| John DeNisco | 06dcd45 | 2018-07-26 12:45:10 -0400 | [diff] [blame] | 1 | .. _performance: |
| 2 | |
| 3 | Performance |
| 4 | =========== |
| 5 | |
| 6 | Overview |
| 7 | ^^^^^^^^ |
| 8 | |
| 9 | One of the benefits of FD.io VPP, is high performance on relatively low-power computing, this performance is based on the following features: |
| 10 | |
| 11 | * A high-performance user-space network stack designed for commodity hardware. |
| 12 | |
| 13 | - L2, L3 and L4 features and encapsulations. |
| 14 | |
| 15 | * Optimized packet interfaces supporting a multitude of use cases. |
| 16 | |
| 17 | - An integrated vhost-user backend for high speed VM-to-VM connectivity. |
| 18 | - An integrated memif container backend for high speed Container-to-Container connectivity. |
| 19 | - An integrated vhost based interface to punt packets to the Linux Kernel. |
| 20 | |
| 21 | * The same optimized code-paths run execute on the host, and inside VMs and Linux containers. |
| 22 | * Leverages best-of-breed open source driver technology: `DPDK <https://www.dpdk.org/>`_. |
| 23 | * Tested at scale; linear core scaling, tested with millions of flows and mac addresses. |
| 24 | |
| 25 | These features have been designed to take full advantage of common micro-processor optimization techniques, such as: |
| 26 | |
| 27 | * Reducing cache and TLS misses by processing packets in vectors. |
| 28 | * Realizing `IPC <https://en.wikipedia.org/wiki/Instructions_per_cycle>`_ gains with vector instructions such as: SSE, AVX and NEON. |
| 29 | * Eliminating mode switching, context switches and blocking, to always be doing useful work. |
| 30 | * Cache-lined aliged buffers for cache and memory efficiency. |
| 31 | |
| 32 | |
| 33 | Packet Throughput Graphs |
| 34 | ^^^^^^^^^^^^^^^^^^^^^^^^ |
| 35 | |
| 36 | These are some of the packet throughput graphs for FD.io VPP 18.04 from the CSIT `18.04 benchmarking report <https://docs.fd.io/csit/rls1804/report/>`_. |
| 37 | |
| 38 | .. toctree:: |
| 39 | |
| 40 | current_l2_throughput.rst |
| 41 | current_ndr_throughput.rst |
| 42 | current_ipv4_throughput.rst |
| 43 | current_ipv6_throughput.rst |
| 44 | |
| 45 | Trending Throughput Graphs |
| 46 | ^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| 47 | |
| 48 | These are some of the trending packet throughput graphs from the CSIT `trending dashboard <https://docs.fd.io/csit/master/trending/introduction/index.html>`_. **Please note that**, performance in the trending graphs will change on a nightly basis in line with the software development cycle. |
| 49 | |
| 50 | .. toctree:: |
| 51 | |
| 52 | trending_l2_throughput.rst |
| 53 | trending_ipv4_throughput.rst |
| 54 | trending_ipv6_throughput.rst |
| 55 | |
| 56 | For More information on CSIT |
| 57 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| 58 | |
| Lijian Zhang | 4af47b8 | 2018-08-07 15:34:45 +0800 | [diff] [blame] | 59 | The FD.io CSIT is implemented with below platforms: |
| 60 | |
| 61 | * - x86/64 |
| 62 | * - ARM-AArch64 |
| 63 | |
| 64 | * - Huawei TaiShan 2280 |
| 65 | * - Marvell MACCHIATObin |
| 66 | |
| 67 | |
| John DeNisco | 06dcd45 | 2018-07-26 12:45:10 -0400 | [diff] [blame] | 68 | These are FD.io Continuous System Integration and Testing (CSIT)'s documentation links. |
| 69 | |
| 70 | * `CSIT Code Documentation <https://docs.fd.io/csit/master/doc/overview.html>`_ |
| 71 | * `CSIT Test Overview <https://docs.fd.io/csit/rls1804/report/introduction/overview.html>`_ |
| 72 | * `VPP Performance Dashboard <https://docs.fd.io/csit/master/trending/introduction/index.html>`_ |