Emc Corporation

Other

Emc Corporation/data General

Brian James Martin

Michael S Ryan

Stephen J Todd

Uday K Gupta

Andreas L Bauer

Mark A Parenti

Peter John McCann

Douglas A Wood

Joseph T Frank

George Garfield Peters

David C Butchart

Thomas G Magorka

Roy E Clark

Giridhar Basava

Todd R Brune

Matthew T Brooks

Described are techniques for processing a data storage configuration request for an application A first user level of a plurality of user levels at which said data storage configuration request is made is determined. One or more rule sets defining mappings between different ones of said plurality of user levels are provided. Each of the different user levels is associated with a different level of abstraction with respect to processing performed in the data storage system for implementing the data storage configuration request. One of the rule sets is selected in accordance with the application, a data service requested in said data storage configuration request, and a user grouping including said plurality of user levels. The data storage configuration request is serviced using rules of the selected rule set.

Configuring data storage for electronic mail application

Application aware storage

Featured is a method for reducing the contention of the highly contended global lock(s) of an operating system, hereinafter dispatcher lock(s) that protects all dispatching structures. Such a method reduces the need for acquiring the global lock for many event notification tasks by introducing local locks for event notifications that occur frequently among well defined, or consistent dispatcher objects. For these frequently occurring event notifications a subset of the dispatching structure is locked thereby providing mutual exclusivity for the subset and allowing concurrent dispatching for one or more of other data structure subsets. The method also includes acquiring one or more local locks where the level of protection of the data structure requires locking of a plurality or more of data structures to provide mutual exclusivity. The method further includes acquiring all local locks and/or acquiring a global lock of the system wide dispatcher data structures wherever a system wide lock is required to provide mutual exclusivity.

Parallel dispatch wait signaling method, method for reducing contention of highly contended dispatcher lock, and related operating systems, multiprocessor computer systems and products

Featured is a method or process for reducing contention of a highly contended software lock(s) that is protecting multiple data items, where the software has a plurality of code paths accessing the data items. The method includes creating additional partition locks to protect subsets of the data items protected by the existing global lock. Such a method further includes acquiring all partition locks and the global lock, wherever a global lock would have been acquired to protect data. The method also includes identifying one or more heavily used code paths and determining which data items are touched by the identified one or more heavily used code paths. These data items are then moved into a partition, if they were not partitioned earlier. The locking requirements for each of the identified one or more heavily used code paths are optimized to match the reduced locking requirements because of the partitioned data items. In other words the locking requirements are reduced so only the locks for the partitions including the data items that touch the code path are acquired. In more specific embodiments, the so-modified software is evaluated to determine if there is an acceptable increase in overall system performance resulting from the optimization of the locking requirements. If the modified system's performance is not acceptable, then the next most heavily used code path is identified and the locking requirements for this code path are optimized. Such optimization is continued until the system exhibits an acceptable overall system performance or all code paths are optimized.

Method of reducing contention of a highly contended lock protecting multiple data items

Featured are methods for writing file systems write data operations to storage medium as well as system and program embodying such a methodology. According to one aspect, the method includes storing a file systems write data operation to a first temporary data store and mirroring the file systems write data operation in a second temporary data store. The method further includes deleting the mirrored file systems write data operation from the second temporary data store if it is successfully written from the first temporary data store to the storage medium and writing the mirrored file systems write data operation from the second temporary data store to the storage medium if it is not successfully written from the first temporary data store. In another aspect, the method includes storing the file systems write data operation in the first temporary data store of one server and mirroring it in the second temporary data store of another server. The method further includes monitoring the operational status of each server and writing the mirrored file systems write data operation from the second temporary data store of the other server to the storage medium when it is determined that one of the servers is not operational.

Apparatus, method and system for writing data to network accessible file system while minimizing risk of cache data loss/ data corruption

Featured is a method for reducing overhead associated with system input output (I/O) operations in a computer system having a plurality of processors and a physical memory accessed and used by the plurality of processors. The physical memory being accessed can be a global physical memory such as that used with SMP types of architectures or distributed physical memory such as that used with CCNUMA types of architectures. Such a method includes creating a pinned virtual memory range database in which is stored virtual memory address information corresponding to pinned physical memory for each applications program being run on the computer system. Also featured is an operating system for execution with a multiprocessor computer system and a multiprocessor computer including such an operating system for execution therein.

Method to reduce overhead associated with system I/O in a multiprocessor computer system

An improved method and apparatus for providing access between the processors and the mass storage devices of a computer system wherein an interprocessor bus interconnects the processors and adapters are connected from the interprocessor bus for communication between the processors and the mass storage devices and the system includes binding utility for communicating with the processors and the adapters to generate pairings between the processors and the adapters. A switch is connected between the adapters and the mass storage devices for connecting each adapter to each mass storage device and a binding mapper operates with the binding utility at each binding of a processor/adapter pair to enumerate the mass storage devices with which a processor/adapter pair is to communicate and determines a mass storage identifier by which the processor identifies the mass storage device. An address mapper references the binding mapper to construct and store an address map having processor set for each mass storage device. Each processor set includes an address map entry for each processor and is indexed by processor number. Each entry contains the mass storage device identifier corresponding to the optimal path of access to the corresponding mass storage device. The address mapper responds to each request for access to a mass storage device by providing the corresponding address map entry and the processor completes the access by directing the request through its paired disk device adapter as determined by the returned address map entry.

Method and apparatus for multiple disk drive access in a multi-processor/multi-disk drive system

Growing community of inventors

Redmond, WA, United States of America

Brian James Martin