Abstract:
A network includes a combination of carrier-sense stations and Universal Multiple Access (UMA) stations using a time slot multiple access protocol. The network is configured to include assigned time slots for the respective UMA stations and unassigned time slots reserved for the carrier-sense stations to access the shared network media. Each of the UMA stations is provided with a corresponding assigned time slot and the total number of time slots. Since the UMA stations access the media only during the assigned time slot, the carrier-sense stations can contend for access to the media after waiting a minimum interpacket gap (IPG) after sensing deassertion of the receive carrier on the media. The UMA stations may also be modified to attempt access of the media using Ethernet-compliant, carrier-sense multiple-access with collision detection (CSMA/CD) protocol when a current time slot corresponds to a mixed-use time slot.
Abstract:
Delay times are modified in an Ethernet network device having captured the media channel by increasing the interframe spacing (IFS) between data packets. The modified IFS interval, increased by adding a delay interval to the minimum interpacket gap (IPG) interval after a predetermined number of consecutive successful transmissions, enables other network stations to transmit data during the deferral interval. The Ethernet network device maintains the modified IFS for a limited deferral interval, based upon a predetermined time interval or a number of successful transmissions by other network stations. Additional delay intervals may be added if the network station continues to exceed the predetermined number of consecutive successful transmissions. Hence, a network station can avoid capturing a network channel while ensuring access latencies.
Abstract:
A network interface transmits data packets between a host computer and a network and includes a first in first out (FIFO) buffer memory with an adaptive transmit start point determined for each data packet. The network interface receives data packets from the host computer via a peripheral component interconnect (PCI) bus. A FIFO control determines the byte length of each data packet based on the header information contained in the first few received bytes of the packet. The FIFO control also measures a minimum fill time indicating the time necessary to fill the FIFO buffer memory with a predetermined minimum amount of data necessary before transmission by the FIFO buffer memory. The FIFO control calculates the time to fill the FIFO buffer memory with each packet based on the determined length and the measured minimum fill time. The time to empty the packet from the FIFO buffer memory is also calculated based upon the length of the packet and predetermined network transmission rates. If the time to empty the packet from the FIFO buffer memory is greater than or equal to the time to fill the FIFO buffer memory, the transmit start point is set to the predetermined minimum amount; otherwise, the transmit start point is adjusted in accordance with the difference in time between filling and emptying the FIFO buffer memory with the packet, a FIFO fill rate based on the measured minimum fill time, and a coefficient that accounts for latencies in the PCI bus. The network interface thus provides an optimal transmit start point for each data packet, minimizing latency and underflow conditions during network transmission.
Abstract:
Flow control signals in half-duplex and full-duplex networks are initiated and maintained based on the detected number of data bytes stored in a receive buffer from payload data of received data packets. If the number of stored data bytes exceeds a predetermined threshold, the network interface initiates flow control. Alternatively, the decision to initiate flow control may be based upon the rate at which the receive buffer is emptied compared to the number of stored data bytes in the receive buffer, or the rate the data bytes are stored into the receive buffer. The duration of the flow control is calculated as a wait time interval selected in response to the number of stored data bytes. The wait time may be selectively set as an integer multiple of slot times, or as a time interval based on the number of stored data bytes relative to the removal rate. Hence, the precise control and the initiation of the flow control for a specific wait time prevents loss of transmitted data while maintaining network throughput.
Abstract:
Delay times are modified in Ethernet network devices by adding a randomized time interval generated in accordance with a propagation delay between two network stations. A server in a client-server arrangement is given priority access over clients by adding to the clients' InterPacket Gap (IPG) interval a random time delay between zero and a maximum value equal to no more than twice the cable delay between the server and the network hub. The server can access the network media after the IPG interval, whereas clients must wait the additional random time delay before accessing the media, thereby improving server throughput and overall network throughput. Collision mediation is improved by adding a randomly selected integer multiple of a propagation delay between two stations, where the integer multiplier is randomly selected from a predetermined range of integers. The randomly selected integer multiple of the propagation delay provides a second dimension of random selection to minimize subsequent collisions and minimize the occurrence of capture effects in losing stations.
Abstract:
Delay times are modified in Ethernet network devices by adding an integer multiple of a delay interval to the minimum interpacket gap (IPG) interval, and decrementing the integer in each network station in response to detected activity on the media. Each station has a unique integer value from the range of zero to the number of stations (N) minus one. The unique integer value ensures that each station has a different delay interval in accessing the media after sensing deassertion of the receive carrier. The station having a zero integer value will have its integer counter reset to (N-1) after a station transmits a data packet on the network, and the stations having nonzero integer values decrement their respective integer counters. Each network station also includes a deferral timer that counts the maximum delay interval of (N-1) delay intervals plus the minimum IPG value, and thus establishes a bounded access latency for a half-duplex shared network.
Abstract:
Efficient communication in a network having a minimum data transmission time interval wherein a data packet is transmitted beginning at a start (t20) of the minimum data transmission time interval. An end (t26) of the minimum data transmission time interval is determined and then at least one next data packet is transmitted after the data packet if the end of the minimum data transmission time (t26) is after the end of the data packet (t21).
Abstract:
Delay times are modified in Ethernet network devices by adding a slot time to the minimum interpacked gap (IPG) interval between uninterrupted consecutive transmissions by a network station. If a network station transmits a data packet and has another data packet to send, modified delay time prevents the station from contending for access of the media, enabling other stations having data to transmit to attempt access on the media. If a collision occurs during the transmission of a second successive data packet, the network station uses a modified collision arbitration and automatically sets the collision delay interval to zero for the first access attempt. If another collision occurs during the access attempt, the collision interval is calculated according to the truncated binary exponential backoff algorithm.
Abstract:
Delay times are modified in full-duplex Ethernet network devices by calculating in each network station a delay interval based on a size of a transmitted data packet and a desired transmission rate. The network station waits the calculated delay time before transmitting another data packet, ensuring that the overall output transmission rate of the network station corresponds to the assigned desired transmission rate. The desired transmission rate is received as a media access control (MAC) control frame from a network management entity, such as a switched hub. Hence, each station operates at the desired transmission rate, minimizing the occurrence of congestion and eliminating the necessity of PAUSE frames.
Abstract:
Collision delay intervals are modified in Ethernet network devices transmitting priority data requiring a guaranteed latency by multiplying an integer multiple number of slot times with a fractional coefficient (92). A network device having priority data for transmission uses the conventional Truncated Binary Exponential Backoff (TREB) algorithm during the first access attempt to calculate a collision delay interval from a randomly selected integer multiple of slot times (88). If the network device encounters another collision (102), the next randomly selected integer multiple of slot times is multiplied by the fractional coefficient (92). Use of the fractional coefficient during collision mediation on a half-duplex Ethernet provides a bounded access latency for real-time and multimedia applications by granting the network device a higher probability of successfully accessing the network media.