Age | Commit message (Collapse) | Author | Files | Lines |
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id2c06f49bcae1a26a2d16d58f9da7a4d3175bf3c
|
|
Experimental support for session layer interrupt mode. When enabled
(use-private-rx-mqs must be set) session queue node switches to
interrupt state when lightly loaded, i.e., no events and less than 1
vector/dispatch.
Because transport protocols require a periodic time update, when in
interrupt state the session queue node workers register a timerfd with
the unix-epoll-input node that when triggered signals, i.e., wakes up,
the queue node. Under light load, the timer is set to trigger every 1ms
whereas if no session is allocated, the worker moves to idle state and
the timeout is set to 100ms.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I905b00777fbc025faf9c4074fce4c516cd139387
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I998c0686f9f7dc556dda8b28e23bbed127d0aafc
|
|
Add option to use per app private segments for app to vpp message
queues, as opposed to exposing internal message queues segment.
When so configured, internal message queues are still polled by the
session queue node but external app message queues are handled by a new
input node (appsl-rx-mqs-input) that runs in interrupt state. Signaling
of the node, when mqs receive new messages, is done through eventfds
epolled by worker epoll input nodes.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Iffe8ce5a9944a56a14e6d0f492a850cb9e392d16
|
|
Type: improvement
Change-Id: If3da7d4338470912f37ff1794620418d928fb77f
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: fix
Signed-off-by: Ivan Shvedunov <ivan4th@gmail.com>
Change-Id: I3fdc1711d508bc5b0c2f56b3bd3fb4a56056eb54
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I6ed2104e9d79c367ca36460047586f9b632c3315
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I2828287c58115aa08c0a4297c01cea60f41f4749
|
|
Avoid synchronizing producers and the consumer. Instead, only use mutex
or spinlock (if eventfds are configured) to synchronize producers.
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ie2aafbdc2e07fced5d5e46ee2df6b30a186faa2f
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I1658a9c19d8eae4c9a42c0a111d4ad343b8eb8a4
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ic373cd2c11272da539eb4b0db27227f36f2f9688
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I1440c11fb9d962a05d877aebb4de364c86f9953e
|
|
Instead of enforcing a "strict" release of data, which relies on
frequent rescheduling of sessions, allow some pacer coalescing, i.e.,
short bursts, that can minimize load on scheduler/session layer and
potentially leverage tso.
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I67e38e5b8dc335bd214113b70c68c27ae92bd6da
|
|
When using classifier to filter traces, not all packets will be traced.
In that case, we should only count traced packets.
Type: fix
Change-Id: I87d1e217b580ebff8c6ade7860eb43950420ae78
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I9e6b5e245533c9ea7bb8dc4f784a31fcb0da88bd
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I69e912ddf64d8ec89f8d93e02a201781b99de0bd
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I769174f0023d00a59bc5a03cf0a05996b616742b
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ia36d86eb108f0651fc3af8b4dbdc2d0b49e283da
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I664cd14c84fc5cf2ffe61efce99c95219b44fad7
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I749f36a7062bf9b073c1b6753436c23ba326a5db
|
|
Request connected udp listener behavior by setting
VPPCOM_ATTR_SET_CONNECTED attribute with vppcom_session_attr
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Iba95155c0f41cea8c6e1a4263946270d49c213ac
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ifa4916ffeaa30039e366011109bbd2e9c91a1b0b
|
|
Type: fix
Change-Id: Ie60b07abe76ad166f048f5885accd7038d8153b2
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ie6c03195019fe18c547b22f4387d7f2b14b71461
|
|
Type: feature
Enhancing the debugging capability of tcp session layer by measing time spent for various events.
This is meant only for debugging purpose
Signed-off-by: Srikanth Akula <srakula@cisco.com>
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I9f401881b345bcae5f7d8050338637fd47b3723b
Signed-off-by: Srikanth Akula <srakula@cisco.com>
|
|
Type: refactor
Signed-off-by: Simon Zhang <yuwei1.zhang@intel.com>
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I11cf806e22158e021a9a405eb4487a9ed6fdbccf
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ida8f9e759b4990ea6e34e71dc45bdb3b5eabc27f
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ie7102355b95eefb233ec7d146e61819051a7bf07
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ieb8bb9c6deb92479fdd3e045778fe5ae4782d1ea
|
|
Type: improvement
- allow apps to request rescheduling of tx events via
SESSION_F_CUSTOM_TX flag
- limit max burst per session custom tx dispatch
In tls
- use the new infra to reschedule tx events
- use max burst bytes as upper limit to number of bytes to be encrypted
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I544a5a3337af7ebdff3406b776adf30cf96ebf3c
|
|
Type: improvement
Change-Id: I9dd850a1ce85b0adb5136233f176117e0ee38817
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I840d43e79b1f826380bd56485441510e45bdfc7f
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ib4bc2ce781887a84055a4d5cdb7f453fc7d52c79
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I6aaaec20a2b6d4c6ddfbe659d9402acc1be2f7e2
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I71df27049ef0193578f0c42f8f8bbd5c54e4d53e
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Iae9f118f710153b6c0e390265039db7434e67ed8
|
|
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
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I01441e958517e31260e67c8caea5f75d684b2711
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ic9174c92ab05b58e62b00999fe9cbf4e9292d43e
|
|
Type: improvement
Unset fifo tx event only if all data has been dequeued. Avoids frequent
re-scheduling of sessions as new sessions.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I36a4c90b97e0255b88782032fb029640e6a73e90
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Idaa7cc26ad941be86daec4ed5920727237712f4a
|
|
Type: fix
Change-Id: Ib823d016c64998779fb1d00b8aad3acb5e8340be
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Call session queue node with the right node runtime instead of the
pre-input node runtime.
Type: fix
Change-Id: I43d20bed4930fc877b187ce7ecdce62034b393c5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I166ab7b96444587a3252925d3a28505e0db52d74
|
|
Type: feature
Change-Id: I3a642626a444504594c5e3df40dbc92df54136f0
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: fix
Change-Id: I8b8875f1dc9203dfbb443ac43df8250cbb0b1edc
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
Type: fix
Change-Id: I7416e827fbc5c63d082273656441c81dd6246d8a
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
This patch adds the logic to pass to connect &
listen msg in the mq the following parameters
* ckpair index
* crypto engine (for now only used in quic)
Change-Id: I7213d8b581cb4532a9a6b18c4b3fe021287b7733
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: refactor
Change-Id: Ic1c3e1f7987702cd88972acc34849dc1f585d5fe
Signed-off-by: Florin Coras <fcoras@cisco.com>
|