Dynamisches Anpassen und Begrenzen der Größe des Netzwerkadapterspeichers zur Speicherung von Umsetzungseinträgen für virtuelle Funktionen

    公开(公告)号:DE112012003342T5

    公开(公告)日:2014-04-24

    申请号:DE112012003342

    申请日:2012-07-13

    Applicant: IBM

    Abstract: Es wird ein Ansatz bereitgestellt, bei dem ein System eine erste virtuelle Funktion aus einer Vielzahl virtueller Funktionen auswählt, die auf einem Netzwerkadapter ausgeführt werden, der einen Speicherbereich aufweist. Als Nächstes ordnet das System im Speicherbereich einen Speicher zu, der der ersten virtuellen Funktion entspricht. Das System speichert anschließend einen oder mehrere Umsetzungseinträge in der zugeordneten Speicherpartition, die zum Senden von Daten genutzt werden, die die erste virtuelle Funktion durchqueren. Das System an sich sendet die Datenpakete unter Nutzung eines oder mehrerer der Umsetzungseinträge vom Netzwerkadapter an ein oder mehrere Ziele. Im Gegenzug ändert das System dynamisch die Größe der Speicherpartition auf der Grundlage einer Größe der Speicherpartition, die zur Speicherung des einen oder der mehreren Umsetzungseinträge genutzt wird.

    Link layer reservation of switch queue capacity

    公开(公告)号:GB2502235B

    公开(公告)日:2014-04-02

    申请号:GB201316080

    申请日:2012-02-15

    Applicant: IBM

    Abstract: A network switch, in response to receipt from a source station of a Layer 2 reservation request, establishes a reservation for capacity of an ingress queue of the network switch for a data flow of the source station. In response to a queue overrun condition on the ingress queue of the network switch while the reservation is active, the network switch preserves data frames in the data flow of the source station transmitted pursuant to the reservation and discards other data frames.

    Link layer reservation of switch queue capacity

    公开(公告)号:GB2502235A

    公开(公告)日:2013-11-20

    申请号:GB201316080

    申请日:2012-02-15

    Applicant: IBM

    Abstract: A network switch, in response to receipt from a source station of a Layer 2 reservation request, establishes a reservation for capacity of an ingress queue of the network switch for a data flow of the source station. In response to a queue overrun condition on the ingress queue of the network switch while the reservation is active, the network switch preserves data frames in the data flow of the source station transmitted pursuant to the reservation and discards other data frames.

    35.
    发明专利
    未知

    公开(公告)号:DE60205952D1

    公开(公告)日:2005-10-06

    申请号:DE60205952

    申请日:2002-10-28

    Applicant: IBM

    Abstract: A data processing network and system in which a network connection is enabled to migrate among a multitude of available servers and/or clients to provide the connection using the most efficient available set of resources. Typically a server and client would indicate their respective support of this connection migration feature when the connection is established. An operating system or application program would monitor existing connections for characteristics including basic functionality and performance. If an existing connection were found to be faulty or low performing and the client and sever associated with the connection supported connection migration, the software would then determine if an alternative and more effective connection existed. Upon discovering such a connection, the parameters that define the connection would be altered to migrate the connection to the preferred hardware. In an embodiment in which the network connections are established with a transmission control protocol (TCP), each connection includes a four-tuple that completely defines the connection, namely, a source IP address, a source port number, a destination IP address, and a destination port number. By altering one or more of the connection's defining four-tuple, the invention is configured to migrate the connection to a NIC or system that is functioning more efficiently.

    METHOD, SYSTEM AND ARTICLE FOR DYNAMIC REAL-TIME STREAM AGGREGATION IN A NETWORK

    公开(公告)号:CA2535759A1

    公开(公告)日:2005-05-06

    申请号:CA2535759

    申请日:2004-08-31

    Applicant: IBM

    Abstract: A graphic user interface of a network client (106) includes a stock ticker from a stock server (110) and a news sidebar from a news server (112) over t he IP addresses advertised to the client (106) in its list of mutli-homed addresses from the video server (104) specified under Stream Control Transmission Protocol (SCTP). The client accepts real-time data from the sto ck exchange server and the news agency server on the multi-homed IP addresses designated in the association with the video server (104) without knowing th at the data is coming from a different source than the video server (104) . The real~time data feeds from the video, stock and news servers are aggregated o n the client (106) with enhanced speed because the feeds come directly to the client and not via the video server. The operating systems of the home serve r and remote servers utilize SCTP and specialized commands to implement the enhanced speed of real-time data aggregation being streamed to network clien ts without requiring modifications to existing client systems.

    Erweiterte Verbindungszusammenfassung (LAG) zur Nutzung in mehreren Switsches

    公开(公告)号:DE112013006420B4

    公开(公告)日:2018-10-25

    申请号:DE112013006420

    申请日:2013-12-11

    Applicant: IBM

    Abstract: Ein System (300) zum Bereitstellen von einer Verbindungszusammenfassung (LAG) für heterogene Switches (310), wobei das System (300) aufweist:mindestens zwei mit einem Server (302) verbundene Switches (310), die mit einer Switch-Steuerung (306) verbunden sind, wobei jeder Switch (310) über eine Mehrzahl von Verbindungen (308) verbunden ist, wobei die mindestens zwei Switches (310) miteinander über Inter-Switch-Verbindungen (ISLs) miteinander verbunden sind, und wobei der Server (302) aufweist:Logik angepasst für ein Senden einer LAG-Anforderung über jede Verbindung (308) zu jedem der mindestens beiden Switches (310), um eine Mehrzahl von LAG-Gruppen zu bilden, wobei eine LAG-Gruppe für jeden der mindestens beiden Switches (310) inklusive aller zwischen ihnen bestehenden Verbindungen (308) gebildet wird,wobei jeder der mindestens zwei Switches (310) aufweist:Logik angepasst für eine Empfangen der LAG-Anforderung von dem Server (302), undLogik angepasst zum Weiterleiten der LAG-Anforderung an die Switch-Steuerung (306), die in elektrisch-kommunikativer Verbindung mit den mindestens zwei Switches (310) steht,wobei die Switch-Steuerung (306) aufweist:Logik angepasst zum Empfangen der weitergeleiteten LAG-Anforderungen von den mindestens zwei Switches (310),Logik angepasst zum Bestimmen, dass die Mehrzahl der LAG-Anforderungen durch den entsprechenden Server (302) empfangen wurden,Logik angepasst zum Gruppieren der Mehrzahl der LAG-Anforderungen in LAG-Gruppen entsprechend einem Switch (310), von dem sie empfangen wurden,Logik angepasst zum Korrelieren aller der LAG-Gruppen mit dem Server (302),Logik angepasst zum Anweisen jeder der mindestens zwei Switches (310), eine LAG-Gruppe mit dem Server (302) entsprechend den LAG-Gruppen, die durch die Switch-Steuerung (306) bestimmt wurden, einzurichten, undLogik angepasst zum Erzeugen von alternierenden Flows, die Flows durch jeden der mindestens zwei Switches (310) zu dem Server (302) entsprechend zu Anweisungen der Switch-Steuerung (306) entsprechen.

    Providing services to virtual overlay network traffic

    公开(公告)号:GB2521572B

    公开(公告)日:2016-03-23

    申请号:GB201506949

    申请日:2013-09-26

    Applicant: IBM

    Abstract: In one embodiment, an apparatus includes a processor and logic integrated with and/or executable by the processor. The logic is configured to communicate with a first physical switch, a second physical switch, and an overlay network that connects the first physical switch to the second physical switch. The logic is also configured to receive a request for a communication path through the overlay network for a packet, the request including at least the packet, first information about a source of the packet, the source of the packet being connected to the first physical switch, and second information about a most closely connected physical switch to a destination of the packet. Moreover, the logic is configured to determine the destination of the packet, the destination of the packet being connected to the second physical switch. Also, the logic is configured to determine whether to apply a security policy to the packet.

    Extended link aggregation (LAG) for use in multiple switches

    公开(公告)号:GB2524218B

    公开(公告)日:2015-11-04

    申请号:GB201513185

    申请日:2013-12-11

    Applicant: IBM

    Abstract: In one embodiment, a method for providing link aggregation (LAG) to heterogeneous switches includes receiving, at a switch controller, LAG requests forwarded by switches and determining that multiple LAG requests corresponding to a server have been received, grouping the multiple LAG requests into LAG groups according to a switch from which they were received and correlating all the LAG groups with the server, instructing each of the switches to setup a LAG group with the server according to the LAG groups determined by the switch controller, and creating alternate flows that correspond to flows through each of the switches to the server through direction from the switch controller. The switches may rely upon OpenFlow to communicate with the switch controller, in some approaches. In addition, other methods for providing LAG to heterogeneous switches are also described, along with systems and computer program products which provide LAG to heterogeneous switches.

    Network adapter hardware state migration discovery in a stateful environment

    公开(公告)号:GB2510508B

    公开(公告)日:2015-07-08

    申请号:GB201407146

    申请日:2012-09-26

    Applicant: IBM

    Abstract: An approach is provided in which a discovery system receives a migration request to move a virtual machine that executes on a first system. The discovery system identifies a first network adapter corresponding to the first system, and identifies hardware state data used by the first network adapter to process data packets generated by the virtual machine. In turn, the discovery system identifies a second network adapter that is compatible with a native format of the hardware state data, and migrates the virtual machine to a second system corresponding to the identified second network adapter.

Patent Agency Ranking