-
公开(公告)号：US20230096238A1
公开(公告)日：2023-03-30
申请号：US17956478
申请日：2022-09-29
摘要： A network device transfers packets from a packet memory to one or more network interfaces for transmission by the one or more network interfaces. The transferring of packets includes transferring the packets via one or more respective transmit data paths that correspond to one or more respective network interfaces. The network device measures one or more respective amounts of time required to transmit respective packet data within the one or more respective transmit data paths. The network device uses the one or more respective measured amounts of time to determine when to start transfer of packets from the packet memory to the one or more network interfaces via the one or more respective transmit data paths.
-
公开(公告)号：US11601361B2
公开(公告)日：2023-03-07
申请号：US17239452
申请日：2021-04-23
申请人： GRASS VALLEY CANADA
发明人： Frederick St-Laurent
IPC分类号： H04L45/302 , G06F9/54 , H04L69/329 , H04L69/321 , H04L69/16 , H04L69/322 , H04L67/60 , H04L43/10 , H04L45/00 , H04L47/34 , H04L47/50
摘要： A system and method is provided for timely and uniform real-time data packet transmission by a computing device. The system can include a shared packet memory buffer for storing data packets generated by a user application and a shared schedule memory buffer for storing packet identifiers and corresponding time slots for the data packets. Moreover, a kernel module is provided that operates in the kernel mode of the operating system directly above the network interface controller and can continuously poll the shared scheduled memory to access packet identifiers at corresponding time slots. Based on the packet identifiers in each time slot, the kernel module can pull the data packet having the packet identifier directly from the ring buffer and send each packet to the network interface controller for transmission as part of a media stream over a network to a media consuming device.
-
公开(公告)号：US11595300B2
公开(公告)日：2023-02-28
申请号：US17323984
申请日：2021-05-18
发明人： Sumit Garg , Gaurav Kumar
IPC分类号： H04L69/22 , H04L45/00 , H04L47/10 , H04L47/22 , H04L9/40 , H04L47/2441 , H04L47/50 , H04L47/2408 , H04L45/741 , H04L47/31 , H04L41/0663 , H04L43/10 , H04W8/04
摘要： A method is disclosed, comprising: receiving a first and a second Internet Protocol (IP) packet at a mesh network node; tagging the first and the second IP packet at the mesh network node based on a type of traffic by adding an IP options header to each of the first and the second IP packet; forwarding the first and the second IP packet toward a mesh gateway node; filtering the first and the second IP packet at the mesh gateway node based on the added IP options header by assigning each of the first and the second IP packet to one of a plurality of message queues, each of the plurality of message queues having a limited forwarding throughput; and forwarding the first and the second IP packet from the mesh gateway node toward a mobile operator core network, thereby providing packet flow filtering based on IP header and traffic type.
-
公开(公告)号：US11588747B2
公开(公告)日：2023-02-21
申请号：US17315933
申请日：2021-05-10
申请人： Reservoir Labs, Inc.
IPC分类号： H04L12/869 , H04L12/873 , H04L12/835 , H04L12/861 , H04L47/50 , H04L47/52 , H04L47/30 , H04L49/90
摘要： In a network system, an application receiving packets can consume one or more packets in two or more stages, where the second and the later stages can selectively consume some but not all of the packets consumed by the preceding stage. Packets are transferred between two consecutive stages, called producer and consumer, via a fixed-size storage. Both the producer and the consumer can access the storage without locking it and, to facilitate selective consumption of the packets by the consumer, the consumer can transition between awake and sleep modes, where the packets are consumed in the awake mode only. The producer may also switch between awake and sleep modes. Lockless access is made possible by controlling the operation of the storage by the producer and the consumer both according to the mode of the consumer, which is communicated via a shared memory location.
-
公开(公告)号：US11546449B2
公开(公告)日：2023-01-03
申请号：US16942331
申请日：2020-07-29
申请人： T-Mobile USA, Inc.
摘要： A component of a cellular communication system is configured to prioritize data packets based on packet tags that have been associated with the data packets. The packet tags may comprise an application identifier and a customer identifier, as examples. A Packet Data Convergence Protocol (PDCP) layer of a radio protocol stack receives a data packet and associated packet tags and assigns the data packet to a preferred transmission queue or a non-preferred transmission queue, based on the packet tags associated with the data packet. In order to manage queue overflows, data packets of the non-preferred transmission queue may be discarded when they have been queued for more than a predetermined length of time. Data packets of the preferred transmission queue, however, are retained regardless of how long they have been queued.
-
公开(公告)号：US11546238B1
公开(公告)日：2023-01-03
申请号：US17456471
申请日：2021-11-24
申请人： NETAPP, INC.
发明人： Houze Xu , Yuepeng Qi
IPC分类号： H04L43/0829 , H04L47/50 , H04L47/36 , H04L43/0823
摘要： Methods and systems for a networked storage environment are provided. One method includes splitting, by a first node, a payload into a plurality of data packets, each data packet having a portion of the payload indicated by an offset value indicating a position of each portion within the payload; transmitting, by the first node, the plurality of data packets to a second node using a network connection for a transaction, each data packet including a header generated by the first node having the offset value and a payload size; receiving, by the first node, a message from the second node indicating an offset value of a missing payload of a missing data packet from among the plurality of data packets; and resending, by the first node, the missing data packet and any other data packet whose offset value occurs after the offset value of the missing payload.
-
公开(公告)号：US11487567B2
公开(公告)日：2022-11-01
申请号：US16181145
申请日：2018-11-05
申请人： Intel Corporation
发明人： Ciara Loftus , Subarna Kar , Namakkal Venkatesan , Mark D. Gray
摘要： A virtual machine (VM) can provision a region of memory for a queue to receive packet header, packet payload, and/or descriptors from the network interface. A virtual switch can provide a routing rule to a network interface to route a received packet header, packet payload, and/or descriptors associated with the VM to the provisioned queue. A direct memory access (DMA) transfer operation can be used to copy the received packet header, packet payload, and/or descriptors associated with the VM from the network interface to the provisioned queue without copying the packet header or payload to an intermediate buffer and from the intermediate buffer to the provisioned queue. A DMA operation can be used to transfer a packet or its descriptor from the provisioned queue to the network interface for transmission.
-
公开(公告)号：US11347665B2
公开(公告)日：2022-05-31
申请号：US16914221
申请日：2020-06-26
申请人： Rambus Inc.
发明人： Hongzhong Zheng , Frederick A Ware
IPC分类号： G06F13/40 , G06F13/16 , H04L47/50 , G06F9/48 , G11C11/4076 , G11C11/4094
摘要： A method of transferring data between a memory controller and at least one memory module via a primary data bus having a primary data bus width is disclosed. The method includes accessing a first one of a memory device group via a corresponding data bus path in response to a threaded memory request from the memory controller. The accessing results in data groups collectively forming a first data thread transferred across a corresponding secondary data bus path. Transfer of the first data thread across the primary data bus width is carried out over a first time interval, while using less than the primary data transfer continuous throughput during that first time interval. During the first time interval, at least one data group from a second data thread is transferred on the primary data bus.
-
公开(公告)号：US11297161B1
公开(公告)日：2022-04-05
申请号：US17065903
申请日：2020-10-08
发明人： Yin-Chen Liu , BaekGyu Kim
IPC分类号： G06F15/173 , H04L67/63 , H04L67/12 , H04L47/50
摘要： Systems and methods described herein relate to managing an automotive edge computing environment. One embodiment receives current status information from one or more edge servers; receives and queues requested computing tasks from one or more connected vehicles; selects, as an optimization trigger number N, a largest number of requested computing tasks for which an optimization process can be completed within a time, per requested computing task, that is less than an average time gap between the requested computing tasks; performs the optimization process when a number of queued requested computing tasks exceeds the optimization trigger number N, wherein the optimization process produces an updated data transfer schedule and an updated data process schedule for N queued requested computing tasks; and transmits the updated data transfer schedule and the updated data process schedule to the one or more edge servers and the one or more connected vehicles.
-
公开(公告)号：US11277369B1
公开(公告)日：2022-03-15
申请号：US17189782
申请日：2021-03-02
申请人： ServiceNow, Inc.
IPC分类号： G06F15/16 , H04L51/226 , H04L67/55 , H04L51/00 , H04L41/5022 , H04L47/50
摘要： Non-volatile memory may contain definitions of: (i) a plurality of message queue implementations respectively associated with different queue behaviors, the different queue behaviors specified by corresponding sets of modes, and (ii) an application programming interface (API) through which applications can access one or more message queues. One or more processors may be configured to: create a message queue of a particular message queue type, supported by a corresponding message queue implementation, by specifying a set of modes corresponding to a queue behavior; receive, from a producing application and by way of the API, one or more messages for the message queue; store the one or more messages in a data structure associated with the message queue; receive, from a consuming application and by way of the API, a request to read from the message queue; and provide a message from the message queue to the consuming application.
-
-
-
-
-
-
-
-
-
搜索结果
70 条记录 (耗时 0.031 秒)