公开(公告)号：EP1609063A4

公开(公告)日：2009-03-11

申请号：EP03816813

申请日：2003-07-21

Applicant: IBM

Inventor： FREIMUTH DOUGLAS ,  MRAZ RONALD ,  NAHUM ERICH ,  PRADHAN PRASHANT ,  SAHU SAMBIT ,  TRACEY JOHN

IPC: G06F11/00 ,  H04B1/74 ,  H04L29/06 ,  H04L29/14

CPC classification number: H04L69/16 ,  H04B1/74 ,  H04L1/1809 ,  H04L1/1835 ,  H04L1/1874 ,  H04L69/12 ,  H04L69/161 ,  H04L69/163 ,  H04L69/40

Abstract: The present invention provides a method, computer program product, and data processing system for efficiently recovering state and performing failover of a network offload engine (904). The present invention distinguishes between the hard state and the soft state of a protocol. Hard state is state information that, when lost, leads to incorrect protocol behavior. Soft state is state information that may be lost or become inconsistent without loss of correctness. The present invention ensures correctness by always being able to recover (1002) the hard state of the protocol. A preferred embodiment of the present invention performs a failover of a network offload engine (904) by temporarily blocking (908) the reception of network packets, recovering (1002) hard state from host information, resuming network operation using a substitute network offload engine (906), and recovering (1008) soft state from the subsequent network activity.

公开(公告)号：AU2003259192A1

公开(公告)日：2004-11-23

申请号：AU2003259192

申请日：2003-07-21

Applicant: IBM

Inventor： TRACEY JOHN ,  FREIMUTH DOUGLAS ,  MRAZ RONALD ,  NAHUM ERICH ,  PRADHAN PRASHANT ,  SAHU SAMBIT

IPC: H04B1/74 ,  H04L69/40 ,  G06F11/00

Abstract: The present invention provides a method, computer program product, and data processing system for efficiently recovering state and performing failover of a network offload engine. The present invention distinguishes between the hard state and the soft state of a protocol. Hard state is state information that, when lost, leads to incorrect protocol behavior. Soft state is state information that may be lost or become inconsistent without loss of correctness. The present invention ensures correctness by always being able to recover the hard state of the protocol. A preferred embodiment of the present invention performs a failover of a network offload engine by temporarily blocking the reception of network packets, recovering hard state from host information, resuming network operation using a substitute network offload engine, and recovering soft state from the subsequent network activity.

公开(公告)号：DE112015003004T5

公开(公告)日：2017-03-23

申请号：DE112015003004

申请日：2015-06-22

Applicant: IBM

Inventor： KASHYAP VIVEK ,  KRAVETZ MICHAEL JOSEPH ,  NAHUM ERICH ,  MA XIULING

IPC: H04L45/74 ,  H04L47/40

Abstract: Es werden ein transparenter, leistungssteigernder Proxy, ein Verfahren zum Betreiben eines transparenten, leistungssteigernden Proxy zwischen einer Quelleneinheit und einer Zieleinheit und ein entsprechendes Computerprogrammprodukt bereitgestellt. Das Verfahren beinhaltet das Beibehalten, ohne Umsetzung, von Paket-Kopfbereichinformationen eines Kopfbereichs für ein von der Quelleneinheit empfangenes Paket, das an die Zieleinheit weitergeleitet werden soll. Das Verfahren beinhaltet des Weiteren das Beibehalten der Verbindungssemantik des Übertragungssteuerungsprotokolls während einer Verbindungsaufbauphase des Übertragungssteuerungsprotokolls für das Paket. Das Verfahren beinhaltet während einer Datenübertragungsphase des Übertragungssteuerungsprotokolls für das Paket auch das Ausführen eines Übertragungssteuerungsprotokolls, indem ein Ausgeben als Quelleneinheit gegenüber der Zieleinheit und ein Ausgeben als Zieleinheit gegenüber der Quelleneinheit erfolgt, um das Paket mit den beibehaltenen Paket-Kopfbereichinformationen an die Zieleinheit zu übertragen.

公开(公告)号：GB2498192A

公开(公告)日：2013-07-10

申请号：GB201200071

申请日：2012-01-04

Applicant: IBM

Inventor： NICHOLSON ROBERT ,  CILLIS CANIO ,  VERMA DINESH C ,  NAHUM ERICH ,  BILLAU RONALD ,  MOORE VICTOR ,  ANTHONY BRUCE JR ,  THORNE COLIN ,  BISDIKIAN CHATSCHIK

IPC: H04W8/08 ,  H04W76/02

Abstract: A method for moving OSI layer 4 connections (such as Transport Control Protocol TCP) seamlessly between wireless User Equipments (UE) connected to a series of cell towers in applications where the connection is extracted out of the underlying cellular protocols at the towers. On detecting that a UE with a broken-out layer 4 connection has moved from a first to a second cell tower, traffic for an existing connection from the UE is tunneled between the first cell-tower and the second cell-tower. On identifying a predetermined trigger event, which may be natural or forced quiescence at the terminal, an ongoing bidirectional flow of packets is migrated to the second cell-tower.

公开(公告)号：AT522865T

公开(公告)日：2011-09-15

申请号：AT03816813

申请日：2003-07-21

Applicant: IBM

Inventor： FREIMUTH DOUGLAS ,  MRAZ RONALD ,  NAHUM ERICH ,  PRADHAN PRASHANT ,  SAHU SAMBIT ,  TRACEY JOHN

IPC: G06F11/00 ,  H04B1/74 ,  H04L69/40

Abstract: The present invention provides a method, computer program product, and data processing system for efficiently recovering state and performing failover of a network offload engine. The present invention distinguishes between the hard state and the soft state of a protocol. Hard state is state information that, when lost, leads to incorrect protocol behavior. Soft state is state information that may be lost or become inconsistent without loss of correctness. The present invention ensures correctness by always being able to recover the hard state of the protocol. A preferred embodiment of the present invention performs a failover of a network offload engine by temporarily blocking the reception of network packets, recovering hard state from host information, resuming network operation using a substitute network offload engine, and recovering soft state from the subsequent network activity.

公开(公告)号：AT424583T

公开(公告)日：2009-03-15

申请号：AT05754067

申请日：2005-05-23

Applicant: IBM

Inventor： FREIMUTH DOUGLAS ,  HU ELBERTB ,  MRAZ RONALD ,  NAHUM ERICH ,  PRADHAN PRASHANT ,  SAHU SAMBIT ,  TRACEY JOHN M

IPC: G06F13/30 ,  G06F13/28

Abstract: A number of improvements in network adapters that offload protocol processing from the host processor are provided. Specifically, mechanisms for handling memory management and optimization within a system utilizing an offload network adapter are provided. The memory management mechanism permits both buffered sending and receiving of data as well as zero-copy sending and receiving of data. In addition, the memory management mechanism permits grouping of DMA buffers that can be shared among specified connections based on any number of attributes. The memory management mechanism further permits partial send and receive buffer operation, delaying of DMA requests so that they may be communicated to the host system in bulk, and expedited transfer of data to the host system.