Hewlett-packard Development Company, L.P.

Hewlett Packard Enterprise Development LP

Giuseppe Scaglione

Brian Peter L'Ecuyer

Charles Tuffli

Jonathan Michael Seely

Sergio Jesus Guillen Hernandez

Paymon Ghamami

Kevin Young

David L Santos

David Tremblay, Jr

Bruno Sartirana

A system for facilitating packet mirroring triggered by a hardware module of a switch is provided. During operation, the hardware module can process a received packet and determine whether the processing of the packet changes a state of the hardware module. If a change to the state is detected, the hardware module can determine whether the changed state of the hardware module satisfies a trigger condition for initiating packet mirroring, and if does, issue a hardware interrupt. The system can then identify a set of packets that are to be mirrored based on one or more mirroring parameters indicated by the trigger condition. Here, the set of packets are subsequent to the packet and to be processed by the hardware module. Accordingly, the system can mirror the set of packets to a target. If the trigger condition is expired, the system can terminate the mirroring of the set of packets.

Hardware-triggered traffic mirroring

A network infrastructure device (e.g., network switch), that integrates solid-state drive (SSD) storage, using Non-volatile Memory Express (NVMe) data transfer protocol, for use by remote application hosts is provided. High availability configurations of network switches using direct rate control (RC) feedback for a plurality of submission queues mapped to SSD storage is provided. NVMe over fabric (NVMe-oF) is an implementation of NVMe protocol over a network fabric. Access to SSDs over network fabrics may be controlled using a direct RC feedback signal between an egress queue congestion accounting (associated with a single egress output) and a source node receiving input/output commands from remote hosts for the integrated SSD devices. In some implementations, direct RC feedback signals use hardware based signals. In some implementations, direct RC feedback signals are implemented in the hardware logic (silicon chip logic) within an internal switch fabric of the network switch.

Mapping NVMe-over-fabric packets using virtual output queues

Non-volatile memory express (NVMe) is a data transfer protocol used to enable high-speed data transfer between a host computer system and a solid-state drive (SSD). NVMe may be implemented over network fabrics and referred to as NVMe over fabrics (NVMe-oF). Access to SSD storage over network fabrics via NVMe-oF allows software defined storage to scale to allow access to a number of NVMe devices and extend distances between devices within a datacenter over which NVMe devices may be accessed. A network device is provided to automatically detect, prioritize, and route NVMe network packets in a network that includes multiple data communication protocols. For example, the network device may obtain network packets, analyze network packets to identify packet type and protocol, and redirect the network packets based on the analysis and detection. Thus, a processing priority may be provided for NVMe packets to assist in lossless communication implementations for storage across a network.

Separate routing of NVMe-over-fabric packets and non-NVMe packets

A network switch is provided. The network switch may incorporate resources for use as network attached resources for remote devices. Resources may include SSD storage for use as network attached storage for remote devices. The network switch may also include one or more client applications configured to detect an intended access path between a remote device and a non-volatile memory express (NVMe) storage device. The intended access path may be based on one of many different NVMe over fabric (NVMe-oF) protocols. The network switch (via the one or more client applications) automatically configures parameters to provide a network connectivity path between the remote device and the NVMe storage device. Communication includes at least one of a virtual local area network (VLAN) and a communication tunnel and/or other form of dedicated communication path to facilitate remotely accessible storage capacity provided from the network switch to the remote device.

Automatic system provisioning for NVME-over-fabric storage

A system for facilitating an integrated traffic profile for indicating congestion and packet drop is provided. During operation, the system can determine a first traffic profile indicating whether to drop a packet based on the utilization of a queue. The packets from the queue can be forwarded via an egress port reachable via a fabric. The system can also determine a second traffic profile indicating whether to indicate congestion in the packet based on the utilization. The system can then determine a third traffic profile by combining the first and second traffic profiles. The third traffic profile can indicate acceptance at the queue for a subset of packets being selected for dropping based on the utilization. Subsequently, the system can, if the packet is selected for dropping, determine whether to accept the packet at the queue and set a congestion indicator in the packet based on the third traffic profile.

Integrated traffic profile for indicating congestion and packet drop for congestion avoidance

A system for facilitating an enhanced traffic profile is provided. During operation, the system can determine a first traffic profile indicating whether to drop a packet based on the utilization of a queue. The packets from the queue can be forwarded via an egress port reachable via a fabric. The system can also determine a second traffic profile indicating whether to indicate congestion in the packet based on the utilization. The system can then determine a third traffic profile by combining the first and second traffic profiles. The third traffic profile can indicate acceptance at the queue for a subset of packets with a low-level congestion indicator or selected for dropping based on the utilization. Subsequently, the system can, if the packet is selected for dropping, determine whether to accept the packet at the queue with a high-level congestion indicator in the packet based on the third traffic profile.

Integrated traffic profile for indicating multi-level congestion and packet drop for congestion avoidance

Embodiments herein relate to running a distributed file system on a network switch. The distributed file system is to manage access to a plurality of storage drives that store data and are connected to the network switch.

Distributed file system at network switch

Example embodiments disclosed herein relate to selectively removing or resetting a restriction from a restricted power sourcing network port. A presence of a computing device coupled to one of a plurality of power sourcing network ports off a network device is determined. A power allocation to the power sourcing network port is determined. The computing device is authenticated to determine whether the computing device has permission to receive power from the network device. The power allocation is restricted. The restriction is selectively reset or removed.

Power sourcing network port reset

A method for configuration of a network device is described herein. Counter information for one or more ports of a plurality of ports of the network device is managed. The one or more ports are aggregated to a logical port in a logical communication channel. The counter information may be determined by the network device. A current load balancing algorithm is determined. The current load balancing algorithm is set for use on network packets on egress out of the logical port. Statistics are determined using the counter information and the current load balancing algorithm. Based on the statistics, the network device is configured with an available load balancing algorithm of a plurality of load balancing algorithms available to the network device.

Method for configuration of a load balancing algorithm in a network device

One embodiment relates to a method for automated correction of duplex mismatches. A duplex mismatch is detected at a port of a network device, and characteristics of the duplex mismatch are determined. The configuration of the mismatched port is automatically modified based upon said characteristics. Another embodiment relates to an apparatus for automated correction of duplex mismatches. The apparatus includes a duplex mismatch detector and an automated duplex mismatch fixer. The duplex mismatch detector is configured to detect a duplex mismatch at a port of a network device and to determine characteristics of the duplex mismatch. The automated duplex mismatch fixer is configured to modify a configuration of the mismatched port based upon said characteristics. Other embodiments and features are also disclosed.

Automated correction of duplex mismatches

In an embodiment, a method for finding duplex mismatches in a copper based network, includes: detecting late collisions and cyclic redundancy check (CRC) errors; if a port is in auto-negotiation and up in half-duplex and over threshold late collisions have been detected, then informing the user of a duplex mismatch and suggesting to the user to set the port to full duplex; and if the port is in forced full-duplex mode and over threshold CRC errors have been detected, then informing the user of a duplex mismatch and suggesting to the user to set the port to auto-negotiations mode.

Growing community of inventors

Granite Bay, CA, United States of America

Giuseppe Scaglione