RussianPatents.com

Enabling network devices to run multiple congestion control algorithms. RU patent 2438162.

FIELD: information technology.

SUBSTANCE: network device for controlling congestion on one or more network connections between that network device and a data network comprises: a processor, memory, a network communications stack and congestion control modules.

EFFECT: enabling selection of a congestion control module from a plurality of available congestion control modules based on the connection.

15 cl, 1 tbl, 9 dwg

IPC classes for russian patent Enabling network devices to run multiple congestion control algorithms. RU patent 2438162. (RU 2438162):

G06F9/50 - Allocation of resources, e.g. of the central processing unit (CPU)

G06F15/173 -

Another patents in same IPC classes:

Reliable, efficient peer-to-peer storage / 2435206
Adaptive coding storage system which uses adaptive erasure resilient code (ERC) changes the number of fragments used for encoding according to the size of the distributed. Adaptive ERC may greatly improve the efficiency and reliability of P2P storage. A number of procedures for P2P storage applications may also be implemented. In one version small, dynamic data files are diverted to the more reliable peers or even a server, while large and static files are stored using the storage capacity of the unreliable peers. Also, for balanced contribution and benefit, a peer must host the same amount of content as it stored on the P2P network. As a result, unreliable peers are allowed to distribute less data, and more reliable peers are allowed to distribute more. Also, smaller files are assigned a higher distribution cost, and the larger files are assigned a lower distribution cost.

Method and apparatus for dynamic computations / 2433454
Invention provides a method of working with a group of nodes in a system for dynamic computations, having a coordinator node and a first computational node which communicate through a connection, and in which the first computational node is capable for executing a task for the coordinator node. The method comprises the following steps: at least one working parameter which indicates the quality of connection between two nodes is tracked; the quality parameter is determined based on the working parameter, wherein the quality parameter indicates the quality of connection between two nodes; and information is transferred from the first computational node to the coordinator node when the value of the quality parameter lies in the transfer interval, wherein the information contains information on part of the task executed by the first computational node.

Quality of service implementation for platform resources / 2431186
Method involves setting a quality of service (QoS) priority level value for one or more computer system platform resources, other than a central processor core, relating to a task running on the computer system, wherein one or more computer system platform resources include at least one a plurality of entries in the memory page table, which correspond to a plurality of memory pages of the computer system platform resources; independently allocating each memory page according to access priority based on the QoS priority level value set for each entry in the memory page table; and determining whether the one or more computer system platform resources will be allocated to the task based on the QoS priority level setting.

Two-input priority device / 2390825
Device has a pulse generator, six AND elements, a comparator circuit, a register, a counter, a logic inverter, a NAND element, three triggers, two pulse formers, two AND elements with non-inverting and inverting inputs and two OR elements.

Levelling network load through connection control / 2387002
Network load levelling module has connection transfer unit which can transfer connections from the said module, where the connection transfer unit can compile the protocol status for connection over a network stack; the connection transfer unit can aggregate the compiled protocol status with data for connection to the aggregated connection status for connection; the connection transfer unit can also initiate sending the aggregated connection status to a host; and a classifier which can accept a connection and give out a connection transfer instruction to the connection transfer unit. An information carrier contains instructions executed by a processor, which order the said module to carry out operations which include: reception from the packet of at least part of the source/destination pair; accessing the encapsulation mapping table using at least part of the source/destination pair and replacing part of the packet with a stream identifier in order to create an encapsulated packet.

Network load balancing using host status information / 2380746
In the first implementation, a media available for processor contains commands which being executed by processor instruct system to perform: accumulation of host status information on multiple hosts and sending accumulated host status information from multiple hosts. In the second implementation, a media available for processor contains commands executed by processor which instruct system to perform: receiving host status information from multiple hosts and making decisions on load balancing in accordance with received host status information. In the third implementation, a media available for processor contains commands executed by processor which instruct system to perform actions: determination of operability and load information for each application; and selection of application from multiple applications according to operability and load information.

Programmable object model for supporting library of name or scheme spaces in programme application / 2371759
Library contains XML-scheme files and appropriate XML-oriented resources for connecting the scheme files to one or more documents and for setting the functional capabilities connected to scheme files and XML-oriented resources. The above programmable object model also provides the possibility to user/programmer to delete scheme files and other XML-oriented resources from the connection to the previously connected documents.

Multichannel priority device / 2364920
Invention concerns computer facilities and can be used for guidance of access of several objects to collectively used resource. The multichannel priority device contains channels, a coding device, the device OR, group of the keys, which number corresponds to number of the channels, thus each channel contains the trigger.

Multi-channel device for priority servicing of queries / 2322689
Device contains impulse generator, AND elements, counters, comparison circuit, register, NOT element, OR elements, delay element, decoder, impulse generator, OR-NOT element, modulo two adder, M channels, each channel containing an AND element, OR element, AND element with direct and reverse inputs.

Method for switching context of tasks and procedures in a processor / 2320002
In accordance to the method, for each new task or procedure free resources are allocated in circular buffer of general purpose registers for data being processed, and in circular stack for switching contexts for data which characterize predetermined location for contexts in external memory. When circular buffer of general purpose registers or circular context switching stack are overflowed, saved contexts at hardware level are fully automatically displaced into memory, without using software means. The data from circular context switching stack make it possible to organize contexts displaced into memory in form of connected list, and to restore saved contexts when necessary.

Interaction between neighbourhoods within federation on rendezvous mechanism / 2433461
Messaging method in a federation infrastructure in a computer system, wherein the federation infrastructure is represented by a joined list of nodes, the joined list of nodes is divided into a hierarchical tree of rings, in which: a message is received in a sub-ring; it is determined whether the node belonging to the sub-ring must send a message to another sub-ring; intra-ring interaction is used within the sub-ring in order to identify the next node with an entry table of a set of side rings; inter-ring interaction is used to sent a message from the next node to an additional sub-ring on the same determined sub-ring level in order to bypass the root ring, which includes a step on which the next node accesses the node for entry into the additional sub-ring from the entry table of the set of side rings of the next node, and a step on which the next node sends a message to the node for entry into the additional sub-ring.

One-way switching matrix / 2424560
One-way switching matrix consists of controlled and non-controlled switches, having 2 ports in a first pair, 2 ports in a second pair and lying on n/2 lines-rows and k levels, wherein the controlled switches also have a bit input for the control code C.

System of gathering and processing information for integrated security system of facility / 2413293
System of gathering and processing information for integrated security systems of facilities has control computers, automated workstation computers and servers connected over an Ethernet. Control computers have multi-port devices whose like ports are connected in pairs through interface converters to groups of transceivers which are connected to interface converters. The transceivers are connected by communication lines to peripheral devices.

Routing in peer-to-peer networks / 2408064
Method of routing in a peer-to-peer network realised in one of the nodes of the network involves: obtaining broadcast indication in a node relative change in the composition of a network; and the program record of the state of the routing table (SSRT), having a set of the said SSRT records for each node is updated, where the said SSRT records describe current system membership; the leafset table which defines the hash space for the node is updated, the hash space has information on resources provided in the peer-to-peer network; the leafset table is maintained through periodic probing of at least one other node; and a table of directions having a set of records of the table of directions is maintained, where each of the said records of the table of directions describes the location of the corresponding node, where the table of directions is maintained by probing each of the said corresponding node indicted in the records of the table of directions.

System and method for downloading updates / 2405260
In computing unit the necessary update is determined from a list of available updates by scanning of computing device, being one of peer-to-peer units, to determine its current condition. Current condition is compared to list of available updates, besides the necessary update may be segmented into multiple parts. List of online computing units, which identify downloading of update, is received in computing unit from host. Update is downloaded into computing device as specified multitude of parts.

Link-port switch / 2405196
LINK-port switch has N LINK-ports, N LINK-port controllers, a switch matrix, a block of resistors, an address allocation protocol decoder, a replay message generator, a comparator circuit, a constant, a LINK-port counter, an RCP-2 former, each LINK-port further includes an input LINK-port, an input buffer register, an input LINK -port, a counter for selecting the input port, an allocation time-out counter, a comparator circuit, a constant, each LINK-port controller further includes a TL field modification unit, two JK flip-flop, three OR elements, FIFO buffer memory, a control state machine, a state register, ROM1 for the switching table, a multiplexer, a comparator circuit, a constant, ROM2, five AND elements, an odd number control unit, a word counter, a control sum storage, a first heading register, a third heading word register, a unit for checking heading words.

Lower-bound estimate search device in fully connected matrix systems during one-way data transfer / 2398270
Device has a matrix comprising m rows and n columns of a homogeneous medium, n blocks for counting units, unit for finding the maximum, adders, a memory unit, a lower-bound estimate search unit which has a pulse generator, element selection multiplexers, row selection decoder, incidental vertex decoders, fixed arc decoders, row and column counters, fixed arc counters, incidental vertex counters, mode triggers, group of m triggers, group of m inhibit circuit units, matrix (i.j) (i=1.2,…, m, j=1.2,…,n) of fixed arc counters, matrix (i.j) (i=1.2,…, m, j=1.2,…,n) of OR elements, matrices (i.j) (i=1.2,…,m, j=1.2,…,n) of AND elements, an OR element, inverters, AND elements, group of m OR elements.

Simplified input/output protocol / 2388039
Invention relates to methods and systems for downloading I/O processes from a first computer onto a second computer using a network interconnection through RDMA. The method and system includes a client on the first computer provided with information through a RDMA connection with a server on the second computer through a simplified input/output protocol. Overall, the protocol includes a network detection step, followed by I/O processing. At the detection step, the client and the server determine the shortest list of shared providers capable of RDMA. During I/O processing, the client gives I/O requests for downloading from the second machine through a mutually authenticated channel. The I/O model is asymmetrical with reading operations carried out through traditional sending. Requests for reading and recording can be completed in poll mode and in interruption mode. Buffers are controlled through a confidence mechanism.

Software interface of applications for administration of software updates distribution in system of updates distribution / 2386218
Application program interface (API) provides for multiple interface calls, by means of which administrator may establish rules, in accordance to which software updates are distributed, being available for unit of updates servicing.

System and method of invitation for interaction / 2385487
Architecture (300) may include platform (302) of interaction services. Platform (302) of interaction services may include service (304) of contacts control, alarm service (306), activity service (310), service (312) of joint access to data, service (314) of authentication and service (316) of connectivity. Service (304) of contacts control may include storage (318) of contacts, storage (320) of presence and service (322) of contacts location. Publication service (306) may include service (324) of synchronisation. Alarm service (308) may include service (326) of invitation. Activity service (310) may include audio/video (A/V) service (328). Service (316) of connectivity may include peer-to-peer (P2P) service (330) and traditional protocol of transportation control and stack (332) of Internet protocol (TCP/IP). Each service (304), (306), (308), (310), (312), (314), (316) may include and/or be included with a peer-to-peer possibility for sending and receiving messages that realise the service.

Device for estimation of difference between current remoteness of position and optimal remoteness of position / 2263953
Device has matrix of m rows and n columns of homogeneous environment elements, block for finding maximum, adder, memory block, m blocks for counting units, block for estimation of channels load level, containing two pulse generators, two row selection decoders, unary value selection decoder, element selection decoder, element selection multiplexer, channel load decoder, two comparison elements, m channel load counters, two groups of m OR elements, two groups of m forbidding elements, current column counter, group of m AND elements, third group of m OR elements, two groups of m triggers, two row counters, two column counters, two OR elements, delay elements, counter of next column.