€•UŒsphinx.addnodes”Œdocument”“”)”}”(Œ rawsource”Œ”Œchildren”]”(Œ translations”Œ LanguagesNode”“”)”}”(hhh]”(hŒ pending_xref”“”)”}”(hhh]”Œdocutils.nodes”ŒText”“”ŒChinese (Simplified)”…””}”Œparent”hsbaŒ attributes”}”(Œids”]”Œclasses”]”Œnames”]”Œdupnames”]”Œbackrefs”]”Œ refdomain”Œstd”Œreftype”Œdoc”Œ reftarget”Œ$/translations/zh_CN/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuŒtagname”hhh ubh)”}”(hhh]”hŒChinese (Traditional)”…””}”hh2sbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ$/translations/zh_TW/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒItalian”…””}”hhFsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ$/translations/it_IT/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒJapanese”…””}”hhZsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ$/translations/ja_JP/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒKorean”…””}”hhnsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ$/translations/ko_KR/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒSpanish”…””}”hh‚sbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ$/translations/sp_SP/infiniband/ipoib”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubeh}”(h]”h ]”h"]”h$]”h&]”Œcurrent_language”ŒEnglish”uh1h hhŒ _document”hŒsource”NŒline”NubhŒsection”“”)”}”(hhh]”(hŒtitle”“”)”}”(hŒIP over InfiniBand”h]”hŒIP over InfiniBand”…””}”(hh¨hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hh£hžhhŸŒ>/var/lib/git/docbuild/linux/Documentation/infiniband/ipoib.rst”h KubhŒ block_quote”“”)”}”(hXvThe ib_ipoib driver is an implementation of the IP over InfiniBand protocol as specified by RFC 4391 and 4392, issued by the IETF ipoib working group. It is a "native" implementation in the sense of setting the interface type to ARPHRD_INFINIBAND and the hardware address length to 20 (earlier proprietary implementations masqueraded to the kernel as ethernet interfaces). ”h]”hŒ paragraph”“”)”}”(hXuThe ib_ipoib driver is an implementation of the IP over InfiniBand protocol as specified by RFC 4391 and 4392, issued by the IETF ipoib working group. It is a "native" implementation in the sense of setting the interface type to ARPHRD_INFINIBAND and the hardware address length to 20 (earlier proprietary implementations masqueraded to the kernel as ethernet interfaces).”h]”hXyThe ib_ipoib driver is an implementation of the IP over InfiniBand protocol as specified by RFC 4391 and 4392, issued by the IETF ipoib working group. It is a “native†implementation in the sense of setting the interface type to ARPHRD_INFINIBAND and the hardware address length to 20 (earlier proprietary implementations masqueraded to the kernel as ethernet interfaces).”…””}”(hh¿hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h Khh¹ubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h Khh£hžhubh¢)”}”(hhh]”(h§)”}”(hŒPartitions and P_Keys”h]”hŒPartitions and P_Keys”…””}”(hhÖhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hhÓhžhhŸh¶h K ubh¸)”}”(hXÙWhen the IPoIB driver is loaded, it creates one interface for each port using the P_Key at index 0. To create an interface with a different P_Key, write the desired P_Key into the main interface's /sys/class/net//create_child file. For example:: echo 0x8001 > /sys/class/net/ib0/create_child This will create an interface named ib0.8001 with P_Key 0x8001. To remove a subinterface, use the "delete_child" file:: echo 0x8001 > /sys/class/net/ib0/delete_child The P_Key for any interface is given by the "pkey" file, and the main interface for a subinterface is in "parent." Child interface create/delete can also be done using IPoIB's rtnl_link_ops, where children created using either way behave the same. ”h]”(h¾)”}”(hXWhen the IPoIB driver is loaded, it creates one interface for each port using the P_Key at index 0. To create an interface with a different P_Key, write the desired P_Key into the main interface's /sys/class/net//create_child file. For example::”h]”hXWhen the IPoIB driver is loaded, it creates one interface for each port using the P_Key at index 0. To create an interface with a different P_Key, write the desired P_Key into the main interface’s /sys/class/net//create_child file. For example:”…””}”(hhèhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h KhhäubhŒ literal_block”“”)”}”(hŒ-echo 0x8001 > /sys/class/net/ib0/create_child”h]”hŒ-echo 0x8001 > /sys/class/net/ib0/create_child”…””}”hhøsbah}”(h]”h ]”h"]”h$]”h&]”Œ xml:space”Œpreserve”uh1höhŸh¶h Khhäubh¾)”}”(hŒxThis will create an interface named ib0.8001 with P_Key 0x8001. To remove a subinterface, use the "delete_child" file::”h]”hŒ{This will create an interface named ib0.8001 with P_Key 0x8001. To remove a subinterface, use the “delete_child†file:”…””}”(hjhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h Khhäubh÷)”}”(hŒ-echo 0x8001 > /sys/class/net/ib0/delete_child”h]”hŒ-echo 0x8001 > /sys/class/net/ib0/delete_child”…””}”hjsbah}”(h]”h ]”h"]”h$]”h&]”jjuh1höhŸh¶h Khhäubh¾)”}”(hŒrThe P_Key for any interface is given by the "pkey" file, and the main interface for a subinterface is in "parent."”h]”hŒzThe P_Key for any interface is given by the “pkey†file, and the main interface for a subinterface is in “parent.—…””}”(hj$hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h Khhäubh¾)”}”(hŒ„Child interface create/delete can also be done using IPoIB's rtnl_link_ops, where children created using either way behave the same.”h]”hŒ†Child interface create/delete can also be done using IPoIB’s rtnl_link_ops, where children created using either way behave the same.”…””}”(hj2hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h Khhäubeh}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KhhÓhžhubeh}”(h]”Œpartitions-and-p-keys”ah ]”h"]”Œpartitions and p_keys”ah$]”h&]”uh1h¡hh£hžhhŸh¶h K ubh¢)”}”(hhh]”(h§)”}”(hŒDatagram vs Connected modes”h]”hŒDatagram vs Connected modes”…””}”(hjQhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hjNhžhhŸh¶h K"ubh¸)”}”(hXThe IPoIB driver supports two modes of operation: datagram and connected. The mode is set and read through an interface's /sys/class/net//mode file. In datagram mode, the IB UD (Unreliable Datagram) transport is used and so the interface MTU has is equal to the IB L2 MTU minus the IPoIB encapsulation header (4 bytes). For example, in a typical IB fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes. In connected mode, the IB RC (Reliable Connected) transport is used. Connected mode takes advantage of the connected nature of the IB transport and allows an MTU up to the maximal IP packet size of 64K, which reduces the number of IP packets needed for handling large UDP datagrams, TCP segments, etc and increases the performance for large messages. In connected mode, the interface's UD QP is still used for multicast and communication with peers that don't support connected mode. In this case, RX emulation of ICMP PMTU packets is used to cause the networking stack to use the smaller UD MTU for these neighbours. ”h]”(h¾)”}”(hŒ The IPoIB driver supports two modes of operation: datagram and connected. The mode is set and read through an interface's /sys/class/net//mode file.”h]”hŒ¢The IPoIB driver supports two modes of operation: datagram and connected. The mode is set and read through an interface’s /sys/class/net//mode file.”…””}”(hjchžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h K$hj_ubh¾)”}”(hX In datagram mode, the IB UD (Unreliable Datagram) transport is used and so the interface MTU has is equal to the IB L2 MTU minus the IPoIB encapsulation header (4 bytes). For example, in a typical IB fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.”h]”hX In datagram mode, the IB UD (Unreliable Datagram) transport is used and so the interface MTU has is equal to the IB L2 MTU minus the IPoIB encapsulation header (4 bytes). For example, in a typical IB fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.”…””}”(hjqhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h K(hj_ubh¾)”}”(hX^In connected mode, the IB RC (Reliable Connected) transport is used. Connected mode takes advantage of the connected nature of the IB transport and allows an MTU up to the maximal IP packet size of 64K, which reduces the number of IP packets needed for handling large UDP datagrams, TCP segments, etc and increases the performance for large messages.”h]”hX^In connected mode, the IB RC (Reliable Connected) transport is used. Connected mode takes advantage of the connected nature of the IB transport and allows an MTU up to the maximal IP packet size of 64K, which reduces the number of IP packets needed for handling large UDP datagrams, TCP segments, etc and increases the performance for large messages.”…””}”(hjhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h K-hj_ubh¾)”}”(hX In connected mode, the interface's UD QP is still used for multicast and communication with peers that don't support connected mode. In this case, RX emulation of ICMP PMTU packets is used to cause the networking stack to use the smaller UD MTU for these neighbours.”h]”hXIn connected mode, the interface’s UD QP is still used for multicast and communication with peers that don’t support connected mode. In this case, RX emulation of ICMP PMTU packets is used to cause the networking stack to use the smaller UD MTU for these neighbours.”…””}”(hjhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h K4hj_ubeh}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h K$hjNhžhubeh}”(h]”Œdatagram-vs-connected-modes”ah ]”h"]”Œdatagram vs connected modes”ah$]”h&]”uh1h¡hh£hžhhŸh¶h K"ubh¢)”}”(hhh]”(h§)”}”(hŒStateless offloads”h]”hŒStateless offloads”…””}”(hj¬hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hj©hžhhŸh¶h K:ubh¸)”}”(hXwIf the IB HW supports IPoIB stateless offloads, IPoIB advertises TCP/IP checksum and/or Large Send (LSO) offloading capability to the network stack. Large Receive (LRO) offloading is also implemented and may be turned on/off using ethtool calls. Currently LRO is supported only for checksum offload capable devices. Stateless offloads are supported only in datagram mode. ”h]”(h¾)”}”(hŒ”If the IB HW supports IPoIB stateless offloads, IPoIB advertises TCP/IP checksum and/or Large Send (LSO) offloading capability to the network stack.”h]”hŒ”If the IB HW supports IPoIB stateless offloads, IPoIB advertises TCP/IP checksum and/or Large Send (LSO) offloading capability to the network stack.”…””}”(hj¾hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h½hŸh¶h K