Home
last modified time | relevance | path

Searched refs:IB (Results 1 – 25 of 30) sorted by relevance

12

/Linux-v5.15/Documentation/translations/zh_CN/infiniband/
Dipoib.rst50 在数据报模式下，使用IB UD（不可靠数据报）传输，因此接口MTU等于IB L2 MTU
51 减去IPoIB封装头（4字节）。例如，在一个典型的具有2K MTU的IB结构中，IPoIB
54 在连接模式下，使用IB RC（可靠的连接）传输。连接模式利用IB传输的连接特性，
65 如果IB HW支持IPoIB无状态卸载，IPoIB会向网络堆栈广播TCP/IP校验和/或大量
76 如果底层IB设备支持CQ事件管理，可以使用ethtool来设置中断缓解参数，从而减少
Dopa_vnic.rst113 对IB设备分配和释放RDMA netdev设备的支持已经被加入。RDMA netdev支持与
124 代理（VEMA）作为一个IB客户端向IB核心注册，并与IB MAD栈接口。它与以太网
133 | IB MAD | | 网络 |
148 | IB 核心 | |
Dcore_locking.rst67 IB中间层不执行任何函数调用的序列化。
112 一个IB设备。使用者必须在从移除方法返回之前完成所有的清理工作并释放
Duser_verbs.rst21 通过“verbs”直接访问IB硬件，如InfiniBand架构规范第11章所述。
43 由于所有IB资源的创建和销毁都是通过文件描述符传递的命令完成的，所以内核可以跟
/Linux-v5.15/Documentation/infiniband/
Dipoib.rst40 In datagram mode, the IB UD (Unreliable Datagram) transport is used
41 and so the interface MTU has is equal to the IB L2 MTU minus the
42 IPoIB encapsulation header (4 bytes). For example, in a typical IB
45 In connected mode, the IB RC (Reliable Connected) transport is used.
46 Connected mode takes advantage of the connected nature of the IB
60 If the IB HW supports IPoIB stateless offloads, IPoIB advertises
73 If the underlying IB device supports CQ event moderation, one can
Dopa_vnic.rst107 The support has been added for IB device to allocate and free the RDMA
123 registers itself with IB core as an IB client and interfaces with the
124 IB MAD stack. It exchanges the management information with the Ethernet
136 | IB MAD | | Network |
151 | IB core | |
Duser_verbs.rst6 enables direct userspace access to IB hardware via "verbs," as
36 Since creation and destruction of all IB resources is done by
Dcore_locking.rst57 The IB midlayer does not perform any serialization of function calls.
111 An upper level protocol consumer may begin using an IB device as
/Linux-v5.15/drivers/infiniband/hw/mlx5/
DKconfig7 Mellanox Connect-IB PCI Express host channel adapters (HCAs).
9 IP-over-IB or SRP with these devices.
/Linux-v5.15/Documentation/admin-guide/cgroup-v1/
Drdma.rst19 RDMA controller allows user to limit RDMA/IB specific resources that a given
70 (b) No resource limits were configured, but IB/RDMA stack tries to
81 IB stack honors limits enforced by the rdma controller. When application
82 query about maximum resource limits of IB device, it returns minimum of
84 IB device.
/Linux-v5.15/drivers/infiniband/hw/hfi1/
Dtrace.h11 packettype_name(IB), \
/Linux-v5.15/drivers/infiniband/ulp/ipoib/
DKconfig7 transports IP packets over InfiniBand so you can use your IB
39 information about IB multicast groups used by the IPoIB
/Linux-v5.15/drivers/infiniband/ulp/opa_vnic/
DKconfig9 data path and IB MAD for the control path.
/Linux-v5.15/drivers/infiniband/hw/mlx4/
DKconfig11 IP-over-IB or SRP with these devices.
/Linux-v5.15/arch/arm/boot/dts/
Dgemini-nas4220b.dts3 * Device Tree file for the Gemini-based Raidsonic NAS IB-4220-B
12 model = "Raidsonic NAS IB-4220-B";
Dkirkwood-ib62x0.dts8 model = "RaidSonic ICY BOX IB-NAS62x0 (Rev B)";
/Linux-v5.15/net/sched/
Dsch_qfq.c123 enum qfq_state { ER, IR, EB, IB, QFQ_MAX_STATE }; enumerator
788 qfq_move_groups(q, mask, IB, IR); in qfq_unblock_groups()
816 qfq_move_groups(q, mask, IB, EB); in qfq_make_eligible()
961 ineligible = q->bitmaps[IR] | q->bitmaps[IB]; in qfq_update_eligible()
1294 __clear_bit(grp->index, &q->bitmaps[IB]); in qfq_schedule_agg()
1372 __clear_bit(grp->index, &q->bitmaps[IB]); in qfq_deactivate_agg()
1382 qfq_move_groups(q, mask, IB, IR); in qfq_deactivate_agg()
1392 __clear_bit(grp->index, &q->bitmaps[IB]); in qfq_deactivate_agg()
/Linux-v5.15/Documentation/networking/
Drds.rst27 as IB.
39 transport has to be IP-based. In fact, RDS over IB uses a
40 reliable IB connection; the IP address is used exclusively to
226 One might think that with reliable IB connections you wouldn't need
227 to ack messages that have been received. The problem is that IB
244 RDS's IB transport uses a credit-based mechanism to verify that
279 As mentioned above, RDS is not IB-specific. Its code is divided
285 The transport layer handles the details of the transport. The IB
/Linux-v5.15/Documentation/admin-guide/nfs/
Dnfs-rdma.rst41 Testing has been performed using several Mellanox-based IB cards, the
118 InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)].
120 Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or
173 running on the network. If your IB switch has an embedded SM, you can
187 assumes you have two IB hosts named host1 and host2):
/Linux-v5.15/Documentation/ABI/stable/
Dsysfs-class-infiniband27 node's hostname, so that IB network management software can tie
231 This could either be "IB/RoCE v1" for IB and RoCE v1 based GIDs
249 ibdev: (RO) Show Infiniband (IB) device name
271 ibdev: (RO) Display Infiniband (IB) device name
273 abi_version: (RO) Show ABI version of IB device specific
287 sysfs interface for Mellanox IB HCA low-level driver (mthca)
307 sysfs interface for Mellanox ConnectX HCA IB driver (mlx4)
426 sysfs interface for Intel IB driver qib
543 sysfs interface for Mellanox Connect-IB HCA driver mlx5
/Linux-v5.15/Documentation/ABI/testing/
Dconfigfs-rdma_cm21 The possible RoCE types are either "IB/RoCE v1" or "RoCE v2".
/Linux-v5.15/drivers/platform/mellanox/
DKconfig24 cables and fans on the wide range Mellanox IB and Ethernet systems.
/Linux-v5.15/Documentation/arm64/
Dpointer-authentication.rst126 disables all keys except the IB key.
139 IB, DA and DB enabled, and are reset to this state on exec(). Processes created
/Linux-v5.15/drivers/infiniband/
DKconfig12 Core support for InfiniBand (IB). Make sure to also select
/Linux-v5.15/drivers/net/ethernet/mellanox/mlx5/core/
DKconfig17 Connect-IB cards by Mellanox Technologies.

12