Abstract: Aspects of the disclosure are directed to supporting time synchronization across a datacenter network with greater accuracy. The time synchronization includes both software based and hardware based time synchronization mechanisms to provide more precise time synchronization across various nodes in the datacenter network. The software based mechanism can provide the initial coarse time synchronization while the hardware based mechanism can provide the subsequent finer time synchronization.

Abstract: In an embodiment, application delivery to end-user devices may be handled by a combination of an application device and a distributed set of split edge devices located closer to the end-user device within a network. The split edge devices are instructed by the application device about how to manage traffic to and from the end-user devices. The application device determines whether content is stored to content cache of a split edge device. The application device, when the content is stored to the split edge device, refrains from sending the content and instead sends instructions to the split edge device that include reference to a location of the content, and instruct the split edge device to send the content to an application and/or device. The application device, when the content is not stored to the split edge device, sends the content with instructions to store the content locally.

Abstract: In an embodiment, application delivery to end-user devices may be handled by a combination of an application device and a distributed set of split edge devices located closer to the end-user device within a network. The split edge devices are instructed by the application device about how to manage traffic to and from the end-user devices. The application device determines whether content is stored to content cache of a split edge device. The application device, when the content is stored to the split edge device, refrains from sending the content and instead sends instructions to the split edge device that include reference to a location of the content, and instruct the split edge device to send the content to an application and/or device. The application device, when the content is not stored to the split edge device, sends the content with instructions to store the content locally.

Abstract: In an embodiment, application delivery to end-user devices may be handled by a combination of an application device and a distributed set of split edge devices located closer to the end-user device within a network. The split edge devices are instructed by the application device about how to manage traffic to and from the end-user devices. The application device determines whether content is stored to content cache of a split edge device. The application device, when the content is stored to the split edge device, refrains from sending the content and instead sends instructions to the split edge device that include reference to a location of the content, and instruct the split edge device to send the content to an application and/or device. The application device, when the content is not stored to the split edge device, sends the content with instructions to store the content locally.

Abstract: In an embodiment, responsive to determining: (a) a first command is not of a particular command type associated with one or more hardware modules associated with a particular routing node, or (b) at least one argument used for executing the first command is not available: transmitting the first command to another routing node in the hardware routing mesh. Upon receiving a second command of the command bundle and determining: (a) the second command is of the particular command type associated with the hardware module(s), and (b) arguments used by the second command are available: transmitting the second command to the hardware module(s) associated with the particular routing node for execution by the hardware module(s). Thereafter, the command bundle is modified based on execution of the second command by at least refraining from transmitting the second command of the command bundle to any other routing nodes in the hardware routing mesh.

Abstract: In an embodiment, a compiler for generating command bundles is configured to receive an execution definition that includes operations for execution. The compiler determines an ordered set of hardware functions corresponding to a hardware architecture to execute at least one operation. The hardware architecture may be selected from typical processor types or a command-aware hardware processor. The compiler generates a command bundle that includes a set of logically independent commands based on hardware functions and functionality of the hardware architecture to optimize execution of the operations. A command-aware hardware processor includes a hardware routing mesh that includes sets of routing nodes that form one or more hardware pipelines. Many hardware pipelines may be included in the hardware routing mesh. A command bundle is transmitted through a selected hardware pipeline via a control path, and is modified by the routing nodes based on execution of commands to achieve a desired outcome.

Abstract: In an embodiment, responsive to determining: (a) a first command is not of a particular command type associated with one or more hardware modules associated with a particular routing node, or (b) at least one argument used for executing the first command is not available: transmitting the first command to another routing node in the hardware routing mesh. Upon receiving a second command of the command bundle and determining: (a) the second command is of the particular command type associated with the hardware module(s), and (b) arguments used by the second command are available: transmitting the second command to the hardware module(s) associated with the particular routing node for execution by the hardware module(s). Thereafter, the command bundle is modified based on execution of the second command by at least refraining from transmitting the second command of the command bundle to any other routing nodes in the hardware routing mesh.

Abstract: In an embodiment, responsive to determining: (a) a first command is not of a particular command type associated with one or more hardware modules associated with a particular routing node, or (b) at least one argument used for executing the first command is not available: transmitting the first command to another routing node in the hardware routing mesh. Upon receiving a second command of the command bundle and determining: (a) the second command is of the particular command type associated with the hardware module(s), and (b) arguments used by the second command are available: transmitting the second command to the hardware module(s) associated with the particular routing node for execution by the hardware module(s). Thereafter, the command bundle is modified based on execution of the second command by at least refraining from transmitting the second command of the command bundle to any other routing nodes in the hardware routing mesh.

Abstract: System utilization related to memory usage can be monitored by storing host memory usage information in the corresponding host physical memory. However, retrieving this information can be a high overhead operation because it involves engaging with the operating system of each host. Moreover, storing memory usage information in the host physical memories can pose a security risk if they also store privileged data. Network interfaces according to the present disclosure provide unobtrusive and secure support for monitoring of network and other system resources such as regions of memory within host physical memories. Implementations according to the present disclosure include a plurality of memory region counters stored on a network interface. Each memory region counter corresponds to one of the memory regions located in a physical memory of a host coupled to the network interface. Each of the counters includes a system utilization metric associated with its corresponding memory region.

Abstract: System utilization related to memory usage can be monitored by storing host memory usage information in the corresponding host physical memory. However, retrieving this information can be a high overhead operation because it involves engaging with the operating system of each host. Moreover, storing memory usage information in the host physical memories can pose a security risk if they also store privileged data. Network interfaces according to the present disclosure provide unobtrusive and secure support for monitoring of network and other system resources such as regions of memory within host physical memories. Implementations according to the present disclosure include a plurality of memory region counters stored on a network interface. Each memory region counter corresponds to one of the memory regions located in a physical memory of a host coupled to the network interface. Each of the counters includes a system utilization metric associated with its corresponding memory region.

Abstract: Methods, apparatuses, and computer-readable medium for providing a fairness protocol in a network element are disclosed herein. An example method includes receiving one or more packets at each of a plurality of ingress ports of the network element, and scheduling the packets into a plurality of queues, wherein each of the queues is associated with packets that are sourced from one of the ingress ports. The method also includes monitoring a bandwidth of traffic sourced from each of the ingress ports, identifying a port among the ingress ports that sources a smallest bandwidth of traffic, and arbitrating among the queues when transmitting packets from an egress port of the network element by giving precedence to the identified port that sources the smallest bandwidth of traffic. Additionally, arbitrating among the queues distributes a bandwidth of the egress port equally among the ingress ports.

Abstract: Methods, apparatuses, and computer-readable medium for providing a fairness protocol in a network element are disclosed herein. An example method includes receiving one or more packets at each of a plurality of ingress ports of the network element, and scheduling the packets into a plurality of queues, wherein each of the queues is associated with packets that are sourced from one of the ingress ports. The method also includes monitoring a bandwidth of traffic sourced from each of the ingress ports, identifying a port among the ingress ports that sources a smallest bandwidth of traffic, and arbitrating among the queues when transmitting packets from an egress port of the network element by giving precedence to the identified port that sources the smallest bandwidth of traffic. Additionally, arbitrating among the queues distributes a bandwidth of the egress port equally among the ingress ports.

Abstract: Methods and systems to explicitly realign packets are described. The system includes a first communications device that receives a first stream of bytes comprising a first packet and generates realignment information for the first packet based on an alignment restriction. The first communications device further transmits a second stream of bytes over the data path comprising the first packet and the realignment information. The transmitting of the first byte of the first packet over the data path being in accordance with the alignment restriction that is associated with an interface. The realignment information identifies a difference between a time that the first byte of the first packet would have been transmitted by the first communications device without the alignment restriction and a time of transmission of the first byte of the first packet by the first communications device in accordance with the alignment restriction.

Abstract: Methods and apparatuses for providing a fairness protocol in a network element are disclosed herein. In accordance with the disclosed fairness protocol, the average bandwidth of traffic sourced from each of a plurality of ingress ports is monitored. The largest bandwidth of traffic sourced from a port within a first group of ingress ports (e.g., ingress ports of a network element) is identified and compared to the largest bandwidth of traffic sourced from a port within a second group of ingress ports (e.g., ingress ports of one or more network elements communicatively connected to the network element). In order to fairly allocate bandwidth when transmitting traffic that is sourced from the first and second groups, precedence is given to traffic flowing from the group associated with the identified port sourcing the lower bandwidth of traffic.

Abstract: Methods and systems to explicitly realign packets are described. The system includes a first communications device that receives a first stream of bytes comprising a first packet and generates realignment information for the first packet based on an alignment restriction. The first communications device further transmits a second stream of bytes over the data path comprising the first packet and the realignment information. The transmitting of the first byte of the first packet over the data path being in accordance with the alignment restriction that is associated with an interface. The realignment information identifies a difference between a time that the first byte of the first packet would have been transmitted by the first communications device without the alignment restriction and a time of transmission of the first byte of the first packet by the first communications device in accordance with the alignment restriction.

Abstract: Methods and apparatuses for providing a fairness protocol in a network element are disclosed herein. In accordance with the disclosed fairness protocol, the average bandwidth of traffic sourced from each of a plurality of ingress ports is monitored. The largest bandwidth of traffic sourced from a port within a first group of ingress ports (e.g., ingress ports of a network element) is identified and compared to the largest bandwidth of traffic sourced from a port within a second group of ingress ports (e.g., ingress ports of one or more network elements communicatively connected to the network element). In order to fairly allocate bandwidth when transmitting traffic that is sourced from the first and second groups, precedence is given to traffic flowing from the group associated with the identified port sourcing the lower bandwidth of traffic.