aboutsummaryrefslogtreecommitdiffstats
path: root/src/vnet/tcp/tcp.h
AgeCommit message (Collapse)AuthorFilesLines
2022-01-12session: pass tx buffers in bulk to transportsFlorin Coras1-2/+2
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I1025cccd784f80b557847f69c3ea1ada5c9de60d
2021-11-03tcp: make buffer reset function publicFlorin Coras1-0/+1
Also does a bit of code cleanup. Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ifbff1e03a2e1fdca98925fdd3db7eb230ff24a37
2021-10-06tcp: fix severity infoFilip Tehlar1-1/+1
Type: fix Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ibe39bc045c3b154209a83b59ef95a37c61b32c0c
2021-07-06tcp: use main thread pool for half-opensFlorin Coras1-7/+1
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I4b3427b966f9ff1ba8895fed7db662d56650f3f5
2021-06-22tcp: api cleanupFilip Tehlar1-0/+3
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: I3c06e9cb3fabdcdce9c17e93cfedfd771295f589
2021-06-15tcp: prevent timer handler being called frequentlyliuyacan1-0/+3
In the current implement, tcp would start or up an one tick retransmit timer for that connection if vlib_buffer_alloc() return 0. Now the tick is 0.1ms, this means that if VPP is in a buffer shortage state, there would be a large number of burst timer expirations. This commit limits the minimum interval of the retransmission timer to 100ms. Type: fix Signed-off-by: liuyacan <liuyacan@corp.netease.com> Change-Id: Ia11d693fe46119c5dc16b24ca93c30c31109057a
2021-05-14tcp: remove ho lockFlorin Coras1-2/+0
Half-open sessions are allocated by main thread and cleaned up on main with timers. Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I37f000920a45908b62b5501ae9d54a88a9e4c609
2021-05-01vlib: refactor trajectory trace debug featureBenoît Ganne1-9/+0
trajectory trace has been broken for a while because we used to save the buffer trajectory in a vector pointed to in opaque2. This does not work well when opaque2 is copied (eg. because of a clone) as 2 buffers end up sharing the same vector. This dedicates a full cacheline in the buffer metadata instead when trajectory is compiled in. No dynamic allocation, no sharing, no tears. Type: refactor Change-Id: I6a028ca1b48d38f393a36979e5e452c2dd48ad3f Signed-off-by: Benoît Ganne <bganne@cisco.com>
2021-04-14session tcp vcl: api to update connection attributesFlorin Coras1-0/+1
Type: feature Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ifdd6024daf044751895bb8d2deabad41d3a80c92
2021-04-05tcp: time infra improvementsFlorin Coras1-4/+7
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I998c0686f9f7dc556dda8b28e23bbed127d0aafc
2020-10-23tcp: remove delack time configFlorin Coras1-3/+0
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Iae5045686c62ad9279be350cffeaa41b8297d179
2020-10-21tcp: updating time constans as timer tick changedRyujiro Shibuya1-7/+7
Type: fix Signed-off-by: Ryujiro Shibuya <ryujiro.shibuya@owmobility.com> Change-Id: Ibe305b96f04ffdc95ddb07d144dc00119ae69a07
2020-09-16tcp: make max gso packet size configurableSimon Zhang1-0/+3
Type: improvement Signed-off-by: Simon Zhang <yuwei1.zhang@intel.com> Change-Id: I14de90f07d825c5c99023996a88173ee855e9a6f
2020-08-03tcp: improve timestamp rtt accuracyFlorin Coras1-3/+1
- switch to using vlib_time as reference for timestamps - use us precision ticks for tcp but keep using ms precision for timestamps. As a result, srtt, rttvar and rto are now measured in us instead of ms. MRTT samples from timestamps are converted from ms to us (not accurate under ms) while high precision samples are used with us precision, i.e., they're no longer converted to ms precision samples. Type: improvement Change-Id: Ibda559575d9b4fdc85b0985264f7c865ff367e34 Signed-off-by: Florin Coras <fcoras@cisco.com>
2020-07-23tcp: track pending timersFlorin Coras1-1/+0
Also removes delack timer and reuses the u32 for the pending timers list. Type: fix Ticket: VPP-1923 Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I4edbb72d5b2aa5e14f87659f49e675af1e834aca
2020-05-24tcp: track buffer alloc failuresFlorin Coras1-0/+1
Reported as part of "show tcp stats" Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I499ab4e41d13aaf1a0d060e37f09087e63d09567
2020-04-04session tls: support tls deschedulingFlorin Coras1-1/+1
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ieb8bb9c6deb92479fdd3e045778fe5ae4782d1ea
2020-04-02tcp: explicit use of timer wheel in timer apisFlorin Coras1-112/+2
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I06120d43c15b2fa3f437ef235bf5f83ec2beb45e
2020-04-02tcp: move features to separate filesFlorin Coras1-939/+24
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ia477b8dba9266f47907967e363c11048e5cd95ab
2020-03-30tcp: reuse session infra for syns and resetsFlorin Coras1-5/+8
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I71df27049ef0193578f0c42f8f8bbd5c54e4d53e
2020-03-23tcp: add lost and in flight to byte trackerFlorin Coras1-1/+7
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I3b0041d72d835cbb11e803cc56ac4c68a68238a0
2020-03-19tcp: move accept init to separate reusable functionFlorin Coras1-0/+8
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I5120eb321e9e2050eb64dca9e2dfb6256ff2b62d
2020-03-19tcp: force deschedule if no send space availableFlorin Coras1-2/+7
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Iae9f118f710153b6c0e390265039db7434e67ed8
2020-03-19session tcp udp: consolidate transport snd apisFlorin Coras1-0/+2
Type: improvement Use only one api to retrieve transport send parameters. Additionally, allow transports to request postponing and descheduling of events. With this, tcp now requests descheduling of sessions when the connections are stuck probing for zero snd_wnd Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I722c974f3e68fa15424c519a1fffacda43af050c
2020-02-25tcp: handle cleanups without timersFlorin Coras1-2/+12
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Ida896e9fbe83b4c76578b089bb3fd2bef5e07fd2
2020-02-24tcp: dynamic max timers per loopFlorin Coras1-0/+3
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: If0a634c277d4f8e4d32321f52253721a990bdb1d
2020-02-18tcp: pace timer handlingFlorin Coras1-8/+11
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I93067054631d6ae2411a7b08d7b681aed7a121b2
2020-02-14tcp: reset fin-wait-2 timeout connectionsFlorin Coras1-0/+1
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Id931f3f308a01788d222d0d62f26f5c579321c6a
2020-02-14tcp: minimal set of worker statsFlorin Coras1-0/+27
Type: feature Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I9dafe564229095d50285276a654f4983f93faff2
2020-02-12tcp: move connections to wrk ctxFlorin Coras1-22/+26
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I06cc3f032a72eacc716eed8d6fe8856a2839def1
2020-02-12tcp: postpone rst handlingFlorin Coras1-6/+10
Type: refactor Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Id09fa54cc5657b3b5616ea6a6180c1344b0141d4
2020-02-10tcp: add option to avoid endpoint cleanupFlorin Coras1-0/+1
Type: feature If set, avoid trying to cleanup the local endpoint table. Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: Iaa382ae74523d608217d2d17544bf1e7d82b2728
2020-01-28session tcp: fix packet tracingFlorin Coras1-0/+1
Type: fix Change-Id: Ib823d016c64998779fb1d00b8aad3acb5e8340be Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-12-27tcp: Enable TCP timewait port useYu Ping1-1/+4
Improve host stack CPS test, and it help improve 10x performance Type: feature Change-Id: I6af61e0bad7c16ee2d30a1422cc46bb89f1cedb4 Signed-off-by: Yu Ping <ping.yu@intel.com> Signed-off-by: Yuwei Zhang <yuwei1.zhang@intel.com>
2019-11-25tcp: invalidate expired timer handles before dispatchingFlorin Coras1-1/+1
Type: fix Change-Id: Icc8cd05cb9c1844a9f8b0399797ad554f4ccf1a1 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-11-21tcp: add no csum offload config optionFlorin Coras1-0/+3
Type: feature Change-Id: I77b3ee74229f3c85e99f74bf9000cb5aedbc1760 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-11-20session tcp: support pacer idle timeoutsFlorin Coras1-1/+0
Type: feature To avoid excessive bursts, pacer must be provided with an estimated rtt for the connection. That's used to compute an idle timeout, i.e., time after which the bucket is reset to 1 mtu due to inactivity. For now, idle timeout is computed as 5% of the rtt. Change-Id: Ia0b752fe7b4ad0ce97b477fb886b0133a2321541 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-11-11tcp: improve lost rxt heuristicFlorin Coras1-2/+8
Type: feature - retransmit first unacked segment if newer retransmitted packets are acked - avoid spurious retransmits if recovery ends with sacked bytes Change-Id: Ic1b56d22e025822edb7609afb136e47440ea6032 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-11-07tcp: fix retransmit with no sacksFlorin Coras1-1/+2
Type: fix Change-Id: I6f7df0d358f57f7feadb9b7a3fcffb99558b2af8 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-11-06tcp: IPv6 flow label supportTarun Gupta1-0/+1
Type:feature For cases when proxy is in use IPv6 flow label received in origin pkt needs to be added to ipv6 header of outgoing pkts from proxy to original destination and vice versa. Signed-off-by: Tarun Gupta <tarungup@cisco.com> Change-Id: I143f7e67237c0f865333078628a016b50ad5e630 Signed-off-by: Tarun Gupta <tarungup@cisco.com>
2019-10-31tcp: track lost rxt segments in byte trackerFlorin Coras1-0/+1
Type: feature Change-Id: I18dfac9c3d2f539edf20dba64cd2b7b541154144 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-23tcp: improve rate samples for retansmitted segmentsFlorin Coras1-2/+3
Type: fix - Initialize max_seq on both transmitted and retransmitted segments - Keep track of segments that have been sacked. - Track new data segments sent during recovery Change-Id: Ice55231a3da200ae6171702e54b2ce155f831143 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-17session tcp: infra for transports to send buffersFlorin Coras1-4/+0
Type: feature Add infra that allows transpors to enqueue pending buffers without the need to build and manage their own pending frames. An important benefit is the fact that buffer wire/tx ordering is ensured by session layer. Change-Id: I764fd1693d610b321a1d0c84b648a314f14583db Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-17tcp: avoid sending acks when data availableFlorin Coras1-0/+1
Type: fix Change-Id: I02e2cb2d349f9ddb2bfed040a08ca448f379d565 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-11tcp: refactor flags into cfg and conn flagsFlorin Coras1-7/+33
Type: refactor Change-Id: Ib5e2ecf55732599e1322736e3662178c9da49c7d Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-10tcp: improve pacing after idle send periodsFlorin Coras1-0/+1
Rest pacer on ack reception if we haven't recently sent anything. Type: feature Change-Id: I820bacd81b65130052dfafbfcbe6ca4553069fbc Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-10tcp: retry lost retransmitsFlorin Coras1-4/+5
Add heuristic that detects lost retransmitted segments and retries sending them. Type: feature Change-Id: I34d1bb16799e1993779222eb2bfad4b40704159e Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-10-10tcp: custom checksum calculations for Ipv4/Ipv6Srikanth A1-0/+3
Type: feature Based on the configuration, we can disable checksum offload capability and calculate checksum while pushing the TCP & IP header. This saves some cycles when VPP stack is used in legacy hardware devices. Signed-off-by: Srikanth A <srakula@cisco.com> Change-Id: Ic1b3fcf3040917e47ee65263694ebf7437ac5668 (cherry picked from commit 3642782a2748503f5b5ccf89d1575c1d489948ef)
2019-09-25tcp: use sacks for timer based recoveryFlorin Coras1-27/+25
Type: feature If available, reuse sack scoreboard in timer triggered retransmit to minimize spurious retransmits. Additional changes/refactoring: - limited transmit updates - add sacked rxt count to scoreboard - prr pacing of fast retransmits - startup pacing updates - changed loss window to flight + mss Change-Id: I057de6a9d6401698bd1031d5cf5cfbb62f2bdf61 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-18tcp: compute snd time for rate sampleFlorin Coras1-2/+2
Type: feature Change-Id: I6bd675dc28dbc34293e895911efe986844c0564f Signed-off-by: Florin Coras <fcoras@cisco.com>