Abstract: An application server may be instrumented to provide a resource measurement framework to collect resource usage data regarding request processing by the application server and applications executing on the application server. The resource measurement framework of an application server may collect hardware and software resource usage data regarding request processing at interception points located at interfaces between application components and services or other components of the application server by instrumenting those interfaces. The resource measurement framework may collect resource usage by instrumenting standard interfaces and/or methods of various specifications, such as implemented by containers or other components of the application server. Thus, the resource measurement framework may collect resource usage for applications or application components that do not include any resource measuring capabilities.

Abstract: A Sharing Data Fabric (SDF) causes flash memory attached to multiple compute nodes to appear to be a single large memory space that is global yet shared by many applications running on the many compute nodes. Flash objects stored in flash memory of a home node are copied to an object cache in DRAM at an action node by SDF threads executing on the nodes. The home node has a flash object map locating flash objects in the home node's flash memory, and a global cache directory that locates copies of the object in other sharing nodes. Application programs use an applications-programming interface (API) into the SDF to transparently get and put objects without regard to the object's location on any of the many compute nodes. SDF threads and tables control coherency of objects in flash and DRAM.

Abstract: A distributed database system has multiple compute nodes each running an instance of a database management system (DBMS) program that accesses database records in a local buffer cache. Records are persistently stored in distributed flash memory on multiple storage nodes. A Sharing Data Fabric (SDF) is a middleware layer between the DBMS programs and the storage nodes and has API functions called by the DBMS programs when a requested record is not present in the local buffer cache. The SDF fetches the requested record from flash memory and loads a copy into the local buffer cache. The SDF has threads on a home storage node that locate database records using a node map. A global cache directory locks and pins records to local buffer caches for updating by a node's DBMS program. DBMS operations are grouped into transactions that are committed or aborted together as a unit.

Abstract: A method and system for increasing reliability and availability of a multi-processor network. A system includes a network with at least two nodes, with each node comprising a multi-processor unit (mpu) and memory. The mpu includes one or more processors and a wiretap unit. The wiretap unit and the memory included in the node are coupled to the processors in the node. The wiretap unit is configured to monitor memory accesses of the processors and convey data indicative of such accesses to a second node. The second node maintains a replica of memory in the first node, and is configured to undo modifications to the memory if needed. In the event of a hardware or software fault, the nodes are configured to restart the application on another node.

Abstract: A system and method for controlling access to data in a distributed computer system. Distributed Token Manager (DTM) is a system-level service that coordinates read/write access of data objects (tokens) in a multi-process and multi-threaded environment. The DTM may support a transactional model such that write operations to a data object performed by a client process or thread can be either committed or rolled back.

Abstract: A cluster topology self-healing process is performed in order to replicate a data set stored on a failed node from a first node storing another copy of the data set to a second non-failed node. The self-healing process is performed by: locking one of several domains included in the data set, where locking that domain does not lock any of the other domains in the data set; storing data sent from the first node to the second node in the domain; and releasing the domain. This process of locking, storing, and releasing is repeated for each other domain in the data set. Each domain may be locked for significantly less time than it takes to copy the entire data set. Accordingly, client access requests targeting a locked domain will be delayed for less time than if the entire data set is locked during the self-healing process.

Abstract: Data stored within a cluster may be distributed among nodes each storing a portion of the data. The data may be replicated wherein different nodes store copies of the same portion of the data. In response to detecting the failure of a node, the cluster may initiate a timeout period. If the node remains failed throughout the timeout period, the cluster may copy the portion of the data stored on the failed node onto one or more other nodes of the cluster. If the node returns to the cluster during the timeout period, the cluster may maintain the copy of the data on the previously failed node without copying the portion of the data stored on the failed node onto any other nodes. By delaying self-healing of the cluster for the timeout period, an unbalanced data distribution may be avoided in cases where a failed node quickly rejoins the cluster.

Abstract: Various systems and methods for testing one or more servers using a distributed test system may involve a master agent synchronously transitioning multiple test agents through several state changes. In some embodiments, a method may involve configuring multiple test agents to execute a test by initiating a state change to a first state at each of the test agents. Each of the test agents is prepared to execute the test when in the first state. Each of the test agents simulates multiple clients of a server under test when executing the test. In response to each of the test agents confirming the state change to the first state, a state change to a second state may be initiated at each of the plurality of test agents. Each of the test agents executes the test when in the second state.

Abstract: An application server may be instrumented to provide a resource measurement framework to collect resource usage data regarding request processing by the application server and applications executing on the application server. The resource measurement framework of an application server may collect hardware and software resource usage data regarding request processing at interception points located at interfaces between application components and services or other components of the application server by instrumenting those interfaces. The resource measurement framework may collect resource usage by instrumenting standard interfaces and/or methods of various specifications, such as implemented by containers or other components of the application server. Thus, the resource measurement framework may collect resource usage for applications or application components that do not include any resource measuring capabilities.

Abstract: A distributed system provides for separate management of dynamic cluster membership and distributed data. Nodes of the distributed system may include a state manager and a topology manager. A state manager handles data access from the cluster. A topology manager handles changes to the dynamic cluster topology. The topology manager enables operation of the state manager by handling topology changes, such as new nodes to join the cluster and node members to exit the cluster. A topology manager may follow a static topology description when handling cluster topology changes. Data replication and recovery functions may be implemented, for example to provide high availability.

Abstract: A system and method for controlling access to data in a distributed computer system. Distributed Token Manager (DTM) is a system-level service that coordinates read/write access of data objects (tokens) in a multi-process and multi-threaded environment. The DTM ensures that at any given time either: 1) One or more client processes or threads currently have read access rights to the data object, and no client processes or threads currently have write access rights to the data object; or 2) One client process or thread currently has write access to the data object and no other client processes or threads currently have read or write access rights to the data object. DTM also ensures that such coordination works smoothly even in the case of process/machine/network failure.

Abstract: A distributed system provides for separate management of dynamic cluster membership and distributed data. Nodes of the distributed system may include a state manager and a topology manager. A state manager handles data access from the cluster. A topology manager handles changes to the dynamic cluster topology. The topology manager enables operation of the state manager by handling topology changes, such as new nodes to join the cluster and node members to exit the cluster. A topology manager may follow a static topology description when handling cluster topology changes. Data replication and recovery functions may be implemented, for example to provide high availability.

Abstract: A distributed system provides for separate management of dynamic cluster membership and distributed data. Nodes of the distributed system may include a state manager and a topology manager. A state manager handles data access from the cluster. A topology manager handles changes to the dynamic cluster topology. The topology manager enables operation of the state manager by handling topology changes, such as new nodes to join the cluster and node members to exit the cluster. A topology manager may follow a static topology description when handling cluster topology changes. Data replication and recovery functions may be implemented, for example to provide high availability.

Abstract: A system and method for enabling failover in an application server cluster. A “primary” application server computer in the cluster may provide a service or data necessary for other application server computers in the cluster to operate. In addition to the primary application server computer, one or more of the other application server computers may be designated as “backup” application server computers. Each backup application server may backup the processing information managed by the primary application server. When the primary application server itself becomes unavailable (e.g., due to a failure of the computer system or network), one or more of the backup application servers may be promoted to the role of primary application server.

Abstract: A distributed data system cluster may include several nodes and an interconnect coupling the nodes. Each node may include a consensus module and a serviceability module. In response to receiving a request to perform a serviceability update from a serviceability module, a consensus module may be configured to send a vote request to the consensus modules included in each of the other nodes. Each consensus module may be configured to send a vote to each other consensus module in response to receiving the vote request. A consensus module in one may also be configured to cause a serviceability module included in the same node to perform the serviceability update dependent on whether a quorum is indicated by the votes received from the consensus modules in the other nodes.

Abstract: A system and method for controlling access to data in a distributed computer system. Distributed Token Manager (DTM) is a system-level service that coordinates read/write access of data objects (tokens) in a multi-process and multi-threaded environment. The DTM may support a transactional model such that write operations to a data object performed by a client process or thread can be either committed or rolled back.

Abstract: A system may include a client and a distributed data manager coupled to the client. The distributed data manager may include a data store storing a data object that includes several sub-elements. The client is configured to update a portion of the data object by sending a message to the distributed data manager. The message specifies one of the sub-elements of the data object to be updated and includes a new value of that sub-element but does not include a new value of the entire data object. The distributed data manager is configured to perform updates to the data object in the data store dependent on which of the sub-elements of the data object are specified by the client.

Abstract: Various systems and methods for testing one or more servers using a distributed test system may involve a master agent synchronously transitioning multiple test agents through several state changes. In some embodiments, a method may involve configuring multiple test agents to execute a test by initiating a state change to a first state at each of the test agents. Each of the test agents is prepared to execute the test when in the first state. Each of the test agents simulates multiple clients of a server under test when executing the test. In response to each of the test agents confirming the state change to the first state, a state change to a second state may be initiated at each of the plurality of test agents. Each of the test agents executes the test when in the second state.

Abstract: Entities within a cluster are uniquely identified with a node ID and an engine ID. The node ID uniquely identifies a node within a cluster of nodes and the engine ID uniquely identifies one of several engines included in the node. Entities may be further identified with a cluster ID, an engine type ID, and/or a virtual server ID. At least some of these IDs may be included in communications received from clients and used to route the communications to the cluster entity identified by the included IDs.

Abstract: A cluster topology self-healing process is performed in order to replicate a data set stored on a failed node from a first node storing another copy of the data set to a second non-failed node. The self-healing process is performed by: locking one of several domains included in the data set, where locking that domain does not lock any of the other domains in the data set; storing data sent from the first node to the second node in the domain; and releasing the domain. This process of locking, storing, and releasing is repeated for each other domain in the data set. Each domain may be locked for significantly less time than it takes to copy the entire data set. Accordingly, client access requests targeting a locked domain will be delayed for less time than if the entire data set is locked during the self-healing process.