18 results about "Remote direct memory access" patented technology

This application discloses a file read operation method, apparatus, and medium for a distributed storage system, relating to the field of communications. To improve the efficiency of read operations in a distributed storage system, this application involves receiving a read operation request; allocating memory space based on the read operation request; packaging the read operation request and the memory space address information into a read operation message; and sending the read operation message to an object storage device using remote direct memory access (RDA) communication, so that the object storage device writes the requested data into the memory space according to the read operation message. The client sends a read operation message containing control data for the read operation request and the memory space address information to the object storage device using RDA communication. The object writes the requested data into the specified memory space, achieving separation of control and data transfer, reducing the number of data copies between memory locations, and improving network transmission efficiency through the application of RDA technology.

This application provides a data transmission method, a network interface card (NIC) for a data receiving end, an electronic device, and a storage medium. The data transmission method is applied to the NIC of the data receiving end. The NIC writes data to the host memory of the data receiving end via a bus. The data transmission method includes: if the bus bandwidth resources required for the NIC to write the target data to the host memory exceed the bus bandwidth resources available to the NIC, then writing a portion of the target data to the NIC's NIC buffer; the NIC buffer includes a first memory buffer configured for the NIC based on its on-chip memory and a second memory buffer configured for the NIC based on its onboard memory; the data sending end sends the target data to the data receiving end via remote direct memory access; and a portion of the data is written from the NIC buffer to the host memory. The solution of this application can better avoid data packet loss problems when facing sudden traffic surges.

A computer is configured to set up a remote direct memory access (RDMA) connection for an application, by performing the steps of: receiving, from the application, by an RDMA driver, a sequence of API requests for setting up the RDMA connection, the API requests including information for setting up the RDMA connection; transmitting, by the RDMA driver to a NIC of the computer, in response to a last API request in the sequence, a first hardware request for setting up the RDMA connection; and generating, by the NIC in response to the first hardware request, a queue pair based on the information for setting up the RDMA connection, and also configuring, by the NIC, the queue pair based on the information for setting up the RDMA connection, the queue pair including memory space for storing receive and send requests of the application.

A computing apparatus (402, 502, 602) configured for Remote Direct Memory Access (RDMA) is provided. The computing apparatus (402, 502, 602) includes a Network Interface Controller (NIC) (410, 704), a memory (408, 508, 708), and a controller (412). The controller (412) is configured to receive an RDMA request (702), determine that the request carries immediate data, and, in response, obtain a memory address to write to. The controller (412) writes the immediate data to the memory (408, 508, 708) using Direct Memory Access (DMA) to the memory address without placing the data in a Receive Queue (RQ). The apparatus facilitates faster data transfer by bypassing the typical queuing process for immediate data, thereby reducing latency during RDMA operations.

This invention discloses a loss-tolerant RDMA transmission method and system based on partially reliable control. The invention configures minimum reliability constraints for the remote direct memory access session between the transmitter and receiver; the transmitter divides the data to be transmitted into multiple data units and assigns continuously increasing group numbers to the data units; the receiver generates feedback information based on the reception status corresponding to each group number and returns it to the transmitter; the transmitter calculates local reliability control quantities based on the feedback information, and determines the transmission mode based on the local reliability control quantities, minimum reliability constraints, and a preset mode switching threshold; when the loss-tolerant trigger condition is met, bounded virtual advancement is performed on subsequent data units to be transmitted, marking the corresponding data units as virtual advancement states and advancing the transmission leading edge number; the transmitter applies boundary constraints to the bounded virtual advancement, and adjusts the window size based on the physical reliability of the control segment to which the advancement position of the sliding transmission window belongs, calculated according to the feedback information.

An integrated circuit formed on (i) a single semiconductor die or (ii) a plurality semiconductor dies that are integrated into a single package. The integrated circuit may include a communication interface including a serializer / deserializer (SerDes) interface; a fabric adapter communicatively coupled to the communication interface; a plurality of inference engine clusters, each inference engine cluster including a respective memory element and / or memory interface; and a data interconnect communicatively coupling each respective memory element and / or memory interfaces of the plurality of inference engine clusters to the fabric adapter. The fabric adapter may be configured to facilitate remote direct memory access (RDMA) read and write services and / or datagram communication over a cell-based switch fabric to and from the respective memory elements and / or memory interfaces of the plurality of inference engine clusters via the data interconnect.

A system for communicating over a physical port includes a Remote Direct Memory Access (RDMA) capable network adapter, a host computing device communicatively coupled to the RDMA capable network adapter, a physical port associated with the host computing device, and a plurality of interfaces associated with the physical port, the plurality of interfaces having different RDMA protocols.

The present specification provides a method and an apparatus for creating a shared remote direct memory access link, which are applied to a local terminal. The method includes: receiving a first creating request for a first shareable remote direct memory access RDMA link initiated by a first application process on the local terminal, where an associated memory address indicated by the first creating request for the first shareable RDMA link is a shared memory address of the first application process and a second application process on the local terminal; creating the first shareable RDMA link between the local terminal and an opposite terminal according to the first creating request, so that the shared memory address is registered to an RDMA device on the local terminal as the associated memory address of the first shareable RDMA link.

This specification discloses a cross-datacenter transaction processing method, apparatus, and device. Applied to a distributed system consisting of multiple data centers, the scheme includes: a coordinator node in a first data center receiving and parsing a transaction request sent by a client to obtain one or more sub-transactions corresponding to different data centers; the coordinator node determining the data center corresponding to the sub-transaction as a second data center; if the second data center is not the first data center, determining a proxy coordinator node within the second data center and sending the sub-transaction to the proxy coordinator node; the proxy coordinator node determining the data node where the copy of the data shard involved in the sub-transaction is located within the second data center, executing the sub-transaction through remote direct memory access to the data node, and responding to the coordinator node based on the execution result; the coordinator node continuing to process transaction requests based on the responses from each proxy coordinator node.

The present disclosure provides a communication configuration method and device, a storage medium and a program product, relates to the technical field of communication, and can solve the problem that transmission efficiency in the prior art cannot meet the demand. The method comprises the following steps: receiving a first message from a second node; the first message is used for requesting a remote direct memory access transmission channel established between a first node and a third node; and sending a second message to the second node; the second message is used for responding to the remote direct memory access transmission channel established between the first node and the third node. The present disclosure can improve transmission efficiency.

Devices, systems, methods, and processes for incast congestion management are described herein. Typically, in a Packet Sequence Number (PSN) based Remote Direct Memory Access (RDMA) network, Priority Flow Control (PFC) is asserted upstream when an incast congestion event occurs, which can victimize unrelated flows. Thus, instead of asserting PFC, a switch in the PSN based RDMA network detects an incast congestion event and directly notifies one or more Reliable Connection (RC) Queue Pairs (QPs) of various sending devices, associated with the incast congestion event using Receiver Not Ready (RNR) negative acknowledgements (NACKs). These RNR NACKs are associated with unique pause time-periods. The associated RC QPs receive the RNR NACKs and pause packet transmission. The associated RC QPs resume packet transmission upon expiration of corresponding pause time-periods. Thus, the packet transmission from the contributing RC QPs is spaced out, avoiding all packets reaching a switch output port at the same time.

A method processes data requests from a requester to a responder over a network by using remote direct memory access. The method includes the requester issuing two or more requests into a work queue of a network interface controller. The method further includes the network interface controller executing the queued requests by sending them to the responder, and receiving responses to the sent request from the responder. One or more given requests each includes dependency information related to the response from the responder to one or more previous requests in the work queue, the method further includes, before executing the given request by the network interface controller, evaluating the dependency information and executing the given request depending on the result of the evaluation.

Systems and methods are described for a cross-site high availability distributed storage system. According to one embodiment, a computer implemented method includes providing a remote direct memory access (RDMA) request for a RDMA stream, and generating, with an interconnect (IC) layer of the first storage node, multiple IC channels and associated IC requests for the RDMA request. The method further includes mapping an IC channel to a group of multiple transport layer sessions to split data traffic of the IC channel into multiple packets for the group of multiple transport layer sessions using an IC transport layer of the first storage node and assigning, with the IC transport layer, a unique transaction identification (ID) to each IC request and assigning a different data offset to each packet of a transport layer session.

Systems and methods for atomic memory operations in a remote direct memory access network are disclosed. A system includes a network interface card (NIC) comprising a first memory and one or more processors coupled to the first memory. The one or more processors receive an atomic memory operation (AMO) remote procedure call (RPC) comprising a memory address and an AMO type. The one or more processors are also to retrieve, from a second memory, a value corresponding to the memory address of the AMO RPC. The one or more processors are also to perform an AMO on the value from the second memory corresponding to the AMO type to obtain a modified value. The one or more processors are also to store the modified value in the first memory.

This invention relates to a congestion control parameter search and optimization method and system for intelligent computing networks. The method includes: real-time acquisition of network monitoring data from servers and switches; if remote direct memory access traffic is detected, checking whether congestion notification packets and priority flow control index values ​​are increasing; if either index increases within a time threshold, determining whether a transmission negative acknowledgment frame or a reception negative acknowledgment frame exists; if a transmission negative acknowledgment frame or a reception negative acknowledgment frame exists, determining whether an acknowledgment timeout frame exists; if an acknowledgment timeout frame exists, determining whether the increment of adaptive retransmission frames exceeds a first threshold; if it exceeds, increasing the priority of the differentiated service code point; if no acknowledgment timeout frame exists, determining whether the priority exceeds a second threshold; if it exceeds, determining whether the increment of transmission congestion notification packets exceeds a third threshold; if it exceeds, decreasing the priority. Compared with existing technologies, this invention has the advantage of strong scalability.

The application discloses a parallel optimization method and system for a high-performance computer and relates to the technical field of computer performance optimization. The method constructs a local task inheritance tree for each parallel process and labels inheritance cost. Each process only exchanges root node inheritance cost with adjacent processes and updates a global load baseline, and triggers pre-splitting when the local cost exceeds the baseline dynamic threshold. Subnode division schemes are enumerated, load balancing benefits and communication costs are quantified through a split benefit formula, the optimal scheme is selected to divide the calculation unit, task meta information is written into the target process through a remote direct memory access one-way write operation, the target process writes back the result after completion, the current process polls the completion flag and recycles, and the timeout task can be re-delegated. The application realizes the pre-perception and dynamic balancing of load and improves parallel computing efficiency.

Various embodiments herein are directed to remote direct memory access (RDMA) support in cellular networks. In particular, some embodiments may relate to enhancements to RDMA over cellular network (RoCN) protocols.

This invention provides a method and system for remote direct memory access transmission based on shared reliable connection queues. The method includes: if the information size carried by an original work queue element (WQE) originating from the upper-layer application of the sending end is greater than a set maximum transmission unit, the original WQE is split, and the resulting sub-WQE is added to a long-flow low-priority queue; otherwise, the original WQE is added to a short-flow high-priority queue. For each scheduling period, if the short-flow high-priority queue is not empty, elements in the short-flow high-priority queue are distributed one by one to the remote direct memory access network interface card (RNIC) through a unique proxy reliable connection queue pair (RC QP) between the sending and receiving ends; otherwise, based on the window size of the current scheduling period, elements are selected from the long-flow low-priority queue according to a set transmission strategy and aggregated and distributed to the RNIC through the unique proxy RC QP. This invention can solve the head-of-queue blocking problem when sharing queue pairs.