Axcient, Inc.

Pivotal Software, Inc.

Intel Corporation

Efolder Inc.

International Business Machines Corporation

Robert Petri

Nitin Parab

Eric Lalonde

Eric J Herde

Vito Caputo

Kong Li

Layne B Miller

Luis F Stevens

George Mark Scott

Roland L Arajs

Greg Limes

Systems, methods, and media for efficient file replication are provided herein. According to some embodiments, exemplary methods may include detecting a write operation occurring within an operating system of the computing system, identifying block parameters for the write operation, as well as one or more of buffering and batching the write operation, and transmitting the write operation to a replication receiver system.

Efficient file replication

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for instrumentation and control of workloads in a massively parallel processing database. Deployment is in a cluster which mirrors the cluster of the database to be controlled. The system includes data publishing modules, action agents, rules processing modules, deployment managers, rule compilation and management tools. Together these provide a distributed, fault tolerant system for the automated rules-based control of work in a database cluster. A first calculation master, upon receiving a request, performs local calculation on a first node, and directs a second calculation master to perform local calculation on a second node. The first calculation master then performs global calculation using intermediate results from the first node and the second node.

Performing global computation in distributed database systems

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for instrumentation and control of workloads in a massively parallel processing database. Deployment is in a cluster which mirrors the cluster of the database to be controlled. The system includes data publishing modules, action agents, rules processing modules, deployment managers, rule compilation and management tools. Together these provide a distributed, fault tolerant system for the automated rules-based control of work in a database cluster. For example, in deploying an update, a deployment manager pushes the update to one or more nodes and instructs each of the one or more nodes to restart in a bootstrap mode. The deployment manager generates a respective configuration package for each of the one or more nodes, and restarts each of the one or more nodes in a production mode.

Deploying updates in a distributed database systems

Efficient cloud storage systems, methods, and media are provided herein. Exemplary methods may include locating a Merkle tree of a stored object on a deduplicating block store, comparing an object at a source location to the Merkle tree of the stored object, determining changed blocks for the object at a source location, and transmitting a message across a network to the deduplicating block store, the message including the change blocks and Merkle nodes that correspond to the change blocks.

Cloud storage using merkle trees

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for instrumentation and control of workloads in a massively parallel processing database. Deployment is in a cluster which mirrors the cluster of the database to be controlled. The system includes data publishing modules, action agents, rules processing modules, deployment managers, rule compilation and management tools. Together these provide a distributed, fault tolerant system for the automated rules-based control of work in a database cluster. A rule specifies an action on the system and a condition for performing the action, the condition including a value, one or more tags corresponding to the value, and a relation between the one or more tags and the value. The system triggers the action based on evaluating the condition.

Workload management in distributed database systems

Systems, methods, and media file system virtualization. Exemplary methods may include rendering a sparse file system and creating a block map for the sparse file system. The block map may include a map record for each file record included in the sparse file system. A map record may include extents for blocks associated with a file record, the map record providing a mapping between allocated block sectors for a file record in the sparse file system and corresponding blocks associated with one or more data sources.

File system virtualization

Cloud storage using Merkle trees

Some of the methods provided herein may include periodically revising a mirror of the target computing system, according to a predetermined backup schedule, the mirror being stored on the virtual failover volume resident on an appliance that is operatively associated with the target computing system, by periodically comparing the mirror to a configuration of the target computing system to determine changed data blocks relative to the mirror, storing the changed data blocks as one or more differential files in the virtual failover volume, and incorporating the changed data blocks into the mirror. In some embodiments, the systems and methods may be utilized to resparsify the virtual failover volume.

Systems and methods for maintaining a virtual failover volume of a target computing system

A method and apparatus is provided for integrating an application into a network of computing resources. Applications using this integration have a virtualized access to one or more computing resources associated with the network. Virtualization is generally assured through at least one network connection between the virtual layer and the native network. Together, the virtual access is used to generate a virtual application network capable of providing the application access to the network of computing resources. The application is created into an orchestration of operations to manipulate the one or more computing resources according to a business process. As needed, the application and orchestration can be further partitioning into components to be distributed and executed over the virtual application network using the virtualized access.

Virtualization method and apparatus for integrating enterprise applications

An arrangement is provided for generating an error chain in a call stack. A function is invoked to perform a functionality. If an error occurs during performing the first function, errors including the ones contained in an error chain, created based on at least one context specific error state and represented by an error tokan, and the error, occurred during said performing the functionality, are processed. The function then returns to another function that invokes it either with a new token error token representing a new error chain containing the error occurred and the errors contained in the error chain or with an error status. If the function does not error, it returns a normal status to the other function that invokes it.

Providing a chain of tokenized error and state information for a call stack

A distributed reader and writer's lock to synchronize object management systems is disclosed. The purpose of the lock is to control access to information that is shared by corresponding object management system components on multiple object management systems. An object management system is a computer-based system for storing, naming, and manipulating objects. One lock is created for each object management system component associated with a particular service within the system. The locks communicate over an interface definition language interface. The reader/writer's lock is created by a remote component synchronization module, which acts as an agent for the object management system component. The lock exposes functions to request or release a write lock and to request or release a read lock.

Growing community of inventors

Santa Clara, CA, United States of America

Robert Petri