An object is to provide a communication apparatus, a communication method, and a program capable of avoiding an increase in network load when input traffic continues to be large and a communication delay when input traffic is very small. A communication apparatus according to the present invention prepares three token buckets and can transfer, discard, or hold a packet in accordance with the amount of tokens in each token bucket. This enables the communication apparatus to operate so as not to exceed a set maximum bandwidth when large traffic is received for the delay guarantee shaping. Further, When the maximum bandwidth is exceeded, the communication apparatus can select whether to discard a packet to prioritize a delay guarantee or to hold a packet to prioritize no loss of packets. Furthermore, the communication apparatus can immediately transmit a packet without increasing a communication delay when input traffic is very small.

An object is to provide a communication apparatus, a communication method, and a program capable of avoiding an increase in network load when input traffic continues to be large and a communication delay when input traffic is very small. A communication apparatus according to the present invention prepares three token buckets and can transfer, discard, or hold a packet in accordance with the amount of tokens in each token bucket. This enables the communication apparatus to operate so as not to exceed a set maximum bandwidth when large traffic is received for the delay guarantee shaping. Further, When the maximum bandwidth is exceeded, the communication apparatus can select whether to discard a packet to prioritize a delay guarantee or to hold a packet to prioritize no loss of packets. Furthermore, the communication apparatus can immediately transmit a packet without increasing a communication delay when input traffic is very small.

This application discloses a method for controlling traffic in a packet-based network. In the method, after receiving a control packet from a transmit end, an intermediate node between the transmit end and the receive end sends a control packet at the head of a first control queue based on a first duration, wherein the first duration is obtained based on a committed burst size (CBS) and a first committed information rate (CIR), and the intermediate node is configured to send a packet of a first transmit end to a first receive end in the packet-based network. After sending the control packet in the control queue, the intermediate node sends a first data packet set at the head of a data queue based on the sent control packet, wherein the first data packet set comprises C data packets, and C is an integer greater than or equal to 1

A method for managing network traffic is shown. The method includes establishing a virtual tunnel between a source endpoint and a destination endpoint, the virtual tunnel including a plurality of data flow paths, each of the plurality of data flow streams connecting the source endpoint and the destination endpoint. The method includes providing, via the destination endpoint, a plurality of credits to the source endpoint, the plurality of credits provided via two or more of the plurality of data flow paths. The method includes updating, at the source endpoint, a data transmission sequence based on the received plurality of credits. The method includes providing a plurality of data packets based on the data transmission sequence to the destination endpoint.

Systems and methods are provided for efficient handling of user requests to access shared resources in a distributed system, which handling may include throttling access to resources on a per-resource basis. A distributed load-balancing system can be logically represented as a hierarchical token bucket cache, where a global cache contains token buckets corresponding to individual resources whose tokens can be dispensed to service hosts each maintaining a local cache with token buckets that limit the servicing of requests to access those resources. Local and global caches can be implemented with a variant of a lazy token bucket algorithm to enable limiting the amount of communication required to manage cache state. High granularity of resource management can thus enable increased throttle limits on user accounts without risking overutilization of individual resources.

Systems and methods are provided for efficient handling of user requests to access shared resources in a distributed system, which handling may include throttling access to resources on a per-resource basis. A distributed load-balancing system can be logically represented as a hierarchical token bucket cache, where a global cache contains token buckets corresponding to individual resources whose tokens can be dispensed to service hosts each maintaining a local cache with token buckets that limit the servicing of requests to access those resources. Local and global caches can be implemented with a variant of a lazy token bucket algorithm to enable limiting the amount of communication required to manage cache state. High granularity of resource management can thus enable increased throttle limits on user accounts without risking overutilization of individual resources.

A method for managing adaptive streaming of an item of digital content within a multimedia stream reading terminal connected to a mobile communication network is disclosed. The item of digital content is associated with a description file for the item and includes a list of time segments of the item of content that are each associated with multiple encoding rates of the item of content. A maximum data volume to be consumed within the mobile communication network, as a data bucket, is allocated to the multimedia stream reading terminal. When the adaptive streaming of the item is launched, the method determines a data volume that would be consumed by the multimedia stream reading terminal as a result of streaming the time segments and selects a maximum encoding rate of the item authorized for the streaming on the basis of the consumed data volume associated therewith and of the data bucket.

A method for managing adaptive streaming of an item of digital content within a multimedia stream reading terminal connected to a mobile communication network is disclosed. The item of digital content is associated with a description file for the item and includes a list of time segments of the item of content that are each associated with multiple encoding rates of the item of content. A maximum data volume to be consumed within the mobile communication network, as a data bucket, is allocated to the multimedia stream reading terminal. When the adaptive streaming of the item is launched, the method determines a data volume that would be consumed by the multimedia stream reading terminal as a result of streaming the time segments and selects a maximum encoding rate of the item authorized for the streaming on the basis of the consumed data volume associated therewith and of the data bucket.

Embodiments include performing a host-initiated link reset in a storage area network (SAN). Aspects include identifying, by a host in communication with the SAN, each link in the SAN, wherein each link is defined by a pair of ports. Aspects also include obtaining, by the host, a buffer credit balance for each port in the SAN and obtaining, by the host, a buffer credit for each port in the SAN and causing a reset of a link associated with the port by transmitting a link reset record from the host to a control device of the link based on a determination that the buffer credit of a port in the SAN is below a threshold value.

Embodiments described herein are directed to utilizing a tokenized system to manage network bandwidth. A total network bandwidth availability is determined for a network, and a total number of tokens is determined for that total network bandwidth. The system also determines a total number of users for the network. When a user sends a network usage request to use or access the network, the system selects and allocates a number of tokens for the user based on the network usage request, the total number of network users, and the total number of tokens. The user's device can then access and use the network if the user has a sufficient number of available tokens for that usage. The number of tokens for the user is reduced based on the amount of data used by the user.