noatm + +.SS Ethernet Overhead Keywords +.PP +.B ethernet +.br + Accounts for Ethernet's preamble, inter-frame gap, and Frame Check +Sequence. Use this keyword when the bottleneck being shaped for is an +actual Ethernet cable. +.br + Equivalent to +.B overhead 38 mpu 84 noatm +.PP +.B ether-vlan +.br + Adds 4 bytes to the overhead compensation, accounting for an IEEE 802.1Q +VLAN header appended to the Ethernet frame header. NB: Some ISPs use one or +even two of these within PPPoE; this keyword may be repeated as necessary to +express this. + +.SH ROUND TRIP TIME PARAMETERS +Active Queue Management (AQM) consists of embedding congestion signals in the +packet flow, which receivers use to instruct senders to slow down when the queue +is persistently occupied. CAKE uses ECN signalling when available, and packet +drops otherwise, according to a combination of the Codel and BLUE AQM algorithms +called COBALT. + +Very short latencies require a very rapid AQM response to adequately control +latency. However, such a rapid response tends to impair throughput when the +actual RTT is relatively long. CAKE allows specifying the RTT it assumes for +tuning various parameters. Actual RTTs within an order of magnitude of this +will generally work well for both throughput and latency management. + +At the 'lan' setting and below, the time constants are similar in magnitude to +the jitter in the Linux kernel itself, so congestion might be signalled +prematurely. The flows will then become sparse and total throughput reduced, +leaving little or no back-pressure for the fairness logic to work against. Use +the "metro" setting for local lans unless you have a custom kernel. +.PP +.B rtt +TIME +.br + Manually specify an RTT. +.PP +.B datacentre +.br + For extremely high-performance 10GigE+ networks only. Equivalent to +.B rtt 100us. +.PP +.B lan +.br + For pure Ethernet (not Wi-Fi) networks, at home or in the office. Don't +use this when shaping for an Internet access link. Equivalent to +.B rtt 1ms. +.PP +.B metro +.br + For traffic mostly within a single city. Equivalent to +.B rtt 10ms. +.PP +.B regional +.br + For traffic mostly within a European-sized country. Equivalent to +.B rtt 30ms. +.PP +.B internet +(default) +.br + This is suitable for most Internet traffic. Equivalent to +.B rtt 100ms. +.PP +.B oceanic +.br + For Internet traffic with generally above-average latency, such as that +suffered by Australasian residents. Equivalent to +.B rtt 300ms. +.PP +.B satellite +.br + For traffic via geostationary satellites. Equivalent to +.B rtt 1000ms. +.PP +.B interplanetary +.br + So named because Jupiter is about 1 light-hour from Earth. Use this to +(almost) completely disable AQM actions. Equivalent to +.B rtt 3600s. + +.SH FLOW ISOLATION PARAMETERS +With flow isolation enabled, CAKE places packets from different flows into +different queues, each of which carries its own AQM state. Packets from each +queue are then delivered fairly, according to a DRR++ algorithm which minimises +latency for "sparse" flows. CAKE uses a set-associative hashing algorithm to +minimise flow collisions. + +These keywords specify whether fairness based on source address, destination +address, individual flows, or any combination of those is desired. +.PP +.B flowblind +.br + Disables flow isolation; all traffic passes through a single queue for +each tin. +.PP +.B srchost +.br + Flows are defined only by source address. Could be useful on the egress +path of an ISP backhaul. +.PP +.B dsthost +.br + Flows are defined only by destination address. Could be useful on the +ingress path of an ISP backhaul. +.PP +.B hosts +.br + Flows are defined by source-destination host pairs. This is host +isolation, rather than flow isolation. +.PP +.B flows +.br + Flows are defined by the entire 5-tuple of source address, destination +address, transport protocol, source port and destination port. This is the type +of flow isolation performed by SFQ and fq_codel. +.PP +.B dual-srchost +.br + Flows are defined by the 5-tuple, and fairness is applied first over +source addresses, then over individual flows. Good for use on egress traffic +from a LAN to the internet, where it'll prevent any one LAN host from +monopolising the uplink, regardless of the number of flows they use. +.PP +.B dual-dsthost +.br + Flows are defined by the 5-tuple, and fairness is applied first over +destination addresses, then over individual flows. Good for use on ingress +traffic to a LAN from the internet, where it'll prevent any one LAN host from +monopolising the downlink, regardless of the number of flows they use. +.PP +.B triple-isolate +(default) +.br + Flows are defined by the 5-tuple, and fairness is applied over source +*and* destination addresses intelligently (ie. not merely by host-pairs), and +also over individual flows. Use this if you're not certain whether to use +dual-srchost or dual-dsthost; it'll do both jobs at once, preventing any one +host on *either* side of the link from monopolising it with a large number of +flows. +.PP +.B nat +.br + Instructs Cake to perform a NAT lookup before applying flow-isolation +rules, to determine the true addresses and port numbers of the packet, to +improve fairness between hosts "inside" the NAT. This has no practical effect +in "flowblind" or "flows" modes, or if NAT is performed on a different host. +.PP +.B nonat +(default) +.br + Cake will not perform a NAT lookup. Flow isolation will be performed +using the addresses and port numbers directly visible to the interface Cake is +attached to. + +.SH PRIORITY QUEUE PARAMETERS +CAKE can divide traffic into "tins" based on the Diffserv field. Each tin has +its own independent set of flow-isolation queues, and is serviced based on a WRR +algorithm. To avoid perverse Diffserv marking incentives, tin weights have a +"priority sharing" value when bandwidth used by that tin is below a threshold, +and a lower "bandwidth sharing" value when above. Bandwidth is compared against +the threshold using the same algorithm as the deficit-mode shaper. + +Detailed customisation of tin parameters is not provided. The following presets +perform all necessary tuning, relative to the current shaper bandwidth and RTT +settings. +.PP +.B besteffort +.br + Disables priority queuing by placing all traffic in one tin. +.PP +.B precedence +.br + Enables legacy interpretation of TOS "Precedence" field. Use of this +preset on the modern Internet is firmly discouraged. +.PP +.B diffserv4 +.br + Provides a general-purpose Diffserv implementation with four tins: +.br + Bulk (CS1), 6.25% threshold, generally low priority. +.br + Best Effort (general), 100% threshold. +.br + Video (AF4x, AF3x, CS3, AF2x, CS2, TOS4, TOS1), 50% threshold. +.br + Voice (CS7, CS6, EF, VA, CS5, CS4), 25% threshold. +.PP +.B diffserv3 +(default) +.br + Provides a simple, general-purpose Diffserv implementation with three tins: +.br + Bulk (CS1), 6.25% threshold, generally low priority. +.br + Best Effort (general), 100% threshold. +.br + Voice (CS7, CS6, EF, VA, TOS4), 25% threshold, reduced Codel interval. + +.SH OTHER PARAMETERS +.B memlimit +LIMIT +.br + Limit the memory consumed by Cake to LIMIT bytes. Note that this does +not translate directly to queue size (so do not size this based on bandwidth +delay product considerations, but rather on worst case acceptable memory +consumption), as there is some overhead in the data structures containing the +packets, especially for small packets. + + By default, the limit is calculated based on the bandwidth and RTT +settings. + +.PP +.B wash + +.br + Traffic entering your diffserv domain is frequently mis-marked in +transit from the perspective of your network, and traffic exiting yours may be +mis-marked from the perspective of the transiting provider. + +Apply the wash option to clear all extra diffserv (but not ECN bits), after +priority queuing has taken place. + +If you are shaping inbound, and cannot trust the diffserv markings (as is the +case for Comcast Cable, among others), it is best to use a single queue +"besteffort" mode with wash. + +.PP +.B split-gso + +.br + This option controls whether CAKE will split General Segmentation +Offload (GSO) super-packets into their on-the-wire components and +dequeue them individually. + +.br +Super-packets are created by the networking stack to improve efficiency. +However, because they are larger they take longer to dequeue, which +translates to higher latency for competing flows, especially at lower +bandwidths. CAKE defaults to splitting GSO packets to achieve the lowest +possible latency. At link speeds higher than 10 Gbps, setting the +no-split-gso parameter can increase the maximum achievable throughput by +retaining the full GSO packets. + +.SH OVERRIDING CLASSIFICATION WITH TC FILTERS + +CAKE supports overriding of its internal classification of packets through the +tc filter mechanism. Packets can be assigned to different priority tins by +setting the +.B priority +field on the skb, and the flow hashing can be overridden by setting the +.B classid +parameter. + +.PP +.B Tin override + +.br + To assign a priority tin, the major number of the priority field needs +to match the qdisc handle of the cake instance; if it does, the minor number +will be interpreted as the tin index. For example, to classify all ICMP packets +as 'bulk', the following filter can be used: + +.br + # tc qdisc replace dev eth0 handle 1: root cake diffserv3 + # tc filter add dev eth0 parent 1: protocol ip prio 1 \\ + u32 match icmp type 0 0 action skbedit priority 1:1 + +.PP +.B Flow hash override + +.br + To override flow hashing, the classid can be set. CAKE will interpret +the major number of the classid as the host hash used in host isolation mode, +and the minor number as the flow hash used for flow-based queueing. One or both +of those can be set, and will be used if the relevant flow isolation parameter +is set (i.e., the major number will be ignored if CAKE is not configured in +hosts mode, and the minor number will be ignored if CAKE is not configured in +flows mode). + +.br +This example will assign all ICMP packets to the first queue: + +.br + # tc qdisc replace dev eth0 handle 1: root cake + # tc filter add dev eth0 parent 1: protocol ip prio 1 \\ + u32 match icmp type 0 0 classid 0:1 + +.br +If only one of the host and flow overrides is set, CAKE will compute the other +hash from the packet as normal. Note, however, that the host isolation mode +works by assigning a host ID to the flow queue; so if overriding both host and +flow, the same flow cannot have more than one host assigned. In addition, it is +not possible to assign different source and destination host IDs through the +override mechanism; if a host ID is assigned, it will be used as both source and +destination host. + + + +.SH EXAMPLES +# tc qdisc delete root dev eth0 +.br +# tc qdisc add root dev eth0 cake bandwidth 100Mbit ethernet +.br +# tc -s qdisc show dev eth0 +.br +qdisc cake 1: root refcnt 2 bandwidth 100Mbit diffserv3 triple-isolate rtt 100.0ms noatm overhead 38 mpu 84 + Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) + backlog 0b 0p requeues 0 + memory used: 0b of 5000000b + capacity estimate: 100Mbit + min/max network layer size: 65535 / 0 + min/max overhead-adjusted size: 65535 / 0 + average network hdr offset: 0 + + Bulk Best Effort Voice + thresh 6250Kbit 100Mbit 25Mbit + target 5.0ms 5.0ms 5.0ms + interval 100.0ms 100.0ms 100.0ms + pk_delay 0us 0us 0us + av_delay 0us 0us 0us + sp_delay 0us 0us 0us + pkts 0 0 0 + bytes 0 0 0 + way_inds 0 0 0 + way_miss 0 0 0 + way_cols 0 0 0 + drops 0 0 0 + marks 0 0 0 + ack_drop 0 0 0 + sp_flows 0 0 0 + bk_flows 0 0 0 + un_flows 0 0 0 + max_len 0 0 0 + quantum 300 1514 762 + +After some use: +.br +# tc -s qdisc show dev eth0 + +qdisc cake 1: root refcnt 2 bandwidth 100Mbit diffserv3 triple-isolate rtt 100.0ms noatm overhead 38 mpu 84 + Sent 44709231 bytes 31931 pkt (dropped 45, overlimits 93782 requeues 0) + backlog 33308b 22p requeues 0 + memory used: 292352b of 5000000b + capacity estimate: 100Mbit + min/max network layer size: 28 / 1500 + min/max overhead-adjusted size: 84 / 1538 + average network hdr offset: 14 + + Bulk Best Effort Voice + thresh 6250Kbit 100Mbit 25Mbit + target 5.0ms 5.0ms 5.0ms + interval 100.0ms 100.0ms 100.0ms + pk_delay 8.7ms 6.9ms 5.0ms + av_delay 4.9ms 5.3ms 3.8ms + sp_delay 727us 1.4ms 511us + pkts 2590 21271 8137 + bytes 3081804 30302659 11426206 + way_inds 0 46 0 + way_miss 3 17 4 + way_cols 0 0 0 + drops 20 15 10 + marks 0 0 0 + ack_drop 0 0 0 + sp_flows 2 4 1 + bk_flows 1 2 1 + un_flows 0 0 0 + max_len 1514 1514 1514 + quantum 300 1514 762 + +.SH SEE ALSO +.BR tc (8), +.BR tc-codel (8), +.BR tc-fq_codel (8), +.BR tc-htb (8) + +.SH AUTHORS +Cake's principal author is Jonathan Morton, with contributions from +Tony Ambardar, Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, +Sebastian Moeller, Ryan Mounce, Dean Scarff, Nils Andreas Svee, and Dave Täht. + +This manual page was written by Loganaden Velvindron. Please report corrections +to the Linux Networking mailing list . --- a/man/man8/tc.8 +++ b/man/man8/tc.8 @@ -776,6 +776,7 @@ was written by Alexey N. Kuznetsov and a .BR tc-basic (8), .BR tc-bfifo (8), .BR tc-bpf (8), +.BR tc-cake (8), .BR tc-cbq (8), .BR tc-cgroup (8), .BR tc-choke (8), --- a/tc/Makefile +++ b/tc/Makefile @@ -66,6 +66,7 @@ TCMODULES += q_codel.o TCMODULES += q_fq_codel.o TCMODULES += q_fq.o TCMODULES += q_pie.o +TCMODULES += q_cake.o TCMODULES += q_hhf.o TCMODULES += q_clsact.o TCMODULES += e_bpf.o --- /dev/null +++ b/tc/q_cake.c @@ -0,0 +1,799 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * Common Applications Kept Enhanced -- CAKE + * + * Copyright (C) 2014-2018 Jonathan Morton + * Copyright (C) 2017-2018 Toke Høiland-Jørgensen + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "utils.h" +#include "tc_util.h" + +struct cake_preset { + char *name; + unsigned int target; + unsigned int interval; +}; + +static struct cake_preset presets[] = { + {"datacentre", 5, 100}, + {"lan", 50, 1000}, + {"metro", 500, 10000}, + {"regional", 1500, 30000}, + {"internet", 5000, 100000}, + {"oceanic", 15000, 300000}, + {"satellite", 50000, 1000000}, + {"interplanetary", 50000000, 1000000000}, +}; + +static const char * diffserv_names[CAKE_DIFFSERV_MAX] = { + [CAKE_DIFFSERV_DIFFSERV3] = "diffserv3", + [CAKE_DIFFSERV_DIFFSERV4] = "diffserv4", + [CAKE_DIFFSERV_DIFFSERV8] = "diffserv8", + [CAKE_DIFFSERV_BESTEFFORT] = "besteffort", + [CAKE_DIFFSERV_PRECEDENCE] = "precedence", +}; + +static const char * flowmode_names[CAKE_FLOW_MAX] = { + [CAKE_FLOW_NONE] = "flowblind", + [CAKE_FLOW_SRC_IP] = "srchost", + [CAKE_FLOW_DST_IP] = "dsthost", + [CAKE_FLOW_HOSTS] = "hosts", + [CAKE_FLOW_FLOWS] = "flows", + [CAKE_FLOW_DUAL_SRC] = "dual-srchost", + [CAKE_FLOW_DUAL_DST] = "dual-dsthost", + [CAKE_FLOW_TRIPLE] = "triple-isolate", +}; + +static struct cake_preset *find_preset(char *argv) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(presets); i++) + if (!strcmp(argv, presets[i].name)) + return &presets[i]; + return NULL; +} + +static void explain(void) +{ + fprintf(stderr, +"Usage: ... cake [ bandwidth RATE | unlimited* | autorate-ingress ]\n" +" [ rtt TIME | datacentre | lan | metro | regional |\n" +" internet* | oceanic | satellite | interplanetary ]\n" +" [ besteffort | diffserv8 | diffserv4 | diffserv3* ]\n" +" [ flowblind | srchost | dsthost | hosts | flows |\n" +" dual-srchost | dual-dsthost | triple-isolate* ]\n" +" [ nat | nonat* ]\n" +" [ wash | nowash* ]\n" +" [ split-gso* | no-split-gso ]\n" +" [ ack-filter | ack-filter-aggressive | no-ack-filter* ]\n" +" [ memlimit LIMIT ]\n" +" [ ptm | atm | noatm* ] [ overhead N | conservative | raw* ]\n" +" [ mpu N ] [ ingress | egress* ]\n" +" (* marks defaults)\n"); +} + +static int cake_parse_opt(struct qdisc_util *qu, int argc, char **argv, + struct nlmsghdr *n, const char *dev) +{ + struct cake_preset *preset, *preset_set = NULL; + bool overhead_override = false; + bool overhead_set = false; + unsigned int interval = 0; + unsigned int diffserv = 0; + unsigned int memlimit = 0; + unsigned int target = 0; + __u64 bandwidth = 0; + int ack_filter = -1; + struct rtattr *tail; + int split_gso = -1; + int unlimited = 0; + int flowmode = -1; + int autorate = -1; + int ingress = -1; + int overhead = 0; + int wash = -1; + int nat = -1; + int atm = -1; + int mpu = 0; + + while (argc > 0) { + if (strcmp(*argv, "bandwidth") == 0) { + NEXT_ARG(); + if (get_rate64(&bandwidth, *argv)) { + fprintf(stderr, "Illegal \"bandwidth\"\n"); + return -1; + } + unlimited = 0; + autorate = 0; + } else if (strcmp(*argv, "unlimited") == 0) { + bandwidth = 0; + unlimited = 1; + autorate = 0; + } else if (strcmp(*argv, "autorate-ingress") == 0) { + autorate = 1; + } else if (strcmp(*argv, "rtt") == 0) { + NEXT_ARG(); + if (get_time(&interval, *argv)) { + fprintf(stderr, "Illegal \"rtt\"\n"); + return -1; + } + target = interval / 20; + if (!target) + target = 1; + } else if ((preset = find_preset(*argv))) { + if (preset_set) + duparg(*argv, preset_set->name); + preset_set = preset; + target = preset->target; + interval = preset->interval; + } else if (strcmp(*argv, "besteffort") == 0) { + diffserv = CAKE_DIFFSERV_BESTEFFORT; + } else if (strcmp(*argv, "precedence") == 0) { + diffserv = CAKE_DIFFSERV_PRECEDENCE; + } else if (strcmp(*argv, "diffserv8") == 0) { + diffserv = CAKE_DIFFSERV_DIFFSERV8; + } else if (strcmp(*argv, "diffserv4") == 0) { + diffserv = CAKE_DIFFSERV_DIFFSERV4; + } else if (strcmp(*argv, "diffserv") == 0) { + diffserv = CAKE_DIFFSERV_DIFFSERV4; + } else if (strcmp(*argv, "diffserv3") == 0) { + diffserv = CAKE_DIFFSERV_DIFFSERV3; + } else if (strcmp(*argv, "nowash") == 0) { + wash = 0; + } else if (strcmp(*argv, "wash") == 0) { + wash = 1; + } else if (strcmp(*argv, "split-gso") == 0) { + split_gso = 1; + } else if (strcmp(*argv, "no-split-gso") == 0) { + split_gso = 0; + } else if (strcmp(*argv, "flowblind") == 0) { + flowmode = CAKE_FLOW_NONE; + } else if (strcmp(*argv, "srchost") == 0) { + flowmode = CAKE_FLOW_SRC_IP; + } else if (strcmp(*argv, "dsthost") == 0) { + flowmode = CAKE_FLOW_DST_IP; + } else if (strcmp(*argv, "hosts") == 0) { + flowmode = CAKE_FLOW_HOSTS; + } else if (strcmp(*argv, "flows") == 0) { + flowmode = CAKE_FLOW_FLOWS; + } else if (strcmp(*argv, "dual-srchost") == 0) { + flowmode = CAKE_FLOW_DUAL_SRC; + } else if (strcmp(*argv, "dual-dsthost") == 0) { + flowmode = CAKE_FLOW_DUAL_DST; + } else if (strcmp(*argv, "triple-isolate") == 0) { + flowmode = CAKE_FLOW_TRIPLE; + } else if (strcmp(*argv, "nat") == 0) { + nat = 1; + } else if (strcmp(*argv, "nonat") == 0) { + nat = 0; + } else if (strcmp(*argv, "ptm") == 0) { + atm = CAKE_ATM_PTM; + } else if (strcmp(*argv, "atm") == 0) { + atm = CAKE_ATM_ATM; + } else if (strcmp(*argv, "noatm") == 0) { + atm = CAKE_ATM_NONE; + } else if (strcmp(*argv, "raw") == 0) { + atm = CAKE_ATM_NONE; + overhead = 0; + overhead_set = true; + overhead_override = true; + } else if (strcmp(*argv, "conservative") == 0) { + /* + * Deliberately over-estimate overhead: + * one whole ATM cell plus ATM framing. + * A safe choice if the actual overhead is unknown. + */ + atm = CAKE_ATM_ATM; + overhead = 48; + overhead_set = true; + + /* Various ADSL framing schemes, all over ATM cells */ + } else if (strcmp(*argv, "ipoa-vcmux") == 0) { + atm = CAKE_ATM_ATM; + overhead += 8; + overhead_set = true; + } else if (strcmp(*argv, "ipoa-llcsnap") == 0) { + atm = CAKE_ATM_ATM; + overhead += 16; + overhead_set = true; + } else if (strcmp(*argv, "bridged-vcmux") == 0) { + atm = CAKE_ATM_ATM; + overhead += 24; + overhead_set = true; + } else if (strcmp(*argv, "bridged-llcsnap") == 0) { + atm = CAKE_ATM_ATM; + overhead += 32; + overhead_set = true; + } else if (strcmp(*argv, "pppoa-vcmux") == 0) { + atm = CAKE_ATM_ATM; + overhead += 10; + overhead_set = true; + } else if (strcmp(*argv, "pppoa-llc") == 0) { + atm = CAKE_ATM_ATM; + overhead += 14; + overhead_set = true; + } else if (strcmp(*argv, "pppoe-vcmux") == 0) { + atm = CAKE_ATM_ATM; + overhead += 32; + overhead_set = true; + } else if (strcmp(*argv, "pppoe-llcsnap") == 0) { + atm = CAKE_ATM_ATM; + overhead += 40; + overhead_set = true; + + /* Typical VDSL2 framing schemes, both over PTM */ + /* PTM has 64b/65b coding which absorbs some bandwidth */ + } else if (strcmp(*argv, "pppoe-ptm") == 0) { + /* 2B PPP + 6B PPPoE + 6B dest MAC + 6B src MAC + * + 2B ethertype + 4B Frame Check Sequence + * + 1B Start of Frame (S) + 1B End of Frame (Ck) + * + 2B TC-CRC (PTM-FCS) = 30B + */ + atm = CAKE_ATM_PTM; + overhead += 30; + overhead_set = true; + } else if (strcmp(*argv, "bridged-ptm") == 0) { + /* 6B dest MAC + 6B src MAC + 2B ethertype + * + 4B Frame Check Sequence + * + 1B Start of Frame (S) + 1B End of Frame (Ck) + * + 2B TC-CRC (PTM-FCS) = 22B + */ + atm = CAKE_ATM_PTM; + overhead += 22; + overhead_set = true; + } else if (strcmp(*argv, "via-ethernet") == 0) { + /* + * We used to use this flag to manually compensate for + * Linux including the Ethernet header on Ethernet-type + * interfaces, but not on IP-type interfaces. + * + * It is no longer needed, because Cake now adjusts for + * that automatically, and is thus ignored. + * + * It would be deleted entirely, but it appears in the + * stats output when the automatic compensation is + * active. + */ + } else if (strcmp(*argv, "ethernet") == 0) { + /* ethernet pre-amble & interframe gap & FCS + * you may need to add vlan tag + */ + overhead += 38; + overhead_set = true; + mpu = 84; + + /* Additional Ethernet-related overhead used by some ISPs */ + } else if (strcmp(*argv, "ether-vlan") == 0) { + /* 802.1q VLAN tag - may be repeated */ + overhead += 4; + overhead_set = true; + + /* + * DOCSIS cable shapers account for Ethernet frame with FCS, + * but not interframe gap or preamble. + */ + } else if (strcmp(*argv, "docsis") == 0) { + atm = CAKE_ATM_NONE; + overhead += 18; + overhead_set = true; + mpu = 64; + } else if (strcmp(*argv, "overhead") == 0) { + char *p = NULL; + + NEXT_ARG(); + overhead = strtol(*argv, &p, 10); + if (!p || *p || !*argv || + overhead < -64 || overhead > 256) { + fprintf(stderr, + "Illegal \"overhead\", valid range is -64 to 256\\n"); + return -1; + } + overhead_set = true; + + } else if (strcmp(*argv, "mpu") == 0) { + char *p = NULL; + + NEXT_ARG(); + mpu = strtol(*argv, &p, 10); + if (!p || *p || !*argv || mpu < 0 || mpu > 256) { + fprintf(stderr, + "Illegal \"mpu\", valid range is 0 to 256\\n"); + return -1; + } + } else if (strcmp(*argv, "ingress") == 0) { + ingress = 1; + } else if (strcmp(*argv, "egress") == 0) { + ingress = 0; + } else if (strcmp(*argv, "no-ack-filter") == 0) { + ack_filter = CAKE_ACK_NONE; + } else if (strcmp(*argv, "ack-filter") == 0) { + ack_filter = CAKE_ACK_FILTER; + } else if (strcmp(*argv, "ack-filter-aggressive") == 0) { + ack_filter = CAKE_ACK_AGGRESSIVE; + } else if (strcmp(*argv, "memlimit") == 0) { + NEXT_ARG(); + if (get_size(&memlimit, *argv)) { + fprintf(stderr, + "Illegal value for \"memlimit\": \"%s\"\n", *argv); + return -1; + } + } else if (strcmp(*argv, "help") == 0) { + explain(); + return -1; + } else { + fprintf(stderr, "What is \"%s\"?\n", *argv); + explain(); + return -1; + } + argc--; argv++; + } + + tail = NLMSG_TAIL(n); + addattr_l(n, 1024, TCA_OPTIONS, NULL, 0); + if (bandwidth || unlimited) + addattr_l(n, 1024, TCA_CAKE_BASE_RATE64, &bandwidth, + sizeof(bandwidth)); + if (diffserv) + addattr_l(n, 1024, TCA_CAKE_DIFFSERV_MODE, &diffserv, + sizeof(diffserv)); + if (atm != -1) + addattr_l(n, 1024, TCA_CAKE_ATM, &atm, sizeof(atm)); + if (flowmode != -1) + addattr_l(n, 1024, TCA_CAKE_FLOW_MODE, &flowmode, + sizeof(flowmode)); + if (overhead_set) + addattr_l(n, 1024, TCA_CAKE_OVERHEAD, &overhead, + sizeof(overhead)); + if (overhead_override) { + unsigned int zero = 0; + + addattr_l(n, 1024, TCA_CAKE_RAW, &zero, sizeof(zero)); + } + if (mpu > 0) + addattr_l(n, 1024, TCA_CAKE_MPU, &mpu, sizeof(mpu)); + if (interval) + addattr_l(n, 1024, TCA_CAKE_RTT, &interval, sizeof(interval)); + if (target) + addattr_l(n, 1024, TCA_CAKE_TARGET, &target, sizeof(target)); + if (autorate != -1) + addattr_l(n, 1024, TCA_CAKE_AUTORATE, &autorate, + sizeof(autorate)); + if (memlimit) + addattr_l(n, 1024, TCA_CAKE_MEMORY, &memlimit, + sizeof(memlimit)); + if (nat != -1) + addattr_l(n, 1024, TCA_CAKE_NAT, &nat, sizeof(nat)); + if (wash != -1) + addattr_l(n, 1024, TCA_CAKE_WASH, &wash, sizeof(wash)); + if (split_gso != -1) + addattr_l(n, 1024, TCA_CAKE_SPLIT_GSO, &split_gso, + sizeof(split_gso)); + if (ingress != -1) + addattr_l(n, 1024, TCA_CAKE_INGRESS, &ingress, sizeof(ingress)); + if (ack_filter != -1) + addattr_l(n, 1024, TCA_CAKE_ACK_FILTER, &ack_filter, + sizeof(ack_filter)); + + tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail; + return 0; +} + +static void cake_print_mode(unsigned int value, unsigned int max, + const char *key, const char **table) +{ + if (value < max && table[value]) { + print_string(PRINT_ANY, key, "%s ", table[value]); + } else { + print_string(PRINT_JSON, key, NULL, "unknown"); + print_string(PRINT_FP, NULL, "(?%s?)", key); + } +} + +static int cake_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt) +{ + struct rtattr *tb[TCA_CAKE_MAX + 1]; + unsigned int interval = 0; + unsigned int memlimit = 0; + __u64 bandwidth = 0; + int ack_filter = 0; + int split_gso = 0; + int overhead = 0; + int autorate = 0; + int ingress = 0; + int wash = 0; + int raw = 0; + int mpu = 0; + int atm = 0; + int nat = 0; + + SPRINT_BUF(b1); + SPRINT_BUF(b2); + + if (opt == NULL) + return 0; + + parse_rtattr_nested(tb, TCA_CAKE_MAX, opt); + + if (tb[TCA_CAKE_BASE_RATE64] && + RTA_PAYLOAD(tb[TCA_CAKE_BASE_RATE64]) >= sizeof(bandwidth)) { + bandwidth = rta_getattr_u64(tb[TCA_CAKE_BASE_RATE64]); + if (bandwidth) { + print_uint(PRINT_JSON, "bandwidth", NULL, bandwidth); + print_string(PRINT_FP, NULL, "bandwidth %s ", + sprint_rate(bandwidth, b1)); + } else + print_string(PRINT_ANY, "bandwidth", "bandwidth %s ", + "unlimited"); + } + if (tb[TCA_CAKE_AUTORATE] && + RTA_PAYLOAD(tb[TCA_CAKE_AUTORATE]) >= sizeof(__u32)) { + autorate = rta_getattr_u32(tb[TCA_CAKE_AUTORATE]); + if (autorate == 1) + print_string(PRINT_ANY, "autorate", "%s ", + "autorate-ingress"); + else if (autorate) + print_string(PRINT_ANY, "autorate", "(?autorate?) ", + "unknown"); + } + if (tb[TCA_CAKE_DIFFSERV_MODE] && + RTA_PAYLOAD(tb[TCA_CAKE_DIFFSERV_MODE]) >= sizeof(__u32)) { + cake_print_mode(rta_getattr_u32(tb[TCA_CAKE_DIFFSERV_MODE]), + CAKE_DIFFSERV_MAX, "diffserv", diffserv_names); + } + if (tb[TCA_CAKE_FLOW_MODE] && + RTA_PAYLOAD(tb[TCA_CAKE_FLOW_MODE]) >= sizeof(__u32)) { + cake_print_mode(rta_getattr_u32(tb[TCA_CAKE_FLOW_MODE]), + CAKE_FLOW_MAX, "flowmode", flowmode_names); + } + + if (tb[TCA_CAKE_NAT] && + RTA_PAYLOAD(tb[TCA_CAKE_NAT]) >= sizeof(__u32)) { + nat = rta_getattr_u32(tb[TCA_CAKE_NAT]); + } + + if (nat) + print_string(PRINT_FP, NULL, "nat ", NULL); + print_bool(PRINT_JSON, "nat", NULL, nat); + + if (tb[TCA_CAKE_WASH] && + RTA_PAYLOAD(tb[TCA_CAKE_WASH]) >= sizeof(__u32)) { + wash = rta_getattr_u32(tb[TCA_CAKE_WASH]); + } + if (tb[TCA_CAKE_ATM] && + RTA_PAYLOAD(tb[TCA_CAKE_ATM]) >= sizeof(__u32)) { + atm = rta_getattr_u32(tb[TCA_CAKE_ATM]); + } + if (tb[TCA_CAKE_OVERHEAD] && + RTA_PAYLOAD(tb[TCA_CAKE_OVERHEAD]) >= sizeof(__s32)) { + overhead = *(__s32 *) RTA_DATA(tb[TCA_CAKE_OVERHEAD]); + } + if (tb[TCA_CAKE_MPU] && + RTA_PAYLOAD(tb[TCA_CAKE_MPU]) >= sizeof(__u32)) { + mpu = rta_getattr_u32(tb[TCA_CAKE_MPU]); + } + if (tb[TCA_CAKE_INGRESS] && + RTA_PAYLOAD(tb[TCA_CAKE_INGRESS]) >= sizeof(__u32)) { + ingress = rta_getattr_u32(tb[TCA_CAKE_INGRESS]); + } + if (tb[TCA_CAKE_ACK_FILTER] && + RTA_PAYLOAD(tb[TCA_CAKE_ACK_FILTER]) >= sizeof(__u32)) { + ack_filter = rta_getattr_u32(tb[TCA_CAKE_ACK_FILTER]); + } + if (tb[TCA_CAKE_SPLIT_GSO] && + RTA_PAYLOAD(tb[TCA_CAKE_SPLIT_GSO]) >= sizeof(__u32)) { + split_gso = rta_getattr_u32(tb[TCA_CAKE_SPLIT_GSO]); + } + if (tb[TCA_CAKE_RAW]) { + raw = 1; + } + if (tb[TCA_CAKE_RTT] && + RTA_PAYLOAD(tb[TCA_CAKE_RTT]) >= sizeof(__u32)) { + interval = rta_getattr_u32(tb[TCA_CAKE_RTT]); + } + + if (wash) + print_string(PRINT_FP, NULL, "wash ", NULL); + print_bool(PRINT_JSON, "wash", NULL, wash); + + if (ingress) + print_string(PRINT_FP, NULL, "ingress ", NULL); + print_bool(PRINT_JSON, "ingress", NULL, ingress); + + if (ack_filter == CAKE_ACK_AGGRESSIVE) + print_string(PRINT_ANY, "ack-filter", "ack-filter-%s ", + "aggressive"); + else if (ack_filter == CAKE_ACK_FILTER) + print_string(PRINT_ANY, "ack-filter", "ack-filter ", "enabled"); + else + print_string(PRINT_JSON, "ack-filter", NULL, "disabled"); + + if (split_gso) + print_string(PRINT_FP, NULL, "split-gso ", NULL); + print_bool(PRINT_JSON, "split_gso", NULL, split_gso); + + if (interval) + print_string(PRINT_FP, NULL, "rtt %s ", + sprint_time(interval, b2)); + print_uint(PRINT_JSON, "rtt", NULL, interval); + + if (raw) + print_string(PRINT_FP, NULL, "raw ", NULL); + print_bool(PRINT_JSON, "raw", NULL, raw); + + if (atm == CAKE_ATM_ATM) + print_string(PRINT_ANY, "atm", "%s ", "atm"); + else if (atm == CAKE_ATM_PTM) + print_string(PRINT_ANY, "atm", "%s ", "ptm"); + else if (!raw) + print_string(PRINT_ANY, "atm", "%s ", "noatm"); + + print_int(PRINT_ANY, "overhead", "overhead %d ", overhead); + + if (mpu) + print_uint(PRINT_ANY, "mpu", "mpu %u ", mpu); + + if (memlimit) { + print_uint(PRINT_JSON, "memlimit", NULL, memlimit); + print_string(PRINT_FP, NULL, "memlimit %s", + sprint_size(memlimit, b1)); + } + + return 0; +} + +static void cake_print_json_tin(struct rtattr **tstat) +{ +#define PRINT_TSTAT_JSON(type, name, attr) if (tstat[TCA_CAKE_TIN_STATS_ ## attr]) \ + print_u64(PRINT_JSON, name, NULL, \ + rta_getattr_ ## type((struct rtattr *) \ + tstat[TCA_CAKE_TIN_STATS_ ## attr])) + + open_json_object(NULL); + PRINT_TSTAT_JSON(u64, "threshold_rate", THRESHOLD_RATE64); + PRINT_TSTAT_JSON(u64, "sent_bytes", SENT_BYTES64); + PRINT_TSTAT_JSON(u32, "backlog_bytes", BACKLOG_BYTES); + PRINT_TSTAT_JSON(u32, "target_us", TARGET_US); + PRINT_TSTAT_JSON(u32, "interval_us", INTERVAL_US); + PRINT_TSTAT_JSON(u32, "peak_delay_us", PEAK_DELAY_US); + PRINT_TSTAT_JSON(u32, "avg_delay_us", AVG_DELAY_US); + PRINT_TSTAT_JSON(u32, "base_delay_us", BASE_DELAY_US); + PRINT_TSTAT_JSON(u32, "sent_packets", SENT_PACKETS); + PRINT_TSTAT_JSON(u32, "way_indirect_hits", WAY_INDIRECT_HITS); + PRINT_TSTAT_JSON(u32, "way_misses", WAY_MISSES); + PRINT_TSTAT_JSON(u32, "way_collisions", WAY_COLLISIONS); + PRINT_TSTAT_JSON(u32, "drops", DROPPED_PACKETS); + PRINT_TSTAT_JSON(u32, "ecn_mark", ECN_MARKED_PACKETS); + PRINT_TSTAT_JSON(u32, "ack_drops", ACKS_DROPPED_PACKETS); + PRINT_TSTAT_JSON(u32, "sparse_flows", SPARSE_FLOWS); + PRINT_TSTAT_JSON(u32, "bulk_flows", BULK_FLOWS); + PRINT_TSTAT_JSON(u32, "unresponsive_flows", UNRESPONSIVE_FLOWS); + PRINT_TSTAT_JSON(u32, "max_pkt_len", MAX_SKBLEN); + PRINT_TSTAT_JSON(u32, "flow_quantum", FLOW_QUANTUM); + close_json_object(); + +#undef PRINT_TSTAT_JSON +} + +static int cake_print_xstats(struct qdisc_util *qu, FILE *f, + struct rtattr *xstats) +{ + struct rtattr *st[TCA_CAKE_STATS_MAX + 1]; + SPRINT_BUF(b1); + int i; + + if (xstats == NULL) + return 0; + +#define GET_STAT_U32(attr) rta_getattr_u32(st[TCA_CAKE_STATS_ ## attr]) +#define GET_STAT_S32(attr) (*(__s32 *)RTA_DATA(st[TCA_CAKE_STATS_ ## attr])) +#define GET_STAT_U64(attr) rta_getattr_u64(st[TCA_CAKE_STATS_ ## attr]) + + parse_rtattr_nested(st, TCA_CAKE_STATS_MAX, xstats); + + if (st[TCA_CAKE_STATS_MEMORY_USED] && + st[TCA_CAKE_STATS_MEMORY_LIMIT]) { + print_string(PRINT_FP, NULL, " memory used: %s", + sprint_size(GET_STAT_U32(MEMORY_USED), b1)); + + print_string(PRINT_FP, NULL, " of %s\n", + sprint_size(GET_STAT_U32(MEMORY_LIMIT), b1)); + + print_uint(PRINT_JSON, "memory_used", NULL, + GET_STAT_U32(MEMORY_USED)); + print_uint(PRINT_JSON, "memory_limit", NULL, + GET_STAT_U32(MEMORY_LIMIT)); + } + + if (st[TCA_CAKE_STATS_CAPACITY_ESTIMATE64]) { + print_string(PRINT_FP, NULL, " capacity estimate: %s\n", + sprint_rate(GET_STAT_U64(CAPACITY_ESTIMATE64), b1)); + print_uint(PRINT_JSON, "capacity_estimate", NULL, + GET_STAT_U64(CAPACITY_ESTIMATE64)); + } + + if (st[TCA_CAKE_STATS_MIN_NETLEN] && + st[TCA_CAKE_STATS_MAX_NETLEN]) { + print_uint(PRINT_ANY, "min_network_size", + " min/max network layer size: %12u", + GET_STAT_U32(MIN_NETLEN)); + print_uint(PRINT_ANY, "max_network_size", + " /%8u\n", GET_STAT_U32(MAX_NETLEN)); + } + + if (st[TCA_CAKE_STATS_MIN_ADJLEN] && + st[TCA_CAKE_STATS_MAX_ADJLEN]) { + print_uint(PRINT_ANY, "min_adj_size", + " min/max overhead-adjusted size: %8u", + GET_STAT_U32(MIN_ADJLEN)); + print_uint(PRINT_ANY, "max_adj_size", + " /%8u\n", GET_STAT_U32(MAX_ADJLEN)); + } + + if (st[TCA_CAKE_STATS_AVG_NETOFF]) + print_uint(PRINT_ANY, "avg_hdr_offset", + " average network hdr offset: %12u\n\n", + GET_STAT_U32(AVG_NETOFF)); + + /* class stats */ + if (st[TCA_CAKE_STATS_DEFICIT]) + print_int(PRINT_ANY, "deficit", " deficit %u", + GET_STAT_S32(DEFICIT)); + if (st[TCA_CAKE_STATS_COBALT_COUNT]) + print_uint(PRINT_ANY, "count", " count %u", + GET_STAT_U32(COBALT_COUNT)); + + if (st[TCA_CAKE_STATS_DROPPING] && GET_STAT_U32(DROPPING)) { + print_bool(PRINT_ANY, "dropping", " dropping", true); + if (st[TCA_CAKE_STATS_DROP_NEXT_US]) { + int drop_next = GET_STAT_S32(DROP_NEXT_US); + + if (drop_next < 0) { + print_string(PRINT_FP, NULL, " drop_next -%s", + sprint_time(drop_next, b1)); + } else { + print_uint(PRINT_JSON, "drop_next", NULL, + drop_next); + print_string(PRINT_FP, NULL, " drop_next %s", + sprint_time(drop_next, b1)); + } + } + } + + if (st[TCA_CAKE_STATS_P_DROP]) { + print_uint(PRINT_ANY, "blue_prob", " blue_prob %u", + GET_STAT_U32(P_DROP)); + if (st[TCA_CAKE_STATS_BLUE_TIMER_US]) { + int blue_timer = GET_STAT_S32(BLUE_TIMER_US); + + if (blue_timer < 0) { + print_string(PRINT_FP, NULL, " blue_timer -%s", + sprint_time(blue_timer, b1)); + } else { + print_uint(PRINT_JSON, "blue_timer", NULL, + blue_timer); + print_string(PRINT_FP, NULL, " blue_timer %s", + sprint_time(blue_timer, b1)); + } + } + } + +#undef GET_STAT_U32 +#undef GET_STAT_S32 +#undef GET_STAT_U64 + + if (st[TCA_CAKE_STATS_TIN_STATS]) { + struct rtattr *tstat[TC_CAKE_MAX_TINS][TCA_CAKE_TIN_STATS_MAX + 1]; + struct rtattr *tins[TC_CAKE_MAX_TINS + 1]; + int num_tins = 0; + + parse_rtattr_nested(tins, TC_CAKE_MAX_TINS, + st[TCA_CAKE_STATS_TIN_STATS]); + + for (i = 1; i <= TC_CAKE_MAX_TINS && tins[i]; i++) { + parse_rtattr_nested(tstat[i-1], TCA_CAKE_TIN_STATS_MAX, + tins[i]); + num_tins++; + } + + if (!num_tins) + return 0; + + if (is_json_context()) { + open_json_array(PRINT_JSON, "tins"); + for (i = 0; i < num_tins; i++) + cake_print_json_tin(tstat[i]); + close_json_array(PRINT_JSON, NULL); + + return 0; + } + + + switch (num_tins) { + case 3: + fprintf(f, " Bulk Best Effort Voice\n"); + break; + + case 4: + fprintf(f, " Bulk Best Effort Video Voice\n"); + break; + + default: + fprintf(f, " "); + for (i = 0; i < num_tins; i++) + fprintf(f, " Tin %u", i); + fprintf(f, "\n"); + }; + +#define GET_TSTAT(i, attr) (tstat[i][TCA_CAKE_TIN_STATS_ ## attr]) +#define PRINT_TSTAT(name, attr, fmts, val) do { \ + if (GET_TSTAT(0, attr)) { \ + fprintf(f, name); \ + for (i = 0; i < num_tins; i++) \ + fprintf(f, " %12" fmts, val); \ + fprintf(f, "\n"); \ + } \ + } while (0) + +#define SPRINT_TSTAT(pfunc, type, name, attr) PRINT_TSTAT( \ + name, attr, "s", sprint_ ## pfunc( \ + rta_getattr_ ## type(GET_TSTAT(i, attr)), b1)) + +#define PRINT_TSTAT_U32(name, attr) PRINT_TSTAT( \ + name, attr, "u", rta_getattr_u32(GET_TSTAT(i, attr))) + +#define PRINT_TSTAT_U64(name, attr) PRINT_TSTAT( \ + name, attr, "llu", rta_getattr_u64(GET_TSTAT(i, attr))) + + SPRINT_TSTAT(rate, u64, " thresh ", THRESHOLD_RATE64); + SPRINT_TSTAT(time, u32, " target ", TARGET_US); + SPRINT_TSTAT(time, u32, " interval", INTERVAL_US); + SPRINT_TSTAT(time, u32, " pk_delay", PEAK_DELAY_US); + SPRINT_TSTAT(time, u32, " av_delay", AVG_DELAY_US); + SPRINT_TSTAT(time, u32, " sp_delay", BASE_DELAY_US); + SPRINT_TSTAT(size, u32, " backlog ", BACKLOG_BYTES); + + PRINT_TSTAT_U32(" pkts ", SENT_PACKETS); + PRINT_TSTAT_U64(" bytes ", SENT_BYTES64); + + PRINT_TSTAT_U32(" way_inds", WAY_INDIRECT_HITS); + PRINT_TSTAT_U32(" way_miss", WAY_MISSES); + PRINT_TSTAT_U32(" way_cols", WAY_COLLISIONS); + PRINT_TSTAT_U32(" drops ", DROPPED_PACKETS); + PRINT_TSTAT_U32(" marks ", ECN_MARKED_PACKETS); + PRINT_TSTAT_U32(" ack_drop", ACKS_DROPPED_PACKETS); + PRINT_TSTAT_U32(" sp_flows", SPARSE_FLOWS); + PRINT_TSTAT_U32(" bk_flows", BULK_FLOWS); + PRINT_TSTAT_U32(" un_flows", UNRESPONSIVE_FLOWS); + PRINT_TSTAT_U32(" max_len ", MAX_SKBLEN); + PRINT_TSTAT_U32(" quantum ", FLOW_QUANTUM); + +#undef GET_STAT +#undef PRINT_TSTAT +#undef SPRINT_TSTAT +#undef PRINT_TSTAT_U32 +#undef PRINT_TSTAT_U64 + } + return 0; +} + +struct qdisc_util cake_qdisc_util = { + .id = "cake", + .parse_qopt = cake_parse_opt, + .print_qopt = cake_print_opt, + .print_xstats = cake_print_xstats, +}; --- a/tc/q_ingress.c +++ b/tc/q_ingress.c @@ -40,7 +40,7 @@ static int ingress_parse_opt(struct qdis static int ingress_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt) { - fprintf(f, "---------------- "); + print_string(PRINT_FP, NULL, "---------------- ", NULL); return 0; }