Microsoft Technology Licensing, LLC

Mihail Gavril Tarta

Gopala Krishna R Kakivaya

Mert Coskun

Lu Xun

Gopal Krishna R Kakivaya

Anurag Gupta

Gopal Kakivaya

Preetha Lakshmi Subbarayalu

Yang Li

Anirudh Badam

Robin Andrew Alexander

Badriddine Khessib

Laura Marie Caulfield

Xiaozhong Xing

Sumukh Shivaprakash

Zhe Tan

Jian Xu

Li Zhang

Peng Song

Lidan Miao

A transactional replicator applying group commit and barrier concepts is disclosed. Group commit means that the transactional replicator commits multiple transactions in a group and is not restricted to committing single transactions one-at-a-time and is not limited to operating on a single state provider. Barrier means that the transactional replicator does not move forward to commit additional transactions until the previous group of transactions are completed. All state providers must apply their transactions and update state before additional transactions will be committed. A quorum acknowledgement 'unlocks' any locks that were acquired to update the state within a state provider. However, as long as there are no lock conflicts, additional transactions can continue to create new group commits as necessary.

Transactional replicator

In various embodiments, methods and systems for optimizing database transactions based on replicable differential data store data structure are provided. A write operation request, having a key for a write operation on a replicable differential store data structure, is accessed. An intent write lock on a differential state and a write lock on the key are acquired. The differential state comprises a result set of currently committing transactions. A transaction instance, of the write operation, is generated for a write set, the transaction instance comprising a modification to the key. The write-set comprises an uncommitted set of writes for in-flight transactions. A determination is made that the write operation is committed. A result of the transaction instance is persisted when the write operation is committed. It is contemplated that the differential state and a consolidated state can be merged, the consolidated state comprises a result set of previously committed transactions.

Replicable differential store data structure

A system includes reception of a request from a first application to create a virtual open-channel solid state drive associated with a first bandwidth and first capacity, association, in response to the request, of block addresses of a virtual address space of the first application with block addresses of one or more blocks of a first one of a first plurality of channels of a first open-channel solid state drive and with block addresses of one or more blocks of a second one of the first plurality of channels, reception, from the first application, of a first I/O call associated with one or more block addresses of the virtual address space, determination of block addresses of one or more blocks of the first one of the first plurality of channels which are associated with the one or more block addresses of the virtual address space, and execution of the first I/O call on the determined block addresses of one or more blocks of the first one of the first plurality of channels.

Virtualized OCSSDs spanning physical OCSSD channels

Various techniques for distributed storage of state information in a computing fabric are disclosed herein. In one embodiment, a method includes executing a software application at a computing device of a computing fabric, and thus resulting in a change to a portion of a copy of state information associated with the software application stored in the computing device. The method also includes automatically replicating the change to the portion of the copy of state information stored on the computing device to one or more other computing devices in the computing fabric. The one or more other computing devices individually contain a copy of the state information associated with the software application.

State management in distributed computing systems

A system includes reception of a request from a first application to create a virtual open-channel solid state drive associated with a first bandwidth and first capacity, association, in response to the request, of block addresses of a virtual address space of the first application with block addresses of one or more blocks of a first one of a first plurality of channels of a first open-channel solid state drive and with block addresses of one or more blocks of a second one of a second plurality of channels of a second open-channel solid state drive, reception, from the first application, of a first I/O call associated with one or more block addresses of the virtual address space, determination of block addresses of one or more blocks of the first one of the first plurality of channels which are associated with the one or more block addresses of the virtual address space, and execution of the first I/O call on the determined block addresses of one or more blocks of the first one of the first plurality of channels.

A state manager provides transactional distributed lifecycle management of a group of different application-level state providers, namely, differently structured application program data structures. The state providers are atomic with respect to one another. The state provider is replicated to one or more secondary nodes of a distributed network. The state providers are persistent despite one or more node operational failures. State provider lifecycle operations include creation of a transactional distributed state provider as a member of a group of different application-level state providers which include differently structured application program data structures, deletion of a previously created transactional distributed state provider, and/or enumeration of any previously created transactional distributed state providers. A given state provider may be read or written by one or more applications. Implementation restrictions and other avoidance conditions are satisfied in particular cases.

Transactional distributed lifecycle management of diverse application data structures

Techniques are described herein that are capable of establishing causality order of computer trace records. A computer trace record is information that indicates an event that occurs with regard to execution of a computer program. For instance, machines in a distributed computer system may generate such computer trace records as the machines execute the computer program. The computer trace records may be ordered in an aggregated trace to accurately reflect the causality order of the computer trace records. A causality order of computer trace records is a temporal sequence of the computer trace records in which each cause event is indicated to occur before each effect event that is caused by the cause event. A cause event is an event that causes an effect event. An effect event is an event that is caused by a cause event.

Establishing causality order of computer trace records

Embodiments are directed to managing multiple different types of applications using service groups. In one scenario, a computer system receives an indication of one or more application dependencies and characteristics that are to be implemented when an application is provisioned on a distributed host computer system. The computer system creates an application manifest that declaratively defines application dependencies and characteristics for various different service groups. Each service group includes applications that match the declaratively defined application dependencies and characteristics. The computer system also sends the manifest to the distributed host computer system which loads those applications that fit the manifest criteria onto available nodes of the distributed host computer system according to the service groups specified in the manifest.

Distributed application optimization using service groups

Arbitrating node failures. A method includes determining at a first node that communication to a second node has been lost. The method further includes sending an arbitration request to a plurality of arbitrators. The method further includes receiving from the plurality of arbitrators a sufficient number of arbitration reply grant messages to have arbitration reply grant messages from a quorum of the arbitrators. As a result of receiving a sufficient number of arbitration reply grant messages to have arbitration reply grant messages from a quorum of the arbitrators, the method further includes declaring the second node down.

Enhanced arbitration protocol for nodes in a cluster

The present invention extends to methods, systems, and computer program products for performing computations in a distributed infrastructure. Embodiments of the invention include a general purpose distributed computation infrastructure that can be used to perform efficient (in-memory), scalable, failure-resilient, atomic, flow-controlled, long-running state-less and state-full distributed computations. Guarantees provided by a distributed computation infrastructure can build upon existent guarantees of an underlying distributed fabric in order to hide the complexities of fault-tolerance, enable large scale highly available processing, allow for efficient resource utilization, and facilitate generic development of stateful and stateless computations. A distributed computation infrastructure can also provide a substrate on which existent distributed computation models can be enhanced to become failure-resilient.

Performing computations in a distributed infrastructure

A model checking system is described herein that more effectively verifies and validates the design of distributed applications by providing a model and a generic framework to check application invariant properties, detect anomaly behaviors, and monitor application health. The model checking system checks on-line application behavior against application models derived from formal descriptions of the application. The system formulates the concrete application as an abstract model and a number of rules or properties that are expected to hold for the application under all conditions. The model checker compares the actual application execution with the models and either confirms that the properties hold true or reports that the properties are violated. Thus, the model checking system provides more efficient and thorough validation of distributed applications under more realistic production conditions.

Model checking for distributed application validation

Detecting failures of interconnected machines. A method includes establishing a machine to machine lease at a first machine using a first lease agent at the first machine to a second lease agent at a second machine as a result of an application on the first machine requesting to establish a lease with an application on the second machine. Using the machine to machine lease, the method further includes detecting a communication failure between the first machine and the second machine or a machine failure of the second machine.

Growing community of inventors

Sammamish, WA, United States of America

Mihail Gavril Tarta