Abstract: A method for managing OpenFlow communications between an OpenFlow Agent and an OpenFlow Controller is disclosed. The method involves extending the command line interface (CLI) based on distributed management task force (DTMF) server management command line protocol (SM CLP) exposed by an integrated Lights Out Management (LOM) software preexisting in enterprise class network equipment to support a plurality of OpenFlow targets, a plurality of verbs, and a plurality of properties, adding a managed element configured to provide handlers for each of the plurality of OpenFlow targets, registering the managed element for the plurality of OpenFlow targets with a manageability access point (MAP) entity, and configuring at least one of the plurality of properties to facilitate communication between an OpenFlow Agent and an OpenFlow Controller within the enterprise class network equipment using the plurality of OpenFlow targets, the plurality of verbs, and the plurality of properties.

Abstract: A source system executing applications in a multiprocessing environment supports transmission control protocol (TCP) connections. In an embodiment, the source system maintains a corresponding list of transmission control blocks (TCBs) for each processing entity. When an application executing on a first processing entity in the source system requests a new TCP connection to a destination system, an open TCP connection request is transmitted to said destination system on a network. A first TCB for the new TCP connection may be formed, indicating that the connection is in the process of being established. The connection may be allocated to a second processing entity, and the first TCB may be migrated as a second TCB, which is included in a list of TCBs associated with the second processing entity.

Abstract: An aspect of the present disclosure provides for migration of a virtual machine (VM) on a switched-fabric based computing system to another (external) switched-fabric based computing system or non-switched-fabric based (external) computing system. Both of such external computing systems are communicatively coupled to the switched-fabric based computing system by Internet such that the data transfer after the migration is based on IP packets on the Internet. According to another aspect of the present disclosure, an appliance contains multiple nodes for hosting virtual machines. A switched fabric switches packets between the nodes based on point-to-point connections between each pair of ports, wherein each port is coupled directly to a corresponding node. A bridge supports migration of a first VM to a first external system coupled to the first appliance by Internet Protocol (IP) based network.

Abstract: Inter-layer communication of events between different concurrent execution entities, where a Transmission Control Protocol (TCP) layer instance executes in a first execution entity and a higher layer instance executes in a second execution entity. In an example transaction, the first execution entity receives a TCP packet, and the TCP layer instance in the first execution entity generates an event message by processing the received TCP packet. The TCP layer instance thereafter stores the event message in an event queue at the second execution entity. The second execution entity identifies the presence of the event message in the event queue (e.g., by polling) and updates a first data structure, subsequent to the processing of the event message by the higher layer instance in the second execution entity. In an embodiment, the updated first data structure corresponds to application control block (ACB) maintained for each TCP connection.

Abstract: An aspect of the present disclosure provides for migration of a virtual machine (VM) on a switched-fabric based computing system to another (external) switched-fabric based computing system or non-switched-fabric based (external) computing system. Both of such external computing systems are communicatively coupled to the switched-fabric based computing system by Internet such that the data transfer after the migration is based on IP packets on the Internet. According to another aspect of the present disclosure, an appliance contains multiple nodes for hosting virtual machines. A switched fabric switches packets between the nodes based on point-to-point connections between each pair of ports, wherein each port is coupled directly to a corresponding node. A bridge supports migration of a first VM to a first external system coupled to the first appliance by Internet Protocol (IP) based network.

Abstract: An aspect of the present disclosure provides for migration of a virtual machine (VM) on a switched-fabric based computing system to another (external) switched-fabric based computing system or non-switched-fabric based (external) computing system. Both of such external computing systems are communicatively coupled to the switched-fabric based computing system by Internet such that the data transfer after the migration is based on IP packets on the Internet. According to another aspect of the present disclosure, an appliance contains multiple nodes for hosting virtual machines. A switched fabric switches packets between the nodes based on point-to-point connections between each pair of ports, wherein each port is coupled directly to a corresponding node. A bridge supports migration of a first VM to a first external system coupled to the first appliance by Internet Protocol (IP) based network.

Abstract: An aspect of the present disclosure provides deep packet inspection (DPI) of network packets for keywords of a vocabulary. In one embodiment, a mapping specifying association of respective keywords to corresponding unique pattern codes is maintained, with each pattern code being shorter in length compared to the corresponding keyword and being computed based on a formula. Upon receiving a network packet, a token (containing a sequence of characters) present in the network packet is first identified and the formula then applied to the identified token to generate a token code. The token is determined to match a specific keyword when the token code equals the pattern code corresponding to the specific keyword in the mapping.

Abstract: A method for transport layer lookup involves receiving a first incoming transport layer packet, and searching a pointer cache for a first matching transport layer data structure including state information corresponding to the first incoming packet. The pointer cache includes pointer cache lines, each of which stores at least one pointer to a subset of global transport layer data structures. The method further involves returning the state information corresponding to the first incoming packet using the first matching transport layer data structure when a pointer cache hit occurs, receiving a second incoming transport layer packet, searching the pointer cache for a second matching transport layer data structure including state information corresponding to the second incoming packet, and searching the plurality of global transport layer data structures in main memory to obtain the matching second transport layer data structure, when a pointer cache miss occurs.

Abstract: An aspect of the present invention reduces blocking instances in parallel processing systems performing operations on trees. In one embodiment, a change operation is performed in a first execution entity and a traversal operation is performed in a second execution entity, with both the change operation and the traversal operation being designed to operate on a same node of a tree, and with the first execution entity and the second execution entity being executed concurrently in a digital processing system. A non-blocking access of the same node to both of the first execution entity and the second execution entity is permitted, thereby enabling the change operation and the traversal operation to be performed concurrently.

Abstract: Providing unblocked read operations concurrent with write operations with respect to shared data resources in parallel processing systems. In an embodiment, for each data resource, a pair of fields and an index field is maintained. The index field indicates which of the two fields (e.g., first field) stores a current value for the data resource. However, when a new value is to be stored for the data resource, the value is first stored in the second field using a execution entity, while ensuring exclusive access for the execution entity to the second field. The index field is then updated to indicate that the second field stores the current value, such that the new value in the second field is thereafter available as the current value for read operations. All read operations by any corresponding concurrent execution entities, during the write operation, are continued unblocked.

Abstract: Inter-layer communication of events between different concurrent execution entities, where a Transmission Control Protocol (TCP) layer instance executes in a first execution entity and a higher layer instance executes in a second execution entity. In an example transaction, the first execution entity receives a TCP packet, and the TCP layer instance in the first execution entity generates an event message by processing the received TCP packet. The TCP layer instance thereafter stores the event message in an event queue at the second execution entity. The second execution entity identifies the presence of the event message in the event queue (e.g., by polling) and updates a first data structure, subsequent to the processing of the event message by the higher layer instance in the second execution entity. In an embodiment, the updated first data structure corresponds to application control block (ACB) maintained for each TCP connection.

Abstract: An aspect of the present disclosure provides for migration of a virtual machine (VM) on a switched-fabric based computing system to another (external) switched-fabric based computing system or non-switched-fabric based (external) computing system. Both of such external computing systems are communicatively coupled to the switched-fabric based computing system by Internet such that the data transfer after the migration is based on IP packets on the Internet. According to another aspect of the present disclosure, an appliance contains multiple nodes for hosting virtual machines. A switched fabric switches packets between the nodes based on point-to-point connections between each pair of ports, wherein each port is coupled directly to a corresponding node. A bridge supports migration of a first VM to a first external system coupled to the first appliance by Internet Protocol (IP) based network.

Abstract: A method for managing OpenFlow communications between an OpenFlow Agent and an OpenFlow Controller is disclosed. The method involves extending the command line interface (CLI) based on distributed management task force (DTMF) server management command line protocol (SM CLP) exposed by an integrated Lights Out Management (LOM) software preexisting in enterprise class network equipment to support a plurality of OpenFlow targets, a plurality of verbs, and a plurality of properties, adding a managed element configured to provide handlers for each of the plurality of OpenFlow targets, registering the managed element for the plurality of OpenFlow targets with a manageability access point (MAP) entity, and configuring at least one of the plurality of properties to facilitate communication between an OpenFlow Agent and an OpenFlow Controller within the enterprise class network equipment using the plurality of OpenFlow targets, the plurality of verbs, and the plurality of properties.

Abstract: A source system executing applications in a multiprocessing environment supports transmission control protocol (TCP) connections. In an embodiment, the source system maintains a corresponding list of transmission control blocks (TCBs) for each processing entity. When an application executing on a first processing entity in the source system requests a new TCP connection to a destination system, an open TCP connection request is transmitted to said destination system on a network. A first TCB for the new TCP connection may be formed, indicating that the connection is in the process of being established. The connection may be allocated to a second processing entity, and the first TCB may be migrated as a second TCB, which is included in a list of TCBs associated with the second processing entity.

Abstract: A network node maintains a neighbor data structure in the form of a hash table containing multiple buckets for storing mapping entries, with each entry specifying a local address corresponding to a global address. The table is based on a hash function that generates a corresponding hash value for each global address. Each bucket is associated with a unique hash value and is implemented as a corresponding balanced tree containing a corresponding set of nodes, with each node storing a corresponding mapping entry. Upon receiving a lookup request containing a first global address, the node determines a first bucket by applying the hash function to the first global address, and then traverses a first tree corresponding to the first bucket to find a first entry having a global address equaling the first global address. Concurrent non-blocking access is permitted to various portions of the tree during changes in the tree.

Abstract: A method for transport layer lookup involves receiving a first incoming transport layer packet, and searching a pointer cache for a first matching transport layer data structure including state information corresponding to the first incoming packet. The pointer cache includes pointer cache lines, each of which stores at least one pointer to a subset of global transport layer data structures. The method further involves returning the state information corresponding to the first incoming packet using the first matching transport layer data structure when a pointer cache hit occurs, receiving a second incoming transport layer packet, searching the pointer cache for a second matching transport layer data structure including state information corresponding to the second incoming packet, and searching the plurality of global transport layer data structures in main memory to obtain the matching second transport layer data structure, when a pointer cache miss occurs.

Abstract: An aspect of the present disclosure provides deep packet inspection (DPI) of network packets for keywords of a vocabulary. In one embodiment, a mapping specifying association of respective keywords to corresponding unique pattern codes is maintained, with each pattern code being shorter in length compared to the corresponding keyword and being computed based on a formula. Upon receiving a network packet, a token (containing a sequence of characters) present in the network packet is first identified and the formula then applied to the identified token to generate a token code. The token is determined to match a specific keyword when the token code equals the pattern code corresponding to the specific keyword in the mapping.

Abstract: A network node maintains a neighbor data structure in the form of a hash table containing multiple buckets for storing mapping entries, with each entry specifying a local address corresponding to a global address. The table is based on a hash function that generates a corresponding hash value for each global address. Each bucket is associated with a unique hash value and is implemented as a corresponding balanced tree containing a corresponding set of nodes, with each node storing a corresponding mapping entry. Upon receiving a lookup request containing a first global address, the node determines a first bucket by applying the hash function to the first global address, and then traverses a first tree corresponding to the first bucket to find a first entry having a global address equaling the first global address. Concurrent non-blocking access is permitted to various portions of the tree during changes in the tree.

Abstract: An aspect of the present invention reduces blocking instances in parallel processing systems performing operations on trees. In one embodiment, a change operation is performed in a first execution entity and a traversal operation is performed in a second execution entity, with both the change operation and the traversal operation being designed to operate on a same node of a tree, and with the first execution entity and the second execution entity being executed concurrently in a digital processing system. A non-blocking access of the same node to both of the first execution entity and the second execution entity is permitted, thereby enabling the change operation and the traversal operation to be performed concurrently.

Abstract: Providing unblocked read operations concurrent with write operations with respect to shared data resources in parallel processing systems. In an embodiment, for each data resource, a pair of fields and an index field is maintained. The index field indicates which of the two fields (e.g., first field) stores a current value for the data resource. However, when a new value is to be stored for the data resource, the value is first stored in the second field using a execution entity, while ensuring exclusive access for the execution entity to the second field. The index field is then updated to indicate that the second field stores the current value, such that the new value in the second field is thereafter available as the current value for read operations. All read operations by any corresponding concurrent execution entities, during the write operation, are continued unblocked.