Age | Commit message (Collapse) | Author | Files | Lines |
|
+ Introduce two explicit handling modes to save memory in scale test.
+ Connect in async mode for both handling modes (to avoid reconnects).
+ Support both pre- and post-37758 VPP PAPI async behavior.
+ Use control-ping in dumps to emulate sync mode.
+ Do not use it for single reply to avoid VPP-2033.
+ Fix call sites to get their replies with correct handling mode.
+ Drain enqueued replies to avoid subsequent errors.
+ Retry if read returns None too early.
+ Update docstrings.
- Complexity issues reported by pylint postponed, needs larger refactor.
- Explicit replace of VAT is done in subsequent changes.
Ticket: CSIT-1547 CSIT-1671
Change-Id: I3c63fa5c578975cc4dd7fce0babe3ab04ec15ed3
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Updated for what is available in (last common ancestor of) 2206.
(So newer messages such as ipsec_spd_entry_add_del_v2 are not used yet.)
+ Removed messgages documented as unused.
- Did not check if more become unused.
+ Restored alphabetical order.
Change-Id: I4191c3f8629106f52ce387d03f30f9f973ffbefe
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Change-Id: Id80b5611bb9a5d4398d4b2d00e92cda469949607
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
The implementation of GTPU offload rx is to use ip4_gtpu flow MARK action
of NIC and vpp flow REDIRECT_TO_NODE and BUFFER_ADVANCE fuction to direct
received gtpu flow to gtpu4-flow-input graph node, skipped ethernet-input,
ip4-input, ip4-lookup, ip4-local, ip4-udp-lookup normal graph node
processing.
Verified on 3n-clx and Intel E810 NIC environment, single core with 64B packet,
performance improve ~33% that compare with pure software way.
Signed-off-by: xinfeng zhao <xinfengx.zhao@intel.com>
Signed-off-by: Yulong Pei <yulong.pei@intel.com>
Change-Id: I2af4589448bdb1729e4ce206a8cf3a1239c61af8
Signed-off-by: Yulong Pei <yulong.pei@intel.com>
|
|
+ Make better error message.
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I2dbb9a50215bd6665c5c278653edd9324314e6b8
|
|
Based on latest common ancestor of master and stable/2106:
1372178e0e674143bfec14b17050d5e92e4fcf1a
Only ipsec_sad_entry_add_del_v3 needs non-trivial argument edits.
Change-Id: I813367292a830e5a1fac765e9f24057b6b0192ee
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Add checks for not unbinding a driver that is not bound and not
trying to remove VFs from interfaces not supporting SR-IOV.
Change-Id: Iae7ce37aabeadbb541fe9eac8b83b4ee18d028e6
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
|
|
We're only initializing interfaces for avf and af_xdp VPP drivers. This
causes issues for the rdma-core driver when the underlying mlnx kernel
driver is not bound. Fix this so that all interfaces are properly bound
to the kernel driver required by rdma-core.
Change-Id: I204309a9bb61b56b96497a287178f0b1efe2f362
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
|
|
+ Implement temporary ugly workaround as I cannot do
driver upgrade now after discussions with PTL.
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I400e3b61bd831b9c9820b1fab8852118f2d48f0e
|
|
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: If45e592aeade12fe643791b431adc860a745be3d
|
|
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I6826add7b3032041632c3952c45a3c64409400b0
|
|
Signed-off-by: xinfeng zhao <xinfengx.zhao@intel.com>
Reviewed-by: Yulong Pei <yulong.pei@intel.com>
Change-Id: Ibe4420529192559a3cdbb84e0a67859750a9e0d5
|
|
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: Ic5bc714b56c8bbd6884264a566eb8554a9735cba
|
|
- enabling for fortville, columbiaville
- enabling experimental for mlx
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I1b7ceb54769f4a0089ac7309350499e60c5cca0a
|
|
Change-Id: I0c973ceffc13f4f3c5f959d56cb0890b87091a82
Signed-off-by: Viliam Luc <viliam.luc@pantheon.tech>
|
|
This patch is to add test suites for vpp plugin crypto_sw_scheduler,
IPsec sync mode is to do crypto and packet forward work in same worker cores,
crypto_sw_scheduler can schedule crypto work to other async crypto cores to
improve whole crypto processing capability.
This test suites configure fixed 1 rx queues per port, then measure IPsec
performance with 1, 2, 3 crypto cores.
This patchset include 1, 2, 4, 8 ipsec tunnels test cases.
+Vratko help to change to count total physical cores instead of previous only
count crypto cores in test cases.
Change-Id: I0e67182e3d13273890a23703d838101900e25126
Signed-off-by: Yulong Pei <yulong.pei@intel.com>
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
Signed-off-by: pmikus <pmikus@cisco.com>
|
|
The mesages are the newest present in last common ancestor
of master and rls2101 (so not yet ipsec_sad_entry_add_del_v3).
Added a TODO for the RDMA create improvement,
to be implemented in a separate change.
Change-Id: I94bcd2f1bc109fb995c4dd6df44f8928865634f5
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Jira: CSIT-1597
Change-Id: I77b746584851331d46eca1caafd4468d18f1e78d
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Fix 1/3: Explicitly put PF interface up (this patch)
Fix 2/3: Done on TB
Fix 3/3: VPP bug displaying VF up if underlying PF is not up
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I45d66986ec76e6e14eebaad6828ef72724c626ab
|
|
for Intel E810CQ 100G NIC, kernel driver of PF is ice, kernel driver of VF
is iavf, its VF hardware support VPP native avf driver.
Signed-off-by: Yulong Pei <yulong.pei@intel.com>
Change-Id: Ic8d86e5ee00057bbbcd09df619a38bd1371c8fd7
|
|
- Part II
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I869a3d7e051dcbae3a230d4646219e70e5de2e87
|
|
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I84b3c07e22a313e96ac59fc7818960c502507651
|
|
Change-Id: Ie2f11cd5144daf249200fe07430b0809185bccce
Signed-off-by: Peter Mikus <pmikus@cisco.com>
|
|
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I6bdce8156ba214be210c195a9f3effd718301a86
|
|
- cover API changes in VPP: https://gerrit.fd.io/r/c/vpp/+/25569
- update vpp stable to version 20.05-rc0~345
- some pylint fixies in Policer.py
Change-Id: Iba2c877d0e74526c69826c5ec4afd64ed2055d31
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Modified cpuutils numa to work with aws 18xlarge instances.
Added dmidecode package to calibration role as is not installed by default.
Added required constants
Signed-off-by: Maros Mullner <maros.mullner@pantheon.tech>
Change-Id: I99608d9df3cff0b085ad26c30e339216b17581eb
|
|
Change-Id: Ib30bc4697fcba93a6723ee492a59a0523425f623
Signed-off-by: Peter Mikus <pmikus@cisco.com>
|
|
Reason is that the traffic generator is initialized with MAC addresses
of physical interfaces in the suite setup while rdma interfaces
are created later.
Change-Id: I2cf182cde20f14778624740a1f0467096c336306
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
- Not adding nf_density tests.
- Not adding hardware ipsec tests.
- Not adding -policy- tests.
- Using old crypto_ia32_plugin.so plugin name.
+ Suitable for cherry-picking to rls2001.
Change-Id: Ibf44d6d91e2afa2320637ecd9eb69d5d5dc364aa
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
+ Detect NUMA
+ Pin based on numa location
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: Ife350f8c70e5437ac7c1413c7753f2a2f62777d9
|
|
- use correct osi_layer=L2 (so L2 spoofing check is switched off
in case of avf driver)
- add pci address information to eth interface in topology file
- nfv_density chain_ipsec tests work only with DPDK
in current implementation
Change-Id: I233c6e5634a14581960c7459b87f11fcee8365bd
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
- cover API changes in VPP: https://gerrit.fd.io/r/c/vpp/+/24225
- update vpp stable to version 20.01-rc0~1011
Change-Id: Ibbfdbe867cf89715619efc5c5507859983025ece
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Change-Id: I9a3c6947da8ab5033e29b39833c97bcdafdc3ca9
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Change-Id: I1392c06b1d64f62b141d24c0d42a8e36913b15e2
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
+ We can see what is happening when debug level is increased
+ Big caveat of VPP is that it does not allow to configure
default global level.
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I5ea1a618161cdb3170cab022d7451e52271f83c0
|
|
+ Add functions for creating rdma interface
+ Fix traffic generator
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I81787b72ff5ee926ed652d350888c4f86da766f1
|
|
- it will avoid situation that corresponding port is not up and
its sw_if_index value in topology file is None that is interpreted
as 0 in vpp api so it set flag for local0 interface
Change-Id: I9145077d787ddde50a29bcd4091035e95077f946
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Change-Id: I7c2a29cfe48eee521cce5fcc3506cef39d51d37b
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
CSIT code alignment with API changes in VPP introduced
by patch https://gerrit.fd.io/r/c/vpp/+/18361
Change-Id: Ib0357bba79f55d297ef1086fbf3b760caca16cdb
Signed-off-by: Jan Gelety <jgelety@cisco.com>
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Change-Id: I90901c4ab14dfa76dc3e1f786a4b986479e0ba47
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
- force a python2 environment in tox for pylint
- let pylint load some compiled modules for member checking
- allow locally enabled pylint rules
- ignore bad enum names
- ignore complexity for code to be refactored by other tickets
- broad excepts are acceptable sometimes
Signed-off-by: Miroslav Los <miroslav.los@pantheon.tech>
Change-Id: If4c3a1b85e8609f074e1de8ce91fc9c4fedbeb38
|
|
- my bad
Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I8c1f57f6b648b99338f3f6a6ff9ec943082e9bc4
|
|
Change-Id: Ibf4a4839c2e8b799b03eebd9dffae891d8f00dd4
Signed-off-by: Jan Gelety <jgelety@cisco.com>
|
|
Change-Id: I0050f715011ecfa92b3ee88b301809a56abb7946
Signed-off-by: Peter Mikus <pmikus@cisco.com>
|
|
Change-Id: I7f1b47725648c8c26e21f42c305395ad620beea6
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Change-Id: I375b7c9f8fe81428cb16fea35128bddec089da1b
Signed-off-by: Peter Mikus <pmikus@cisco.com>
|
|
+ NF_density compatible
+ Baseline VM tests compatible
+ Scalability NxM
- 3n variant is missing in VXLAN and DOT1Q due to requests to have it
asymmetrical - TODO
Change-Id: Ia817d7be00622b594b451bc07756240d1a379e04
Signed-off-by: Peter Mikus <pmikus@cisco.com>
|
|
Ticket: CSIT-1541
Ticket: VPP-1722
Ticket: CSIT-1546
+ Increase timeout to hide x520 slownes of show hardware detail.
- Install sshpass and update ssh client in virl bootstrap.
+ Added TODOs to remove when CSIT-1546 is fixed.
+ Enable default socksvr on any startup conf.
+ Improve OptionString init and repr.
- The non-socket executor still kept for stats.
+ Remove everything unrelated to stats from non-socket executor.
- Remove some debug-loooking calls to avoid failures.
TODO: Introduce proper parsing to the affected keywords.
+ Reduce logging from PAPI code to level INFO.
- Needs https://gerrit.fd.io/r/20660 to fully work.
+ Change default values for LocalExecution.run()
+ Return code check enabled by default.
Code is more readable when rc!=0 is allowed explicitly,
and the test code will now detect unexpected failures.
+ Logging disabled by default.
Output XML is large already. Important logging can be enabled explicitly.
+ Restore alphabetical order in common.sh functions.
Change-Id: I05882cb6b620ad14638f7404b5ad38c7a5de9e6c
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Do not support returning unverified replies anymore.
Basically, ".get_replies().verify_replies()" is now just ".get_replies()".
This allows fairly large simplifications both at call sites
and in PapiExecutor.py
+ Rename get_dumps to get_details.
+ Introduce get_reply and get_sw_if_index.
+ Rename variables holding get_*() value,
+ e.g. get_stats() value is stored to variable named "stats".
+ Rename "item" of subsequent loop to hint the type instead.
+ Rename "details" function argument to "verbose".
+ Process reply details in place, instead of building new list.
- Except hybrid blocks which can return both list or single item.
- Except human readable text building blocks.
+ Rename most similar names to sw_if_index.
- Except "vpp_sw_index" and some function names.
+ Use single run_cli_cmd from PapiExecutor.
+ Do not chain methods over multiple lines.
+ Small space gain is not worth readability loss.
+ Include minor code and docstrings improvement.
+ Add some TODOs.
Change-Id: Ib2110a3d2101a74d5837baab3a58dc46aafc6ce3
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Because some NICs are known to not allow jumbo frames.
Change-Id: I45fe636e3a880c6640922468c170f50e85dd2ba2
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|