X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=docs%2Ftesting%2Fdeveloper%2Fdevguide%2Fdevguide_nsb_prox.rst;h=44a216b753a5744826eb458bfcee82bce417bbaa;hb=HEAD;hp=22628413b78b68999c80d1c3195b1d87783018c3;hpb=4b8b674b65830a24230faed71e8d9a1048139c89;p=yardstick.git diff --git a/docs/testing/developer/devguide/devguide_nsb_prox.rst b/docs/testing/developer/devguide/devguide_nsb_prox.rst index 22628413b..44a216b75 100755 --- a/docs/testing/developer/devguide/devguide_nsb_prox.rst +++ b/docs/testing/developer/devguide/devguide_nsb_prox.rst @@ -8,14 +8,17 @@ for Telco customers, investigate the impact of new Intel compute, network and storage technologies, characterize performance, and develop optimal system architectures and configurations. +NSB PROX Supports Baremetal, Openstack and standalone configuration. + .. contents:: Prerequisites ============= -In order to integrate PROX tests into NSB, the following prerequisites are required. +In order to integrate PROX tests into NSB, the following prerequisites are +required. -.. _`dpdk wiki page`: http://dpdk.org/ +.. _`dpdk wiki page`: https://www.dpdk.org/ .. _`yardstick wiki page`: https://wiki.opnfv.org/display/yardstick/ .. _`Prox documentation`: https://01.org/intel-data-plane-performance-demonstrators/documentation/prox-documentation .. _`openstack wiki page`: https://wiki.openstack.org/wiki/Main_Page @@ -159,11 +162,13 @@ A NSB Prox test is composed of the following components :- ``tc_prox_heat_context_vpe-4.yaml``. This file describes the components of the test, in the case of openstack the network description and server descriptions, in the case of baremetal the hardware - description location. It also contains the name of the Traffic Generator, the SUT config file - and the traffic profile description, all described below. See nsb-test-description-label_ + description location. It also contains the name of the Traffic Generator, + the SUT config file and the traffic profile description, all described below. + See `Test Description File`_ -* Traffic Profile file. Example ``prox_binsearch.yaml``. This describes the packet size, tolerated - loss, initial line rate to start traffic at, test interval etc See nsb-traffic-profile-label_ +* Traffic Profile file. Example ``prox_binsearch.yaml``. This describes the + packet size, tolerated loss, initial line rate to start traffic at, test + interval etc See `Traffic Profile File`_ * Traffic Generator Config file. Usually called ``gen_-.cfg``. @@ -176,7 +181,7 @@ A NSB Prox test is composed of the following components :- under test. Example traffic generator config file ``gen_l2fwd-4.cfg`` - See nsb-traffic-generator-label_ + See `Traffic Generator Config file`_ * SUT Config file. Usually called ``handle_-.cfg``. @@ -190,7 +195,7 @@ A NSB Prox test is composed of the following components :- the ports to the Traffic Verifier tasks of the Traffic Generator. Example traffic generator config file ``handle_l2fwd-4.cfg`` - See nsb-sut-generator-label_ + See `SUT Config File`_ * NSB PROX Baremetal Configuration file. Usually called ``prox-baremetal-.yaml`` @@ -199,12 +204,12 @@ A NSB Prox test is composed of the following components :- This is required for baremetal only. This describes hardware, NICs, IP addresses, Network drivers, usernames and passwords. - See baremetal-config-label_ + See `Baremetal Configuration File`_ * Grafana Dashboard. Usually called ``Prox__--.json`` where - * Is either ``BM`` or ``heat`` + * Is ``BM``,``heat``,``ovs_dpdk`` or ``sriov`` * Is the a one or 2 word description of the test. * is the number of ports used express as ``2Port`` or ``4Port`` * is the Date and Time expressed as a string. @@ -214,15 +219,15 @@ A NSB Prox test is composed of the following components :- Other files may be required. These are test specific files and will be covered later. -.. _nsb-test-description-label: -**Test Description File** +Test Description File +--------------------- -Here we will discuss the test description for both -baremetal and openstack. +Here we will discuss the test description for +baremetal, openstack and standalone. -*Test Description File for Baremetal* -------------------------------------- +Test Description File for Baremetal +----------------------------------- This section will introduce the meaning of the Test case description file. We will use ``tc_prox_baremetal_l2fwd-2.yaml`` as an example to @@ -235,7 +240,8 @@ show you how to understand the test description file. Now let's examine the components of the file in detail 1. ``traffic_profile`` - This specifies the traffic profile for the - test. In this case ``prox_binsearch.yaml`` is used. See nsb-traffic-profile-label_ + test. In this case ``prox_binsearch.yaml`` is used. See + `Traffic Profile File`_ 2. ``topology`` - This is either ``prox-tg-topology-1.yaml`` or ``prox-tg-topology-2.yaml`` or ``prox-tg-topology-4.yaml`` @@ -244,10 +250,16 @@ Now let's examine the components of the file in detail 3. ``nodes`` - This names the Traffic Generator and the System under Test. Does not need to change. -4. ``prox_path`` - Location of the Prox executable on the traffic +4. ``interface_speed_gbps`` - This is an optional parameter. If not present + the system defaults to 10Gbps. This defines the speed of the interfaces. + +5. ``collectd`` - (Optional) This specifies we want to collect NFVI statistics + like CPU Utilization, + +6. ``prox_path`` - Location of the Prox executable on the traffic generator (Either baremetal or Openstack Virtual Machine) -5. ``prox_config`` - This is the ``SUT Config File``. +7. ``prox_config`` - This is the ``SUT Config File``. In this case it is ``handle_l2fwd-2.cfg`` A number of additional parameters can be added. This example @@ -256,6 +268,14 @@ Now let's examine the components of the file in detail options: interface_speed_gbps: 10 + traffic_config: + tolerated_loss: 0.01 + test_precision: 0.01 + packet_sizes: [64] + duration: 30 + lower_bound: 0.0 + upper_bound: 100.0 + vnf__0: prox_path: /opt/nsb_bin/prox prox_config: ``configs/handle_vpe-4.cfg`` @@ -269,53 +289,75 @@ Now let's examine the components of the file in detail ``configs/vpe_rules.lua`` : ```` prox_generate_parameter: True - ``interface_speed_gbps`` - this specifies the speed of the interface - in Gigabits Per Second. This is used to calculate pps(packets per second). - If the interfaces are of different speeds, then this specifies the speed - of the slowest interface. This parameter is optional. If omitted the - interface speed defaults to 10Gbps. + ``interface_speed_gbps`` - this specifies the speed of the interface + in Gigabits Per Second. This is used to calculate pps(packets per second). + If the interfaces are of different speeds, then this specifies the speed + of the slowest interface. This parameter is optional. If omitted the + interface speed defaults to 10Gbps. + + ``traffic_config`` - This allows the values here to override the values in + in the traffic_profile file. e.g. "prox_binsearch.yaml". Values provided + here override values provided in the "traffic_profile" section of the + traffic_profile file. Some, all or none of the values can be provided here. - ``prox_files`` - this specified that a number of addition files - need to be provided for the test to run correctly. This files - could provide routing information,hashing information or a - hashing algorithm and ip/mac information. + The values describes the packet size, tolerated loss, initial line rate + to start traffic at, test interval etc See `Traffic Profile File`_ - ``prox_generate_parameter`` - this specifies that the NSB application - is required to provide information to the nsb Prox in the form - of a file called ``parameters.lua``, which contains information - retrieved from either the hardware or the openstack configuration. + ``prox_files`` - this specified that a number of addition files + need to be provided for the test to run correctly. This files + could provide routing information,hashing information or a + hashing algorithm and ip/mac information. -6. ``prox_args`` - this specifies the command line arguments to start + ``prox_generate_parameter`` - this specifies that the NSB application + is required to provide information to the nsb Prox in the form + of a file called ``parameters.lua``, which contains information + retrieved from either the hardware or the openstack configuration. + +8. ``prox_args`` - this specifies the command line arguments to start prox. See `prox command line`_. -7. ``prox_config`` - This specifies the Traffic Generator config file. +9. ``prox_config`` - This specifies the Traffic Generator config file. + +10. ``runner`` - This is set to ``ProxDuration`` - This specifies that the + test runs for a set duration. Other runner types are available + but it is recommend to use ``ProxDuration``. The following parameters + are supported + + ``interval`` - (optional) - This specifies the sampling interval. + Default is 1 sec + + ``sampled`` - (optional) - This specifies if sampling information is + required. Default ``no`` + + ``duration`` - This is the length of the test in seconds. Default + is 60 seconds. + + ``confirmation`` - This specifies the number of confirmation retests to + be made before deciding to increase or decrease line speed. Default 0. -8. ``runner`` - This is set to ``Duration`` - This specified that the - test run for a set duration. Other runner types are available - but it is recommend to use ``Duration`` +11. ``context`` - This is ``context`` for a 2 port Baremetal configuration. -9. ``context`` - This is ``context`` for a 2 port Baremetal configuration. If a 4 port configuration was required then file ``prox-baremetal-4.yaml`` would be used. This is the NSB Prox baremetal configuration file. -.. _nsb-traffic-profile-label: +Traffic Profile File +-------------------- -*Traffic Profile file* ----------------------- - -This describes the details of the traffic flow. In this case ``prox_binsearch.yaml`` is used. +This describes the details of the traffic flow. In this case +``prox_binsearch.yaml`` is used. .. image:: images/PROX_Traffic_profile.png :width: 800px :alt: NSB PROX Traffic Profile -1. ``name`` - The name of the traffic profile. This name should match the name specified in the - ``traffic_profile`` field in the Test Description File. +1. ``name`` - The name of the traffic profile. This name should match the + name specified in the ``traffic_profile`` field in the Test + Description File. -2. ``traffic_type`` - This specifies the type of traffic pattern generated, This name matches - class name of the traffic generator See:: +2. ``traffic_type`` - This specifies the type of traffic pattern generated, + This name matches class name of the traffic generator. See:: network_services/traffic_profile/prox_binsearch.py class ProxBinSearchProfile(ProxProfile) @@ -326,21 +368,29 @@ This describes the details of the traffic flow. In this case ``prox_binsearch.ya Custom traffic types can be created by creating a new traffic profile class. -3. ``tolerated_loss`` - This specifies the percentage of packets that can be lost/dropped before - we declare success or failure. Success is Transmitted-Packets from Traffic Generator is greater than or equal to +3. ``tolerated_loss`` - This specifies the percentage of packets that + can be lost/dropped before + we declare success or failure. Success is Transmitted-Packets from + Traffic Generator is greater than or equal to packets received by Traffic Generator plus tolerated loss. -4. ``test_precision`` - This specifies the precision of the test results. For some tests the success criteria - may never be achieved because the test precision may be greater than the successful throughput. For finer - results increase the precision by making this value smaller. +4. ``test_precision`` - This specifies the precision of the test + results. For some tests the success criteria may never be + achieved because the test precision may be greater than the + successful throughput. For finer results increase the precision + by making this value smaller. -5. ``packet_sizes`` - This specifies the range of packets size this test is run for. +5. ``packet_sizes`` - This specifies the range of packets size this + test is run for. -6. ``duration`` - This specifies the sample duration that the test uses to check for success or failure. +6. ``duration`` - This specifies the sample duration that the test + uses to check for success or failure. -7. ``lower_bound`` - This specifies the test initial lower bound sample rate. On success this value is increased. +7. ``lower_bound`` - This specifies the test initial lower bound sample rate. + On success this value is increased. -8. ``upper_bound`` - This specifies the test initial upper bound sample rate. On success this value is decreased. +8. ``upper_bound`` - This specifies the test initial upper bound sample rate. + On success this value is decreased. Other traffic profiles exist eg prox_ACL.yaml which does not compare what is received with what is transmitted. It just @@ -365,20 +415,25 @@ See this prox_vpe.yaml as example:: lower_bound: 0.0 upper_bound: 100.0 -*Test Description File for Openstack* -------------------------------------- +Test Description File for Openstack +----------------------------------- We will use ``tc_prox_heat_context_l2fwd-2.yaml`` as a example to show you how to understand the test description file. -.. image:: images/PROX_Test_HEAT_Script.png - :width: 800px - :alt: NSB PROX Test Description File + .. image:: images/PROX_Test_HEAT_Script1.png + :width: 800px + :alt: NSB PROX Test Description File - Part 1 + + + .. image:: images/PROX_Test_HEAT_Script2.png + :width: 800px + :alt: NSB PROX Test Description File - Part 2 Now lets examine the components of the file in detail -Sections 1 to 8 are exactly the same in Baremetal and in Heat. Section -``9`` is replaced with sections A to F. Section 9 was for a baremetal +Sections 1 to 9 are exactly the same in Baremetal and in Heat. Section +``10`` is replaced with sections A to F. Section 10 was for a baremetal configuration file. This has no place in a heat configuration. A. ``image`` - yardstick-samplevnfs. This is the name of the image @@ -418,21 +473,75 @@ F. ``networks`` - is composed of a management network labeled ``mgmt`` gateway_ip: 'null' port_security_enabled: False enable_dhcp: 'false' - downlink_1: + uplink_1: cidr: '10.0.4.0/24' gateway_ip: 'null' port_security_enabled: False enable_dhcp: 'false' - downlink_2: + downlink_1: cidr: '10.0.5.0/24' gateway_ip: 'null' port_security_enabled: False enable_dhcp: 'false' -.. _nsb-traffic-generator-label: +Test Description File for Standalone +------------------------------------ + +We will use ``tc_prox_ovs-dpdk_l2fwd-2.yaml`` as a example to show +you how to understand the test description file. + + .. image:: images/PROX_Test_ovs_dpdk_Script_1.png + :width: 800px + :alt: NSB PROX Test Standalone Description File - Part 1 -*Traffic Generator Config file* -------------------------------- + .. image:: images/PROX_Test_ovs_dpdk_Script_2.png + :width: 800px + :alt: NSB PROX Test Standalone Description File - Part 2 + +Now lets examine the components of the file in detail + +Sections 1 to 9 are exactly the same in Baremetal and in Heat. Section +``10`` is replaced with sections A to F. Section 10 was for a baremetal +configuration file. This has no place in a heat configuration. + +A. ``file`` - Pod file for Baremetal Traffic Generator configuration: + IP Address, User/Password & Interfaces + +B. ``type`` - This defines the type of standalone configuration. + Possible values are ``StandaloneOvsDpdk`` or ``StandaloneSriov`` + +C. ``file`` - Pod file for Standalone host configuration: + IP Address, User/Password & Interfaces + +D. ``vm_deploy`` - Deploy a new VM or use an existing VM + +E. ``ovs_properties`` - OVS Version, DPDK Version and configuration + to use. + +F. ``flavor``- NSB image generated when installing NSB using ansible-playbook:: + + ram- Configurable RAM for SUT VM + extra_specs + hw:cpu_sockets - Configurable number of Sockets for SUT VM + hw:cpu_cores - Configurable number of Cores for SUT VM + hw:cpu_threads- Configurable number of Threads for SUT VM + +G. ``mgmt`` - Management port of the SUT VM. Preconfig needed on TG & SUT host machines. + is the system under test. + + +H. ``xe0`` - Upline Network port + +I. ``xe1`` - Downline Network port + +J. ``uplink_0`` - Uplink Phy port of the NIC on the host. This will be used to create + the Virtual Functions. + +K. ``downlink_0`` - Downlink Phy port of the NIC on the host. This will be used to + create the Virtual Functions. + +Traffic Generator Config file +----------------------------- This section will describe the traffic generator config file. This is the same for both baremetal and heat. See this example @@ -673,23 +782,29 @@ Now let's examine the components of the file in detail physical core improves performance, however sometimes it is optimal to move task to a separate core. This is best decided by checking performance. - c. ``mode=lat`` - Specifies the action carried out by this task on this core. Supported modes are: acl, - classify, drop, gredecap, greencap, ipv6_decap, ipv6_encap, l2fwd, lbnetwork, lbpos, lbqinq, nop, - police, qinqdecapv4, qinqencapv4, qos, routing, impair, lb5tuple, mirror, unmpls, tagmpls, - nat, decapnsh, encapnsh, gen, genl4 and lat. This task(0) per core(3) receives packets on port. - d. ``rx port=p0`` - The port to receive packets on ``Port 0``. Core 4 will receive packets on ``Port 1``. - e. ``lat pos=42`` - Describes where to put a 4-byte timestamp in the packet. Note that the packet length should - be longer than ``lat pos`` + 4 bytes to avoid truncation of the timestamp. It defines where the timestamp is - to be read from. Note that the SUT workload might cause the position of the timestamp to change - (i.e. due to encapsulation). - -.. _nsb-sut-generator-label: - -*SUT Config file* -------------------------------- + c. ``mode=lat`` - Specifies the action carried out by this task on this + core. + Supported modes are: ``acl``, ``classify``, ``drop``, ``gredecap``, + ``greencap``, ``ipv6_decap``, ``ipv6_encap``, ``l2fwd``, ``lbnetwork``, + ``lbpos``, ``lbqinq``, ``nop``, ``police``, ``qinqdecapv4``, + ``qinqencapv4``, ``qos``, ``routing``, ``impair``, ``lb5tuple``, + ``mirror``, ``unmpls``, ``tagmpls``, ``nat``, ``decapnsh``, ``encapnsh``, + ``gen``, ``genl4`` and ``lat``. This task(0) per core(3) receives packets + on port. + d. ``rx port=p0`` - The port to receive packets on ``Port 0``. Core 4 will + receive packets on ``Port 1``. + e. ``lat pos=42`` - Describes where to put a 4-byte timestamp in the packet. + Note that the packet length should be longer than ``lat pos`` + 4 bytes + to avoid truncation of the timestamp. It defines where the timestamp is + to be read from. Note that the SUT workload might cause the position of + the timestamp to change (i.e. due to encapsulation). + +SUT Config File +--------------- This section will describes the SUT(VNF) config file. This is the same for both -baremetal and heat. See this example of ``handle_l2fwd_multiflow-2.cfg`` to explain the options. +baremetal and heat. See this example of ``handle_l2fwd_multiflow-2.cfg`` to +explain the options. .. image:: images/PROX_Handle_2port_cfg.png :width: 1400px @@ -699,13 +814,15 @@ See `prox options`_ for details Now let's examine the components of the file in detail -1. ``[eal options]`` - same as the Generator config file. This specified the EAL (Environmental Abstraction Layer) - options. These are default values and are not changed. - See `dpdk wiki page`_. +1. ``[eal options]`` - same as the Generator config file. This specified the + EAL (Environmental Abstraction Layer) options. These are default values and + are not changed. See `dpdk wiki page`_. -2. ``[port 0]`` - This section describes the DPDK Port. The number following the keyword ``port`` usually refers to the DPDK Port Id. usually starting from ``0``. - Because you can have multiple ports this entry usually repeated. Eg. For a 2 port setup ``[port0]`` and ``[port 1]`` and for a 4 port setup ``[port 0]``, ``[port 1]``, - ``[port 2]`` and ``[port 3]``:: +2. ``[port 0]`` - This section describes the DPDK Port. The number following + the keyword ``port`` usually refers to the DPDK Port Id. usually starting + from ``0``. Because you can have multiple ports this entry usually + repeated. E.g. For a 2 port setup ``[port0]`` and ``[port 1]`` and for a 4 + port setup ``[port 0]``, ``[port 1]``, ``[port 2]`` and ``[port 3]``:: [port 0] name=if0 @@ -714,10 +831,14 @@ Now let's examine the components of the file in detail tx desc=2048 promiscuous=yes - a. In this example ``name =if0`` assigned the name ``if0`` to the port. Any name can be assigned to a port. - b. ``mac=hardware`` sets the MAC address assigned by the hardware to data from this port. - c. ``rx desc=2048`` sets the number of available descriptors to allocate for receive packets. This can be changed and can effect performance. - d. ``tx desc=2048`` sets the number of available descriptors to allocate for transmit packets. This can be changed and can effect performance. + a. In this example ``name =if0`` assigned the name ``if0`` to the port. Any + name can be assigned to a port. + b. ``mac=hardware`` sets the MAC address assigned by the hardware to data + from this port. + c. ``rx desc=2048`` sets the number of available descriptors to allocate + for receive packets. This can be changed and can effect performance. + d. ``tx desc=2048`` sets the number of available descriptors to allocate + for transmit packets. This can be changed and can effect performance. e. ``promiscuous=yes`` this enables promiscuous mode for this port. 3. ``[defaults]`` - Here default operations and settings can be over written.:: @@ -726,35 +847,46 @@ Now let's examine the components of the file in detail mempool size=8K memcache size=512 - a. In this example ``mempool size=8K`` the number of mbufs per task is altered. Altering this value could effect performance. See `prox options`_ for details. - b. ``memcache size=512`` - number of mbufs cached per core, default is 256 this is the cache_size. Altering this value could effect performance. + a. In this example ``mempool size=8K`` the number of mbufs per task is + altered. Altering this value could effect performance. See + `prox options`_ for details. + b. ``memcache size=512`` - number of mbufs cached per core, default is 256 + this is the cache_size. Altering this value could affect performance. -4. ``[global]`` - Here application wide setting are supported. Things like application name, start time, duration and memory configurations can be set here. +4. ``[global]`` - Here application wide setting are supported. Things like + application name, start time, duration and memory configurations can be set + here. In this example.:: [global] start time=5 name=Basic Gen - a. ``start time=5`` Time is seconds after which average stats will be started. + a. ``start time=5`` Time is seconds after which average stats will be + started. b. ``name=Handle L2FWD Multiflow (2x)`` Name of the configuration. -5. ``[core 0]`` - This core is designated the master core. Every Prox application must have a master core. The master mode must be assigned to +5. ``[core 0]`` - This core is designated the master core. Every Prox + application must have a master core. The master mode must be assigned to exactly one task, running alone on one core.:: [core 0] mode=master -6. ``[core 1]`` - This describes the activity on core 1. Cores can be configured by means of a set of [core #] sections, where # represents either: +6. ``[core 1]`` - This describes the activity on core 1. Cores can be + configured by means of a set of [core #] sections, where # represents + either: - a. an absolute core number: e.g. on a 10-core, dual socket system with hyper-threading, - cores are numbered from 0 to 39. + a. an absolute core number: e.g. on a 10-core, dual socket system with + hyper-threading, cores are numbered from 0 to 39. - b. PROX allows a core to be identified by a core number, the letter 's', and a socket number. - However NSB PROX is hardware agnostic (physical and virtual configurations are the same) it - is advisable no to use physical core numbering. + b. PROX allows a core to be identified by a core number, the letter 's', + and a socket number. However NSB PROX is hardware agnostic (physical and + virtual configurations are the same) it is advisable no to use physical + core numbering. - Each core can be assigned with a set of tasks, each running one of the implemented packet processing modes.:: + Each core can be assigned with a set of tasks, each running one of the + implemented packet processing modes.:: [core 1] name=none @@ -765,20 +897,33 @@ Now let's examine the components of the file in detail tx port=if1 a. ``name=none`` - No name assigned to the core. - b. ``task=0`` - Each core can run a set of tasks. Starting with ``0``. Task 1 can be defined later in this core or - can be defined in another ``[core 1]`` section with ``task=1`` later in configuration file. Sometimes running - multiple task related to the same packet on the same physical core improves performance, however sometimes it - is optimal to move task to a separate core. This is best decided by checking performance. - c. ``mode=l2fwd`` - Specifies the action carried out by this task on this core. Supported modes are: acl, - classify, drop, gredecap, greencap, ipv6_decap, ipv6_encap, l2fwd, lbnetwork, lbpos, lbqinq, nop, - police, qinqdecapv4, qinqencapv4, qos, routing, impair, lb5tuple, mirror, unmpls, tagmpls, - nat, decapnsh, encapnsh, gen, genl4 and lat. This code does ``l2fwd`` .. ie it does the L2FWD. - - d. ``dst mac=@@tester_mac1`` - The destination mac address of the packet will be set to the MAC address of ``Port 1`` of destination device. (The Traffic Generator/Verifier) - e. ``rx port=if0`` - This specifies that the packets are received from ``Port 0`` called if0 - f. ``tx port=if1`` - This specifies that the packets are transmitted to ``Port 1`` called if1 - - If this example we receive a packet on core on a port, carry out operation on the packet on the core and transmit it on on another port still using the same task on the same core. + b. ``task=0`` - Each core can run a set of tasks. Starting with ``0``. + Task 1 can be defined later in this core or can be defined in another + ``[core 1]`` section with ``task=1`` later in configuration file. + Sometimes running multiple task related to the same packet on the same + physical core improves performance, however sometimes it is optimal to + move task to a separate core. This is best decided by checking + performance. + c. ``mode=l2fwd`` - Specifies the action carried out by this task on this + core. Supported modes are: ``acl``, ``classify``, ``drop``, + ``gredecap``, ``greencap``, ``ipv6_decap``, ``ipv6_encap``, ``l2fwd``, + ``lbnetwork``, ``lbpos``, ``lbqinq``, ``nop``, ``police``, + ``qinqdecapv4``, ``qinqencapv4``, ``qos``, ``routing``, ``impair``, + ``lb5tuple``, ``mirror``, ``unmpls``, ``tagmpls``, ``nat``, + ``decapnsh``, ``encapnsh``, ``gen``, ``genl4`` and ``lat``. This code + does ``l2fwd``. i.e. it does the L2FWD. + + d. ``dst mac=@@tester_mac1`` - The destination mac address of the packet + will be set to the MAC address of ``Port 1`` of destination device. + (The Traffic Generator/Verifier) + e. ``rx port=if0`` - This specifies that the packets are received from + ``Port 0`` called if0 + f. ``tx port=if1`` - This specifies that the packets are transmitted to + ``Port 1`` called if1 + + In this example we receive a packet on core on a port, carry out operation + on the packet on the core and transmit it on on another port still using + the same task on the same core. On some implementation you may wish to use multiple tasks, like this.:: @@ -798,59 +943,76 @@ Now let's examine the components of the file in detail tx port=if0 drop=no - In this example you can see Core 1/Task 0 called ``rx_task`` receives the packet from if0 and perform the l2fwd. However instead of sending the packet to a - port it sends it to a core see ``tx cores=1t1``. In this case it sends it to Core 1/Task 1. + In this example you can see Core 1/Task 0 called ``rx_task`` receives the + packet from if0 and perform the l2fwd. However instead of sending the + packet to a port it sends it to a core see ``tx cores=1t1``. In this case it + sends it to Core 1/Task 1. - Core 1/Task 1 called ``l2fwd_if0``, receives the packet, not from a port but from the ring. See ``rx ring=yes``. It does not perform any operation on the packet See ``mode=none`` - and sends the packets to ``if0`` see ``tx port=if0``. + Core 1/Task 1 called ``l2fwd_if0``, receives the packet, not from a port but + from the ring. See ``rx ring=yes``. It does not perform any operation on the + packet See ``mode=none`` and sends the packets to ``if0`` see + ``tx port=if0``. - It is also possible to implement more complex operations be chaining multiple operations in sequence and using rings to pass packets from one core to another. + It is also possible to implement more complex operations by chaining + multiple operations in sequence and using rings to pass packets from one + core to another. - In thus example we show a Broadband Network Gateway (BNG) with Quality of Service (QoS). Communication from task to task is via rings. + In this example, we show a Broadband Network Gateway (BNG) with Quality of + Service (QoS). Communication from task to task is via rings. .. image:: images/PROX_BNG_QOS.png :width: 1000px :alt: NSB PROX Config File for BNG_QOS -*Baremetal Configuration file* ------------------------------- - -.. _baremetal-config-label: +Baremetal Configuration File +---------------------------- -This is required for baremetal testing. It describes the IP address of the various ports, the Network devices drivers and MAC addresses and the network +This is required for baremetal testing. It describes the IP address of the +various ports, the Network devices drivers and MAC addresses and the network configuration. -In this example we will describe a 2 port configuration. This file is the same for all 2 port NSB Prox tests on the same platforms/configuration. +In this example we will describe a 2 port configuration. This file is the same +for all 2 port NSB Prox tests on the same platforms/configuration. .. image:: images/PROX_Baremetal_config.png :width: 1000px :alt: NSB PROX Yardstick Config -Now lets describe the sections of the file. - - 1. ``TrafficGen`` - This section describes the Traffic Generator node of the test configuration. The name of the node ``trafficgen_1`` must match the node name - in the ``Test Description File for Baremetal`` mentioned earlier. The password attribute of the test needs to be configured. All other parameters - can remain as default settings. - 2. ``interfaces`` - This defines the DPDK interfaces on the Traffic Generator. - 3. ``xe0`` is DPDK Port 0. ``lspci`` and `` ./dpdk-devbind.py -s`` can be used to provide the interface information. ``netmask`` and ``local_ip`` should not be changed - 4. ``xe1`` is DPDK Port 1. If more than 2 ports are required then ``xe1`` section needs to be repeated and modified accordingly. - 5. ``vnf`` - This section describes the SUT of the test configuration. The name of the node ``vnf`` must match the node name in the - ``Test Description File for Baremetal`` mentioned earlier. The password attribute of the test needs to be configured. All other parameters - can remain as default settings +Now let's describe the sections of the file. + + 1. ``TrafficGen`` - This section describes the Traffic Generator node of the + test configuration. The name of the node ``trafficgen_1`` must match the + node name in the ``Test Description File for Baremetal`` mentioned + earlier. The password attribute of the test needs to be configured. All + other parameters can remain as default settings. + 2. ``interfaces`` - This defines the DPDK interfaces on the Traffic + Generator. + 3. ``xe0`` is DPDK Port 0. ``lspci`` and ``./dpdk-devbind.py -s`` can be used + to provide the interface information. ``netmask`` and ``local_ip`` should + not be changed + 4. ``xe1`` is DPDK Port 1. If more than 2 ports are required then ``xe1`` + section needs to be repeated and modified accordingly. + 5. ``vnf`` - This section describes the SUT of the test configuration. The + name of the node ``vnf`` must match the node name in the + ``Test Description File for Baremetal`` mentioned earlier. The password + attribute of the test needs to be configured. All other parameters can + remain as default settings 6. ``interfaces`` - This defines the DPDK interfaces on the SUT 7. ``xe0`` - Same as 3 but for the ``SUT``. 8. ``xe1`` - Same as 4 but for the ``SUT`` also. 9. ``routing_table`` - All parameters should remain unchanged. 10. ``nd_route_tbl`` - All parameters should remain unchanged. -*Grafana Dashboard* -------------------- +Grafana Dashboard +----------------- -The grafana dashboard visually displays the results of the tests. The steps required to produce a grafana dashboard are described here. +The grafana dashboard visually displays the results of the tests. The steps +required to produce a grafana dashboard are described here. .. _yardstick-config-label: - a. Configure ``yardstick`` to use influxDB to store test results. See file ``/etc/yardstick/yardstick.conf``. + a. Configure ``yardstick`` to use influxDB to store test results. See file + ``/etc/yardstick/yardstick.conf``. .. image:: images/PROX_Yardstick_config.png :width: 1000px @@ -859,10 +1021,12 @@ The grafana dashboard visually displays the results of the tests. The steps requ 1. Specify the dispatcher to use influxDB to store results. 2. "target = .. " - Specify location of influxDB to store results. "db_name = yardstick" - name of database. Do not change - "username = root" - username to use to store result. (Many tests are run as root) + "username = root" - username to use to store result. (Many tests are + run as root) "password = ... " - Please set to root user password - b. Deploy InfludDB & Grafana. See how to Deploy InfluxDB & Grafana. See `grafana deployment`_. + b. Deploy InfludDB & Grafana. See how to Deploy InfluxDB & Grafana. See + `grafana deployment`_. c. Generate the test data. Run the tests as follows .:: yardstick --debug task start tc_prox__-ports.yaml @@ -879,7 +1043,8 @@ How to run NSB Prox Test on an baremetal environment In order to run the NSB PROX test. - 1. Install NSB on Traffic Generator node and Prox in SUT. See `NSB Installation`_ + 1. Install NSB on Traffic Generator node and Prox in SUT. See + `NSB Installation`_ 2. To enter container:: @@ -891,8 +1056,8 @@ In order to run the NSB PROX test. cd /home/opnfv/repos/yardstick/samples/vnf_samples/nsut/prox - b. Install prox-baremetal-2.yam and prox-baremetal-4.yaml for that topology - into this directory as per baremetal-config-label_ + b. Install prox-baremetal-2.yam and prox-baremetal-4.yaml for that + topology into this directory as per `Baremetal Configuration File`_ c. Install and configure ``yardstick.conf`` :: @@ -937,12 +1102,11 @@ Frequently Asked Questions Here is a list of frequently asked questions. -*NSB Prox does not work on Baremetal, How do I resolve this?* -------------------------------------------------------------- +NSB Prox does not work on Baremetal, How do I resolve this? +----------------------------------------------------------- -If PROX NSB does not work on baremetal, problem is either in network configuration or test file. - -*Solution* +If PROX NSB does not work on baremetal, problem is either in network +configuration or test file. 1. Verify network configuration. Execute existing baremetal test.:: @@ -980,13 +1144,11 @@ If PROX NSB does not work on baremetal, problem is either in network configurati See ``Link detected`` if ``yes`` .... Cable is good. If ``no`` you have an issue with your cable/port. -2. If existing baremetal works then issue is with your test. Check the traffic generator gen_-.cfg to ensure - it is producing a valid packet. - -*How do I debug NSB Prox on Baremetal?* ---------------------------------------- +2. If existing baremetal works then issue is with your test. Check the traffic + generator gen_-.cfg to ensure it is producing a valid packet. -*Solution* +How do I debug NSB Prox on Baremetal? +------------------------------------- 1. Execute the test as follows:: @@ -1002,7 +1164,8 @@ If PROX NSB does not work on baremetal, problem is either in network configurati cd /opt/nsb_bin/prox -f /tmp/handle_-.cfg -4. Now let's examine the Generator Output. In this case the output of gen_l2fwd-4.cfg. +4. Now let's examine the Generator Output. In this case the output of + ``gen_l2fwd-4.cfg``. .. image:: images/PROX_Gen_GUI.png :width: 1000px @@ -1017,10 +1180,12 @@ If PROX NSB does not work on baremetal, problem is either in network configurati It appears what is transmitted is received. .. Caution:: - The number of packets MAY not exactly match because the ports are read in sequence. + The number of packets MAY not exactly match because the ports are read in + sequence. .. Caution:: - What is transmitted on PORT X may not always be received on same port. Please check the Test scenario. + What is transmitted on PORT X may not always be received on same port. + Please check the Test scenario. 5. Now lets examine the SUT Output @@ -1033,7 +1198,7 @@ If PROX NSB does not work on baremetal, problem is either in network configurati 1. What is received on 0 is transmitted on 1, received on 1 transmitted on 0, received on 2 transmitted on 3 and received on 3 transmitted on 2. 2. No packets are Failed. - 3. No Packets are discarded. + 3. No packets are discarded. We can also dump the packets being received or transmitted via the following commands. :: @@ -1049,26 +1214,24 @@ If PROX NSB does not work on baremetal, problem is either in network configurati dump_tx 1 0 1 -*NSB Prox works on Baremetal but not in Openstack. How do I resolve this?* --------------------------------------------------------------------------- +NSB Prox works on Baremetal but not in Openstack. How do I resolve this? +------------------------------------------------------------------------ -NSB Prox on Baremetal is a lot more forgiving than NSB Prox on Openstack. A badly -formed packed may still work with PROX on Baremetal. However on +NSB Prox on Baremetal is a lot more forgiving than NSB Prox on Openstack. A +badly formed packed may still work with PROX on Baremetal. However on Openstack the packet must be correct and all fields of the header correct. -Eg A packet with an invalid Protocol ID would still work in Baremetal -but this packet would be rejected by openstack. +E.g. A packet with an invalid Protocol ID would still work in Baremetal but +this packet would be rejected by openstack. -*Solution* 1. Check the validity of the packet. 2. Use a known good packet in your test - 3. If using ``Random`` fields in the traffic generator, disable them and retry. + 3. If using ``Random`` fields in the traffic generator, disable them and + retry. -*How do I debug NSB Prox on Openstack?* ---------------------------------------- - -*Solution* +How do I debug NSB Prox on Openstack? +------------------------------------- 1. Execute the test as follows:: @@ -1080,7 +1243,8 @@ but this packet would be rejected by openstack. 3. Install openstack credentials. - Depending on your openstack deployment, the location of these credentials may vary. + Depending on your openstack deployment, the location of these credentials + may vary. On this platform I do this via:: scp root@10.237.222.55:/etc/kolla/admin-openrc.sh . @@ -1096,8 +1260,8 @@ but this packet would be rejected by openstack. b. Get the Floating IP of the Traffic Generator & SUT - This generates a lot of information. Please not the floating IP of the VNF and - the Traffic Generator. + This generates a lot of information. Please note the floating IP of the + VNF and the Traffic Generator. .. image:: images/PROX_Openstack_stack_show_a.png :width: 1000px @@ -1138,10 +1302,8 @@ but this packet would be rejected by openstack. Now continue as baremetal. -*How do I resolve "Quota exceeded for resources"* -------------------------------------------------- - -*Solution* +How do I resolve "Quota exceeded for resources" +----------------------------------------------- This usually occurs due to 2 reasons when executing an openstack test. @@ -1175,16 +1337,15 @@ This usually occurs due to 2 reasons when executing an openstack test. openstack quota set -*Openstack Cli fails or hangs. How do I resolve this?* ------------------------------------------------------- - -*Solution* +Openstack CLI fails or hangs. How do I resolve this? +---------------------------------------------------- If it fails due to :: Missing value auth-url required for auth plugin password -Check your shell environment for Openstack variables. One of them should contain the authentication URL :: +Check your shell environment for Openstack variables. One of them should +contain the authentication URL :: OS_AUTH_URL=``https://192.168.72.41:5000/v3`` @@ -1208,16 +1369,16 @@ Result :: and visible. -If the Openstack Cli appears to hang, then verify the proxys and no_proxy are set correctly. -They should be similar to :: +If the Openstack CLI appears to hang, then verify the proxys and ``no_proxy`` +are set correctly. They should be similar to :: - FTP_PROXY="http://proxy.ir.intel.com:911/" - HTTPS_PROXY="http://proxy.ir.intel.com:911/" - HTTP_PROXY="http://proxy.ir.intel.com:911/" + FTP_PROXY="http://:/" + HTTPS_PROXY="http://:/" + HTTP_PROXY="http://:/" NO_PROXY="localhost,127.0.0.1,10.237.222.55,10.237.223.80,10.237.222.134,.ir.intel.com" - ftp_proxy="http://proxy.ir.intel.com:911/" - http_proxy="http://proxy.ir.intel.com:911/" - https_proxy="http://proxy.ir.intel.com:911/" + ftp_proxy="http://:/" + http_proxy="http://:/" + https_proxy="http://:/" no_proxy="localhost,127.0.0.1,10.237.222.55,10.237.223.80,10.237.222.134,.ir.intel.com" Where @@ -1225,10 +1386,95 @@ Where 1) 10.237.222.55 = IP Address of deployment node 2) 10.237.223.80 = IP Address of Controller node 3) 10.237.222.134 = IP Address of Compute Node - 4) ir.intel.com = local no proxy +How to Understand the Grafana output? +------------------------------------- + + .. image:: images/PROX_Grafana_1.png + :width: 1000px + :alt: NSB PROX Grafana_1 + + .. image:: images/PROX_Grafana_2.png + :width: 1000px + :alt: NSB PROX Grafana_2 + + .. image:: images/PROX_Grafana_3.png + :width: 1000px + :alt: NSB PROX Grafana_3 + + .. image:: images/PROX_Grafana_4.png + :width: 1000px + :alt: NSB PROX Grafana_4 + + .. image:: images/PROX_Grafana_5.png + :width: 1000px + :alt: NSB PROX Grafana_5 + + .. image:: images/PROX_Grafana_6.png + :width: 1000px + :alt: NSB PROX Grafana_6 + +A. Test Parameters - Test interval, Duration, Tolerated Loss and Test Precision + +B. No. of packets send and received during test + +C. Generator Stats - Average Throughput per step (Step Duration is specified by + "Duration" field in A above) + +D. Packet size + +E. No. of packets sent by the generator per second per interface in millions + of packets per second. + +F. No. of packets recieved by the generator per second per interface in millions + of packets per second. + +G. No. of packets received by the SUT from the generator in millions of packets + per second. + +H. No. of packets sent by the the SUT to the generator in millions of packets + per second. + +I. No. of packets sent by the Generator to the SUT per step per interface + in millions of packets per second. + +J. No. of packets received by the Generator from the SUT per step per interface + in millions of packets per second. + +K. No. of packets sent and received by the generator and lost by the SUT that + meet the success criteria + +L. The change in the Percentage of Line Rate used over a test, The MAX and the + MIN should converge to within the interval specified as the + ``test-precision``. + +M. Packet size supported during test. If *N/A* appears in any field the + result has not been decided. + +N. The Theretical Maximum no. of packets per second that can be sent for this + packet size. + +O. No. of packets sent by the generator in MPPS + +P. No. of packets received by the generator in MPPS + +Q. No. of packets sent by SUT. + +R. No. of packets received by the SUT +S. Total no. of dropped packets -- Packets sent but not received back by the + generator, these may be dropped by the SUT or the generator. +T. The tolerated no. of dropped packets. +U. Test throughput in Gbps +V. Latencey per Port + * Va - Port XE0 + * Vb - Port XE1 + * Vc - Port XE0 + * Vd - Port XE0 +W. CPU Utilization + * Wa - CPU Utilization of the Generator + * Wb - CPU Utilization of the SUT