Age | Commit message (Collapse) | Author | Files | Lines |
|
Type: refactor
Change-Id: Ic1c3e1f7987702cd88972acc34849dc1f585d5fe
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Improves fairness for sessions that are snd space or pacer constrained.
Change-Id: Ida5f523090f1dcbfb17bf5116bc7917747ac8593
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
Type: fix
Connect ctrl message recently outgrew the maximum ctrl msg size, so
increase the limit. Also add static asserts for messages that could
potentially exceed the limit.
Change-Id: I0d3e32e0d4d67d7e222cff14ddba59a0c3fb8b00
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Allow session cli filtering based on thread index, transport protocol,
session state and range of session pool indices. For instance
show session thread 1 proto tcp state ready range 0 20 verbose
Shows the session ids for the first 20 tcp sessions in thread 1 that are
in ready state.
To avoid excessive output that could reasult in the worker barrier being
held by the main thread for long periods of time, the session cli will
only output:
- session ids (verbose == 1) for a maximum of 50 sessions / worker
- verbose > 1 details for a maximum of 10 sessions
Change-Id: I2cfb351b548e2e0a1d5b4345810be613e2917d17
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type:refactor
Moves connect, disconnect, bind, unbind and app detach to message
queue from binary api. Simplifies app/vcl interaction with the session
layer since all session control messages are now handled over the mq.
Add/del segment messages require internal C api changes which affect all
builtin applications. They'll be moved in a different patch and might
not be back portable to 19.08.
Change-Id: I93f6d18e551b024effa75d47f5ff25f23ba8aff5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
This can be used to forcefully close a session. It's only available to
builtin applications for now. Transports must support the reset api
otherwise normal close is used.
Change-Id: I5e6d681cbc4c8045385e293e0e9d86fa2bf45849
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Change-Id: I5e030b23943c012d8191ff657165055d33ec87a2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Control ack generation and retransmissions with session layer scheduler.
Change-Id: Iacdf9f84ab81f44851980aa45a83e75f29be2b7b
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type:refactor
Change-Id: Id796d0103e61e15c35a586d8cbd3d8916487b84d
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type:feature
Change-Id: I67a52ee48963a66915e2ebd116626eb9c296a9a5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: refactor
Change-Id: I24159e0a848f552b4e27acfb5fe6f2cd91b50a19
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: refactor
Change-Id: I97fa59a0ba0b6b7a98698926020ffffcf6ae6ba3
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Change-Id: I58e713661a38cecbfdebd4609292d9d12e880cd2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
This allows QUIC & TLS specific logic to be implemented, and meaningfull
IP/port to be returned when connection is overridden.
Change-Id: Id79c59fe4d7b16d36f0e96ad3e281c4026b5fe65
Signed-off-by: Aloys Augustin <aloaugus@cisco.com>
|
|
Problems Addressed:
- Contention of cursize by producer and consumer.
- Reduce the no of modulo operations.
Changes:
- Synchronization between producer and consumer changed from cursize
to head and tail indexes
Implications: reduces the usable size of fifo by 1.
- Using weaker memory ordering C++11 atomics to access head and tail
based on producer and consumer role.
- Head and tail indexes are unsigned 32 bit integers. Additions and
subtraction on them are implicit 32 bit Modulo operation.
- Adding weaker memory ordering variants of max_enq, max_deq, is_empty
and is_full Using them appropriately in all places.
Perfomance improvement (iperf3 via Hoststack):
iperf3 Server: Marvell ThunderX2(AArch64) - iperf3 Client: Skylake(x86)
~6%(256 rxd/txd) - ~11%(2048 rxd/txd)
Change-Id: I1d484e000e437430fdd5a819657d1c6b62443018
Signed-off-by: Sirshak Das <sirshak.das@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
|
|
- Avoid doing cc in closing states.
- Rest connections closed with unread data
Change-Id: I97d46b0459f03ea5439eeb0f233b6c17d3e06dfd
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Currently supports on single stream exposed through standard internal APIs
Based on libquicly & picotls by h2o
Change-Id: I7bc1ec0e399d1fb02bfd1da91aa7410076d08d14
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Change-Id: I4a119937842eb188f5e5a7706cbe70e91ae4def8
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- use flag instead of enqueue_epoch for enqueueing rx events.
- use flag for proxy sessions
Change-Id: Iec3eee55a68d02536ece6329348a3369c7c7412e
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Instead of allocating pairs of message queues per cut-thru session and
having the applications map them, this uses vpp as an io event message
switch.
Change-Id: I51db1c7564df479a7d1a3288342394251fd188bb
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- remove unused functions
- rename old "stream" functions
Change-Id: Icbb03daa9f9f1c58b5be5c38aa8a9cbcf9159b47
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I87bdf705341dd760f0be907a663aa64140977d39
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Move local session to separate header and source files. First step to
refactoring local sessions.
Change-Id: I280fdfef20ba8a0977d15c1c8ce030ea2fb72dde
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I92a009b9630b0d882ea3c5c99aad88ed6f5109a0
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I1662ec4b5503cb64a8a86a2441842311d959b3a6
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I286d0d53a9ef2d6e28cd301eae25fc119d491f22
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Make app-listener the handle for app listens. Consequently transport and
local listen sessions are now associated to the app-listener.
Change-Id: I9397a26d42cccb100970b6b4794c15bac2e11465
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- move transport specific types to transport_types
- add transport wrapper functions for interaction with transport
protocol vfts
Change-Id: I93f70d884585fc2f41c4a605e310c80e8a8972f2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Aggregate session specific types, getters and setters under
session_types.h
Change-Id: Ib205337502654969d60c72d1800c90247e1a9068
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Rename core data structures. This will break compatibility for out of
tree builtin apps.
- stream_session_t to session_t
- server_rx/tx_fifo to rx/tx_fifo
- stream_session.h to session_types.h
- update copyright
Change-Id: I414097c6e28bcbea866fbf13b8773c7db3f49325
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I2ad54b20b96f10b009c3e651b2a2f885577ca5b6
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ied476c417c8ba5b4d7c615125c36eecd9ca64fbc
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
In case of multi process apps, after forking, the parent may decide to
close part or all of the sessions it shares with the child. Because the
sessions have fifos allocated in the parent's segment manager, they must
be moved to the child's segment manager.
Change-Id: I85b4c8c8545005724023ee14043647719cef61dd
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
In addition to that, a bit of refactoring.
Change-Id: Iea1eabc2167bcdef185ec53bc09bae087c5398e6
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I90056176194cb2a144d49a3cb283653d8d30f051
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Also cleanup session table when transport closes and app didn't reply to
the close notification.
Change-Id: Ie3d518e3afff73437561561b46dbf695c24632ad
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
For tcp this means that the last enqueued data goes out with a psh bit
set.
Change-Id: I29d357ecae6f02e748b59a7b799150ec73d14ba2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I03884b6cde9d4c38ae13d1994fd8d37d44016ef0
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Id4f37f5d4a03160572954a416efa1ef9b3d79ad1
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Instead of reusing buffers for acking, consume all buffers and program
output for (dup)ack generation. This implicitly fixes the drop counters
that were artificially inflated by both data and feedback traffic.
Moreover, the patch also significantly reduces the ack traffic as we now
only generate an ack per frame, unless duplicate acks need to be sent.
Because of the reduced feedback traffic, a sender's rx path and a
receiver's tx path are now significantly less loaded. In particular, a
sender can overwhelm a 40Gbps NIC and generate tx drop bursts for low
rtts. Consequently, tx pacing is now enforced by default.
Change-Id: I619c29a8945bf26c093f8f9e197e3c6d5d43868e
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Also reset pacer on tcp retransmit timeout
Change-Id: I5a9edee4c00d1d169248d79587a9b10437c2bd87
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
If sessions cannot be handled during the current dispatch loop
iteration, ensure that they are first to be handled in the next.
Change-Id: Ifc6215900f8cfd530d4886b58641189f0ccf9bb7
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I66ca0ddea872948507d078e405eb90f9f3a0e897
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ie4c5cfc4c97acb321a46b4df589dc44de1b616ba
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Adds tx pacing infrastructure for transport protocols that want to use
it. Particularly useful for connections with non-negligible rtt and
constrained network throughput as it avoids large tx bursts that lead to
local interface tx or network drops.
By default the pacer is disabled. To enabled it for tcp, add tx-pacing
to tcp's startup conf. We are still slightly inefficient in the handling
of incoming packets in established state so the pacer slightly affect
maximum throughput in low lacency scenarios.
Change-Id: Id445b2ffcd64cce015f75b773f7d722faa0f7ca9
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- ensure session enqueue epoch does not wrap between two enqueues
- use 3 states for echo clients app, to distinguish between starting and
closing phases
- force tcp fin retransmit if out of buffers while sending a fin
Change-Id: I6f2cab46affd1148aba2a33fb6d58bcc54f32805
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
TLS can enqueue events to itself when app session queue cannot be
entirely drained. If a pending disconnect is handled before any such
event, session layer may try to dequeue data on deallocated sessions.
Change-Id: I5bfc4d53ce95bc16b6a01e1b0e644aafa1ca311b
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I6201a044e70ab6a58db8212960c57edc77c41f96
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Allows app workers to listen on the same session endpoint. Incoming
connects are spread across the workers in a round-robin fashion
Change-Id: Ib5f5817230d9abc6127a85cdbdcad70d980c0f7f
Signed-off-by: Florin Coras <fcoras@cisco.com>
|