Age | Commit message (Collapse) | Author | Files | Lines |
|
If an application worker calls listen on a session, vpp registers the
worker to the listener's work load balance group and, as new connections
are accepted, it may potentially push accept notifications to it.
There are however applications, like nginx, that on some workers may
never accept new connections on a session they've started listening on.
To avoid accumulating accept events on such workers, this patch adds
support for passive listeners. That is, workers that have started
listening on a session but then never call accept or epoll/select on
that listener.
Change-Id: I007e6dcb54fc88a0e3aab3c6e2a3d1ef135cbd58
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I9faaa321113e435844931247f23dbc1d190cc9da
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ie598443f024a677a9c6938b3f3634960fd712b09
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
nit tab fix for pep8
Change-Id: I81f62bf5f547497c9aabfb3180ef24f50b7c3283
Signed-off-by: Ed Kern <ejk@cisco.com>
|
|
Change-Id: I8894a7a8f2be117a4c1cec9ce5134a1572da7ec7
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Change-Id: Ib1316482dd7b1ae3c27c7eeb55839ed8af9ca162
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
- More fine tuning for multi-process applications.
- Experimental support for multi-thread apps. This is meant for app
whose threads are not vcl workers and the sessions are shared between
them.
Change-Id: Ie07651da5f2cdcf39f5dead5431f50ad39cf3f74
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
This variable without any needed 'define' becoming unused.
Change-Id: I661a75a78dba03abb861ed918ad1e634a8ecd0af
Signed-off-by: Dmitry Vakhrushev <dmitry@netgate.com>
|
|
Change-Id: I55b89f0d9fb082c7763b64b09ab14573468c6704
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
Change-Id: Ib94637ec09799c23f3179599b54a2be6e2768425
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Need to align with 3.0.0 version
Change-Id: I4e8aec1f1226ce09963a9bbb3a9170d1863059ec
Signed-off-by: Ping Yu <ping.yu@intel.com>
|
|
Outside FIB index doesn't change in this case. We register
callback for changing of outside FIB if table binding is changed
on an interface.
Change-Id: I1ebbd7c3c547fc999089db07abd2019734395a6e
Signed-off-by: Dmitry Vakhrushev <dmitry@netgate.com>
|
|
Change-Id: I7bd43f57d23b1ecf031530c4a7508f949ddf616f
Signed-off-by: Ping Yu <ping.yu@intel.com>
|
|
Change-Id: I3a33fb81f31ed473811e9e7a6197b81135913865
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I79b213b34c6071d14acf1922f89037a4a5a36c45
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I36b3ae56e6ca160081c892367fd6a979751fe717
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Add missing pre-input node runtime fork and refork code.
unix-epoll-input runs on all threads; each instance needs its own
runtime stats.
Change-Id: I16b02e42d0c95f863161176c4bb9f9917bef809d
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Previous scheme was not cross-compile friendly...
Change-Id: Ib103b136231673157a02b8750312aa6073052c7e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Modify the dirs assignment in configure_check_timestamp to
add the build-data/platforms/$(PLATFORM).mk file, all the CMakeLists.txt
files in the $(PACKAGE_SOURCE) tree, and the $(PACKAGE_SOURCE)/cmake
directory.
(For example, for package vpp, $(PACKAGE_SOURCE) is <Top of Tree>/src).
Note that in an earlier era there was no build-data/platforms directory and
no CMakeLists.txt files.
Also, we tacitly assume that $(SOURCE_PATH_BUILD_DATA_DIRS) is only one
directory whereas ebuild has been used in environments where there are two
treetops.
Change-Id: I761219adbdb4c7e675bb12b3e7f052db68f0294c
Signed-off-by: Burt Silverman <burtms@gmail.com>
|
|
This only works if vcl is configured to do eventd based message queue
notifications, instead of condvars. For that, add "use-mq-eventfd" to
vcl startup conf.
Change-Id: Id0f0288a40ec7d3daef7370f8b88420425867ab6
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I3423191c53ab6100ee9ecc4e24b06506ff1b25c8
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I82dceaa27a7b0c96de077cf283e4f64aa426f271
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I1554d9a4d6e4a4007cda9d0f83b03feb8fdbe853
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
this means we test the dumps - to some extent
Change-Id: I8d90745701012012b41a7b3aaf9be97b4dd2bdf8
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I74d69b8d686ad2395267eaee38cf3a7efc76d127
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
it was specified to 0 after https://gerrit.fd.io/r/16909
causes unformat_pg_ip4_header to wrongly set ip header len.
do more check when assigning e->lsb_bit_offset to avoid
negative value
Change-Id: Ib772c7135cdeb355f0d60f1ee11602f6b5a0ff21
Signed-off-by: Kingwel Xie <kingwel.xie@ericsson.com>
|
|
Change-Id: Iaa57ace6df96bfacd1235c80ec7bb08e5f335530
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Thanks Eliot....
Change-Id: I19c9557bf827d4a5b2af344f6f4eedf25cda86d7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I9b0a101e5d78c10257e3c5d8f5573c3eb29bfdef
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I2ad54b20b96f10b009c3e651b2a2f885577ca5b6
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
thanks, Eliot...
Change-Id: I8d8fee09bf1fe24933e6ef4e126dba8e22fe62b1
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
don't do the setup and teardown in class methods so that with
each test the config is added and deleted. that way we test that
delete actually removes state.
more helpful error codes from VPP for existing IPSEC state.
Change-Id: I5de1578f73b935b420d4cdd85aa98d5fdcc682f6
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Adding "Mtrie mheap usage" in output of "show ip fib memory" command, for displaying the total Mtrie Mheap usage together with memery usage of each node and each table
Change-Id: I2bcc570924e44a2b406f69cfc2f2f8d5abb61a39
Signed-off-by: Lollita Liu <lollita.liu@ericsson.com>
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
As a FUD reduction measure, this patch implements 2-way parallel
counter collection. Synthetic stat component counter pairs run at the
same time. Running two counters (of any kind) at the same time
naturally reduces the aggregate time required by an approximate
factor-of-2, depending on whether an even or odd number of stats have
been requested.
I don't completely buy the argument that computing synthetic stats
such as instructions-per-clock will be inaccurate if component counter
values are collected sequentially. Given uniform traffic pattern, it
must make no difference.
As the collection interval increases, the difference between serial
and parallel component counter collection will approach zero, see also
the Central Limit theorem.
Change-Id: I36ebdcf125e8882cca8a1929ec58f17fba1ad8f1
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I9df96264e30806ac3daf7121f314f34f06232413
Signed-off-by: Damjan Marion <damjan.marion@gmail.com>
|
|
It is actually a bitmap....
Change-Id: Ie359e085df3f371512f773600f8d7460b2232b3e
Signed-off-by: Damjan Marion <damjan.marion@gmail.com>
|
|
Change-Id: I2e5fd45abcd07e9eda6184587889bdcd9613a159
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
We register callback for VNET_HW_INTERFACE_LINK_UP_DOWN_FUNCTION and
VNET_SW_INTERFACE_ADMIN_UP_DOWN_FUNCTION to add and remove the slave
interface from the bond interface accordingly. For static bonding without
lacp, one would think that it is good enough to put the slave interface into
the ective slave set as soon as it is configured. Wrong, sometimes the slave
interface is configured to be part of the bonding without ever bringing up the
hardware carrier or setting the admin state to up. In that case, we send
traffic to the "dead" slave interface.
The fix is to make sure both the carrier and admin state are up before we put
the slave into the active set for forwarding traffic.
Change-Id: I93b1c36d5481ca76cc8b87e8ca1b375ca3bd453b
Signed-off-by: Steven <sluong@cisco.com>
|
|
Change-Id: I1c12e2941cae198ededbb65eb5be51a4eabe2c1b
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
1. show packet-generator verbose, display all edit-groups and hdr-size
2. unformat_pg_payload, always mark payload hdr-size as 0
3. packet-generator now can change rate/limit/size at runtime
4. validate_stream checks buffer min-size/max-size against all edit
groups' header size
5. remove incorrect max packet size limit check in validate_stream(...)
Change-Id: Ic45e4f2b98bc0fd7330e0b480dd677fa3c69a677
Signed-off-by: Kingwel Xie <kingwel.xie@ericsson.com>
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I312beccb1bb6c02d6356bc9b8247178f11b8feb0
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ib3f030e906da9828fdad27e19b9efb0c349b0734
Signed-off-by: Brian Nesbitt <brian.nesbitt@owmobility.com>
|
|
Change-Id: Ic141162acaf39878ab978a997e3f6757d4f7c240
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I975d46a82e9f884a9cd0ac2bd5f57181695f4124
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ieadf0a97379ed8b17241e454895c4e5e195dc52f
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
exceeded
Change-Id: Id5b47f78521a0cbedf7bd2c72babfb2ffe9fa67d
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I92af6455b50a49de4c912737fcd3b7787dd31de0
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
allow routes that are local and connected to be added via the API.
this emulates the addition of a second address in the same subnet
added to an interface.
Change-Id: Ib18a08c26956be9a07b3360664210c8cf6734c84
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I6e96607f09c18755eead2c7099e1f546bdae7b88
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
The latest version moved to lark from pyparsing. The developers were
kind enough to verify that their new grammar works with our tests.
Change-Id: I260b7e4641f6e283862f706c1e52199e28facc5c
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|