Age | Commit message (Collapse) | Author | Files | Lines |
|
Adds multi-queue for vanilla OVS using virtio-net.
TunTap ports will use multi_queue parameter when ports are
created/deleted if guest nic queues are enabled and
vswitch is ovs vanilla. Virtio net will now add guest nic
queues to qemu command line if appropriate.
Reworked multi-queue documentation to reflect these changes.
Adds vhost net thread affinitization which is recommended
when performing vanilla ovs multi-queue.
Guests will require ethtool if using l2fwd or linux bridge
as the loopback application when vanilla ovs multi-queue
is enabled.
Modified dpdk setting in vswitch conf to be better worded
for separation from vanilla ovs multi-queue.
Updated release and installation doc for new vloop image
that includes required ethtool utility.
JIRA: VSPERF-373
Change-Id: Idb550515190b1a93390308c11f54da368f962512
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Adds boot and mounted drive configuration options.
JIRA: VSPERF-379
Change-Id: Ic0673a9b9f7a3430d7ac4db5fb9bf4228872f501
signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Support of vHost Cuse interface is not supported
by OVS anymore, so it was removed also from VSPERF.
Cuse can be used with older VSPERF release if needed.
JIRA: VSPERF-376
Change-Id: Id786bddf5fa9dce5706a93de7b089707a60317cd
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: Bill Michalowski <bmichalo@redhat.com>
|
|
|
|
Implementation of 3 testcases with multi-VMs in parallel.
Flows are explicitly set on UDP destination ports so that
each packet is sent to a specific VM.
Topology is: Phy1-VM1-Phy2, Phy1-VM2-Phy2,..
This patch requires change #16855 "ovs/ofctl: Fix validation
method for complex flows."
JIRA: VSPERF-326
Change-Id: I59d23354bc9c6db470a59faba13bdcd6f2beb19d
Signed-off-by: Antonio Fischetti <antonio.fischetti@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Martin Klozik <martinx.klozik@intel.com>
|
|
The test case for verifying the vxlan tunneling feature without using any
ingress tunnel traffic. The virtual switch(OVS) is configured to mangle and
generate tunnel traffic in the deployment. The packet flow in the test case is
as follows
TRAFFIC-IN --> [ENCAP-PKT] --> [MOD-PKT] --> [DECAP-PKT] --> TRAFFIC-OUT
ENCAP-PKT - Encapsulate the ingress packet to a tunnel type.
MOD-PKT - Modify the tunnel header to match the following decap interface.
DECAP-PKT - Decapsulate the newly generated tunneled packet.
Change-Id: Ie24bacb3cb1c069bd60403e5a4ef8bcdf0e12e54
Signed-off-by: Sugesh Chandran <sugesh.chandran@intel.com>
|
|
Enables multi-queue option for OVS versions 2.5.0 or less with
dpdk. Instead of enabling MQ on a port by port basis this sets
the global MQ option after starting the ovs switch.
JIRA: VSPERF-372
Change-Id: I245c76779695518d0005122d8214bbf3f141bb96
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Change-Id: I8a89ee3eedd3b439f0243eaef2fafc50ee807739
Signed-off-by: Maryam Tahhan <maryam.tahhan@intel.com>
|
|
|
|
Fixes minor grammar and link issues.
JIRA: VSPERF-349
Change-Id: Id8708aee5b099287b5c99e79ca6da9ab8778897f
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Added changes to make use of the tests parameter.
The change is minor.
Prior to this the value was taken from configuration file.
With this change, the tests value is used as passed.
JIRA: VSPERF-367
Change-Id: I9d1553d3b53dd19a79428ddaaacadb55fc27324f
Signed-off-by: Sridhar Rao <sridhar.rao@spirent.com>
|
|
Fix build issues and add the LTP to index.rst.
JIRA: DOCS-95
Change-Id: I2d22646af935c544645c01600b92a5f51ede39ec
Signed-off-by: Maryam Tahhan <maryam.tahhan@intel.com>
|
|
Updating MoonGen configuration guide
JIRA: VSPERF-370
Change-Id: I577491a6ece249a6162e1a3595a8682b826e5734
Signed-off-by: bmichalo <bmichalo@redhat.com>
|
|
Fixes hugepage free calculation when hugepage size is not
1GB. Calculation previously assumed 1GB in size. This change
allows for all sizes to be calculated properly.
Change-Id: Ib05800f51992e9757c412a66296a47ad29e88a3b
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
|
|
|
|
|
|
|
|
Change-Id: Id0b2ce7460e76ffb3d478bd255a7e5b8e75ba001
Signed-off-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
Reviewed-by: <sridhar.rao@spirent.com>
|
|
During testcase development on the integration side, if
namespaces are used or veth ports and an exception is raised.
The namespaces and veth ports are not properly cleanup up
because the run_finalize does not get executed.
This patch wraps the testing block in a try block where
a finally will ALWAYS execute the run_finalize thus
preventing the possiblity of leftover testing artifacts.
JIRA: VSPERF-328
Change-Id: I4ea5f29a48b9171f330847f34b5b30ef3ab22f27
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Adds options to Xena for testing options when running RFC 2544
throughput testing.
JIRA: VSPERF-369
Change-Id: I3145bd1a4d697d7b06cafda4f9d77cce859d1839
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
|
|
|
|
Instead of hard coding line speed numbers for rate calcuation,
MoonGen should use its class object initialized at start time.
JIRA: VSPERF-368
Change-Id: I68c688f8c244df16d98cfd15efabf491a317256b
Signed-off-by: bmichalo <bmichalo@redhat.com>
|
|
One of the new tests we agreed by working on Etherpad
was MatchAction. Maryam led the development, and many
provided comments there. This is another chance for
comments before we merge.
JIRA: VSPERF-242
Change-Id: I9da74efb703d5f221280567159e4ed6d830eb92c
Signed-off-by: Al Morton <acmorton@att.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Billy O'Mahony<billy.o.mahony@intel.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
|
|
|
|
Change the default number of allocated pages to the min 10GB. Deallocate
hugepages if we allocated them on the fly.
Change-Id: If9946cec423dd095c1ca1ab3bee3698e2f025047
Signed-off-by: Maryam Tahhan <maryam.tahhan@intel.com>
|
|
Change hugepage detection to check if hugepages are configured. Also
verifies enough free hugepages are available based on test
configuration. Will result in an exception if not enough hugepages
are found. This performs the check based on the guest memory configs
as well as the dpdk socket configs.
Adds some new methods to check for free hugepages based on all
hugepages or for socket free hugepages.
Adds new logging indicitaing needed and free hugepages as well as info
level event if hugepages are not configured at recommended 1GB size.
JIRA: VSPerf-255
Change-Id: I80d5605308861070c412568d8d40339f01b9718b
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
|
|
For MoonGen, the final results parameters: throughput_rx_percent,
throughput_tx_percent were incorrectly calculated when converting
MoonGen to VSPERF format. In particular, this would occur when more
than one data stream (single channel unidirectional traffic) was used in
the test. When calculating these percentages, only aggregate throughput
values equaling unidirectional traffic were used (for example, for 64
byte frames bidirectional traffic should use 29.76 Mpps, not 14.88 Mpps)
JIRA: VSPERF-341
Change-Id: Ie62bded7aea023c287697f18c4172b58c320e050
Signed-off-by: bmichalo <bmichalo@redhat.com>
|
|
|
|
|
|
|
|
|
|
Initial creation of namespace fails because var/run/netns does not
exist.
JIRA: VSPERF-366
Change-Id: I02e5aef52e1675f303405b69c7461ca6482903af
Signed-off-by: Christian Trautman <ctrautma@redhat.com>
|
|
Order of NIC PCI IDs handling was changed to ensure their
check and possible expansion (by missing domain part)
before their first usage. This avoids a vsperf crash
in case that sriov is configured and short NIC PCI IDs
are used.
JIRA: VSPERF-363
Change-Id: I91f724e9558bce5a92520de72b4bf000f33d2f29
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
Testpmd forwarding mode mac_retry was obsoleted in DPDK v16.07.
Retry option is supported by multiple forwarding modes now.
Former "mac_retry" mode can be replaced by "mac retry" construct.
JIRA: VSPERF-333
Change-Id: I1563427985966264f07d10b1a8351784fe999d74
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
|
|
|
|
Recent versions of DPDK (16.xx) depend on numa library.
Thus installation scripts were updated to install both
binary and development packages.
JIRA: VSPERF-360
Change-Id: Idd0eac8758f30a355909bb804e99e650b67bba8b
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
VSPERF framework was updated to follow RFC2544 definition
of 'test' and 'trial' terms. Test parameter 'rfc2544_trials'
was replaced by new parameter 'rfc2544_tests'.
Both code and documentation were updated to reflect
these changes.
JIRA: VSPERF-300
Change-Id: I144a28359fd06394f1f87ef324458bafd5aad45f
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
Updated version of vloop-vnf image was added into the changelog inside
installation guide.
JIRA: VSPERF-349
Change-Id: I64a1acdf2191858dc282ea6c3b588048b3bdd742
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
If no hugepages are available, try to allocate HUGEPAGE_RAM_ALLOCATION
amount of RAM for hugepages.
JIRA: VSPERF-290
Change-Id: I092b3831254579eeebbe45e85884828f9d749895
Signed-off-by: Mars Toktonaliev <mars.toktonaliev@nokia.com>
|
|
Xena exception when no stats collected on receive on one port
during bi-directional traffic. Modify aggregate_stats in the
XenaDriver.py, add judge whether the two port both has stats,
if one port has no stats, the result use the port's value which
has stats.
JIRA: VSPERF-327
Change-Id: I18c349d609a2834907f0383dbfbebd5cd281f541
Signed-off-by: liting <tli@redhat.com>
|
|
The VSPERF traffic profile for starting rate is in a
percentage of line rate. MoonGen programs its
starting rate as Mpps. Therefore the traffic profile
for VSPERF needs to be converted to a MoonGen format.
There was a hardcoding of 14.88 that was used for the
starting frame rate for all frame sizes. This needs
to be corrected to take into account all frame sizes.
JIRA: VSPERF-350
Change-Id: Ied71668a560d7d2b03483f9a1192dd2fb4965996
Signed-off-by: bmichalo <bmichalo@redhat.com>
|
|
|
|
Release notes were updated with features introduced by Colorado
release.
JIRA: VSPERF-349
Change-Id: I43179028c973cae4be6746e633c27fd3419e951a
Signed-off-by: Martin Klozik <martinx.klozik@intel.com>
Reviewed-by: Maryam Tahhan <maryam.tahhan@intel.com>
Reviewed-by: Al Morton <acmorton@att.com>
Reviewed-by: Christian Trautman <ctrautma@redhat.com>
Reviewed-by: <bmichalo@redhat.com>
|
|
|
|
|
|
Results from other traffic generators are reported as
pure numbers, i.e. 2477356.0000. These values are
consumed and processed by other scripts (e.g. CI or
OPNFV results visualization), so we should keep it
consistent among various traffic generators.
JIRA: VSPERF-342
Change-Id: I305421287eb632707038f2c8bc594fcb255ec939
Signed-off-by: bmichalo <bmichalo@redhat.com>
|