Age | Commit message (Collapse) | Author | Files | Lines |
|
Change-Id: Id6e82910f8d991e355d3f26222eea4ac3ab091b1
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Upstream DPDK changed the names of the options to use dlopen()
with libibverbs and libmlx[45] from RTE_LIBRTE_MLX[45]_DLOPEN_DEPS
to RTE_IBVERBS_LINK_DLOPEN (handles both mlx4 and mlx5).
VPP's build option to enable this configuration when building DPDK
no longer worked starting when VPP moved to DPDK 19.02. Update VPP's
build options to enable the correct option name.
Change-Id: I8e34e1d3fc4ee8aac4fd6f2a7d27177f2b0dea50
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Change-Id: Icb919a053b35ef62f958c60c725d3aae4c32358f
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Change-Id: I0af8104f6d35820aa39d22cd23d4f9211d61faa0
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Change-Id: Id3c281e680683c7267c9db66cc806fed58c8cfcb
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
- Switches local connects to cut-thru transport
- Removes local sessions as a separate session type
Change-Id: I997c6355d8c8e4f2110678f785b0f5d96bba47f7
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ica6a0b4133ccc1997ef0547274982d0cc9761724
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
They mask dependencies and confuse third party tools.
Change-Id: I24ee16bfa0d746a8e8cb99891ba8b20523048b69
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Naveen suggested earlier today that we should refactor duplicate code.
This commit kicks off the effort.
Change-Id: I855b0f40d41d1f3a2e673f3b254b76b596409656
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Comes in handy when looking at core files from optimized images.
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I45c8400d15614d5a04a3dcfb9b7daccab47ab446
|
|
Change-Id: I22f866bacbc9c6e3abb0405f5c5a205910cec17b
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
|
|
Change-Id: I9c92d51cc0e9dccf3c3726c4de8d7f15537778c9
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: Id8a48299eb26f62561b54aa4d240d312f47a952d
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
wrapper/decorator.
Change-Id: Iab41bb972e3c7ec005a1a13d5a25f654ae8c3932
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Change-Id: I2c347daeecd5441b8fe3e3f7527a8e21844668d0
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Change-Id: I087b057da526c18f8cce1902dcb594dd5ce0a4b8
Signed-off-by: Naveen Joy <najoy@cisco.com>
|
|
Expose interface name to sw_if_index table as a directory node in the stats segment.
Change-Id: Ie50e4af01997d141880f02e3a8496bfeb91b9944
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: I7b74b0b98b2c427bf29bb1d2932044d9924588cb
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I55f45d84212e2293e3798dff6850d86d75414d02
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Change-Id: I4adf713f4a1d596b9c8a78b79b5df2c7eb0c56f0
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I5ef8b3f4be40a7a0b0f1cb90dc0e15a4711e8664
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Introduce a cut-through transport as replacement to local sessions. This
first patch removes the per app local listener pools and switches local
listeners to sessions with cut-through transport.
Change-Id: I98b20c25bc5df5f4110bf66f76c650a973032618
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I326204d26b613254e39c6a0ffe9f9491981ba3c3
Signed-off-by: jdenisco <jdenisco@cisco.com>
|
|
Change-Id: I8b59b2e1c0525abf4b0492e50a7af57df4cd3ce2
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
More detail on why it's important to supply .debs or .rpms which
precisely match core files. Probably won't help, but we can try...
Change-Id: I7842eaea0ef921b934e84b7f18f6a333b1381292
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Me: "Mr Coverity, I thought I fixed the dead code warning just few days ago in
this file. Why are you still complaining about the same stuff to me?"
Mr. Coverity: "Duh! But you are supposed to fix all occurences in the same file."
Me: "Mr. Coverity, I didn't see you flag the warning in the other places last
time?"
Mr. Coverity: "Shh! That is the secret of my dark side!"
Change-Id: I565eccd90bf1bb39c9881664d361f83396ca8bcc
Signed-off-by: Steven Luong <sluong@cisco.com>
|
|
Change-Id: If6b0edb0dd242e0ef6953c8f4c1826eb80b9e1cc
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
session synchronization so that we can build a plain active-passive HA NAT pair
Change-Id: I21db200491081ca46b7af3e82afc677c1985abf4
Signed-off-by: Matus Fabian <matfabia@cisco.com>
|
|
Change-Id: I6819dd9dbfc15c17740bdb98b51bdd639ef8c4d2
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Configurable up to 16 RX queues per interface. Default is 1.
Change-Id: If9e2beffeb7e7dc8c2264b4db902132b2fea02c1
Signed-off-by: Steven Luong <sluong@cisco.com>
|
|
Grab the thread barrier across a set of RPCs, to greatly increase
efficiency. Avoids running afoul of the barrier sync holddown
timer.
Change-Id: I782dfdb1bed398b290169c83266681c9edd57a3f
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Iafe8b3a38f2a7d7571e60db91608d8130bb07cb3
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Change-Id: I500b8e72d7e021b9564dad0ffc087cb0e1ceb96f
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: Iaa78ee181589584885b0f377eafb89e603718bd4
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: I1d92bec29c718de7a517bbbb335d09c68c221c71
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Update the syntax to support abstract classes in python 2 and python 3.
Depends on: new style classes -- https://gerrit.fd.io/r/16166
Change-Id: Iad2c1240149f38b3faca1b37ab95d3d210e1daee
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Add lro/tso and rx checksum support. lro/tso is configured via startup.conf
vmxnet3 { lro }
It is disable by default due to not all versions of ESXi supports it.
Change-Id: Icf224ff528884ecd9e655b4fcf4481194e8c5a63
Signed-off-by: Steven Luong <sluong@cisco.com>
|
|
Moved code to the ethernet input node, and the interface output
path(s). Since we no longer skip ethernet-input, there's no reason
for device drivers to know anything about pcap rx tracing, etc.
Change-Id: I08d32fb1b90cbee1bd4f609837d533e047b36fa4
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
mmap does not fail but writing to mapped memory is causing sigbus.
Change-Id: I5135f32eede67fccb4aaa07a501cd262d254ed8d
Signed-off-by: Artem Belov <artem.belov@xored.com>
|
|
Use the installed version of pip. If a newer version of pip is needed,
it can be specified in requirements.txt. This is to improve idempotence
by providing some control over upstream changes.
Change-Id: I07b7651f8ddba6005bf85d11fef9e3343ee2dcd2
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
This cleans up exception catching to identify oserrors. By raising the
specific exception closer to the offending call, we get additional stack history
and can add clearer error logging to assist in troubleshooting.
Change-Id: I592e4d46844b822a816485bf54910f8daed92088
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Fix what appears to be a cut-n-past error.
Change-Id: I71ee32c1b0d2dc38ed3df4bd24ec4248005a6008
Signed-off-by: Jon Loeliger <jdl@netgate.com>
|
|
Change unicode references to use text_type
Change-Id: Ia71c16e3235bc509abd3b1c651ae125f892ab108
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Problematic:
- It didn't have its counters initialized, so vpp crashed
during a "show map stat"
- Not all the tests for "are there any domains" actually
accounted for the fake entry at pool slot 0.
- Dump details happily returned its bogus entry.
Change-Id: I57aaa9f63917686334fd4a9fa7bc80044bf1718c
Signed-off-by: Jon Loeliger <jdl@netgate.com>
|
|
Change-Id: I20d7c8c1a59b3a9aa016bec860289b7aef4ce06b
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Fix "make TEST=test_vcl test-debug" ASSERT failures.
Change-Id: I58a67b12806660973c8def0e598ef0c5b296eec5
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I606b28dfb820f8f19e338c7642bfe0e4c116ca58
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Ia3f8616cbf424c7f2d29d16cf7a457be6cd1b33a
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
|
|
for easy integration with ptoducts running their own Ike stack.
Without the VPP IKE plugin loaded, the product is free to handle
IKE packets as it pleases.
Change-Id: Id0839f4d58b797f4c2da0382eb499fc08b05f66f
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Rewrite vlib_buffer_chain_linearize function so that it works as intended.
Linearize buffer chains coming out of reassembly to work around some
dpdk-tx issues. Note that this is not a complete workaround
as a sufficiently large packet will still cause the resulting chain to
be too long.
Drop features from reassembly code which relies on knowing which and how
many buffers were freed during linearization, buffer counts and tracing
capabilities for these cases.
Change-Id: Ic65de53ecb5c78cd96b178033f6a576ab4060ed1
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|