Certains contenus de cette application ne sont pas disponibles pour le moment.
Si cette situation persiste, veuillez nous contacter àObservations et contact
1. (WO2018224865) PROCÉDÉS ET NŒUDS DE RÉSEAU POUR ASSURER UNE RÉGULATION DE FLUX COORDONNÉE POUR UN GROUPE DE CONNECTEURS DANS UN RÉSEAU
Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

CLAIMS

What is claimed is:

1. A method performed by a receiver socket in a group of sockets in a network for providing flow control for the group, comprising:

advertising a minimum window as a message size limit to a sender socket when the sender socket joins the group;

receiving a message from the sender socket; and

upon receiving the message, advertising a maximum window to the sender socket to increase the message size limit, wherein the minimum window is a fraction of the maximum window.

2. The method of claim 1, wherein advertising the maximum window further comprises:

transitioning the sender socket from a joined state to an active state; and if a total number of sockets in the active state is within a threshold from an allowable number of active sockets, reclaiming capacity from a selected socket in the active state.

3. The method of claim 2, wherein the selected active socket is a least active socket among the sockets in the active state.

4. The method of claim 1, wherein advertising the maximum window further comprises:

transitioning the sender socket from a joined state to a pending state when a total number of sockets in an active state is equal to an allowable number of active sockets.

5. The method of claim 4, further comprising:

reclaiming capacity from a least active socket among the sockets in the active state; and

transitioning the sender socket from the pending state to the active state upon receiving the reclaimed capacity from the least active socket.

6. The method of claim 3 or claim 5, wherein reclaiming the capacity further comprises:

reclaiming the capacity from the least active socket by reducing the message size limit of the least active socket to the minimum window.

7. The method of any one of claims 1-5, wherein a combined total capacity provided by the receiver socket to peer members in the group is a sum of the maximum window multiplied by the number of active sockets in the group and the minimum window multiplied by the number of non-active sockets in the group.

8. The method of claim 7, further comprising:

updating, by the receiver socket, an advertised window after receiving the message from the sender socket, wherein the advertised window keeps track of an available capacity provided to the sender socket; and

when the advertised window is below a predetermined limit, replenishing the available capacity provided to the sender socket to the maximum window.

9. The method of any one of claims 1-5, wherein the receiver socket is selected as a recipient of an anycast message from a subset of the sockets associated with a same member identifier, based on, at least in part, a load level of the receiver socket.

10. A method performed by a sender socket in a group of sockets in a network for providing sequence control for the group, comprising:

sending a first message from the sender socket to a peer member socket by unicast;

detecting that a second message from the sender socket, which immediately follows the first message, is to be sent by broadcast; and

sending the second message by replicated unicasts, in which the second message is replicated for all destination nodes and each replicated second message is sent by unicast.

11. The method of claim 10, further comprising:

blocking a next broadcast message until all of the destination nodes have acknowledged receipt of the replicated unicasts.

12. The method of claim 10 or claim 11, further comprising:

subsequent to receiving acknowledgements from all of the destination nodes, determining whether to send the next broadcast message by broadcast or by replicated unicasts based on the number of the destination nodes in the group versus a size of a cluster in which the destination nodes are located.

13. The method of claim 10, further comprising:

broadcasting a message in the group with a first broadcast sequence number; and sending a unicast message immediately after the broadcast message with a second broadcast sequence number that uniquely identifies the first broadcast sequence number.

14. The method of claim 13, further comprising:

sending one or more subsequent unicast messages with the second broadcast sequence number until a next broadcast is sent.

15. A node containing a receiver socket in a group of sockets in a network, the node adapted to perform flow control for communicating with the sockets in the group, comprising:

a circuitry adapted to cause the receiver socket in the node to:

advertise a minimum window as a message size limit to a sender socket when the sender socket joins the group;

receive a message from the sender socket; and

upon receiving the message, advertise a maximum window to the sender socket to increase the message size limit, wherein the minimum window is a fraction of the maximum window.

16. The node of claim 15, wherein the circuitry comprises a processor, a memory and an interface both coupled with the processor, the memory containing instructions that when executed cause the processor to perform operations of advertising the minimum window, receiving the message and advertising the maximum window.

17. The node of claim 15, wherein the circuitry is further adapted to cause the receiver socket in the node to:

transition the sender socket from a joined state to an active state when receiving the message; and

if a total number of sockets in the active state is within a threshold from an allowable number of active sockets, reclaim capacity from a selected socket in the active state.

18. The node of claim 17, wherein the selected active socket is a least active socket among the sockets in the active state.

19. The node of claim 15, wherein the circuitry is further adapted to cause the receiver socket in the node to:

transition the sender socket from a joined state to a pending state when a total number of sockets in an active state is equal to an allowable number of active sockets.

20. The node of claim 19, wherein the circuitry is further adapted to cause the receiver socket in the node to:

reclaim capacity from a least active socket among the sockets in the active state; and

transition the sender socket from the pending state to the active state upon receiving the reclaimed capacity from the least active socket.

21. The node of claim 18 or claim 20, wherein the circuitry is further adapted to cause the receiver socket in the node to:

reclaim the capacity from the least active socket by reducing the message size limit of the least active socket to the minimum window.

22. The node of any one of claims 15-20, wherein a combined total capacity provided by the receiver socket to peer members in the group is a sum of the maximum window multiplied by the number of active sockets in the group and the minimum window multiplied by the number of non-active sockets in the group.

23. The node of claim 22, wherein the circuitry is further adapted to cause the receiver socket in the node to:

update an advertised window after receiving the message from the sender socket, wherein the advertised window keeps track of an available capacity provided to the sender socket; and

when the advertised window is below a predetermined limit, replenish the available capacity provided to the sender socket to the maximum window.

24. The node of any one of claims 15-20, wherein the receiver socket is selected as a recipient of an anycast message from a subset of the sockets associated with a same member identifier, based on, at least in part, a load level of the receiver socket.

25. A node containing a sender socket in a group of sockets in a network, the node adapted to perform sequence control for communicating with the sockets in the group, comprising:

a circuitry adapted to cause the sender socket in the node to:

send a first message to a peer member socket by unicast;

detect that a second message from the sender socket, which immediately follows the first message, is to be sent by broadcast; and

send the second message by replicated unicasts, in which the second message is replicated for all destination nodes and each replicated second message is sent by unicast.

26. The node of claim 25, wherein the circuitry comprises a processor, a memory and an interface both coupled with the processor, the memory containing instructions that when executed cause the processor to perform operations of the sending of the first message, the detecting, and the sending of the second message.

27. The node of claim 25, wherein the circuitry is further adapted to cause the sender socket in the node to:

block a next broadcast until all of the destination nodes have acknowledged receipt of the replicated unicasts.

28. The node of any one of claims 25-27, wherein the circuitry is further adapted to:

subsequent to receiving acknowledgements from all of the destination nodes, determine whether to send the next broadcast message by broadcast or by replicated unicasts based on the number of the destination nodes in the group versus a size of a cluster in which the destination nodes are located.

29. The node of claim 25, wherein the circuitry is further adapted to cause the sender socket in the node to:

broadcast a message in the group with a first broadcast sequence number; and send a unicast message immediately after the broadcast message with a second broadcast sequence number that uniquely identifies the first broadcast sequence number.

30. The node of claim 29, wherein the circuitry is further adapted to cause the sender socket in the node to send one or more subsequent unicast messages with the second broadcast sequence number until a next broadcast is sent.

31. A node containing a receiver socket in a group of sockets in a network, the node adapted to perform flow control for communicating with the sockets in the group, comprising:

a flow control module adapted to advertise a minimum window as a message size limit to a sender socket when the sender socket joins the group; and

an input/output module adapted to receive a message from the sender socket, wherein the advertisement module is further adapted to advertise, upon receiving the message, a maximum window to the sender socket to increase the message size limit, wherein the minimum window is a fraction of the maximum window.

32. A node containing a sender socket in a group of sockets in a network, the node adapted to perform sequence control for communicating with the sockets in the group, comprising:

an input/output module adapted to send a first message from the sender socket to a peer member socket by unicast; and

a sequence control module adapted to detect that a second message is to be sent by broadcast, which is immediately preceded by a first message sent from the sender socket by unicast,

wherein the input/output module is further adapted to send the second message by replicated unicasts, in which the second message is replicated for all destination nodes and each replicated second message is sent by unicast.

33. A method performed by a receiver socket in a group of sockets in a network for providing flow control for the group, comprising:

initiating an instantiation of a node instance in a cloud computing environment which provides processing circuitry and memory for running the node instance, said node instance being operative to:

advertise a minimum window as a message size limit to a sender socket when the sender socket joins the group;

receive a message from the sender socket; and

upon receiving the message, advertising a maximum window to the sender socket to increase the message size limit, wherein the minimum window is a fraction of the maximum window.

34. A method performed by a sender socket in a group of sockets in a network for providing sequence control for the group, comprising:

initiating an instantiation of a node instance in a cloud computing environment which provides processing circuitry and memory for running the node instance, said node instance being operative to:

send a first message from the sender socket to a peer member socket by unicast;

detect that a second message from the sender socket, which immediately follows the first message, is to be sent by broadcast; and

send the second message by replicated unicasts, in which the second message all destination nodes and each replicated second message is sent by unicast.