A computing system uses a memory for storing data, one or more clients for generating network traffic and a communication fabric with network switches. The network switches include centralized storage structures, rather than separate input and output storage structures. The network switches store particular metadata corresponding to received packets in a single, centralized collapsing queue where the age of the packets corresponds to a queue entry position. The payload data of the packets are stored in a separate memory, so the relatively large amount of data is not shifted during the lifetime of the packet in the network switch. The network switches select sparse queue entries in the collapsible queue, deallocate the selected queue entries, and shift remaining allocated queue entries toward a first end of the queue with a delay proportional to the radix of the network switches.

Implementations are provided herein for accepting operations asynchronously in a particular order and efficiently committing them into an append-only log while preserving relative order. Operations that are dependent on one or more operations prior to it in the log will be guaranteed to fail, and not accepted, if any of the prior operations failed. If an operation succeeds, it is guaranteed that all operations it depended on are also successful.

The present disclosure discloses a method and an apparatus for adjusting a working status of an aggregated link. The method includes: when determining to switch a modulation mode of a first sub-link of an aggregated link from a first modulation mode to a second modulation mode, determining a transmission delay of transmitting a data slice in the second modulation mode by using the first sub-link; comparing the transmission delay of transmitting a data slice in the second modulation mode by using the first sub-link with a transmission delay of transmitting a data slice by using another sub-link of the aggregated link, to obtain a difference; and if the difference meets a preset condition, sending information for controlling a working status of the first sub-link to a transmit end device, so that the transmit end device controls the working status of the first sub-link in the second modulation mode.

A bandwidth control method, apparatus, and a device, in the field of computer technologies includes determining an upper bandwidth limit of the device when providing a service for registered clients, resetting an upper bandwidth limit of each client based on a working status of each client and the upper bandwidth limit of the device, and reallocating a bandwidth to each client based on the upper bandwidth limit of each client.

Detection of the congestion on a link based on an exchange of messages between a sender and a receiver, one sender and several receivers or several senders and one receiver. This equipment is connected to the ends of a transmission channel. One of the items of equipment is designated as the master and the others slaves. These exchanges are aimed at enabling the master to calculate and compare the rate of the data send and the rate of the data received. A divergence in the rates calculated reveals a congestion on the link. All these exchanges are made in the application layer and therefore do not involve the underlying layers.

A method for performing in-band operations, administration, and management (OAM) using fixed bytes. According to one aspect, data packets are selected from a packet flow according to a sampling rate. A network device's OAM information is inserted into a fixed length field of each selected packet as a selected packet is processed by the network device.

The provision of redundancy in a sync network, which protects the sync network against faults, such as broken cables in the sync network. The gateway comprises a sync propagation module configured to provide redundant sync requests that are sent along different pathways in the sync network. These sync requests are sent to towards different masters in the sync network. If a fault occurs at a point in one of the paths, the gateway will still receive a sync acknowledgment returned along the other path. Furthermore, the use of redundant sync networks, propagating the sync requests across different paths, allows fault detection in the wiring to be detected.

A computing system uses a memory for storing data, one or more clients for generating network traffic and a communication fabric with network switches. The network switches include centralized storage structures, rather than separate input and output storage structures. The network switches store particular metadata corresponding to received packets in a single, centralized collapsing queue where the age of the packets corresponds to a queue entry position. The payload data of the packets are stored in a separate memory, so the relatively large amount of data is not shifted during the lifetime of the packet in the network switch. The network switches select sparse queue entries in the collapsible queue, deallocate the selected queue entries, and shift remaining allocated queue entries toward a first end of the queue with a delay proportional to the radix of the network switches.

A token bucket or leaky bucket is maintained at least partially through the use of two separate counters. A full counter, is maintained in relatively lower cost memory, and indicates the amount of tokens within the bucket on a potentially delayed basis. An intermediate counter is stored in a relatively higher cost memory that supports high access rates, and indicates the amount of tokens assigned (or unassigned) to the bucket since the full counter was last updated. Various adjustment processes remove (or add) tokens as needed for performing tasks. A background process updates the full counter from the corresponding intermediate counter on a periodic, scheduled, or other basis. The buckets are replenished (or deleted) with tokens periodically at assigned rates. Traffic management or other decisions are based on the bucket's current status, as determined from the full counter during the background process and then stored in the higher cost memory.

A method for performing in-band operations, administration, and management (OAM) using fixed bytes. According to one aspect, data packets are selected from a packet flow according to a sampling rate. A network device's OAM information is inserted into a fixed length field of each selected packet as a selected packet is processed by the network device.