diff options
Diffstat (limited to 'docs/report/vpp_performance_tests')
7 files changed, 458 insertions, 4 deletions
diff --git a/docs/report/vpp_performance_tests/containers.rst b/docs/report/vpp_performance_tests/containers.rst index 8fd03207d8..d3eeb71b0b 100644 --- a/docs/report/vpp_performance_tests/containers.rst +++ b/docs/report/vpp_performance_tests/containers.rst @@ -535,10 +535,10 @@ Following container networking topologies are tested in CSIT |release|: - Kubernetes/Ligato topologies: - - eth-l2xcbase-eth-2memif-1vnf. - - eth-l2xcbase-eth-4memif-2vnf. - - eth-l2bdbasemaclrn-eth-2memif-1vnf. - - eth-l2bdbasemaclrn-eth-4memif-2vnf. + - eth-1drcl2xcbase-eth-2memif-1drcl2xc. + - eth-1drcl2xcbase-eth-4memif-2drcl2xc. + - eth-1drcl2bdbasemaclrn-eth-2memif-1drcl2xc. + - eth-1drcl2bdbasemaclrn-eth-4memif-2drcl2xc. References diff --git a/docs/report/vpp_performance_tests/packet_latency_graphs/container_memif.rst b/docs/report/vpp_performance_tests/packet_latency_graphs/container_memif.rst new file mode 100644 index 0000000000..3ac7da60a4 --- /dev/null +++ b/docs/report/vpp_performance_tests/packet_latency_graphs/container_memif.rst @@ -0,0 +1,74 @@ +Container memif Connections +=========================== + +This section includes summary graphs of VPP Phy-to-Phy packet latency +with Container memif Connections measured at 50% of discovered NDR throughput +rate. Latency is reported for VPP running in multiple configurations of +VPP worker thread(s), a.k.a. VPP data plane thread(s), and their +physical CPU core(s) placement. + +VPP packet latency in 1t1c setup (1thread, 1core) is presented in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_memif-ndrdisc-lat50.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_memif-ndrdisc-lat50} + \label{fig:64B-1t1c-container_memif-ndrdisc-lat50} + \end{figure} + +*Figure 1. VPP 1thread 1core - packet latency for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + +VPP packet latency in 2t2c setup (2thread, 2core) is presented in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_memif-ndrdisc-lat50.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_memif-ndrdisc-lat50} + \label{fig:64B-2t2c-container_memif-ndrdisc-lat50} + \end{figure} + +*Figure 2. VPP 2threads 2cores - packet latency for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * diff --git a/docs/report/vpp_performance_tests/packet_latency_graphs/container_orchestrated.rst b/docs/report/vpp_performance_tests/packet_latency_graphs/container_orchestrated.rst new file mode 100644 index 0000000000..fd3cd3423d --- /dev/null +++ b/docs/report/vpp_performance_tests/packet_latency_graphs/container_orchestrated.rst @@ -0,0 +1,74 @@ +Container Orchestrated Topologies +================================= + +This section includes summary graphs of VPP Phy-to-Phy packet latency +with CContainer Orchestrated Topologies measured at 50% of discovered NDR +throughput rate. Latency is reported for VPP running in multiple configurations +of VPP worker thread(s), a.k.a. VPP data plane thread(s), and their +physical CPU core(s) placement. + +VPP packet latency in 1t1c setup (1thread, 1core) is presented in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_orchestrated-ndrdisc-lat50.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_orchestrated-ndrdisc-lat50} + \label{fig:64B-1t1c-container_orchestrated-ndrdisc-lat50} + \end{figure} + +*Figure 1. VPP 1thread 1core - packet latency for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + +VPP packet latency in 2t2c setup (2thread, 2core) is presented in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_orchestrated-ndrdisc-lat50.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_orchestrated-ndrdisc-lat50} + \label{fig:64B-2t2c-container_orchestrated-ndrdisc-lat50} + \end{figure} + +*Figure 2. VPP 2threads 2cores - packet latency for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * diff --git a/docs/report/vpp_performance_tests/packet_latency_graphs/index.rst b/docs/report/vpp_performance_tests/packet_latency_graphs/index.rst index 7db10ee0cd..c42b4c9325 100644 --- a/docs/report/vpp_performance_tests/packet_latency_graphs/index.rst +++ b/docs/report/vpp_performance_tests/packet_latency_graphs/index.rst @@ -30,4 +30,6 @@ TGint2-to-SUT2-to-SUT1-to-TGint1. ip4_tunnels ip6_tunnels vm_vhost + container_memif + container_orchestrated ipsec diff --git a/docs/report/vpp_performance_tests/packet_throughput_graphs/container_memif.rst b/docs/report/vpp_performance_tests/packet_throughput_graphs/container_memif.rst new file mode 100644 index 0000000000..8c26762fcf --- /dev/null +++ b/docs/report/vpp_performance_tests/packet_throughput_graphs/container_memif.rst @@ -0,0 +1,151 @@ +Container memif Connections +=========================== + +Following sections include summary graphs of VPP Phy-to-Phy performance +with Container memif Connections, including NDR throughput (zero packet loss) +and PDR throughput (<0.5% packet loss). Performance is reported for VPP +running in multiple configurations of VPP worker thread(s), a.k.a. VPP +data plane thread(s), and their physical CPU core(s) placement. + +NDR Throughput +~~~~~~~~~~~~~~ + +VPP NDR 64B packet throughput in 1t1c setup (1thread, 1core) is presented +in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_memif-ndrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_memif-ndrdisc} + \label{fig:64B-1t1c-container_memif-ndrdisc} + \end{figure} + +*Figure 1. VPP 1thread 1core - NDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + +VPP NDR 64B packet throughput in 2t2c setup (2thread, 2core) is presented +in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_memif-ndrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_memif-ndrdisc} + \label{fig:64B-2t2c-container_memif-ndrdisc} + \end{figure} + +*Figure 2. VPP 2threads 2cores - NDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + + +PDR Throughput +~~~~~~~~~~~~~~ + +VPP PDR 64B packet throughput in 1t1c setup (1thread, 1core) is presented +in the graph below. PDR measured for 0.5% packet loss ratio. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_memif-pdrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_memif-pdrdisc} + \label{fig:64B-1t1c-container_memif-pdrdisc} + \end{figure} + +*Figure 3. VPP 1thread 1core - PDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + +VPP PDR 64B packet throughput in 2t2c setup (2thread, 2core) is presented +in the graph below. PDR measured for 0.5% packet loss ratio. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_memif-pdrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_memif-pdrdisc} + \label{fig:64B-2t2c-container_memif-pdrdisc} + \end{figure} + +*Figure 4. VPP 2thread 2core - PDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/vpp/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/vpp/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * diff --git a/docs/report/vpp_performance_tests/packet_throughput_graphs/container_orchestrated.rst b/docs/report/vpp_performance_tests/packet_throughput_graphs/container_orchestrated.rst new file mode 100644 index 0000000000..f9601c032a --- /dev/null +++ b/docs/report/vpp_performance_tests/packet_throughput_graphs/container_orchestrated.rst @@ -0,0 +1,151 @@ +Container Orchestrated Topologies +================================= + +Following sections include summary graphs of VPP Phy-to-Phy performance +with Container Orchestrated Topologies, including NDR throughput (zero packet +loss) and PDR throughput (<0.5% packet loss). Performance is reported for VPP +running in multiple configurations of VPP worker thread(s), a.k.a. VPP +data plane thread(s), and their physical CPU core(s) placement. + +NDR Throughput +~~~~~~~~~~~~~~ + +VPP NDR 64B packet throughput in 1t1c setup (1thread, 1core) is presented +in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_orchestrated-ndrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_orchestrated-ndrdisc} + \label{fig:64B-1t1c-container_orchestrated-ndrdisc} + \end{figure} + +*Figure 1. VPP 1thread 1core - NDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + +VPP NDR 64B packet throughput in 2t2c setup (2thread, 2core) is presented +in the graph below. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_orchestrated-ndrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_orchestrated-ndrdisc} + \label{fig:64B-2t2c-container_orchestrated-ndrdisc} + \end{figure} + +*Figure 2. VPP 2threads 2cores - NDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*ndrdisc" * + + +PDR Throughput +~~~~~~~~~~~~~~ + +VPP PDR 64B packet throughput in 1t1c setup (1thread, 1core) is presented +in the graph below. PDR measured for 0.5% packet loss ratio. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-1t1c-container_orchestrated-pdrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-1t1c-container_orchestrated-pdrdisc} + \label{fig:64B-1t1c-container_orchestrated-pdrdisc} + \end{figure} + +*Figure 3. VPP 1thread 1core - PDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-1t1c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + +VPP PDR 64B packet throughput in 2t2c setup (2thread, 2core) is presented +in the graph below. PDR measured for 0.5% packet loss ratio. + +.. raw:: html + + <iframe width="700" height="1000" frameborder="0" scrolling="no" src="../../_static/vpp/64B-2t2c-container_orchestrated-pdrdisc.html"></iframe> + +.. raw:: latex + + \begin{figure}[H] + \centering + \graphicspath{{../_build/_static/vpp/}} + \includegraphics[clip, trim=0cm 8cm 5cm 0cm, width=0.70\textwidth]{64B-2t2c-container_orchestrated-pdrdisc} + \label{fig:64B-2t2c-container_orchestrated-pdrdisc} + \end{figure} + +*Figure 4. VPP 2thread 2core - PDR Throughput for Phy-to-Phy L2 Ethernet +Switching (base).* + +CSIT source code for the test cases used for above plots can be found in CSIT +git repository: + +.. only:: html + + .. program-output:: cd ../../../../../ && set -x && cd tests/kubernetes/perf/container_memif && grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * + :shell: + +.. only:: latex + + .. code-block:: bash + + $ cd tests/kubernetes/perf/container_memif + $ grep -E "64B-2t2c-(eth|dot1q|dot1ad)-[1-9]drc(l2xcbase|l2bdbasemaclrn)-.*pdrdisc" * diff --git a/docs/report/vpp_performance_tests/packet_throughput_graphs/index.rst b/docs/report/vpp_performance_tests/packet_throughput_graphs/index.rst index 91191ef412..7c2a1a9e26 100644 --- a/docs/report/vpp_performance_tests/packet_throughput_graphs/index.rst +++ b/docs/report/vpp_performance_tests/packet_throughput_graphs/index.rst @@ -42,4 +42,6 @@ and their indices. ip4_tunnels ip6_tunnels vm_vhost + container_memif + container_orchestrated ipsec |