summaryrefslogtreecommitdiffstats
path: root/VNFs
AgeCommit message (Collapse)AuthorFilesLines
6 daysPreparation for packet mis-ordering statsHEADmasterLuc Provoost6-24/+34
Changed PROX and the python scripts so that the "lat all stats" command also returns the mis_ordered, extent and duplicate statistics. In order to make this work properly, we need now to also stop and restart the latency cores, every time we stop and start the generator cores, since the sequence numbers are reinitialised every time we start the generator core. Change-Id: Ic4212a989c8ee9d0f026a34ca63a08b982c32b71 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
6 daysFix mbuf corruption when handling icmp messages.Xavier Simonart1-1/+1
Signed-off-by: Xavier Simonart <simonartxavier@gmail.com> Change-Id: I3eeacb550d1ef51a13802d06f06973437afe7d9b
2021-02-11Add support for native Kubernetes CPU Manager0.0.1Yury Kylulin33-21/+132
For Kubernetes environment core ids in the config and test files are relative and automatically remapped to the allowed cores allocated for container. There is no change to the baremetal or VM environment. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: I63e499723e8213de1b05d4175eb3eddc4492ccf5
2021-02-10Improve prefetching in handle_mirrorLuc Provoost1-3/+3
Some of the prefetching code was commented out, which was wrong. The prefetching is back in. Change-Id: Id7e7f09bd62faa7b9faf3d677962a99ba2a71080 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2021-02-10Expand mirror functionalityLuc Provoost3-24/+67
In order to deal with non-symmetrical load, the mirror function can now change the packet size of each packet it receives. It can also send the incoming packet multiple times on each of the tx ports. To support this feature, 2 new parameters in the cfg file have been added for the mirror mode: - multiplier: specifies how many times a packet needs to be sent on each tx port. Default is 1. - mirror_size: the size of the packets that need to be sent. This will just change (increase) the packet size of each incoming packet. If not specified or invalid value (e.g. <64), the size will not be changed. The packet size will only be changed for IPv4 UDP and IPv4 TCP. Note that these parameters have no effect on the mirror copy submode. Change-Id: Ic46b52abdd80ed51cffee667bd04ade9ec23ff6d Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2021-02-01Fix the default test fileLuc Provoost1-1/+1
In a previous change, all test files were moved to the tests subdirectory. When not specifying the test file on the command line as a parameter, the default test file is used, as specified in rapid_defaults.py It did not reflect the fact that all test files were moved to this directory. Change-Id: I5c77b75dbdde040d0e30dda2b97e981dff572f2f Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2021-01-29Add rapid script sources in the imageYury Kylulin2-17/+22
Make image more universal and add rapid scripts for mgmt from the container. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: Ia46a8e147f978dd64bfe6c7b44f7dff92e241855
2021-01-27creation of tests and configs subdirectoriesLuc Provoost40-58/+136
All test files are now in the tests directory. All PROX config files moved to the configs directory. When specifying a test on the runrapid.py command line, you should now also mention the directory: e.g. --test tests/basicrapid.test In these test files, you need now to also include the configs subdirectory when specifying the prox configuration that needs to be used. The --map parameter has also changed. It can still take the file name of the map file, that specifies which PROX instance to use during a test. On top of that, you can now also specify a list of indices of the machines to be used during a test: e.g. --map [1,3]. Change-Id: I887cba59834dd8c903a22bc80959b10da2775398 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2021-01-27Add default SSH keysYury Kylulin2-0/+50
Adding default RSA keys for SSH access. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: Id9552717591a805562f3ed2f840251bd9f6a71c1
2020-12-28Improved PROX cleanup when exitingLuc Provoost23-167/+232
Sending now a 'quit' command to PROX, so that the thread running PROX in an ssh session is now cleaned up correctly. Also fixed a problem with the logging when running the code more than once. We only create handlers now, when they do not yet exist. Updated the rapid version. Also added some more tests in the testcases.yaml for xtesting. At the end of a run, the PROX.log files are copied in the results directory. The success criterium for a test 'pass_threshold' has been removed from the test files and is to be controlled by the xtesting testcases.yaml file. Change-Id: Ifbbb1c91f32c9176f52025d9ae4c495b432a94c9 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-12-10Fix for new config file structureYury Kylulin3-1/+21
Fix subnet configuration for the dataplane interface. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: I612113a86a960284303915d5d003bf67a1b48a72
2020-12-10Moving to python 3 for kubernetes scriptsYury Kylulin4-13/+11
Move to python version 3 in all scripts for kubernetes environment. Streamline file names to match existing libraries. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: Id875f4240a87ab600b445cb9a7fd97ec1335f88a
2020-12-08Reporting test details for all testsopnfv-10.0.0stable/jermaLuc Provoost8-60/+44
Test details were only implemented in rapid_flowsizetest.py. When executing other tests, an error occured. That is now fixed, although in some cases, None is returned. The format.yaml files defines now alsowhat will be reported in the Xtesting details. Change-Id: I5feae62dcf228664b24451d3fc5dfaaadf7edb5e Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-11-18Support for xtestingLuc Provoost12-15/+197
Some files were added to for rapid testing in the xtesting framework Change-Id: Id912789c5007ca8390a67fb5b359296089aa9618 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-11-13Fix for latency reporting and log file handlerLuc Provoost3-5/+5
The latency histogram dat did not contain samples collected during the first measurement of each step. The maximum latency did take the first step into account. As a result, you might see a test run with a maximum latency not showing up in the latency histogram data. This has been fixed by also including the data from the first measurement in the histogram data. In some cases, we also reported the wrong speed from the last unsuccessful step. This is now fixed and we do report the speed from the last successful step. In rapid_log.py, a fix was added to execute the rollover on the file handler of the log file in all cases. In some cases, the file handler with index 0 was not the file handler of the log file. Change-Id: I6c2b16c21dd0ee17d1d14e46c4c544e185324256 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-11-10Fix potential crash in parsing unusual commandsXavier Simonart1-2/+2
'reset values all' and 'reset randoms all' commands were potentially causing some crash. This has been fixed. Change-Id: Idc2c4f7c90db73e7fdf9e8ef76b00ba956a0d854 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-11-05Fix setting imx pkt sizes through config filesXavier Simonart1-1/+9
Change-Id: I0e5098747cc496da8632e8d6f779e418da03dc4a Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-10-19Support dataplane subnet mask & latency histogramLuc Provoost16-36/+76
There is a new parameter in the config_file: dataplane_subnet_mask. This parameter is added to the dataplane IP addresses and is needed by the Linux stack to deal with some protocols (e.g. ARP). If not present, the default value of 24 will be used. In the end, this will make sure that IP addresses in the rapid.env file will have this mask, e.g. /24 If you use other tools than createrapid.py to create the rapid.env file, make sure to add the mask. This commit also introduces a change when exiting: we only copy the prox.log files from the different prox instances in case we expect a new prox.log file to be created in these instances. When using a valid format.yaml file, the tool will now also send the latency distribution data (histogram) to the URL. The tool is now also checking the value of bucket_size_exp: it needs to be 11 or more. Change-Id: I633cdc64ef687fdb6625be1e7482a5a371f83e93 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-10-16Report failure when tap port is not mapped to real dpdk port.Xavier Simonart4-6/+20
When using "vdev=" in port section, a tap device and an additional dpdk port are created. In most cases, we still want to use a real DPDK device (i.e. bound to an interface such as virtio or a PF or a VF). PROX will now report by default an error when the used [port] is not a DPDK bound device. An additional parameter "virtual=yes" can be added in the port section in case one want to disable this error checking (e.g. specify additional parameter for the vdev device). This patch also fixes a potential endianess issue when configuring IP addresses. Change-Id: Iffdd9552308be3b77cfe2067630647acac2c01fe Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-29New PROX version, background traffic reportingLuc Provoost18-86/+89
deploycentostools.sh is now installing a recent PROX version. When using background traffic, the tool is also reporting the total traffic that was handled by the NFVi stack, including foreground & background traffic. The use of the prox_socket and prox_launch_exit was also broken in a previous release and is now fixed. When setting prox_socket to false for a PROX instance, we will not create a socket connection to control that PROX instance. Setting this option to false is not meaningful for the generator PROX instances since we would not be able to control the behavior of the PROX generator during the test. You could use the generator against another non-PROX instance and then set prox_socket to false for that non-PROX instance. Default is true. prox_launch_exit is used to start and stop the PROX program inside the instance. Default is true. This is useful in case you want to start PROX manually to be able to inspect the PROX UI, but at the same time, let the rapid scripts control the testing. Change-Id: Ib5aa809f4be201859542769f5f55f4989dad97ef Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-09-21Add git version.Xavier Simonart2-1/+12
git version is now printed in prox.log file. - git_version.c is always recompiled - If source have been locally changed, the build is shown as dirty - If git is not available on the build system, a message such as 'make: git: Command not found' will be printed, but the build will succeed. Change-Id: If551832c6079f5e3bd04cd4d8ac5f8204e6be8cd Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-21Added support for multiple vlans in ipv4 vdev modeXavier Simonart13-82/+184
When the following conditions are met: - ipv4 - vdev enabled Then multiple vlans are supported. Multiple vlans can be configured using the vlan_tag option within the port section of the config file. Multiple (different) local_ipv4/prefix must then also be configured within the same section. Note that for ipv6 multiple vlans are not supported (yet) Also, when vdev is not enabled, multiple vlans are also not (yet) supported. Change-Id: I38b6cd98ff2a0f484d1bf0910b15413ba21ae6d6 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-21Improve performance in IPv6 generatorXavier Simonart4-45/+28
Change-Id: I3abc92652402162d15249e345446debdeb778176 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-21Added support for VLAN in IPv6Xavier Simonart5-54/+87
Change-Id: Ib1b3d54f9cb8e4284eee7ed0998e96370762a17e Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-21Added support for gateway ipv6 & cmd for sending unsollicited neighbor ↵Xavier Simonart5-16/+73
advertisement Change-Id: Iae35d3fa19ad7cf90d8c2e0c104b0e798ac34787 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-21Added support for reporting packet (mis)order.Xavier Simonart18-48/+227
The "Latency" screen has been updated with 3 columns: - mis-ordered Count the number of mis-ordered packets. - extent: Gives an indication of how mis-ordered the packets are. Receiving packet "x - 5" after receiving packet "x" will cause an extent of 5. - duplicate: Count number of duplicate packets. Following commands have been added for the impair mode: - proba no drop: replaces the former "probability" command. Percentage of forwarded packets. So 99.5 means 0.5% of packet drop. - proba delay Percentage of delayed packets for the impair mode. - proba duplicate Percentage of duplicate packets. Similar parameters are supported within the config files: - proba no drop - proba delay - proba duplicate Note: it is recommanded to use the signature when measuring packet misorder, as otherwise unexpected packet would cause miscounts. Change-Id: I037f606f264d6e2bd7f123df5ed57ab7df8386d7 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-09-17Using python concurrent futuresLuc Provoost3-63/+29
Different PROX instances are now started in parallel. The script is starting multiple threads. Change-Id: Ia8785a792240d4e9b5d5d98174bc4c5d7ae5657c Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-09-16ramp generator traffic & prox.log copyLuc Provoost6-1/+75
A new parameter can be put in the *.test files so that the requested traffic is not generated at once, but slowly increasing up to the requested traffic. This is important for some SW switched that adapt and learn from the applied traffic. When suddenly applying a high traffic, the switch might not have enough time to learn and lose packets. Only after a period of time (up to 10 seconds?), the switch can cope with the traffic without packet loss. In order to get reproducible results in this case with low packet loss, please put the parameter ramp_step in the test section of the *.test file. The step is expressed in percentage of a 10Gb/s traffic. If the parameter is not present, the load will be immediately applied. When the runrapid.py script is now finished, it also copies the prox.log files from all the prox instances. In case of issues, please investigate this log file. When using background traffic, the tool will also print the average background traffic for each step in the DEBUG log. In this way, you can check that the background traffic is actually dealing with the same amount of traffic as the foreground. The tool is printing the packet reception rate of the background generators. A bug was also fixed regarding the latency percentile reporting. When using tests involving l2gen.cfg, the values of the percentile latency were wrong. Change-Id: Id3dd02ed5cab084414c717cf898b30e6980ddf31 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-09-07deploycentostools.sh to use latest PROXLuc Provoost1-1/+1
Rapid scripts are communicating to the PROX instances. Rapid scripts will not work with every PROX version sice sometime we change the interface between the scripts and PROX. Hence we have a commit ID in deploycentostools.sh to make sure we have a version of PROX that we can work with. This change will now ensure we have a recent PROX version when we use deploycentostools.sh to build an image. Change-Id: Ia634f61a2dc8f49188cec6697ebf5f980d35ce7d Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-20Allow latency thresholds for TST009 testingLuc Provoost2-3/+4
Even if the latency thresholds were defined in the TST009 test files, the values were ignored and replaced by 'inf', whcih means the thresholds were not taken into account to define a successful step. If the thresholds are not defined in the test files, they are still set to 'inf'. Change-Id: I9559f05fb6066ab8759900abe3eb53ff4662e510 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-18Add all_rx_queues port flag to use all rx queuesLuc Provoost3-0/+51
In the port section of the PROX configuration file, a new parameter can be added: all_rx_queues. The default is all_rx_queues=no. When the rx port variable of a task is listing a port name, all rx queues will be used when the all_rx_queues is set for that port. If not set, only one queue of that port will be "consumed", each time the port is referenced in the rx port variable. When the all_rx_queues is set for a port, you should NOT reference that port more than once in the rx port variables. Change-Id: If9662b1ac07adeec9db88d2a25ca68aed0b9e213 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-18Setting mq_mode for virtio to ETH_MQ_RX_NONELuc Provoost1-6/+12
As described in https://patches.dpdk.org/patch/60354/, we cannot set mq_mode for a vertio device to ETH_MQ_RX_RSS. Therefore adding this extra test before setting mq_mode. Change-Id: I8a33cf73afaa2cef8b9b012bf8ebe7296e1e692d Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-07Support DPDK 19.11 rc0Luc Provoost3-18/+18
Change-Id: I7ac1bb78fe00407ff66945fcdf7b5d54c9025214 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-06fix: IPV6 packet generation, packet loss reportingLuc Provoost10-28/+70
UDP and IP packet length and source UDP port and destination UDP port were wrongly set for IPv6 packets. In the *.test files, there is now an optional boolean field (ipv6) in the [TestParameters] section. When set to true, the generator will use the IPv6 packet layout to place the right values at the proper offset in the packet. If not present or set to false, the IPv4 layout will be used. Note also that packet size needs to be at least 84 bytes for IPV6 traffic since we need space for latency and other information in each packet. Packet loss ratio is now printed as a percentage of the total packets sent. Change-Id: I2136e87f3032348ae95b69052be7da8461c6303c Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-08-03Improved IRQ measurements and pushing resultsLuc Provoost12-134/+373
The IRQ test has been reworked to increase the accuracy of the IRQ measurements. Results can now also be pushed to a Prometheus push gateway or to OPNFV's Xtesting. In order to do so, a new file format.yaml has been introduced. Please use this file now to specify the details of the PushGateway or the Xtesting server. Added new test: increment_till_fail.test Change-Id: I111aae3e099bc03e3d2ddd1014a0301bac356e0b Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-07-24Fix execution in the Kubernetes environmentYury Kylulin3-3/+14
Due to the recent changes in the rapid scripts, Kubernetes environment need to be adjusted. Ready for test flag file for the runrapid script created during the container start. TUN device configuration added. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: I097aafbd1d1d102aa61b8b86842afcb2d6a51338
2020-07-10Fix gateway l3 wrongly inserting VLANsXavier Simonart1-1/+20
Change-Id: I187ed4f282c6332a7e906bc03b51d26295a475ac Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-07-10Fixed compilation issue on dpdk 19.08 (and more recent)Xavier Simonart1-0/+5
Change-Id: Iae0a0d95b5a216463ec7511337be4019fdd4359f Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-07-06Fix minor compilation issue on recent gcc compilersXavier Simonart1-1/+1
Change-Id: I7eeaaa3a0dfa1c0a831863e772b50697c5ff5054 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-07-05Adding vdev support and vfioLuc Provoost30-112/+179
Using vfio in stead of igb_uio. DPDK 2020.5 is NOT compiling the igb_uio driver by default any more. For the l3 mode, we are now using the new PROX vdev feature. This is achieved by adding the vdev parameter in the port section of the PROX config files. One of the advantages is that we can now ping a port managed by PROX: the requests will be forwarded by PROX to the LINUX stack, who will reply to the ping. A tap device is being created by PROX to support this feature. Installing old version of nasm since latest causes some issues. If not pushgateway is being used, it should be commented out in the config_file. vfio is now loaded by specifying the module in /etc/modules-load.d There is also an after_boot.sh script that will be run by check_prox_system_setup.sh, which can be used for further configuration of the instance after boot. There is now also a file created /opt/rapid/system_ready_for_rapid by the check_prox_system_setup.sh script. This file is created once all configuration is done. The runrapid.py script will wait till this file is created before executing any tests. Change-Id: Ic5c41af82642066af42134c3323297f5a06f6f72 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-06-05Clean up for the test podsYury Kylulin2-10/+31
Option for Kubernetes environment clean up (createrapidk8s.py -c) from the test pods added. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: I1c6c7090462b55fbadd1d8f1a277470a6eeb2dee
2020-06-03Fix for containers to use /opt/rapidYury Kylulin5-10/+12
Fix scripts and build procedure to use /opt/rapid as a main directory for binaries and config files. Signed-off-by: Yury Kylulin <yury.kylulin@intel.com> Change-Id: Icb38c37a85a78a6f2de2e751df5fafd624b4f1b3
2020-06-02Using /opt/rapid to run proxLuc Provoost4-12/+17
All config files are now copied into /opt/rapid. We are not using the home directory any more. The prox executable is now also copied into the same /opt/rapid. Change-Id: I838636167f370bf8a855a3cfb0796c659e27a3ad Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-05-29Fixing some more copyright datesLuc Provoost14-13/+30
New files created in 2020 have now the right date in the copyright notice. Change-Id: I8eb244beec3d793e819cce1f63c39671f18286a1 Signed-off-by: Luc Provoost <luc.provoost@intel.com>
2020-05-30Updated PROX version to 20.05 to reflect support of DPDK 20.05Xavier Simonart2-2/+3
Change-Id: Iad6882cc28ac2039984b12f6b7a897b81d975d9b Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-05-29Fix compilation issues on old DPDKXavier Simonart8-5/+54
Also fixed minor issues such as - prevent using vdev on DPDK <= 17.05 as not supported - potential segmentation fault after panic (if panic thrown early in prox initialization) Change-Id: I49a1962e95a4a44dddadd1fdd906e1b3b232465c Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-05-29VLAN support with vdev devices + few other changesXavier Simonart13-97/+200
- vdev devices now support VLAN. - kernel tap device can be configured with a netmask (/24 was always used in previous version). - when sending a (fake) packet to the kernel, this packet will now not be routed by the kernel (i.e. it will leave through the interface configured by PROX). This might change in the futture when PROX supports multiple VLANs per port. But today it prevents ARP being sent on management interfaces. - Log error in case kernel unable to send packet. - Added support for comments (';') in lua sections. - Prevent duplication of local_ipv4 - should now be configured in port section local_ipv4 in core section still supported Change-Id: I8f9a40fe6ad6f3013ff91b58b44627c7f34081e6 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-05-29Add support for latency measurement for IMIX packetsXavier Simonart1-6/+26
Before this patch latency measurements were only supported if signature was disabled. Change-Id: I565b00f76818ab42e9cca4ddc32f9d857648929d Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-05-29Fix Idle countXavier Simonart1-7/+6
Change-Id: Idd72b593504139ac9d42c33767f8a18395b2cc87 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
2020-05-29Fix source mac address when applying imixXavier Simonart1-0/+3
Change-Id: I8cbbe1b08af9b5472c304f2fba3635f0a084fdd8 Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>