Abstract: System and method representing PMA attributes as SMA attributes in a high performance computing environment. In general legacy systems, performance metrics, as collected by a performance management agent, can only be collected via the use of general data packets traversing a subnet. In accordance with an embodiment, by configuring a SMA attribute to comprise the same performance metrics as collected by a PMA, a subnet manager, or another management component, can access the performance metrics in-band via the use of a subnet management packet.

Abstract: A system and method can support subnet management in a network environment. A network switch in the network environment can provide a transactional interface, wherein the transactional interface allows a user to interact with the network environment using a transaction. The transactional interface allows a user to group one or more operations in the transaction, and ensures that no conflicting operations are included in the transaction.

Abstract: A system and method can support subnet management in a network environment. One or more inactivated switches can be included in a subnet, wherein each of the inactivated switches is associated with an empty set of known secret keys. A subnet manager (SM) in a dry-run mode can perform one or more dry-run operations on the one or more inactivated switches, before activating the one or more inactivated switches.

Abstract: A system and method for supporting subnet management in a network environment is described. The system and method can be used in an engineered system for middleware and application execution, or a middleware machine environment. The system can associate a subnet administrator (SA) in a subnet with a plurality of SA proxies, each of which can receive plurality of requests from one or more client nodes. The SA can handle the requests, which are forwarded from the SA proxies. Additionally, each client node can be assigned a dedicated queue pair (QP) number, so that there is no need for always sending an initial request to a pre-defined well-known QP number.

Abstract: A system and method can implement highly available Internet Protocol (IP) based communication across multiple independent communication paths. The system can have different IP addresses associated with different interfaces and communication paths and can implement communication fail-over as part of the communication layers above the IP layer, e.g. at the application level. The system can provide a balance between an average fail-over time and implementation complexity, and can achieve simplicity and robustness while providing high communication performance.

Abstract: A system and method can support master negotiation in a network environment. A subnet manager (SM) can perform subnet discovery on a subnet in the network environment via a subnet manager (SM) in the subnet, wherein the subnet includes a plurality of SMs. Furthermore, the SM can communicate with the other SMs in the subnet to check for a number of known secret keys, and select a SM from the plurality of SMs as a master SM, wherein the master SM has the highest number of known keys.

Abstract: A system and method can support a middleware machine environment that includes a set of subnet manager instances, which reside on one or more nodes in the middleware machine environment and cooperate to provide a highly available subnet manager service within a subnet, wherein each said subnet manager instance is associated with a different private secure key. The subnet manager instances can negotiate with each other and elect a master subnet manager responsible for configuring and managing the middleware machine environment using the private secure key associated with the master subnet manager. The subnet can be reconfigured to be associated with a different private secure key, when a new subnet manager instance is elected as the master subnet manager. An old master subnet manager can be automatically prevented from resuming normal operations as the master subnet manager, in order to avoid undesired consequence such as a “split brain” scenario.

Abstract: A system and method can support subnet management in a network environment, such as an engineered system for middleware and application execution or a middleware machine environment. A subnet manager (SM) can retrieve information for setting up a reliable connection (RC) between a subnet administrator (SA) and a client node in a subnet. Furthermore, the system can set up one or more connection states for a port associated with the SM node to establish the RC connection between the port associated with the SM node and a port associated with said client node. Then, the SM can activate the port associated with said client node.

Abstract: A system and method can ensure Internet Protocol (IP) address and node name consistency when performing remote transactions via multiple un-related IP addresses for the same remote peer. The system can ensure that all cooperating peer nodes are in full agreement of the names and IP addresses at any point in time. In particular, when network configurations can be updated dynamically, the system can ensure that such updates do not lead to inconsistent or failed transactions because a peer node has a stale view of what addresses to use. Furthermore, the peer node that initiates the transaction can verify that all the other peer nodes have exactly the same view of the overall system configuration, in order to ensure that each distributed transaction is carried out using consistent address information.

Abstract: A system and method can support subnet management in a network environment, such as an engineered system for middleware and application execution or a middleware machine environment. The system can associate a subnet administrator (SA) in a subnet with one or more SA proxies. Furthermore, said one or more SA proxies can receive one or more requests from one or more client nodes. Then, said SA can handle said one or more requests, which are forwarded from said one or more SA proxies. Additionally, a dedicated queue pair (QP) number can be allocated for each client node, so that there is no need for always sending an initial request to a pre-defined well-known QP number.

Abstract: A system and method can support subnet management in a network environment, such as an engineered system for middleware and application execution or a middleware machine environment. A subnet manager (SM) can retrieve information for setting up a reliable connection (RC) between a subnet administrator (SA) and a client node in a subnet. Furthermore, the system can set up one or more connection states for a port associated with the SM node to establish the RC connection between the port associated with the SM node and a port associated with said client node. Then, the SM can activate the port associated with said client node.

Abstract: A system and method can use a secure subnet management agent (SMA) to perform fencing operations in an InfiniBand (IB) fabric. A host channel adapter (HCA) in the fabric can be associated with a plurality of ports, wherein the HCA operates to implement a SMA in its embedded firmware. Furthermore, the SMA operates to be used as a proxy, by a port on the HCA, for updating one or more states associated with another port on the HCA. The one or more states are associated with at least one of updating a management key and resetting a link at another port on the HCA.

Abstract: A system and method can provide subnet manager (SM) restrictions in an InfiniBand (IB) network. A first SM in a subnet in the IB network operates to determine whether a second SM associated with a remote port is trustworthy. Furthermore, the first SM is allowed to send at least one of a request and a response that contains a management key to the second SM, if the first SM determines that the second SM is trustworthy. Additionally, the first SM is prevented from attempting to initiate communication with the second SM, if otherwise.

Abstract: A system and method can ensure Internet Protocol (IP) address and node name consistency when performing remote transactions via multiple un-related IP addresses for the same remote peer. The system can ensure that all cooperating peer nodes are in full agreement of the names and IP addresses at any point in time. In particular, when network configurations can be updated dynamically, the system can ensure that such updates do not lead to inconsistent or failed transactions because a peer node has a stale view of what addresses to use. Furthermore, the peer node that initiates the transaction can verify that all the other peer nodes have exactly the same view of the overall system configuration, in order to ensure that each distributed transaction is carried out using consistent address information.

Abstract: A system and method can implement highly available Internet Protocol (IP) based communication across multiple independent communication paths. The system can have different IP addresses associated with different interfaces and communication paths and can implement communication fail-over as part of the communication layers above the IP layer, e.g. at the application level. The system can provide a balance between an average fail-over time and implementation complexity, and can achieve simplicity and robustness while providing high communication performance.

Abstract: A system and method can support security management in a network environment. A switch in the network environment includes a switch chip, which is configured with a secure management key (M_Key) prior to one or more external links becoming operational. Furthermore, a local daemon in the switch can monitor the secure M_key on the switch chip, and persistently store a current M_key used by a local subnet manager (SM). The current M_key is a state that is dynamically updated in a fabric in the network environment.

Abstract: A system and method can support master negotiation in a network environment. A subnet manager (SM) can perform subnet discovery on a subnet in the network environment via a subnet manager (SM) in the subnet, wherein the subnet includes a plurality of SMs. Furthermore, the SM can communicate with the other SMs in the subnet to check for a number of known secret keys, and select a SM from the plurality of SMs as a master SM, wherein the master SM has the highest number of known keys.

Abstract: A system and method can support subnet management in a network environment. A network switch in the network environment can provide a transactional interface, wherein the transactional interface allows a user to interact with the network environment using a transaction. The transactional interface allows a user to group one or more operations in the transaction, and ensures that no conflicting operations are included in the transaction.

Abstract: A system and method can support subnet management in a network environment. One or more inactivated switches can be included in a subnet, wherein each of the inactivated switches is associated with an empty set of known secret keys. A subnet manager (SM) in a dry-run mode can perform one or more dry-run operations on the one or more inactivated switches, before activating the one or more inactivated switches.

Abstract: A system and method can support automatic disabling of degraded links in an InfiniBand (IB) network. At least one node in a fabric can monitor one or more local ports of the at least one node for one or more error states associated with a link at the at least one node, wherein the link is connected to a local port of the at least one node. The at least one node further allows a subnet manager to observe the one or more error states associated with the link at the at least one node, and allows the subnet manager to set the link in a basic state if the observed error states exceed a threshold. In this basic state, the link allows only SMP traffic and prevents data traffic and non-SMP based management traffic.