7.11.1.1. chain¶
7.11.1.1.1. 2n-10ge2p1x710-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 10 chains 10 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 10R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 10DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-10ch-20mif-10dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${10}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-10c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.1.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.1.2. 64B-1c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.1.3. 64B-2c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.1.4. 64B-4c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.1.5. 1518B-1c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.1.6. 1518B-2c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.1.7. 1518B-4c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.1.8. 9000B-1c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.1.9. 9000B-2c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.1.10. 9000B-4c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.1.11. IMIX-1c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.1.12. IMIX-2c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.1.13. IMIX-4c-eth-l2bd-10ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.2. 2n-10ge2p1x710-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 10 chains 10 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 10R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 10DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-10ch-20mif-10dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${10}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-10c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.2.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.2.2. 64B-1c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.2.3. 64B-2c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.2.4. 64B-4c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.2.5. 1518B-1c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.2.6. 1518B-2c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.2.7. 1518B-4c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.2.8. 9000B-1c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.2.9. 9000B-2c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.2.10. 9000B-4c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.2.11. IMIX-1c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.2.12. IMIX-2c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.2.13. IMIX-4c-eth-l2bd-10ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.3. 2n-10ge2p1x710-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 10 chains 20 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 10R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 20DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-10ch-40mif-20dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${10}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-10c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.3.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.3.2. 64B-1c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.3.3. 64B-2c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.3.4. 64B-4c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.3.5. 1518B-1c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.3.6. 1518B-2c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.3.7. 1518B-4c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.3.8. 9000B-1c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.3.9. 9000B-2c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.3.10. 9000B-4c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.3.11. IMIX-1c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.3.12. IMIX-2c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.3.13. IMIX-4c-eth-l2bd-10ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.4. 2n-10ge2p1x710-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 6 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R6C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 6DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-12mif-6dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${6}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c6n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.4.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.4.2. 64B-1c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.4.3. 64B-2c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.4.4. 64B-4c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.4.5. 1518B-1c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.4.6. 1518B-2c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.4.7. 1518B-4c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.4.8. 9000B-1c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.4.9. 9000B-2c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.4.10. 9000B-4c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.4.11. IMIX-1c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.4.12. IMIX-2c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.4.13. IMIX-4c-eth-l2bd-1ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.5. 2n-10ge2p1x710-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 6 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R6C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 6DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-12mif-6dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${6}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c6n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.5.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.5.2. 64B-1c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.5.3. 64B-2c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.5.4. 64B-4c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.5.5. 1518B-1c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.5.6. 1518B-2c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.5.7. 1518B-4c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.5.8. 9000B-1c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.5.9. 9000B-2c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.5.10. 9000B-4c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.5.11. IMIX-1c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.5.12. IMIX-2c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.5.13. IMIX-4c-eth-l2bd-1ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.6. 2n-10ge2p1x710-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R8C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-16mif-8dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${8}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c8n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.6.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.6.2. 64B-1c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.6.3. 64B-2c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.6.4. 64B-4c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.6.5. 1518B-1c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.6.6. 1518B-2c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.6.7. 1518B-4c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.6.8. 9000B-1c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.6.9. 9000B-2c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.6.10. 9000B-4c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.6.11. IMIX-1c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.6.12. IMIX-2c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.6.13. IMIX-4c-eth-l2bd-1ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.7. 2n-10ge2p1x710-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R8C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-16mif-8dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${8}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c8n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.7.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.7.2. 64B-1c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.7.3. 64B-2c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.7.4. 64B-4c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.7.5. 1518B-1c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.7.6. 1518B-2c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.7.7. 1518B-4c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.7.8. 9000B-1c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.7.9. 9000B-2c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.7.10. 9000B-4c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.7.11. IMIX-1c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.7.12. IMIX-2c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.7.13. IMIX-4c-eth-l2bd-1ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.8. 2n-10ge2p1x710-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 10 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R10C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 10DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-20mif-10dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${10}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c10n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.8.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.8.2. 64B-1c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.8.3. 64B-2c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.8.4. 64B-4c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.8.5. 1518B-1c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.8.6. 1518B-2c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.8.7. 1518B-4c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.8.8. 9000B-1c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.8.9. 9000B-2c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.8.10. 9000B-4c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.8.11. IMIX-1c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.8.12. IMIX-2c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.8.13. IMIX-4c-eth-l2bd-1ch-20mif-10dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.9. 2n-10ge2p1x710-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 10 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domainsand MAC learning enabled. DUT1 tested with ${nic_name}.
Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R10C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 10DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-20mif-10dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${10}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c10n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.9.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.9.2. 64B-1c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.9.3. 64B-2c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.9.4. 64B-4c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.9.5. 1518B-1c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.9.6. 1518B-2c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.9.7. 1518B-4c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.9.8. 9000B-1c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.9.9. 9000B-2c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.9.10. 9000B-4c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.9.11. IMIX-1c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.9.12. IMIX-2c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.9.13. IMIX-4c-eth-l2bd-1ch-20mif-10dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.10. 2n-10ge2p1x710-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 1 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 1DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-2mif-1dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.10.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.10.2. 64B-1c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.10.3. 64B-2c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.10.4. 64B-4c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.10.5. 1518B-1c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.10.6. 1518B-2c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.10.7. 1518B-4c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.10.8. 9000B-1c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.10.9. 9000B-2c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.10.10. 9000B-4c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.10.11. IMIX-1c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.10.12. IMIX-2c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.10.13. IMIX-4c-eth-l2bd-1ch-2mif-1dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.11. 2n-10ge2p1x710-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 1 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 1DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-2mif-1dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.11.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.11.2. 64B-1c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.11.3. 64B-2c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.11.4. 64B-4c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.11.5. 1518B-1c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.11.6. 1518B-2c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.11.7. 1518B-4c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.11.8. 9000B-1c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.11.9. 9000B-2c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.11.10. 9000B-4c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.11.11. IMIX-1c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.11.12. IMIX-2c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.11.13. IMIX-4c-eth-l2bd-1ch-2mif-1dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.12. 2n-10ge2p1x710-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 2 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 2DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-4mif-2dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.12.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.12.2. 64B-1c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.12.3. 64B-2c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.12.4. 64B-4c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.12.5. 1518B-1c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.12.6. 1518B-2c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.12.7. 1518B-4c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.12.8. 9000B-1c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.12.9. 9000B-2c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.12.10. 9000B-4c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.12.11. IMIX-1c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.12.12. IMIX-2c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.12.13. IMIX-4c-eth-l2bd-1ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.13. 2n-10ge2p1x710-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 2 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 2DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-4mif-2dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.13.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.13.2. 64B-1c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.13.3. 64B-2c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.13.4. 64B-4c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.13.5. 1518B-1c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.13.6. 1518B-2c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.13.7. 1518B-4c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.13.8. 9000B-1c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.13.9. 9000B-2c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.13.10. 9000B-4c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.13.11. IMIX-1c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.13.12. IMIX-2c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.13.13. IMIX-4c-eth-l2bd-1ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.14. 2n-10ge2p1x710-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-8mif-4dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.14.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.14.2. 64B-1c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.14.3. 64B-2c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.14.4. 64B-4c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.14.5. 1518B-1c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.14.6. 1518B-2c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.14.7. 1518B-4c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.14.8. 9000B-1c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.14.9. 9000B-2c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.14.10. 9000B-4c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.14.11. IMIX-1c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.14.12. IMIX-2c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.14.13. IMIX-4c-eth-l2bd-1ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.15. 2n-10ge2p1x710-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 1 chain 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 1R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-1ch-8mif-4dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${1}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-1c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.15.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.15.2. 64B-1c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.15.3. 64B-2c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.15.4. 64B-4c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.15.5. 1518B-1c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.15.6. 1518B-2c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.15.7. 1518B-4c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.15.8. 9000B-1c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.15.9. 9000B-2c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.15.10. 9000B-4c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.15.11. IMIX-1c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.15.12. IMIX-2c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.15.13. IMIX-4c-eth-l2bd-1ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.16. 2n-10ge2p1x710-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-16mif-8dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.16.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.16.2. 64B-1c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.16.3. 64B-2c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.16.4. 64B-4c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.16.5. 1518B-1c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.16.6. 1518B-2c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.16.7. 1518B-4c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.16.8. 9000B-1c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.16.9. 9000B-2c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.16.10. 9000B-4c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.16.11. IMIX-1c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.16.12. IMIX-2c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.16.13. IMIX-4c-eth-l2bd-2ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.17. 2n-10ge2p1x710-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-16mif-8dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.17.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.17.2. 64B-1c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.17.3. 64B-2c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.17.4. 64B-4c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.17.5. 1518B-1c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.17.6. 1518B-2c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.17.7. 1518B-4c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.17.8. 9000B-1c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.17.9. 9000B-2c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.17.10. 9000B-4c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.17.11. IMIX-1c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.17.12. IMIX-2c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.17.13. IMIX-4c-eth-l2bd-2ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.18. 2n-10ge2p1x710-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 12 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R6C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 12DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-24mif-12dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${6}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c6n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.18.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.18.2. 64B-1c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.18.3. 64B-2c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.18.4. 64B-4c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.18.5. 1518B-1c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.18.6. 1518B-2c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.18.7. 1518B-4c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.18.8. 9000B-1c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.18.9. 9000B-2c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.18.10. 9000B-4c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.18.11. IMIX-1c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.18.12. IMIX-2c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.18.13. IMIX-4c-eth-l2bd-2ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.19. 2n-10ge2p1x710-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 12 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R6C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 12DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-24mif-12dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${6}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c6n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.19.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.19.2. 64B-1c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.19.3. 64B-2c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.19.4. 64B-4c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.19.5. 1518B-1c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.19.6. 1518B-2c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.19.7. 1518B-4c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.19.8. 9000B-1c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.19.9. 9000B-2c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.19.10. 9000B-4c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.19.11. IMIX-1c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.19.12. IMIX-2c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.19.13. IMIX-4c-eth-l2bd-2ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.20. 2n-10ge2p1x710-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R8C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-32mif-16dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${8}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c8n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.20.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.20.2. 64B-1c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.20.3. 64B-2c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.20.4. 64B-4c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.20.5. 1518B-1c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.20.6. 1518B-2c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.20.7. 1518B-4c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.20.8. 9000B-1c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.20.9. 9000B-2c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.20.10. 9000B-4c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.20.11. IMIX-1c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.20.12. IMIX-2c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.20.13. IMIX-4c-eth-l2bd-2ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.21. 2n-10ge2p1x710-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R8C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-32mif-16dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${8}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c8n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.21.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.21.2. 64B-1c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.21.3. 64B-2c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.21.4. 1518B-1c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.21.5. 1518B-2c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.21.6. 9000B-1c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.21.7. 9000B-2c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.21.8. IMIX-1c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.21.9. IMIX-2c-eth-l2bd-2ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.22. 2n-10ge2p1x710-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 20 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R10C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 20DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-40mif-20dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${10}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c10n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.22.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.22.2. 64B-1c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.22.3. 64B-2c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.22.4. 64B-4c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.22.5. 1518B-1c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.22.6. 1518B-2c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.22.7. 1518B-4c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.22.8. 9000B-1c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.22.9. 9000B-2c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.22.10. 9000B-4c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.22.11. IMIX-1c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.22.12. IMIX-2c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.22.13. IMIX-4c-eth-l2bd-2ch-40mif-20dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.23. 2n-10ge2p1x710-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 2 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 2DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-4mif-2dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.23.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.23.2. 64B-1c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.23.3. 64B-2c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.23.4. 64B-4c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.23.5. 1518B-1c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.23.6. 1518B-2c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.23.7. 1518B-4c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.23.8. 9000B-1c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.23.9. 9000B-2c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.23.10. 9000B-4c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.23.11. IMIX-1c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.23.12. IMIX-2c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.23.13. IMIX-4c-eth-l2bd-2ch-4mif-2dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.24. 2n-10ge2p1x710-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 2 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 2DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-4mif-2dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.24.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.24.2. 64B-1c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.24.3. 64B-2c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.24.4. 64B-4c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.24.5. 1518B-1c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.24.6. 1518B-2c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.24.7. 1518B-4c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.24.8. 9000B-1c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.24.9. 9000B-2c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.24.10. 9000B-4c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.24.11. IMIX-1c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.24.12. IMIX-2c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.24.13. IMIX-4c-eth-l2bd-2ch-4mif-2dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.25. 2n-10ge2p1x710-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-8mif-4dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.25.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.25.2. 64B-1c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.25.3. 64B-2c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.25.4. 64B-4c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.25.5. 1518B-1c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.25.6. 1518B-2c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.25.7. 1518B-4c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.25.8. 9000B-1c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.25.9. 9000B-2c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.25.10. 9000B-4c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.25.11. IMIX-1c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.25.12. IMIX-2c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.25.13. IMIX-4c-eth-l2bd-2ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.26. 2n-10ge2p1x710-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 2 chains 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 2R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-2ch-8mif-4dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${2}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-2c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.26.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.26.2. 64B-1c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.26.3. 64B-2c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.26.4. 64B-4c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.26.5. 1518B-1c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.26.6. 1518B-2c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.26.7. 1518B-4c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.26.8. 9000B-1c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.26.9. 9000B-2c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.26.10. 9000B-4c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.26.11. IMIX-1c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.26.12. IMIX-2c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.26.13. IMIX-4c-eth-l2bd-2ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.27. 2n-10ge2p1x710-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-16mif-8dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.27.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.27.2. 64B-1c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.27.3. 64B-2c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.27.4. 64B-4c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.27.5. 1518B-1c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.27.6. 1518B-2c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.27.7. 1518B-4c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.27.8. 9000B-1c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.27.9. 9000B-2c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.27.10. 9000B-4c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.27.11. IMIX-1c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.27.12. IMIX-2c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.27.13. IMIX-4c-eth-l2bd-4ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.28. 2n-10ge2p1x710-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-16mif-8dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.28.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.28.2. 64B-1c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.28.3. 64B-2c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.28.4. 64B-4c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.28.5. 1518B-1c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.28.6. 1518B-2c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.28.7. 1518B-4c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.28.8. 9000B-1c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.28.9. 9000B-2c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.28.10. 9000B-4c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.28.11. IMIX-1c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.28.12. IMIX-2c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.28.13. IMIX-4c-eth-l2bd-4ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.29. 2n-10ge2p1x710-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-32mif-16dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.29.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.29.2. 64B-1c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.29.3. 64B-2c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.29.4. 64B-4c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.29.5. 1518B-1c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.29.6. 1518B-2c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.29.7. 1518B-4c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.29.8. 9000B-1c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.29.9. 9000B-2c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.29.10. 9000B-4c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.29.11. IMIX-1c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.29.12. IMIX-2c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.29.13. IMIX-4c-eth-l2bd-4ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.30. 2n-10ge2p1x710-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-32mif-16dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.30.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.30.2. 64B-1c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.30.3. 64B-2c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.30.4. 1518B-1c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.30.5. 1518B-2c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.30.6. 9000B-1c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.30.7. 9000B-2c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.30.8. IMIX-1c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.30.9. IMIX-2c-eth-l2bd-4ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.31. 2n-10ge2p1x710-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 24 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R6C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 24DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-48mif-24dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${6}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c6n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.31.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.31.2. 64B-1c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.31.3. 64B-2c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.31.4. 1518B-1c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.31.5. 1518B-2c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.31.6. 9000B-1c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.31.7. 9000B-2c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.31.8. IMIX-1c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.31.9. IMIX-2c-eth-l2bd-4ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.32. 2n-10ge2p1x710-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-8mif-4dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.32.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.32.2. 64B-1c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.32.3. 64B-2c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.32.4. 64B-4c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.32.5. 1518B-1c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.32.6. 1518B-2c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.32.7. 1518B-4c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.32.8. 9000B-1c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.32.9. 9000B-2c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.32.10. 9000B-4c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.32.11. IMIX-1c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.32.12. IMIX-2c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.32.13. IMIX-4c-eth-l2bd-4ch-8mif-4dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.33. 2n-10ge2p1x710-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 4 chains 4 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 4R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 4DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-4ch-8mif-4dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${4}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-4c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.33.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.33.2. 64B-1c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.33.3. 64B-2c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.33.4. 64B-4c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.33.5. 1518B-1c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.33.6. 1518B-2c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.33.7. 1518B-4c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.33.8. 9000B-1c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.33.9. 9000B-2c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.33.10. 9000B-4c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.33.11. IMIX-1c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.33.12. IMIX-2c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.33.13. IMIX-4c-eth-l2bd-4ch-8mif-4dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.34. 2n-10ge2p1x710-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 6 chains 6 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 6R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 6DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-6ch-12mif-6dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${6}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-6c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.34.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.34.2. 64B-1c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.34.3. 64B-2c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.34.4. 64B-4c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.34.5. 1518B-1c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.34.6. 1518B-2c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.34.7. 1518B-4c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.34.8. 9000B-1c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.34.9. 9000B-2c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.34.10. 9000B-4c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.34.11. IMIX-1c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.34.12. IMIX-2c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.34.13. IMIX-4c-eth-l2bd-6ch-12mif-6dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.35. 2n-10ge2p1x710-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 6 chains 6 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 6R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 6DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-6ch-12mif-6dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${6}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-6c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.35.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.35.2. 64B-1c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.35.3. 64B-2c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.35.4. 64B-4c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.35.5. 1518B-1c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.35.6. 1518B-2c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.35.7. 1518B-4c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.35.8. 9000B-1c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.35.9. 9000B-2c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.35.10. 9000B-4c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.35.11. IMIX-1c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.35.12. IMIX-2c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.35.13. IMIX-4c-eth-l2bd-6ch-12mif-6dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.36. 2n-10ge2p1x710-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 6 chains 12 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domainsand MAC learning enabled. DUT1 tested with ${nic_name}.
Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 6R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 12DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-6ch-24mif-12dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${6}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-6c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.36.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.36.2. 64B-1c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.36.3. 64B-2c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.36.4. 64B-4c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.36.5. 1518B-1c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.36.6. 1518B-2c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.36.7. 1518B-4c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.36.8. 9000B-1c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.36.9. 9000B-2c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.36.10. 9000B-4c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.36.11. IMIX-1c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.36.12. IMIX-2c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.36.13. IMIX-4c-eth-l2bd-6ch-24mif-12dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.37. 2n-10ge2p1x710-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 6 chains 12 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 6R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 12DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-6ch-24mif-12dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${6}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-6c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.37.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.37.2. 64B-1c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.37.3. 64B-2c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.37.4. 64B-4c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.37.5. 1518B-1c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.37.6. 1518B-2c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.37.7. 1518B-4c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.37.8. 9000B-1c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.37.9. 9000B-2c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.37.10. 9000B-4c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.37.11. IMIX-1c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.37.12. IMIX-2c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.37.13. IMIX-4c-eth-l2bd-6ch-24mif-12dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.38. 2n-10ge2p1x710-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 6 chains 24 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 6R4C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 24DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-6ch-48mif-24dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${6}
| ${nf_nodes}= | ${4}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-6c4n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.38.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.38.2. 64B-1c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.38.3. 64B-2c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.38.4. 1518B-1c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.38.5. 1518B-2c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.38.6. 9000B-1c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.38.7. 9000B-2c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.38.8. IMIX-1c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.38.9. IMIX-2c-eth-l2bd-6ch-48mif-24dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.39. 2n-10ge2p1x710-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 8 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 8R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-8ch-16mif-8dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${8}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-8c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.39.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.39.2. 64B-1c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.39.3. 64B-2c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.39.4. 64B-4c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.39.5. 1518B-1c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.39.6. 1518B-2c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.39.7. 1518B-4c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.39.8. 9000B-1c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.39.9. 9000B-2c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.39.10. 9000B-4c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.39.11. IMIX-1c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.39.12. IMIX-2c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.39.13. IMIX-4c-eth-l2bd-8ch-16mif-8dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.40. 2n-10ge2p1x710-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 8 chains 8 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 8R1C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 8DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-8ch-16mif-8dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${8}
| ${nf_nodes}= | ${1}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-8c1n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.40.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.40.2. 64B-1c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.40.3. 64B-2c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.40.4. 64B-4c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.40.5. 1518B-1c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.40.6. 1518B-2c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.40.7. 1518B-4c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.40.8. 9000B-1c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.40.9. 9000B-2c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.40.10. 9000B-4c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.40.11. IMIX-1c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.40.12. IMIX-2c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.40.13. IMIX-4c-eth-l2bd-8ch-16mif-8dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.41. 2n-10ge2p1x710-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 8 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 8R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR1T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-8ch-32mif-16dcr1t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${2}
| ${nf_dtc}= | ${0.5}
| ${nf_chains}= | ${8}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-8c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.41.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.41.2. 64B-1c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.41.3. 64B-2c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.41.4. 64B-4c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${4}
7.11.1.1.41.5. 1518B-1c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.41.6. 1518B-2c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.41.7. 1518B-4c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${4}
7.11.1.1.41.8. 9000B-1c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.41.9. 9000B-2c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.41.10. 9000B-4c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${4}
7.11.1.1.41.11. IMIX-1c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.41.12. IMIX-2c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}
7.11.1.1.41.13. IMIX-4c-eth-l2bd-8ch-32mif-16dcr1t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${4}
7.11.1.1.42. 2n-10ge2p1x710-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr suite¶
RFC2544: Pkt throughput L2BD test cases with memif 8 chains 16 docker container
[Top] Network Topologies: TG-DUT1-TG 2-node circular topology with single links between nodes.
[Enc] Packet Encapsulations: Eth-IPv4 for L2 bridge domain.
[Cfg] DUT configuration: DUT1 is configured with two L2 bridge domains and MAC learning enabled. DUT1 is tested with ${nic_name}. Container is connected to VPP via Memif interface. Container is running same VPP version as running on DUT. Container is limited via cgroup to use cores allocated from pool of isolated CPUs. There are no memory contraints.
[Ver] TG verification: TG finds and reports throughput NDR (Non Drop Rate) with zero packet loss tolerance and throughput PDR (Partial Drop Rate) with non-zero packet loss tolerance (LT) expressed in percentage of packets transmitted. NDR and PDR are discovered for different Ethernet L2 frame sizes using MLRsearch library.
Test packets are generated by TG on links to DUTs. TG traffic profile contains two L3 flow-groups (flow-group per direction, 254 flows per flow-group) with all packets containing Ethernet header, IPv4 header with IP protocol=61 and static payload. MAC addresses are matching MAC addresses of the TG node interfaces.
*** Settings ***
| Resource | resources/libraries/robot/shared/default.robot
|
| Force Tags | 2_NODE_SINGLE_LINK_TOPO | PERFTEST | HW_ENV | NDRPDR
| ... | NIC_Intel-X710 | ETH | L2BDMACLRN | BASE | MEMIF | DOCKER | 8R2C
| ... | NF_DENSITY | CHAIN | NF_VPPIP4 | 16DCR2T | DRV_VFIO_PCI
| ... | RXQ_SIZE_0 | TXQ_SIZE_0
| ... | eth-l2bd-8ch-32mif-16dcr2t-vppip4
|
| Suite Setup | Setup suite topology interfaces | performance
| Suite Teardown | Tear down suite | performance
| Test Setup | Setup test | performance
| Test Teardown | Tear down test | performance | container
|
| Test Template | Local Template
|
| *** Variables ***
| @{plugins_to_enable}= | dpdk_plugin.so | perfmon_plugin.so | memif_plugin.so
| ${crypto_type}= | ${None}
| ${nic_name}= | Intel-X710
| ${nic_driver}= | vfio-pci
| ${nic_rxq_size}= | 0
| ${nic_txq_size}= | 0
| ${nic_pfs}= | 2
| ${nic_vfs}= | 0
| ${osi_layer}= | L2
| ${overhead}= | ${0}
| ${nf_dtcr}= | ${1}
| ${nf_dtc}= | ${1}
| ${nf_chains}= | ${8}
| ${nf_nodes}= | ${2}
# Traffic profile:
| ${traffic_profile}= | trex-stl-2n3n-ethip4-ip4src254-8c2n
# Container
| ${container_engine}= | Docker
| ${container_chain_topology}= | chain_ip47.11.1.1.42.1. Local Template¶
[Cfg] DUT runs L2BD switching config. Each DUT uses ${phy_cores} physical core(s) for worker threads.
[Ver] Measure NDR and PDR values using MLRsearch algorithm.
Arguments: - frame_size - Framesize in Bytes in integer or string (IMIX_v4_1). Type: integer, string - phy_cores - Number of physical cores. Type: integer - rxq - Number of RX queues, default value: ${None}. Type: integer
Set Test Variable \${frame_size}
Given Set Max Rate And Jumbo
And Add worker threads to all DUTs ${phy_cores} ${rxq}
And Pre-initialize layer driver ${nic_driver}
And Apply startup configuration on all VPP DUTs
When Initialize layer driver ${nic_driver}
And Initialize layer interface count=${nf_chains}
And Start containers for test nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
And Initialize L2 Bridge Domain for multiple chains with memif pairs nf_chains=${nf_chains} nf_nodes=${nf_nodes} auto_scale=${False}
Then Find NDR and PDR intervals using optimized search
7.11.1.1.42.2. 64B-1c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${1}
7.11.1.1.42.3. 64B-2c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${64} phy_cores=${2}
7.11.1.1.42.4. 1518B-1c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${1}
7.11.1.1.42.5. 1518B-2c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${1518} phy_cores=${2}
7.11.1.1.42.6. 9000B-1c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${1}
7.11.1.1.42.7. 9000B-2c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=${9000} phy_cores=${2}
7.11.1.1.42.8. IMIX-1c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${1}
7.11.1.1.42.9. IMIX-2c-eth-l2bd-8ch-32mif-16dcr2t-vppip4-ndrpdr¶
frame_size=IMIX_v4_1 phy_cores=${2}