US20220086105A1 - Direct Packet Placement - Google Patents
Direct Packet Placement Download PDFInfo
- Publication number
- US20220086105A1 US20220086105A1 US17/535,608 US202117535608A US2022086105A1 US 20220086105 A1 US20220086105 A1 US 20220086105A1 US 202117535608 A US202117535608 A US 202117535608A US 2022086105 A1 US2022086105 A1 US 2022086105A1
- Authority
- US
- United States
- Prior art keywords
- data
- packet
- buffer
- sequence numbers
- payloads
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/55—Prevention, detection or correction of errors
- H04L49/552—Prevention, detection or correction of errors by ensuring the integrity of packets received through redundant connections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/901—Buffering arrangements using storage descriptor, e.g. read or write pointers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/9057—Arrangements for supporting packet reassembly or resequencing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/9063—Intermediate storage in different physical parts of a node or terminal
- H04L49/9068—Intermediate storage in different physical parts of a node or terminal in the network interface card
-
- H04L65/4069—
-
- H04L65/608—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/61—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/61—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio
- H04L65/612—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio for unicast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/65—Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/04—Error control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0041—Arrangements at the transmitter end
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0045—Arrangements at the receiver end
Definitions
- the present invention relates to apparatus and methods for transmission and reception of packet streams across a network with high speed and reliability.
- High-speed packet streaming schemes are commonly used in transmitting real-time video and other digital media across a network. Because of the real-time nature of the data, the packet transmissions typically use a non-reliable protocol, without acknowledgment from the destination or retransmission by the source when packets are lost or corrupted. Therefore, in applications requiring high data availability, a source host may transmit multiple parallel, redundant streams of the data to the destination. Each packet is thus transmitted multiple times—once in each stream—over multiple different paths through the network-in order to increase the likelihood that at least one copy of each packet will be received intact at the destination.
- U.S. Patent Application Publication 2009/0034633 describes a method for simultaneous processing of media and redundancy streams for mitigating impairments.
- the method comprises receiving a primary stream of encoded frames and a separate stream of redundant frames.
- the method further comprises decoding and reconstructing in parallel the frames in the primary stream and the separate stream of redundant frames, on a real-time basis, in accordance with a specified common clock reference.
- Embodiments of the present invention that are described herein provide efficient apparatus and methods for receiving and handling redundant data streams from a network.
- communication apparatus including a host interface, which is configured to be connected to a bus of a host computer having a processor and a memory, in which a buffer is allocated for receiving a data segment.
- a network interface is configured to receive from a packet communication network at least first and second redundant packet streams.
- Each packet stream includes a sequence of data packets, which include headers containing respective packet sequence numbers and data payloads of a predefined, fixed size containing respective slices of the data segment, such that redundant first and second copies of each slice are transmitted respectively in at least a first data packet in the first packet stream and a second data packet in the second packet stream.
- Packet processing circuitry is configured to receive the data packets from the network interface, to map the data packets in both the first and second packet streams, using the packet sequence numbers, to respective addresses in the buffer, and to write the data payloads to the respective addresses via the host interface while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the packet sequence numbers.
- the data payloads include video data, including multiple data segments corresponding to frames of the video data.
- the headers contain an indication of a start and end of each frame, and the packet processing circuitry is configured to identify the indication in the headers and to select the buffer to which the data payloads are to be written responsively to the identified indication.
- the packet processing circuitry is configured to maintain a record of the packet sequence numbers for which the data payloads have been written to the buffer, and responsively to the record, to discard redundant copies of the data payloads so that each slice is transmitted over the bus via the host interface no more than once.
- the packet processing circuitry is configured to transmit all of the copies of each slice over the bus so that the redundant data in the buffer are overwritten.
- the packet processing circuitry is configured to receive a work item from the processor indicating, for each data segment, an address of the buffer and the size of the slices, and to submit a completion report to the processor when all slices of the data segment have been written to the buffer.
- the first and second packet streams are transmitted in accordance with a Real-time Transport Protocol (RTP), and the headers include an RTP header, which contains the packet sequence numbers.
- RTP Real-time Transport Protocol
- a method for data communication which includes allocating a buffer in a memory of a host computer for receiving a data segment.
- NIC network interface controller
- the data packets in the packet stream are mapped to respective addresses in the buffer using a linear mapping of the packet sequence numbers to the addresses.
- the data payloads are written to the respective addresses in the buffer, ordered in accordance with the packet sequence numbers.
- FIG. 2 is a block diagram that schematically illustrates a process of data reconstruction that is carried out by a network interface controller (NIC), in accordance with an embodiment of the invention
- FIG. 5 is a block diagram that schematically illustrates a data communication system, in accordance with another embodiment of the invention.
- each of the packets in each transmitted stream contains a respective sequence number, such as a packet sequence number (PSN), which can be used at the destination in detecting missing packets and restoring the packet data to the transmit order.
- PSN packet sequence number
- these reordering and reconstruction functions are carried out by hardware logic in the network interface controller (NIC) of the destination computer, thus offloading these tasks from the host processor.
- NIC network interface controller
- the disclosed embodiments relate to a single stream of data (which in some cases is duplicated in at least one redundant stream), in general the destination computer may receive and process many such streams concurrently from different sources.
- the destination host processor allocates a single buffer to receive the reconstructed video data in each segment of an incoming data stream, for example, in each video frame, based on the expected segment size and data rate.
- These stream parameters may be preset or negotiated in each instance by exchange of control messages over the network between the source and destination hosts.
- the packet sizes can thus be assumed to be fixed and known to the host processors.
- Each transmitted packet is labeled with a successive sequence number, as provided by RTP or another suitable protocol.
- the receiving NIC performs the functions of data integrity checking, packet reordering, and elimination of redundant data, using the known packet data sizes and sequence numbers.
- the receiving NIC writes the data payloads to the proper locations in the allocated buffer, in accordance with the transmit order (and irrespective of the receive order), while discarding or overwriting the data from redundant packets.
- the receiving NIC notifies the destination host processor only when the data segment in memory is complete.
- the process of packet reception and reordering is thus entirely transparent to the destination host processor, which deals only with complete data segments. Assuming the receiving NIC is able to receive data from the network at wire speed, the latency and throughput of video data transfer at the destination are limited only by the processing and bus access rates of the receiving NIC. This solution not only maximizes data bandwidth, but also substantially reduces the processing load, memory footprint, and power consumption of the host processor.
- the principles of the present invention may similarly be applied to single streams of packets (transmitted without redundancy), as well as to schemes with higher degrees of redundancy.
- the above embodiments make use of the packet sequence numbers of the video packets
- other embodiments make use of other sorts of sequence numbers that appear in the packet header, with data payloads containing slices of a data segment having a predefined, fixed size per slice.
- the NIC uses the sequence numbers, along with the fixed size per slice, in mapping the data payloads to respective addresses in the assigned memory buffer using a linear mapping of the sequence numbers. For example, in an alternative embodiment (as illustrated in FIGS.
- a packet stream is transmitted in accordance with an enhanced Common Public Radio Interface (eCPRI), and the data payloads that are to be written to a buffer by the receiving NIC comprise radio data.
- the headers comprise an open radio access network (O-RAN) application layer header, and the starting physical resource block (startPrbu) values contained in the O-RAN header serve as sequence numbers.
- O-RAN open radio access network
- startPrbu starting physical resource block
- FIG. 1 is a block diagram that schematically illustrates a data communication system 20 , in accordance with an embodiment of the invention.
- multiple transmitting (Tx) host computers 24 , 26 , 28 , . . . are connected to a packet data network 22 , such as an Internet Protocol (IP) network, for example.
- IP Internet Protocol
- Each host computer receives a streaming data input, for example from a respective video camera 30 .
- This data input comprises a series of data segments, such as video frame or fields, of a predefined size.
- the host computer encapsulates the data in a stream of data packets, each comprising a header, containing, inter alia, a respective PSN, and a data payload of a predefined, fixed size containing a respective slice of a given data segment.
- host computers 24 , 26 , 28 and respective video cameras 30 are shown in FIG. 1 , for the sake of conceptual clarity, as separate physical entities, in some implementations the host computer is incorporated into the video camera (typically together with a NIC, as well).
- a NIC 32 in each host computer 24 , 26 , 28 , . . . transmits the data packets over network 22 in two redundant packet streams 34 and 36 , as indicated by the dashed arrows in FIG. 1 .
- redundant copies of each slice are transmitted concurrently in two packets, one in each of the two packet streams.
- Streams 34 and 36 are typically transmitted through network 22 over different, respective paths, for example by transmitting the streams through different ports of NIC 32 , which are connected respectively to different switches 38 in the network.
- the packets are typically transmitted using an unreliable transport protocol, such as RTP over User Datagram Protocol (UDP) transport, which gives no guarantee that any given packet will reach its destination.
- UDP User Datagram Protocol
- Transmitting the two redundant streams ensures that at least one copy of each packet will, with few exceptions, reach its destination. For even higher confidence of delivery, three or even more redundant streams can be transmitted and handled at the receiver in the manner described herein.
- the techniques described herein are useful in efficient handling of even a single packet stream by a receiving NIC, when redundancy is not required.
- FIG. 2 is a block diagram that schematically illustrates a process of data reconstruction that is carried out by NIC 42 , in accordance with an embodiment of the invention.
- Video camera 30 captures an image frame 50 , which is divided into slices for transmission by NIC 32 in a sequence of data packets 52 , 54 , 56 , 58 .
- Each packet comprises a header 60 , containing a packet sequence number (PSN) 62 , and a payload 64 containing a respective slice of image frame 50 .
- PSN packet sequence number
- NIC 32 transmits two copies of each packet 52 , 54 , 56 , 58 , i.e., one in each of streams 34 and 36 .
- NIC 42 detects and discards corrupted packets, for example by computing and checking packet checksums or other error detection codes, as provided by the applicable protocols.
- NIC 42 has received only packets 54 , 58 and 56 (in that order) from stream 34 and packets 52 , 56 and 58 from stream 36 .
- packet serial numbers 62 Using packet serial numbers 62 , however, NIC 42 is able to directly place data from the appropriate payloads 64 in the designated buffer in memory 44 , and thus reconstruct a complete image frame 66 in memory 44 .
- NIC 42 eliminates redundant data so that the buffer contains exactly one copy of each slice of the frame, ordered in accordance with the packet sequence numbers.
- the process of reconstruction is transparent to software running on host computer 40 and requires no involvement by the software in data reordering or eliminating redundancies.
- FIG. 3 is a block diagram that schematically shows details of host computer 40 and NIC 42 , in accordance with an embodiment of the invention.
- Host computer 40 comprises a processor 70 , typically comprising at least one central processing unit (CPU), and memory 44 , which are connected to NIC 42 by a host bus 72 , such as a PCI Express® bus, as is known in the art.
- Processor 70 runs various software programs, including, in this example, a video processing application 74 and a driver 75 for controlling operation of NIC 42 .
- Driver 75 creates a respective work queue 76 (conventionally referred to as a queue pair, or QP) for each incoming stream of video packets that NIC 42 is to receive. For each segment in the incoming stream (such as a video frame) that NIC 42 is to receive, driver 75 posts a corresponding work item (referred to as a work queue element, or WQE) in the appropriate work queue 76 pointing to a buffer 78 that is to receive the data in the segment.
- this functionality is implemented as follows:
- NIC 42 comprises a host interface 82 , connected to bus 72 , and a network interface 84 , which connects to network 22 .
- Network interface 84 in this example comprises two ports 88 with different addresses, serving as the respective destination addresses for streams 34 and 36 . Alternatively, both streams may be received through the same port.
- Packet processing circuitry 86 is coupled between host interface 82 and network interface 84 .
- FIG. 3 shows only certain specific elements of packet processing circuitry 86 : packet parsing logic 90 and a scatter engine 92 , which are used in implementing the direct data placement functionality that is the subject of the present description. In a typical NIC, these elements are combined with other components for transmitting and receiving packets for other purposes and in accordance with other sorts of protocols. These latter components will be apparent to those skilled in the art and are beyond the scope of the present description.
- Packet processing circuitry 86 including parsing logic 90 and scatter engine 92 , is typically implemented in hardware logic circuits within one or more integrated circuit chips. The logic may be hard-wired or programmable, or a combination of hard-wired and programmable elements. Additionally or alternatively, certain functions of packet processing circuitry 86 may be carried out in software or firmware by an embedded microprocessor or microcontroller.
- Network interface 84 passes incoming packets in streams 34 and 36 to packet parsing logic 90 .
- packet processing circuitry 86 reads and makes use of the information posted in the appropriate work queue 76 in memory 44 by driver 75 . This information enables packet parsing logic 90 to locate and extract PSN 62 and payload 64 from each packet.
- Scatter engine 92 uses PSN 62 , together with the base address of buffer 78 , to map each slice 80 to the respective address in the buffer, and thus to write the data payloads to the appropriate addresses via host interface 82 .
- FIG. 4 is a block diagram that schematically shows details of a method for direct placement of packet data that is performed by NIC 42 , in accordance with an embodiment of the invention.
- FIG. 4 illustrates how scatter engine 92 uses PSN 62 in an RTP header 100 of a video packet in placing the packet data in buffer 78 .
- Other examples of video networking protocols that can be handled in similar fashion include (without limitation):
- the packet illustrated in FIG. 4 belongs to a stream in which the payload size of all packets is fixed and known in advance.
- Driver 75 running on host processor 70 assigns and informs NIC 42 of the base address of buffer 78 to which each data segment in the stream is to be written, as explained above.
- RTP header 100 comprises a timestamp 102 and other protocol information 104 , in addition to PSN 62 .
- packet parsing logic 90 advances to the known location of PSN 62 in each packet and extracts the PSN value, as well as extracting data slice 80 from payload 64 .
- scatter engine 92 is able to write the data slices from payloads 64 to buffer 78 in the proper order by simple linear translation of the PSN.
- scatter engine 92 will write the payload of each packet to an address:
- Payload ⁇ ⁇ address A + ( PSN - X ) ⁇ B .
- Scatter engine 92 may overwrite the payload of the packet that arrives first with that of the second copy of the packet, or it may write only one of the payloads to the buffer and discard the other.
- segment definition is also indicated in the packet headers, thus enabling alternative implementations that reduce the involvement of driver software even further. For example:
- packet processing circuitry 86 can monitor PSNs and, when the payload from a given packet having a given PSN in one of the streams has already been written to the buffer, simply discard the corresponding packet from the other stream, rather than overwriting the data already in the buffer. For this purpose, processing circuitry 86 may maintain a record, such as a PSN vector and a rolling PSN window, for each flow. Each packet arriving causes processing circuitry 86 to flip a bit in the PSN vector. When the bit for a given PSN is set when corresponding packet from the other stream arrives, packet parsing logic 90 drops this latter packet without further processing.
- FIG. 5 is a block diagram that schematically illustrates a data communication system 110 for transmission of radio data, in accordance with another embodiment of the invention.
- System 110 is assumed to operate in accordance with the enhanced Common Public Radio Interface (eCPRI) specification, and the Open Radio Access Network (O-RAN) fronthaul requirements, as defined in the O - RAN Fronthaul Working Group Control, User and Synchronization Plane Specification , published by the O-RAN Alliance as Technical Specification ORAN-WG4.CUS.0-v01.00 (2019).
- eCPRI Common Public Radio Interface
- OF-RAN Open Radio Access Network
- an O-RAN Distributed Unit (O-DU) 112 communicates over a network 116 , such as an IP network, for example, with an O-RAN Radio Unit (O-RU) 114 , in accordance with the above-mentioned eCPRI and O-RAN specifications.
- O-DU 112 and O-RU 114 comprise general-purpose computer processors, which have respective memories 118 , 120 and are connected to network 116 by respective NICs 122 and 124 .
- NICs 122 and 124 respective NICs 122 and 124 .
- O-DU 112 and O-RU 114 typically have other, special-purpose interfaces, such as a radio transceiver associated with the O-RU, but these features of system 110 are beyond the scope of the present description.
- O-RU 112 transmits a sequence of data packets over network 116 , comprising respective headers and data payloads, which contain data segments of radio signals received by O-RU 114 .
- Each data segment comprises one or more physical resource blocks (PRBs), which are divided into slices in the form of data samples, typically comprising alternating iSamples and qSamples, as defined by the O-RAN specification (see particularly section 6.3, including Table 6-2 on page 95). These samples have a fixed size, between 1 bit and 16 bits per sample, which is defined in the O-RAN header of each packet, as explained below with reference to FIG. 6 .
- PRBs physical resource blocks
- NIC 124 transmits the data packets over network 116 , typically using an unreliable transport protocol, such as eCPRI over UDP transport.
- NIC 122 maps the samples contained in the packets to respective addresses in a buffer in memory 118 of O-DU 112 , with the samples ordered in the buffer in accordance with respective sequence numbers given by the O-RAN headers in the packets.
- the radio data are thus made immediately available in memory 120 , in the proper order for processing by O-DU 112 .
- FIG. 6 is a block diagram that schematically illustrates a method for direct placement of packet data in a buffer 152 in memory 118 , in accordance with the embodiment of FIG. 5 .
- the method is applied to the O-RAN data packets that are received by O-DU 112 , illustrated in FIG. 6 by a packet 130 .
- This packet has network and transport headers 132 , including an IP header 134 , a UDP header 136 , and an eCPRI header 138 , for example as defined in section 3.1.3 of the above-mentioned O-RAN specification (page 32).
- the transport headers are followed by an O-RAN application header 140 (as defined in Table 6-2 of the O-RAN specification) and a payload 142 containing a sequence of data samples.
- O-RAN header 140 comprises a set of frameID fields 144 , followed by sectionID fields 146 , which define the data layout of the data segment in payload 142 .
- section ID fields include, inter alia, a startPrbu field 148 , which identifies the starting physical resource block (PRB) in packet 130 and thus can serve as a sequence number for purposes of mapping of the samples in payload 142 .
- a numPrbu field 150 indicates the number of contiguous PRBs in this section; and a udCompHdr field 151 indicates the size, in bits, of each sample, i.e., the size of each slice of the PRB in payload 142 .
- section ID fields 146 will be repeated as the header of each section.
- NIC 122 extracts the data samples from payload and writes them to respective addresses 154 in a buffer 152 in memory 118 , using a linear mapping of the startPrbu value in field 148 .
- the startPrbu value indicates the address 154 to which the NIC is to write the first sample in each section, followed contiguously by the succeeding samples.
- NIC 122 maps the samples to addresses 154 using the following formula for the first sample in each section:
- Payload ⁇ ⁇ address A + ( SN - X ) ⁇ B .
- X is the initial sequence number
- SN is the current sequence number given by the startPrbu value in field 148
- B is the fixed size of the samples, given by the udCompHdr value in field 151
- A is a base address of the buffer.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Communication apparatus includes a host interface and a network interface, which receives from a packet communication network at least one packet stream including a sequence of data packets, which include headers containing respective sequence numbers and data payloads containing slices of the data segment having a predefined, fixed size per slice. Packet processing circuitry is configured to receive the data packets from the network interface, and to map the data payloads of the data packets in the at least one packet stream, using a linear mapping of the sequence numbers, to respective addresses in the buffer.
Description
- This application is a continuation in part of U.S. patent application Ser. No. 15/473,668, filed Mar. 30, 2017, which claims the benefit of U.S.
Provisional Patent Application 62/457,919, filed Feb. 12, 2017, which is incorporated herein by reference. - The present invention relates to apparatus and methods for transmission and reception of packet streams across a network with high speed and reliability.
- High-speed packet streaming schemes are commonly used in transmitting real-time video and other digital media across a network. Because of the real-time nature of the data, the packet transmissions typically use a non-reliable protocol, without acknowledgment from the destination or retransmission by the source when packets are lost or corrupted. Therefore, in applications requiring high data availability, a source host may transmit multiple parallel, redundant streams of the data to the destination. Each packet is thus transmitted multiple times—once in each stream—over multiple different paths through the network-in order to increase the likelihood that at least one copy of each packet will be received intact at the destination.
- In this sort of scheme, there is still no guarantee that all the packets in any given stream will reach the destination, nor can it be ensured that the packets will arrive at the destination in the order in which they were transmitted. Therefore, in many applications (such as broadcast or storage of the video data), the destination computer must store, reorder and interleave packets from the two (or more) received streams in order to reconstruct the data. This solution enables reliable video reconstruction, but at the cost of a substantial memory footprint and a heavy processing burden on the host processor, which increases data latency and can limit the data throughput.
- Various schemes for handling data from redundant transmissions are known in the art. For example, U.S. Patent Application Publication 2009/0034633 describes a method for simultaneous processing of media and redundancy streams for mitigating impairments. The method comprises receiving a primary stream of encoded frames and a separate stream of redundant frames. The method further comprises decoding and reconstructing in parallel the frames in the primary stream and the separate stream of redundant frames, on a real-time basis, in accordance with a specified common clock reference. The method further comprises, upon determining that a frame in the primary stream exhibits an error or impairment, determining a decoded redundant frame in the separate stream that corresponds to the impaired frame, and substituting at least a portion of the information in the decoded redundant frame for a corresponding decoded version of the impaired frame.
- Embodiments of the present invention that are described herein provide efficient apparatus and methods for receiving and handling redundant data streams from a network.
- There is therefore provided, in accordance with an embodiment of the invention, communication apparatus, including a host interface, which is configured to be connected to a bus of a host computer having a processor and a memory, in which a buffer is allocated for receiving a data segment. A network interface is configured to receive from a packet communication network at least first and second redundant packet streams. Each packet stream includes a sequence of data packets, which include headers containing respective packet sequence numbers and data payloads of a predefined, fixed size containing respective slices of the data segment, such that redundant first and second copies of each slice are transmitted respectively in at least a first data packet in the first packet stream and a second data packet in the second packet stream. Packet processing circuitry is configured to receive the data packets from the network interface, to map the data packets in both the first and second packet streams, using the packet sequence numbers, to respective addresses in the buffer, and to write the data payloads to the respective addresses via the host interface while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the packet sequence numbers.
- In some embodiments, the packet processing circuitry is configured to map the packet sequence numbers to the respective addresses, using a linear mapping defined so that the first and second copies of any given data slice are both mapped to a common address in the buffer. In a disclosed embodiment, the mapping is defined such that each packet sequence number PSN is mapped to an address equal to A+(PSN−X)×B, wherein X is an initial sequence number, B is the fixed size of the data payloads, and A is a base address of the buffer.
- In some embodiments, the data payloads include video data, including multiple data segments corresponding to frames of the video data. In one embodiment, the headers contain an indication of a start and end of each frame, and the packet processing circuitry is configured to identify the indication in the headers and to select the buffer to which the data payloads are to be written responsively to the identified indication.
- In a disclosed embodiment, the packet processing circuitry is configured to maintain a record of the packet sequence numbers for which the data payloads have been written to the buffer, and responsively to the record, to discard redundant copies of the data payloads so that each slice is transmitted over the bus via the host interface no more than once. Alternatively, the packet processing circuitry is configured to transmit all of the copies of each slice over the bus so that the redundant data in the buffer are overwritten.
- In a disclosed embodiment, the packet processing circuitry is configured to receive a work item from the processor indicating, for each data segment, an address of the buffer and the size of the slices, and to submit a completion report to the processor when all slices of the data segment have been written to the buffer.
- In one embodiment, the first and second packet streams are transmitted in accordance with a Real-time Transport Protocol (RTP), and the headers include an RTP header, which contains the packet sequence numbers.
- There is also provided, in accordance with an embodiment of the invention, a method for data communication, including allocating a buffer in a memory of a host computer for receiving a data segment. At least first and second redundant packet streams are received in a network interface controller (NIC) of the host computer from a packet communication network. Each packet stream includes a sequence of data packets, which include headers containing respective packet sequence numbers and data payloads of a predefined, fixed size containing respective slices of the data segment, such that redundant first and second copies of each slice are transmitted respectively in at least a first data packet in the first packet stream and a second data packet in the second packet stream. The data packets in both the first and second packet streams are mapped, using the packet sequence numbers, to respective addresses in the buffer. The data payloads are written to the respective addresses in the buffer while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the packet sequence numbers.
- There is additionally provided, in accordance with an embodiment of the invention, a method for data communication, which includes allocating a buffer in a memory of a host computer for receiving a data segment. A packet stream including a sequence of data packets, which include headers containing respective packet sequence numbers and data payloads of a predefined, fixed size containing respective slices of the data segment, is received in a network interface controller (NIC) of the host computer from a packet communication network. The data packets in the packet stream are mapped to respective addresses in the buffer using a linear mapping of the packet sequence numbers to the addresses. The data payloads are written to the respective addresses in the buffer, ordered in accordance with the packet sequence numbers.
- The present invention will be more fully understood from the following detailed description of the embodiments thereof, taken together with the drawings in which:
-
FIG. 1 is a block diagram that schematically illustrates a data communication system, in accordance with an embodiment of the invention; -
FIG. 2 is a block diagram that schematically illustrates a process of data reconstruction that is carried out by a network interface controller (NIC), in accordance with an embodiment of the invention; -
FIG. 3 is a block diagram that schematically illustrates a host computer with a NIC, in accordance with an embodiment of the invention; -
FIG. 4 is a block diagram that schematically illustrates a method for direct placement of packet data, in accordance with an embodiment of the invention; -
FIG. 5 is a block diagram that schematically illustrates a data communication system, in accordance with another embodiment of the invention; and -
FIG. 6 is a block diagram that schematically illustrates a method for direct placement of packet data, in accordance with the embodiment ofFIG. 5 . - In many real time streaming protocols, such as the Real-time Transport Protocol (RTP), each of the packets in each transmitted stream contains a respective sequence number, such as a packet sequence number (PSN), which can be used at the destination in detecting missing packets and restoring the packet data to the transmit order. In the present embodiments, as explained in detail hereinbelow, these reordering and reconstruction functions are carried out by hardware logic in the network interface controller (NIC) of the destination computer, thus offloading these tasks from the host processor. Although the disclosed embodiments relate to a single stream of data (which in some cases is duplicated in at least one redundant stream), in general the destination computer may receive and process many such streams concurrently from different sources.
- In some embodiments, the destination host processor allocates a single buffer to receive the reconstructed video data in each segment of an incoming data stream, for example, in each video frame, based on the expected segment size and data rate. These stream parameters may be preset or negotiated in each instance by exchange of control messages over the network between the source and destination hosts. The packet sizes can thus be assumed to be fixed and known to the host processors. Each transmitted packet is labeled with a successive sequence number, as provided by RTP or another suitable protocol.
- The receiving NIC performs the functions of data integrity checking, packet reordering, and elimination of redundant data, using the known packet data sizes and sequence numbers. Thus the receiving NIC writes the data payloads to the proper locations in the allocated buffer, in accordance with the transmit order (and irrespective of the receive order), while discarding or overwriting the data from redundant packets. The receiving NIC notifies the destination host processor only when the data segment in memory is complete. The process of packet reception and reordering is thus entirely transparent to the destination host processor, which deals only with complete data segments. Assuming the receiving NIC is able to receive data from the network at wire speed, the latency and throughput of video data transfer at the destination are limited only by the processing and bus access rates of the receiving NIC. This solution not only maximizes data bandwidth, but also substantially reduces the processing load, memory footprint, and power consumption of the host processor.
- Although the above embodiments relate specifically to scenarios in which the source host transmits multiple redundant streams of packets to the destination, the principles of the present invention may similarly be applied to single streams of packets (transmitted without redundancy), as well as to schemes with higher degrees of redundancy. Furthermore, although the above embodiments make use of the packet sequence numbers of the video packets, other embodiments make use of other sorts of sequence numbers that appear in the packet header, with data payloads containing slices of a data segment having a predefined, fixed size per slice. The NIC uses the sequence numbers, along with the fixed size per slice, in mapping the data payloads to respective addresses in the assigned memory buffer using a linear mapping of the sequence numbers. For example, in an alternative embodiment (as illustrated in
FIGS. 5 and 6 ), a packet stream is transmitted in accordance with an enhanced Common Public Radio Interface (eCPRI), and the data payloads that are to be written to a buffer by the receiving NIC comprise radio data. In one of these embodiments, the headers comprise an open radio access network (O-RAN) application layer header, and the starting physical resource block (startPrbu) values contained in the O-RAN header serve as sequence numbers. -
FIG. 1 is a block diagram that schematically illustrates adata communication system 20, in accordance with an embodiment of the invention. In the pictured scenario, multiple transmitting (Tx)host computers packet data network 22, such as an Internet Protocol (IP) network, for example. Each host computer receives a streaming data input, for example from arespective video camera 30. This data input comprises a series of data segments, such as video frame or fields, of a predefined size. The host computer encapsulates the data in a stream of data packets, each comprising a header, containing, inter alia, a respective PSN, and a data payload of a predefined, fixed size containing a respective slice of a given data segment. Althoughhost computers respective video cameras 30 are shown inFIG. 1 , for the sake of conceptual clarity, as separate physical entities, in some implementations the host computer is incorporated into the video camera (typically together with a NIC, as well). - A
NIC 32 in eachhost computer network 22 in two redundant packet streams 34 and 36, as indicated by the dashed arrows inFIG. 1 . Thus, redundant copies of each slice are transmitted concurrently in two packets, one in each of the two packet streams.Streams network 22 over different, respective paths, for example by transmitting the streams through different ports ofNIC 32, which are connected respectively todifferent switches 38 in the network. The packets are typically transmitted using an unreliable transport protocol, such as RTP over User Datagram Protocol (UDP) transport, which gives no guarantee that any given packet will reach its destination. Transmitting the two redundant streams ensures that at least one copy of each packet will, with few exceptions, reach its destination. For even higher confidence of delivery, three or even more redundant streams can be transmitted and handled at the receiver in the manner described herein. Alternatively, as noted above, the techniques described herein are useful in efficient handling of even a single packet stream by a receiving NIC, when redundancy is not required. -
Streams hosts host computer 40, which is connected to network 22 by aNIC 42. Upon receiving the data packets fromnetwork 22,NIC 42 maps the packets in both of packet streams 34 and 36, using the packet sequence numbers, to respective addresses in a buffer in amemory 44 ofhost computer 40.NIC 42 writes the data payloads to the respective addresses while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the packet sequence numbers. The video frames are thus immediately available in memory for retransmission (over a television network, for example) or other access. -
FIG. 2 is a block diagram that schematically illustrates a process of data reconstruction that is carried out byNIC 42, in accordance with an embodiment of the invention.Video camera 30 captures animage frame 50, which is divided into slices for transmission byNIC 32 in a sequence ofdata packets header 60, containing a packet sequence number (PSN) 62, and apayload 64 containing a respective slice ofimage frame 50.NIC 32 transmits two copies of eachpacket streams - In the pictured scenario, certain packets are lost or corrupted in transmission through
network 22, and others reachNIC 42 out of order.NIC 42 detects and discards corrupted packets, for example by computing and checking packet checksums or other error detection codes, as provided by the applicable protocols. In the pictured example,NIC 42 has received onlypackets stream 34 andpackets stream 36. Using packetserial numbers 62, however,NIC 42 is able to directly place data from theappropriate payloads 64 in the designated buffer inmemory 44, and thus reconstruct acomplete image frame 66 inmemory 44. As noted earlier,NIC 42 eliminates redundant data so that the buffer contains exactly one copy of each slice of the frame, ordered in accordance with the packet sequence numbers. The process of reconstruction is transparent to software running onhost computer 40 and requires no involvement by the software in data reordering or eliminating redundancies. -
FIG. 3 is a block diagram that schematically shows details ofhost computer 40 andNIC 42, in accordance with an embodiment of the invention.Host computer 40 comprises aprocessor 70, typically comprising at least one central processing unit (CPU), andmemory 44, which are connected toNIC 42 by ahost bus 72, such as a PCI Express® bus, as is known in the art.Processor 70 runs various software programs, including, in this example, avideo processing application 74 and adriver 75 for controlling operation ofNIC 42. -
Driver 75 creates a respective work queue 76 (conventionally referred to as a queue pair, or QP) for each incoming stream of video packets thatNIC 42 is to receive. For each segment in the incoming stream (such as a video frame) thatNIC 42 is to receive,driver 75 posts a corresponding work item (referred to as a work queue element, or WQE) in theappropriate work queue 76 pointing to abuffer 78 that is to receive the data in the segment. In some embodiments, this functionality is implemented as follows: -
-
Driver 75, upon receiving a control message indicating that such a video stream is to be initiated, creates a QP for the flow, and specifies the following parameters, for example in the QP context inmemory 44, to be accessed byNIC 42 via bus 72:- Packet size;
- Header size;
- Range of expected packet sequence numbers in the segment;
- PSN offset within the packet header;
- Size and offset of the payload data (excluding the frame checksum that follows the data).
- In some embodiments, for every segment (which may comprise tens, hundreds, or even thousands of IP packets), the
driver 75 posts a WQE inqueue 76 containing the following information, to be accessed by NIC 42:- Segment PSN start (X);
- Segment buffer base address (A).
- The WQE thus specifies the location and contents of
buffer 78, which is divided intoslices 80 of the payload size indicated by the QP context. In some implementations, the WQE contains a memory key (MKEY), to be used byNIC 42 in accessingbuffer 78. Alternatively, the above information can be included in the QP context, which points to a cyclic buffer to whichNIC 42 will writeslices 80 in succession (thus relieving the software of the burden of continually allocating buffers and posting WQEs). - When another identical, redundant flow is to be sent in a second stream,
driver 75 creates another QP, specifying the same parameters (packet size, header size, etc.) - For every segment of this redundant flow, the software will post the following information to the NIC:
- Segment PSN start (Y)—The two streams need not have the same PSNs, although it is simpler if Y=X. If not,
driver 75 providesNIC 42 with the necessary context information to synchronize between the corresponding packet sequence numbers in the two streams. - Segment buffer base address (A).
- Segment PSN start (Y)—The two streams need not have the same PSNs, although it is simpler if Y=X. If not,
-
- The result will be that both copies of any given data slice are mapped to a common slice address in
buffer 78, and thus the corresponding, redundant data will be written to the same place in the host memory, regardless of the arrival order. -
NIC 42 comprises ahost interface 82, connected tobus 72, and anetwork interface 84, which connects to network 22.Network interface 84 in this example comprises twoports 88 with different addresses, serving as the respective destination addresses forstreams -
Packet processing circuitry 86 is coupled betweenhost interface 82 andnetwork interface 84. For the sake of simplicity,FIG. 3 shows only certain specific elements of packet processing circuitry 86:packet parsing logic 90 and ascatter engine 92, which are used in implementing the direct data placement functionality that is the subject of the present description. In a typical NIC, these elements are combined with other components for transmitting and receiving packets for other purposes and in accordance with other sorts of protocols. These latter components will be apparent to those skilled in the art and are beyond the scope of the present description.Packet processing circuitry 86, including parsinglogic 90 andscatter engine 92, is typically implemented in hardware logic circuits within one or more integrated circuit chips. The logic may be hard-wired or programmable, or a combination of hard-wired and programmable elements. Additionally or alternatively, certain functions ofpacket processing circuitry 86 may be carried out in software or firmware by an embedded microprocessor or microcontroller. -
Network interface 84 passes incoming packets instreams packet parsing logic 90. To process these packets,packet processing circuitry 86 reads and makes use of the information posted in theappropriate work queue 76 inmemory 44 bydriver 75. This information enablespacket parsing logic 90 to locate and extractPSN 62 andpayload 64 from each packet. Scatterengine 92 usesPSN 62, together with the base address ofbuffer 78, to map eachslice 80 to the respective address in the buffer, and thus to write the data payloads to the appropriate addresses viahost interface 82. -
FIG. 4 is a block diagram that schematically shows details of a method for direct placement of packet data that is performed byNIC 42, in accordance with an embodiment of the invention.FIG. 4 illustrates howscatter engine 92 usesPSN 62 in anRTP header 100 of a video packet in placing the packet data inbuffer 78. Other examples of video networking protocols that can be handled in similar fashion include (without limitation): -
- SMPTE 2022-5/6/7
- VSF TR-03/IETF RFC 4175
- intoPIX TICO
- Sony
IP Live RDD 34 and NMI - NewTek
- GigE vision GVSP
- The packet illustrated in
FIG. 4 belongs to a stream in which the payload size of all packets is fixed and known in advance.Driver 75 running onhost processor 70 assigns and informsNIC 42 of the base address ofbuffer 78 to which each data segment in the stream is to be written, as explained above. Withinpacket header 60,RTP header 100 comprises atimestamp 102 andother protocol information 104, in addition toPSN 62. Based on the context information provided bydriver 75,packet parsing logic 90 advances to the known location ofPSN 62 in each packet and extracts the PSN value, as well as extracting data slice 80 frompayload 64. On this basis,scatter engine 92 is able to write the data slices frompayloads 64 to buffer 78 in the proper order by simple linear translation of the PSN. - In other words, for a packet stream beginning from an initial sequence number X, with a data payload of size B in each packet, and a buffer base address A,
scatter engine 92 will write the payload of each packet to an address: -
- When the payloads of two valid packets from different, respective streams in a redundant transmission scheme map to the same address (whether they have the same or different PSNs), only one of them will ultimately be written to the buffer. Scatter
engine 92 may overwrite the payload of the packet that arrives first with that of the second copy of the packet, or it may write only one of the payloads to the buffer and discard the other. - For some protocols, the segment definition is also indicated in the packet headers, thus enabling alternative implementations that reduce the involvement of driver software even further. For example:
-
- A segment in most video applications corresponds to a single frame (or a single field of interlaced video).
- In some video protocols, a frame-end marker is entered in the packet transport header: The first and last packets in the segment are identified by a special field in the transport header indicating that they are the first or last packet.
- When the frame size is fixed and the frame start and end are marked in the headers in this manner, the NIC can automatically start to write the data into the allocated host buffers when the start marker is received. Thus, the need to specify segment boundaries is also offloaded from the software to the NIC hardware logic.
- For a NIC operating at very high speed (for example, receiving incoming video data at 400 Gbps), access from
NIC 42 tomemory 44 overbus 72 can become a bottleneck. To reduce the bus pressure,packet processing circuitry 86 can monitor PSNs and, when the payload from a given packet having a given PSN in one of the streams has already been written to the buffer, simply discard the corresponding packet from the other stream, rather than overwriting the data already in the buffer. For this purpose, processingcircuitry 86 may maintain a record, such as a PSN vector and a rolling PSN window, for each flow. Each packet arrivingcauses processing circuitry 86 to flip a bit in the PSN vector. When the bit for a given PSN is set when corresponding packet from the other stream arrives,packet parsing logic 90 drops this latter packet without further processing. -
FIG. 5 is a block diagram that schematically illustrates adata communication system 110 for transmission of radio data, in accordance with another embodiment of the invention.System 110 is assumed to operate in accordance with the enhanced Common Public Radio Interface (eCPRI) specification, and the Open Radio Access Network (O-RAN) fronthaul requirements, as defined in the O-RAN Fronthaul Working Group Control, User and Synchronization Plane Specification, published by the O-RAN Alliance as Technical Specification ORAN-WG4.CUS.0-v01.00 (2019). - In
system 110, an O-RAN Distributed Unit (O-DU) 112 communicates over anetwork 116, such as an IP network, for example, with an O-RAN Radio Unit (O-RU) 114, in accordance with the above-mentioned eCPRI and O-RAN specifications. O-DU 112 and O-RU 114 comprise general-purpose computer processors, which haverespective memories respective NICs DU 112 and O-RU 114 typically have other, special-purpose interfaces, such as a radio transceiver associated with the O-RU, but these features ofsystem 110 are beyond the scope of the present description.) - O-
RU 112 transmits a sequence of data packets overnetwork 116, comprising respective headers and data payloads, which contain data segments of radio signals received by O-RU 114. Each data segment comprises one or more physical resource blocks (PRBs), which are divided into slices in the form of data samples, typically comprising alternating iSamples and qSamples, as defined by the O-RAN specification (see particularly section 6.3, including Table 6-2 on page 95). These samples have a fixed size, between 1 bit and 16 bits per sample, which is defined in the O-RAN header of each packet, as explained below with reference toFIG. 6 .NIC 124 transmits the data packets overnetwork 116, typically using an unreliable transport protocol, such as eCPRI over UDP transport. Upon receiving the data packets fromnetwork 116,NIC 122 maps the samples contained in the packets to respective addresses in a buffer inmemory 118 of O-DU 112, with the samples ordered in the buffer in accordance with respective sequence numbers given by the O-RAN headers in the packets. The radio data are thus made immediately available inmemory 120, in the proper order for processing by O-DU 112. -
FIG. 6 is a block diagram that schematically illustrates a method for direct placement of packet data in abuffer 152 inmemory 118, in accordance with the embodiment ofFIG. 5 . The method is applied to the O-RAN data packets that are received by O-DU 112, illustrated inFIG. 6 by apacket 130. This packet has network andtransport headers 132, including anIP header 134, aUDP header 136, and aneCPRI header 138, for example as defined in section 3.1.3 of the above-mentioned O-RAN specification (page 32). The transport headers are followed by an O-RAN application header 140 (as defined in Table 6-2 of the O-RAN specification) and apayload 142 containing a sequence of data samples. O-RAN header 140 comprises a set of frameID fields 144, followed bysectionID fields 146, which define the data layout of the data segment inpayload 142. These section ID fields include, inter alia, astartPrbu field 148, which identifies the starting physical resource block (PRB) inpacket 130 and thus can serve as a sequence number for purposes of mapping of the samples inpayload 142. AnumPrbu field 150 indicates the number of contiguous PRBs in this section; and audCompHdr field 151 indicates the size, in bits, of each sample, i.e., the size of each slice of the PRB inpayload 142. When a data packet contains multiple sections of data, section ID fields 146 will be repeated as the header of each section. -
NIC 122 extracts the data samples from payload and writes them torespective addresses 154 in abuffer 152 inmemory 118, using a linear mapping of the startPrbu value infield 148. The startPrbu value indicates theaddress 154 to which the NIC is to write the first sample in each section, followed contiguously by the succeeding samples. Specifically, in the present embodiment,NIC 122 maps the samples toaddresses 154 using the following formula for the first sample in each section: -
- Here X is the initial sequence number; SN is the current sequence number given by the startPrbu value in
field 148; B is the fixed size of the samples, given by the udCompHdr value infield 151; and A is a base address of the buffer. - Although the embodiment described above refers specifically to transmission of data from O-
RU 114 to O-DU 112, the principles of this embodiment may similarly be applied by O-RU 114 in buffering data transmitted by O-DU 112. - It will thus be appreciated that the embodiments described above are cited by way of example, and that the present invention is not limited to what has been particularly shown and described hereinabove. Rather, the scope of the present invention includes both combinations and subcombinations of the various features described hereinabove, as well as variations and modifications thereof which would occur to persons skilled in the art upon reading the foregoing description and which are not disclosed in the prior art.
Claims (18)
1. Communication apparatus, comprising:
a host interface, which is configured to be connected to a bus of a host computer having a processor and a memory, in which a buffer is allocated for receiving a data segment;
a network interface, which is configured to receive from a packet communication network at least one packet stream comprising a sequence of data packets, which comprise headers containing respective sequence numbers and data payloads containing slices of the data segment having a predefined, fixed size per slice; and
packet processing circuitry, which is configured to receive the data packets from the network interface, and to map the data payloads of the data packets in the at least one packet stream, using a linear mapping of the sequence numbers, to respective addresses in the buffer.
2. The apparatus according to claim 1 , wherein the at least one packet stream comprises first and second redundant packet streams, containing redundant first and second copies of each slice, and wherein the packet processing circuitry is configured to write the data payloads to the respective addresses via the host interface while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the sequence numbers.
3. The apparatus according to claim 2 , wherein the linear mapping is defined so that the first and second copies of any given slice are both mapped to a common address in the buffer.
4. The apparatus according to claim 1 , wherein the mapping is defined such that each sequence number SN is mapped to an address equal to A+(SN−X)×B, wherein X is an initial sequence number, B is the fixed size of the slices, and A is a base address of the buffer.
5. The apparatus according to claim 1 , wherein the data payloads comprise video data, comprising multiple data segments corresponding to frames of the video data.
6. The apparatus according to claim 1 , wherein the packet processing circuitry is configured to receive a work item from the processor indicating, for each data segment, an address of the buffer and the size of the slices, and to submit a completion report to the processor when all slices of the data segment have been written to the buffer.
7. The apparatus according to claim 1 , wherein the at least one packet stream is transmitted in accordance with a Real-time Transport Protocol (RTP), and wherein the headers comprise an RTP header, which contains the sequence numbers.
8. The apparatus according to claim 1 , wherein the data payloads comprise radio data, and wherein the at least one packet stream is transmitted in accordance with an enhanced Common Public Radio Interface (eCPRI).
9. The apparatus according to claim 8 , wherein the headers comprise an open radio access network (O-RAN) application layer header, and wherein the sequence numbers comprise starting physical resource block (startPrbu) values contained in the O-RAN header.
10. A method for data communication, comprising:
allocating a buffer in a memory of a host computer for receiving a data segment;
receiving in a network interface controller (NIC) of the host computer from a packet communication network at least one packet stream, comprising a sequence of data packets, which comprise headers containing respective sequence numbers and data payloads containing slices of the data segment having a predefined, fixed size per slice; and
mapping the data payloads of the data packets in the at least one packet stream, using a linear mapping of the sequence numbers, to respective addresses in the buffer.
11. The method according to claim 10 , wherein the at least one packet stream comprises first and second redundant packet streams, containing redundant first and second copies of each slice, and wherein mapping the data packets comprises writing the data payloads to the respective addresses while eliminating redundant data so that the buffer contains exactly one copy of each slice of the data segment, ordered in accordance with the sequence numbers.
12. The method according to claim 11 , wherein the linear mapping is defined so that the first and second copies of any given slice are both mapped to a common address in the buffer.
13. The method according to claim 10 , wherein the mapping is defined such that each sequence number SN is mapped to an address equal to A+(SN−X)×B, wherein X is an initial sequence number, B is the fixed size of the slices, and A is a base address of the buffer.
14. The method according to claim 10 , wherein the data payloads comprise video data, comprising multiple data segments corresponding to frames of the video data.
15. The method according to claim 10 , wherein mapping the data payloads comprises receiving a work item from a processor of the host computer indicating, for each data segment, an address of the buffer and the size of the slices, and submitting a completion report to the processor when all slices of the data segment have been written to the buffer.
16. The method according to claim 10 , wherein the at least one packet stream is transmitted in accordance with a Real-time Transport Protocol (RTP), and wherein the headers comprise an RTP header, which contains the sequence numbers.
17. The method according to claim 10 , wherein the data payloads comprise radio data, and wherein the at least one packet stream is transmitted in accordance with an enhanced Common Public Radio Interface (eCPRI).
18. The method according to claim 17 , wherein the headers comprise an open radio access network (O-RAN) application layer header, and wherein the sequence numbers comprise starting physical resource block (startPrbu) values contained in the O-RAN header.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/535,608 US20220086105A1 (en) | 2017-02-12 | 2021-11-25 | Direct Packet Placement |
US17/824,954 US11979340B2 (en) | 2017-02-12 | 2022-05-26 | Direct data placement |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201762457919P | 2017-02-12 | 2017-02-12 | |
US15/473,668 US10516710B2 (en) | 2017-02-12 | 2017-03-30 | Direct packet placement |
US16/693,302 US11190462B2 (en) | 2017-02-12 | 2019-11-24 | Direct packet placement |
US17/535,608 US20220086105A1 (en) | 2017-02-12 | 2021-11-25 | Direct Packet Placement |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/693,302 Continuation US11190462B2 (en) | 2017-02-12 | 2019-11-24 | Direct packet placement |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/824,954 Continuation-In-Part US11979340B2 (en) | 2017-02-12 | 2022-05-26 | Direct data placement |
Publications (1)
Publication Number | Publication Date |
---|---|
US20220086105A1 true US20220086105A1 (en) | 2022-03-17 |
Family
ID=69773258
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/693,302 Active 2037-04-03 US11190462B2 (en) | 2017-02-12 | 2019-11-24 | Direct packet placement |
US17/535,608 Abandoned US20220086105A1 (en) | 2017-02-12 | 2021-11-25 | Direct Packet Placement |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/693,302 Active 2037-04-03 US11190462B2 (en) | 2017-02-12 | 2019-11-24 | Direct packet placement |
Country Status (1)
Country | Link |
---|---|
US (2) | US11190462B2 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11700414B2 (en) | 2017-06-14 | 2023-07-11 | Mealanox Technologies, Ltd. | Regrouping of video data in host memory |
US11835999B2 (en) | 2022-01-18 | 2023-12-05 | Mellanox Technologies, Ltd. | Controller which adjusts clock frequency based on received symbol rate |
US11917045B2 (en) | 2022-07-24 | 2024-02-27 | Mellanox Technologies, Ltd. | Scalable synchronization of network devices |
US11979340B2 (en) | 2017-02-12 | 2024-05-07 | Mellanox Technologies, Ltd. | Direct data placement |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11564077B2 (en) | 2018-10-25 | 2023-01-24 | Commscope Technologies Llc | Multi-carrier radio point for a centralized radio access network |
US11552842B2 (en) | 2019-03-06 | 2023-01-10 | Commscope Technologies Llc | Flexible interface between a baseband controller and remote units of a C-RAN |
EP3836420A1 (en) | 2019-11-04 | 2021-06-16 | Mavenir Networks, Inc. | Method for beamforming weights transmission over o-ran fronthaul interface in c-rans |
WO2022006106A1 (en) * | 2020-06-30 | 2022-01-06 | Commscope Technologies Llc | Open radio access network with unified remote units supporting multiple functional splits, multiple wireless interface protocols, multiple generations of radio access technology, and multiple radio frequency bands |
KR20220037305A (en) * | 2020-09-17 | 2022-03-24 | 삼성전자주식회사 | Apparatus and method for front haul transmission in wireless communication system |
KR20220037308A (en) * | 2020-09-17 | 2022-03-24 | 삼성전자주식회사 | Apparatus and method for front haul transmission in wireless communication system |
KR20220037306A (en) * | 2020-09-17 | 2022-03-24 | 삼성전자주식회사 | Apparatus and method for front haul transmission in wireless communication system |
US11234163B1 (en) * | 2020-09-18 | 2022-01-25 | Nokia Solutions And Networks Oy | Dynamic eCPRI header compression |
JP2022139706A (en) * | 2021-03-12 | 2022-09-26 | 株式会社東芝 | Communication apparatus, processor, communication method and program |
US20220377823A1 (en) * | 2021-05-20 | 2022-11-24 | Qualcomm Incorporated | Path management with direct device communication |
KR20230018955A (en) * | 2021-07-30 | 2023-02-07 | 삼성전자주식회사 | Apparatus and method for fronthaul transmission in wireless communication system |
US11522931B1 (en) * | 2021-07-30 | 2022-12-06 | Avago Technologies International Sales Pte. Limited | Systems and methods for controlling high speed video |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030005164A1 (en) * | 2001-06-27 | 2003-01-02 | Solomon Trainin | Dynamic network interface |
US20130191549A1 (en) * | 2006-05-17 | 2013-07-25 | Audinate Pty Limited | Redundant media packet streams |
US20140201587A1 (en) * | 2013-01-17 | 2014-07-17 | Qualcomm Incorporated | Fec-based reliable transport control protocols for multipath streaming |
US20150085863A1 (en) * | 2013-09-24 | 2015-03-26 | Broadcom Corporation | Efficient memory bandwidth utilization in a network device |
US20160277473A1 (en) * | 2015-03-16 | 2016-09-22 | Imagine Communications Corp. | Video stream transmission over ip network |
US20200076521A1 (en) * | 2018-08-30 | 2020-03-05 | Keysight Technologies, Inc. | Methods, systems, and computer readable media for testing a central unit using a distributed unit emulation |
US10735339B1 (en) * | 2017-01-16 | 2020-08-04 | Innovium, Inc. | Intelligent packet queues with efficient delay tracking |
US20220070797A1 (en) * | 2018-12-20 | 2022-03-03 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and units of a base station system for handling a signal for transmission over a fronthaul link between the units |
Family Cites Families (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3732398B2 (en) | 2000-10-11 | 2006-01-05 | 三菱電機株式会社 | Crew protection device |
JP4154157B2 (en) | 2002-02-25 | 2008-09-24 | 株式会社東芝 | Imaging device |
ATE386951T1 (en) | 2002-08-05 | 2008-03-15 | Elbit Systems Ltd | NIGHT VISION IMAGING SYSTEM AND METHOD FOR MOUNTING IN A VEHICLE |
JP3846410B2 (en) | 2002-11-21 | 2006-11-15 | ソニー株式会社 | Image processing apparatus and method, recording medium, and program |
US7881496B2 (en) | 2004-09-30 | 2011-02-01 | Donnelly Corporation | Vision system for vehicle |
JP4452161B2 (en) | 2004-11-12 | 2010-04-21 | パナソニック株式会社 | Imaging device |
EP2420954B8 (en) | 2004-12-01 | 2017-04-12 | Datalogic USA, Inc. | Data reader with automatic exposure adjustment and methods of operating a data reader |
GB2435974A (en) | 2006-03-07 | 2007-09-12 | I S G Thermal Systems Ltd | Imaging system including detectors using plural sensitivity levels |
US7855740B2 (en) | 2007-07-20 | 2010-12-21 | Eastman Kodak Company | Multiple component readout of image sensor |
US8958486B2 (en) * | 2007-07-31 | 2015-02-17 | Cisco Technology, Inc. | Simultaneous processing of media and redundancy streams for mitigating impairments |
KR101572874B1 (en) * | 2007-08-24 | 2015-11-30 | 엘지전자 주식회사 | Digital broadcasting system and method of processing data in digital broadcasting system |
JP2009152669A (en) | 2007-12-18 | 2009-07-09 | Sony Corp | Imaging apparatus, imaging processing method and imaging control program |
JP5040776B2 (en) | 2008-03-31 | 2012-10-03 | アイシン精機株式会社 | Imaging device |
US20100149393A1 (en) | 2008-05-22 | 2010-06-17 | Panavision Imaging, Llc | Increasing the resolution of color sub-pixel arrays |
US9749607B2 (en) | 2009-07-16 | 2017-08-29 | Digimarc Corporation | Coordinated illumination and image signal capture for enhanced signal detection |
GB2480308A (en) * | 2010-05-13 | 2011-11-16 | Skype Ltd | Data recovery for encrypted packet streams at relay nodes using correction data |
WO2013074964A1 (en) | 2011-11-16 | 2013-05-23 | Vanguard Software Solutions, Inc. | Video compression for high efficiency video coding |
WO2013131561A1 (en) * | 2012-03-06 | 2013-09-12 | Appear Tv As | Method, device and system for packet transmission over ip networks |
CN109889888B (en) * | 2013-06-05 | 2022-04-01 | 太阳专利托管公司 | Reproduction method, reproduction apparatus, generation method, and generation apparatus |
JP6600241B2 (en) * | 2015-12-11 | 2019-10-30 | キヤノン株式会社 | Arithmetic apparatus, arithmetic method, and communication apparatus |
-
2019
- 2019-11-24 US US16/693,302 patent/US11190462B2/en active Active
-
2021
- 2021-11-25 US US17/535,608 patent/US20220086105A1/en not_active Abandoned
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030005164A1 (en) * | 2001-06-27 | 2003-01-02 | Solomon Trainin | Dynamic network interface |
US20130191549A1 (en) * | 2006-05-17 | 2013-07-25 | Audinate Pty Limited | Redundant media packet streams |
US20140201587A1 (en) * | 2013-01-17 | 2014-07-17 | Qualcomm Incorporated | Fec-based reliable transport control protocols for multipath streaming |
US20150085863A1 (en) * | 2013-09-24 | 2015-03-26 | Broadcom Corporation | Efficient memory bandwidth utilization in a network device |
US20160277473A1 (en) * | 2015-03-16 | 2016-09-22 | Imagine Communications Corp. | Video stream transmission over ip network |
US10735339B1 (en) * | 2017-01-16 | 2020-08-04 | Innovium, Inc. | Intelligent packet queues with efficient delay tracking |
US20200076521A1 (en) * | 2018-08-30 | 2020-03-05 | Keysight Technologies, Inc. | Methods, systems, and computer readable media for testing a central unit using a distributed unit emulation |
US20220070797A1 (en) * | 2018-12-20 | 2022-03-03 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and units of a base station system for handling a signal for transmission over a fronthaul link between the units |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11979340B2 (en) | 2017-02-12 | 2024-05-07 | Mellanox Technologies, Ltd. | Direct data placement |
US11700414B2 (en) | 2017-06-14 | 2023-07-11 | Mealanox Technologies, Ltd. | Regrouping of video data in host memory |
US11835999B2 (en) | 2022-01-18 | 2023-12-05 | Mellanox Technologies, Ltd. | Controller which adjusts clock frequency based on received symbol rate |
US11917045B2 (en) | 2022-07-24 | 2024-02-27 | Mellanox Technologies, Ltd. | Scalable synchronization of network devices |
Also Published As
Publication number | Publication date |
---|---|
US20200092229A1 (en) | 2020-03-19 |
US11190462B2 (en) | 2021-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220086105A1 (en) | Direct Packet Placement | |
US10516710B2 (en) | Direct packet placement | |
US11855881B2 (en) | System and method for facilitating efficient packet forwarding using a message state table in a network interface controller (NIC) | |
US7142540B2 (en) | Method and apparatus for zero-copy receive buffer management | |
US8208470B2 (en) | Connectionless packet data transport over a connection-based point-to-point link | |
US6310884B1 (en) | Data transfer method and apparatus that allocate storage based upon a received relative offset | |
US7383483B2 (en) | Data transfer error checking | |
CA2548966C (en) | Increasing tcp re-transmission process speed | |
US20050129045A1 (en) | Limiting number of retransmission attempts for data transfer via network interface controller | |
US20050129039A1 (en) | RDMA network interface controller with cut-through implementation for aligned DDP segments | |
US11979340B2 (en) | Direct data placement | |
US20050265352A1 (en) | Recovery from MSS change | |
US7346078B2 (en) | Processing of received data within a multiple processor device | |
EP1692707A2 (en) | Data transfer error checking | |
EP2099177A1 (en) | A method for transferring data packets, computer network assembly and adapted network station | |
CN117424849A (en) | Data transmission method, device, computer equipment and readable medium | |
JP2023020924A (en) | Systems and methods for controlling high speed video | |
Perkins et al. | Comparison of transport protocols for high-speed data networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: MELLANOX TECHNOLOGIES, LTD., ISRAEL Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LEVI, DOTAN DAVID;URMAN, AVI;NARKIS, LIOR;SIGNING DATES FROM 20191121 TO 20200512;REEL/FRAME:058211/0058 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |