X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=doc%2Fguides%2Fnics%2Fmlx5.rst;h=98d134190a39290e7048e74243a0faaea126aed2;hb=9ba3d0ae2090;hp=2d68914408e64da0683c832a96156249738e812a;hpb=1ca601d160fc9ec56847c772526576f425159991;p=dpdk.git diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst index 2d68914408..98d134190a 100644 --- a/doc/guides/nics/mlx5.rst +++ b/doc/guides/nics/mlx5.rst @@ -31,7 +31,7 @@ MLX5 poll mode driver ===================== The MLX5 poll mode driver library (**librte_pmd_mlx5**) provides support for -**Mellanox ConnectX-4 EN** and **Mellanox ConnectX-4 Lx EN** families of +**Mellanox ConnectX-4** and **Mellanox ConnectX-4 Lx** families of 10/25/40/50/100 Gb/s adapters as well as their virtual functions (VF) in SR-IOV context. @@ -48,11 +48,6 @@ There is also a `section dedicated to this poll mode driver be enabled manually by setting ``CONFIG_RTE_LIBRTE_MLX5_PMD=y`` and recompiling DPDK. -.. warning:: - - ``CONFIG_RTE_BUILD_COMBINE_LIBS`` with ``CONFIG_RTE_BUILD_SHARED_LIB`` - is not supported and thus the compilation will fail with this configuration. - Implementation details ---------------------- @@ -78,19 +73,30 @@ Features - Multiple TX and RX queues. - Support for scattered TX and RX frames. -- IPv4, TCPv4 and UDPv4 RSS on any number of queues. +- IPv4, IPv6, TCPv4, TCPv6, UDPv4 and UDPv6 RSS on any number of queues. - Several RSS hash keys, one for each flow type. +- Configurable RETA table. - Support for multiple MAC addresses. - VLAN filtering. +- RX VLAN stripping. +- TX VLAN insertion. +- RX CRC stripping configuration. - Promiscuous mode. +- Multicast promiscuous mode. +- Hardware checksum offloads. +- Flow director (RTE_FDIR_MODE_PERFECT, RTE_FDIR_MODE_PERFECT_MAC_VLAN and + RTE_ETH_FDIR_REJECT). +- Secondary process TX is supported. +- KVM and VMware ESX SR-IOV modes are supported. +- RSS hash result is supported. Limitations ----------- -- IPv6 and inner VXLAN RSS are not supported yet. +- Inner RSS for VXLAN frames is not supported yet. - Port statistics through software counters only. -- No allmulticast mode. -- Hardware checksum offloads are not supported yet. +- Hardware checksum offloads for VXLAN inner header are not supported yet. +- Secondary process RX is not supported. Configuration ------------- @@ -110,18 +116,6 @@ These options can be modified in the ``.config`` file. adds additional run-time checks and debugging messages at the cost of lower performance. -- ``CONFIG_RTE_LIBRTE_MLX5_SGE_WR_N`` (default **4**) - - Number of scatter/gather elements (SGEs) per work request (WR). Lowering - this number improves performance but also limits the ability to receive - scattered packets (packets that do not fit a single mbuf). The default - value is a safe tradeoff. - -- ``CONFIG_RTE_LIBRTE_MLX5_MAX_INLINE`` (default **0**) - - Amount of data to be inlined during TX operations. Improves latency but - lowers throughput. - - ``CONFIG_RTE_LIBRTE_MLX5_TX_MP_CACHE`` (default **8**) Maximum number of cached memory pools (MPs) per TX queue. Each MP from @@ -130,6 +124,23 @@ These options can be modified in the ``.config`` file. This value is always 1 for RX queues since they use a single MP. +Environment variables +~~~~~~~~~~~~~~~~~~~~~ + +- ``MLX5_PMD_ENABLE_PADDING`` + + Enables HW packet padding in PCI bus transactions. + + When packet size is cache aligned and CRC stripping is enabled, 4 fewer + bytes are written to the PCI bus. Enabling padding makes such packets + aligned again. + + In cases where PCI bandwidth is the bottleneck, padding can improve + performance by 10%. + + This is disabled by default since this can also decrease performance for + unaligned packet sizes. + Run-time configuration ~~~~~~~~~~~~~~~~~~~~~~ @@ -139,6 +150,44 @@ Run-time configuration - **ethtool** operations on related kernel interfaces also affect the PMD. +- ``rxq_cqe_comp_en`` parameter [int] + + A nonzero value enables the compression of CQE on RX side. This feature + allows to save PCI bandwidth and improve performance at the cost of a + slightly higher CPU usage. Enabled by default. + + Supported on: + + - x86_64 with ConnectX4 and ConnectX4 LX + - Power8 with ConnectX4 LX + +- ``txq_inline`` parameter [int] + + Amount of data to be inlined during TX operations. Improves latency. + Can improve PPS performance when PCI back pressure is detected and may be + useful for scenarios involving heavy traffic on many queues. + + It is not enabled by default (set to 0) since the additional software + logic necessary to handle this mode can lower performance when back + pressure is not expected. + +- ``txqs_min_inline`` parameter [int] + + Enable inline send only when the number of TX queues is greater or equal + to this value. + + This option should be used in combination with ``txq_inline`` above. + +- ``txq_mpw_en`` parameter [int] + + A nonzero value enables multi-packet send. This feature allows the TX + burst function to pack up to five packets in two descriptors in order to + save PCI bandwidth and improve performance at the cost of a slightly + higher CPU usage. + + It is currently only supported on the ConnectX-4 Lx family of adapters. + Enabled by default. + Prerequisites ------------- @@ -192,10 +241,12 @@ DPDK and must be installed separately: Currently supported by DPDK: -- Mellanox OFED **3.1**. -- Minimum firmware version: - - ConnectX-4: **12.12.0780**. - - ConnectX-4 Lx: **14.12.0780**. +- Mellanox OFED **3.4-1.0.0.0**. + +- firmware version: + + - ConnectX-4: **12.17.1010** + - ConnectX-4 Lx: **14.17.1010** Getting Mellanox OFED ~~~~~~~~~~~~~~~~~~~~~ @@ -217,6 +268,23 @@ required from that distribution. this DPDK release was developed and tested against is strongly recommended. Please check the `prerequisites`_. +Notes for testpmd +----------------- + +Compared to librte_pmd_mlx4 that implements a single RSS configuration per +port, librte_pmd_mlx5 supports per-protocol RSS configuration. + +Since ``testpmd`` defaults to IP RSS mode and there is currently no +command-line parameter to enable additional protocols (UDP and TCP as well +as IP), the following commands must be entered from its CLI to get the same +behavior as librte_pmd_mlx4: + +.. code-block:: console + + > port stop all + > port config all rss all + > port start all + Usage example ------------- @@ -229,6 +297,13 @@ devices managed by librte_pmd_mlx5. modprobe -a ib_uverbs mlx5_core mlx5_ib + Alternatively if MLNX_OFED is fully installed, the following script can + be run: + + .. code-block:: console + + /etc/init.d/openibd restart + .. note:: User space I/O kernel modules (uio and igb_uio) are not used and do