FABRIC(7) - Linux man page online | Overview, conventions, and miscellany
Fabric Interface Library.
fabric(7) @VERSION@ fabric(7)
Libfabric Programmer's Manual 2016-06-29 fabric(7)
NAMEfabric - Fabric Interface Library
SYNOPSIS#include <rdma/fabric.h> Libfabric is a high-performance fabric software library designed to provide low-latency interfaces to fabric hardware.
OVERVIEWLibfabric provides 'process direct I/O' to application software communicating across fab‐ ric software and hardware. Process direct I/O, historically referred to as RDMA, allows an application to directly access network resources without operating system interven‐ tions. Data transfers can occur directly to and from application memory. There are two components to the libfabric software: Fabric Providers : Conceptually, a fabric provider may be viewed as a local hardware NIC driver, though a provider is not limited by this definition. The first component of lib‐ fabric is a general purpose framework that is capable of handling different types of fab‐ ric hardware. All fabric hardware devices and their software drivers are required to sup‐ port this framework. Devices and the drivers that plug into the libfabric framework are referred to as fabric providers, or simply providers. Provider details may be found in fi_provider(7). Fabric Interfaces : The second component is a set of communication operations. Libfabric defines several sets of communication functions that providers can support. It is not required that providers implement all the interfaces that are defined; however, providers clearly indicate which interfaces they do support.
FABRIC INTERFACESThe fabric interfaces are designed such that they are cohesive and not simply a union of disjoint interfaces. The interfaces are logically divided into two groups: control inter‐ faces and communication operations. The control interfaces are a common set of operations that provide access to local communication resources, such as address vectors and event queues. The communication operations expose particular models of communication and fabric functionality, such as message queues, remote memory access, and atomic operations. Com‐ munication operations are associated with fabric endpoints. Applications will typically use the control interfaces to discover local capabilities and allocate necessary resources. They will then allocate and configure a communication end‐ point to send and receive data, or perform other types of data transfers, with remote end‐ points.
CONTROL INTERFACESThe control interfaces APIs provide applications access to network resources. This involves listing all the interfaces available, obtaining the capabilities of the inter‐ faces and opening a provider. fi_getinfo - Fabric Information : The fi_getinfo call is the base call used to discover and request fabric services offered by the system. Applications can use this call to indicate the type of communication that they desire. The results from fi_getinfo, fi_info, are used to reserve and configure fabric resources. fi_getinfo returns a list of fi_info structures. Each structure references a single fab‐ ric provider, indicating the interfaces that the provider supports, along with a named set of resources. A fabric provider may include multiple fi_info structures in the returned list. fi_fabric - Fabric Domain : A fabric domain represents a collection of hardware and soft‐ ware resources that access a single physical or virtual network. All network ports on a system that can communicate with each other through the fabric belong to the same fabric domain. A fabric domain shares network addresses and can span multiple providers. lib‐ fabric supports systems connected to multiple fabrics. fi_domain - Access Domains : An access domain represents a single logical connection into a fabric. It may map to a single physical or virtual NIC or a port. An access domain defines the boundary across which fabric resources may be associated. Each access domain belongs to a single fabric domain. fi_endpoint - Fabric Endpoint : A fabric endpoint is a communication portal. An endpoint may be either active or passive. Passive endpoints are used to listen for connection requests. Active endpoints can perform data transfers. Endpoints are configured with specific communication capabilities and data transfer interfaces. fi_eq - Event Queue : Event queues, are used to collect and report the completion of asyn‐ chronous operations and events. Event queues report events that are not directly associ‐ ated with data transfer operations. fi_cq - Completion Queue : Completion queues are high-performance event queues used to report the completion of data transfer operations. fi_cntr - Event Counters : Event counters are used to report the number of completed asyn‐ chronous operations. Event counters are considered light-weight, in that a completion simply increments a counter, rather than placing an entry into an event queue. fi_mr - Memory Region : Memory regions describe application local memory buffers. In order for fabric resources to access application memory, the application must first grant permission to the fabric provider by constructing a memory region. Memory regions are required for specific types of data transfer operations, such as RMA transfers (see below). fi_av - Address Vector : Address vectors are used to map higher level addresses, such as IP addresses, which may be more natural for an application to use, into fabric specific addresses. The use of address vectors allows providers to reduce the amount of memory required to maintain large address look-up tables, and eliminate expensive address resolu‐ tion and look-up methods during data transfer operations.
DATA TRANSFER INTERFACESFabric endpoints are associated with multiple data transfer interfaces. Each interface set is designed to support a specific style of communication, with an endpoint allowing the different interfaces to be used in conjunction. The following data transfer inter‐ faces are defined by libfabric. fi_msg - Message Queue : Message queues expose a simple, message-based FIFO queue inter‐ face to the application. Message data transfers allow applications to send and receive data with message boundaries being maintained. fi_tagged - Tagged Message Queues : Tagged message lists expose send/receive data transfer operations built on the concept of tagged messaging. The tagged message queue is concep‐ tually similar to standard message queues, but with the addition of 64-bit tags for each message. Sent messages are matched with receive buffers that are tagged with a similar value. fi_rma - Remote Memory Access : RMA transfers are one-sided operations that read or write data directly to a remote memory region. Other than defining the appropriate memory region, RMA operations do not require interaction at the target side for the data transfer to complete. fi_atomic - Atomic : Atomic operations can perform one of several operations on a remote memory region. Atomic operations include well-known functionality, such as atomic-add and compare-and-swap, plus several other pre-defined calls. Unlike other data transfer inter‐ faces, atomic operations are aware of the data formatting at the target memory region.
LOGGING INTERFACELogging can be controlled using the FI_LOG_LEVEL, FI_LOG_PROV, and FI_LOG_SUBSYS environ‐ ment variables. FI_LOG_LEVEL : FI_LOG_LEVEL controls the amount of logging data that is output. The fol‐ lowing log levels are defined. · Warn : Warn is the least verbose setting and is intended for reporting errors or warn‐ ings. · Trace : Trace is more verbose and is meant to include non-detailed output helpful to tracing program execution. · Info : Info is high traffic and meant for detailed output. · Debug : Debug is high traffic and is likely to impact application performance. Debug output is only available if the library has been compiled with debugging enabled. FI_LOG_PROV : The FI_LOG_PROV environment variable enables or disables logging from spe‐ cific providers. Providers can be enabled by listing them in a comma separated fashion. If the list begins with the '^' symbol, then the list will be negated. By default all providers are enabled. Example: To enable logging from the psm and sockets provider: FI_LOG_PROV="psm,sockets" Example: To enable logging from providers other than psm: FI_LOG_PROV="^psm" FI_LOG_SUBSYS : The FI_LOG_SUBSYS environment variable enables or disables logging at the subsystem level. The syntax for enabling or disabling subsystems is similar to that used for FI_LOG_PROV. The following subsystems are defined. · core : Provides output related to the core framework and its management of providers. · fabric : Provides output specific to interactions associated with the fabric object. · domain : Provides output specific to interactions associated with the domain object. · ep_ctrl : Provides output specific to endpoint non-data transfer operations, such as CM operations. · ep_data : Provides output specific to endpoint data transfer operations. · av : Provides output specific to address vector operations. · cq : Provides output specific to completion queue operations. · eq : Provides output specific to event queue operations. · mr : Provides output specific to memory registration.
NOTESBecause libfabric is designed to provide applications direct access to fabric hardware, there are limits on how libfabric resources may be used in conjunction with system calls. These limitations are notable for developers who may be familiar programming to the sock‐ ets interface. Although limits are provider specific, the following restrictions apply to many providers and should be adhered to by applications desiring portability across providers. fork : Fabric resources are not guaranteed to be available by child processes. This includes objects, such as endpoints and completion queues, as well as application con‐ trolled data buffers which have been assigned to the network. For example, data buffers that have been registered with a fabric domain may not be available in a child process because of copy on write restrictions.
SEE ALSOfi_provider(7), fi_getinfo(3), fi_endpoint(3), fi_domain(3), fi_av(3), fi_eq(3), fi_cq(3), fi_cntr(3), fi_mr(3)
|This manual||Reference||Other manuals|
|fabric(7)||referred by||fi_errno(3) | fi_fabric(3) | fi_pingpong(1) | fi_psm(7) | fi_sockets(7) | fi_strerror(1) | fi_udp(7) | fi_verbs(7) | fi_version(3)|
|refer to||fi_av(3) | fi_cntr(3) | fi_cq(3) | fi_domain(3) | fi_endpoint(3) | fi_eq(3) | fi_getinfo(3) | fi_mr(3) | fi_provider(7)|