Xerox Corporation

Sun Microsystems, Inc.

Google Inc.

Panasas, Inc.

Brent B Welch

Marvin Michael Theimer

Douglas Brian Terry

Alan J Demers

Karin Petersen

Michael J Spreitzer

Scott Alan Elrod

Steve Uhler

Roy Want

William Noah Schilit

David Goldberg

Mark D Weiser

Richard J Goldstein

Mark C Holland

Ozan Demir

Roy Peterkofsky

Mikhail Basilyan

Timothy Smith

Jose Casillas

David A Maltz

Philipp Keller

Systems, methods, devices, and other techniques for managing a computing resource shared by a set of online entities. A system can receive a request from a first online entity to reserve capacity of the computing resource. The system determines a relative priority of the first online entity and identifies a reservation zone that corresponds to the relative priority of the first online entity. The system determines whether to satisfy the request based on comparing (i) an amount of the requested capacity of the computing resource and (ii) an amount of the portion of unused capacity of the computing resource designated by the reservation zone that online entities having relative priorities at or below the relative priority of the first online entity are permitted to reserve.

Dynamic capacity optimization for shared computing resources segmented into reservation zones

A data storage methodology wherein a data file is initially stored in a format consistent with RAID-1 and RAID-X and then migrated to a format consistent with RAID-X and inconsistent with RAID-1 when the data file grows in size beyond a certain threshold. Here, RAID-X refers to any non-mirrored storage scheme employing XOR-based error correction coding (e.g., a RAID-5 configuration). Each component object (including the data objects and the parity object) for the data file is configured to be stored in a different stripe unit per object-based secure disk. Each stripe unit may store, for example, 64 KB of data. So long as the data file does not grow beyond the size threshold of a stripe unit (e.g., 64 KB), the parity stripe unit contains a mirrored copy of the data stored in one of the data stripe units because of the exclusive-ORing of the input data with 'all zeros' assumed to be contained in empty or partially-filled stripe units. When the file grows beyond the size threshold, the parity stripe unit starts storing parity information instead of a mirrored copy of the file data. Thus, the data file can be automatically migrated from a format consistent with RAID-1 and RAID-X to a format consistent with RAID-X and inconsistent with RAID-1 without the necessity to duplicate or rewrite the stored data.

Data file migration from a mirrored RAID to a non-mirrored XOR-based RAID without rewriting the data

A method for dynamically adding new functionality to a first set of instructions that processes Web documents. The invention includes the first step of the first set of instructions decoding a first statement of the Web document. The first statement includes a first command and at least one instruction provided as an argument to the first command. In response to executing the first command, the first set of instructions decodes the instruction provided as the argument to the first command and issues the instruction to be executed. Executing the instruction provided as an argument to the first command, results in new Web document processing functionality being added to the first set of instructions.

Method and apparatus for dynamically adding functionality to a set of instructions for processing a web document based on information contained in the web document

Method and apparatus for dynamically adding functionality to a set of

Write operations for weakly consistent replicated database systems have application-specific embedded dependency queries and related descriptions of the results that are expected to be returned when the respective dependency queries are run against the database. The dependency queries are arbitrary queries that are provided by the application to satisfy the requirements of the application. Write operations that conflict with the current state of any given instance of such a database are detected by comparing (a) the results that are returned when the dependency queries for those writes are run against the given instance of the database with (b) the results that are expected to be returned.

Application-specific conflict detection for weakly consistent replicated

Write operations for weakly consistent replicated database systems have embedded application-specific merge procedures that are invoked for resolving conflicts whenever it is found that the related write operation conflicts with the current state of a given instance of such a database. The effect of executing such a merge procedure is deterministic for any state of the given instance of the database happens to be in when the merge procedure is executed.

Application-specific conflict resolution for weakly consistent

The present invention provides client-selected consistency guarantees to clients of a weakly consistent replicated database on a per 'session' basis. The clients have access to utilities which allow the clients to, individually or collectively, define a 'session' over which the selected guarantees are enforced. A 'session' is broadly defined as a sequence of logically related Reads and Writes to the database. Sessions are initiated and terminated substantially independently of other sessions which may exist concurrently. Clients are allowed, however, to clone sessions and/or merge sessions with other clients. Clients select a minimum relevant subset of guarantees from among a set of pre-defined consistency guarantees, where 'relevancy' is a client determined factor. At any given time, the system may be enforcing a number of different combinations of consistency guarantees. The guarantees ensure that all clients participating in a particular session view the database as having certain conditions of data consistency--the consistency of which is only provided with respect to the participants' Read and Write requests. Clients are allowed to downgrade their selected guarantees during the course of their sessions. One implementation of the present invention permits the selection of any one of four consistency guarantees.

Method for providing session consistency guarantees

Write operations for weakly consistent replicated database systems have embedded conflict detection and conflict resolution procedures for identifying and resolving, respectively conflicts between such write operations and the current state of any given instance of such a database. These write operations are committed to a firm execution order by the host for one instance of such a database, and this execution order propagates to the other instances of the database. Accordingly, a write log distinguishes between the writes that are known to be committed to a firm execution order (the 'tentative writes') is maintained for each instance of the database, thereby enabling the user to explicitly identifying the stable data and the potentially unstable data in any given instance of the database. Furthermore, provision is made for enabling users to select from a set of predefined consistency guarantees across all instances of such a database for any given session.

Methodology for managing weakly consistent replicated databases

A write log that distinguishes between write operations that are known to be in a stable write order ('committed writes') and write operations that still are in a potentially unstable write order ('tentative writes') are maintained for each instance of a weakly consistent replicated database so that the stable and the potentially unstable data in any given instance of such a database can be explicitly identified.

Identification of stable writes in weakly consistent replicated

A system is provided for servicing requests by a mobile controller to utilize stationary or mobile resources present within a partitioned communication cell such as an office or room in a building. The mobile controller has a control signal mechanism for generating control request signals to modify behavior of the stationary or mobile resource, with the range of the control request signals substantially limited to the partitioned communication cell. A room agent receives and acts upon the control request signals after dynamically determining availability of both mobile resources entering and exiting the partitioned communication cell and stationary resources already present in the partitioned communication cell. In operation, the room agent is configured to grant requests for utilization of mobile and stationary resources located within the partitioned communication cell when predetermined contextual attributes within the partitioned communication cell are consistent with previously specified interaction policies.

Method and system for the dynamic selection, allocation and arbitration

In a large area display system, multiple persons may work together with multiple input devices for supplying and receiving information in an interactive system with a single large area display. The large area display system comprises a screen wherein computer generated information is projected upon one side of the screen, and users interact with the computer from the opposite side of the the screen. Data coordinates for an input device corresponding to a pseudo image sensed by the receiving subsystem electronics are provided to the controlling computer. The input data coordinates from the pseudo image are normalized for variations due to frequency dependence and electronic drift. The normalized data coordinates are looked up in a calibration table to account for distortion in the pseudo image detection electronics. Screen coordinates corresponding to pixel locations on the large area screen are found by interpolation from the data From the calibration table. The calibration table is prepared off-line, based on a bicubic spline interpolating function which is then compressed using a delta compression scheme. During on-line operation of the system, screen coordinates are looked-up directly from the compressed table. The screen coordinates are then jitter smoothed to provide a smooth path of response closely conforming to original input locations. The jitter smoothing method uses an exponential function based on the magnitude of the change in the position of the input.

Growing community of inventors

Mountain View, CA, United States of America

Brent B Welch