International Business Machines Corporation

Honesty Cheng Young

Windsor Wee Sun Hsu

Kun Wang

Hua Wang

Ying Chen

Jaishankar Moothedath Menon

Eugene Jon Shekita

Stephen P Morgan

Shauchi Ong

Lawrence Yium-Chee Chiu

Bruce Gilbert Lindsay

Spencer W Ng

Jyh-Herng Chow

John Frederick Hornibrook

Huayong Wang

Arun N Swami

Raymond Amand Lorie

Edward Gustav Chron

Amit Radheshyam Somani

Geoffrey Peddle

Surendra Kumar Verma

Techniques for simulating a multiprocessor system. Aspects of the present invention are based on such an observation that most memory accesses from different simulated processors do not conflict, and therefore the conservative policy for performing synchronization of all the memory accesses can waste a large amount of processing time. By identifying possibly conflicting memory accesses and only performing synchronization of these memory accesses, the synchronization cost can be reduced considerably. Since the function simulator is able to operate faster and to perform the same memory accesses, the possibly conflicting memory accesses can be identified by first executing the function simulator.

System and method for simulating a multiprocessor system

Monitoring an activity profile for a given row of a database and determining a target database for a given row based on the activity profile of the given row. Identifying any row related to the given row and moving the given row and any row related to the given row into the target database while preserving referential integrity.

Managing a hierarchy of databases

A method for performing rapid memory management unit emulation of a computer program in a computer system, wherein address injection space of predefined size is allocated in the computer system and a virtual page number and a corresponding physical page number are stored in said address injection space, said method comprising steps of: comparing the virtual page number of the virtual address of a load/store instruction in a code segment in said computer program with the virtual address page number stored in said address injection space; if the two virtual page numbers are the same, then obtaining the corresponding physical address according to the physical page number stored in said address injection space; otherwise, performing address translation lookaside buffer search, that is, TLB search to obtain the corresponding physical address; and reading/writing data from/to said obtained corresponding physical address. The present invention also provides an apparatus and computer program product for implementing the method described above.

Apparatus and method for executing rapid memory management unit emulation and full-system simulator

Disclosed is a method of recognizing a process in a full-system Instruction Set Architecture (ISA) emulator, comprising the steps of: recognizing a process based on a base address of a page table thereof, recognizing the switch between the processes when said base address of the page table has changed, recognizing the termination of a recorded process when the base address of the page table of the process which tries to modify the page table is not equal to the base address of the page table of the recorded process in the page table. With the recognized process, the binary translation results indexed based on content can be saved into a corresponding process repository, thereby achieving the permanent saving of the translation results and the reuse of translation and optimization on the basis of a previously executed program. Consequently, the overall performance of the full-system Industry Standard Architecture emulator is enhanced.

Full-system ISA emulating system and process recognition method

An intelligent router routes a user request to a storage server that is capable of handling that request natively, without emulation. The request is routed automatically, without any instruction or interaction on the part of the user. The intelligent router includes a storage tank-like computing environment and a set of intelligent routers. The set of intelligent routers appears as a single entity to users by presenting a single network IP address. When the intelligent router receives a request, it examines the protocol type and routes the request to one of the appropriate storage tank clients. The intelligent router does not change the contents of the request message, and thus the storage tank system do not become aware of the existence of the intelligent router. Consequently, any return messages do not need to go through the intelligent router, unless desired.

System and method for efficiently supporting multiple native network protocol implementations in a single system

A method for managing data is provided which includes monitoring an activity profile for a given row of a database and determining a target database for a given row based on the activity profile of the given row. The method further includes identifying any row related to the given row and moving the given row and any row related to the given row into the target database while preserving referential integrity.

System and method for managing a hierarchy of databases

A cost-adaptive cache including the ability to dynamically maximize performance in a caching system by preferentially caching data according to the cost of replacing data. The cost adaptive cache includes a partitioned real cache, wherein data is stored in each of the real cache partitions according to its replacement cost. Also, the cost-adaptive cache includes a partitioned phantom cache to provide a directory of information pertaining to blocks of data which do not qualify for inclusion in the real cache. The partitions in the phantom cache correspond to the partitions in the real cache. Moreover, the cost-adaptive cache maximizes performance in a system by preferentially caching data that is more costly to replace. In one embodiment of the system, the cost of replacing a block of data is estimated by the previous cost incurred to fetch that block of data.

System and method for providing a cost-adaptive cache

Stored data can be recovered from a disk array having at least 2n+1 physical disks that are capable of storing n physical disks worth of data when any two disks fail, or when more than two dependent disks fail. Data is stored in data stripes that are divided into n substantially equal-sized strips and are distributed across the n disks. Each data stripe has a corresponding parity strip that is generated by including the data strips in the data stripe only once when the parity strip is generated. The data strips of each data stripe, the copy of each such data strip and the corresponding parity strip are distributed across the disks in such a manner that the data strips of each data stripe, the copy of each such data strip and the corresponding parity strip are each on a respectively different disk of the disk array.

Method and means for tolerating multiple dependent or arbitrary double disk failures in a disk array

A method for reorganizing data in a storage device for improved performance is provided where the device stores data as data units each associated with a sequential address. The method for reorganizing data includes allocating a reorganization region capable of storing N units and grouping the data units into a plurality of extents each having a generally large number of units. The method further includes sorting the extents based on the frequency of request of the units in the extents and copying N most frequently requested units from the sorted extents into the reorganization region while preserving the order of the sorted extents and the order of the sequential addresses of the units in each extent. The method also includes servicing requests for data using data in the reorganization region.

Storage system and method for reorganizing data to improve prefetch effectiveness and reduce seek distance

A method, apparatus, and article of manufacture provide the ability to maintain cache in a clustered environment. The cache is maintained in both a primary and secondary node. When data is requested, a symbolic list in a cache directory is examined to determine which node's cache contains the requested data. If the symbolic list indicates data is not currently in cache of any node, any node may be used as the secondary node. However, if an original primary node maintains the data in cache, the original primary node is selected as the secondary node. Once a new write I/O operation is performed, the symbolic list is updated to provide. To install a new node, after applying for cluster admission, symbolic information and a modified track list is requested. The modified track list is merged with new symbolic entries and the new node then broadcasts its availability to the cluster.

Method and apparatus for a global cache directory in a storage cluster

A data storage system and method for reorganizing data to improve the effectiveness of data prefetching and reduce the data seek distance. A data reorganization region is allocated in which data is reorganized to service future requests for data. Sequences of data units that have been repeatedly requested are determined from a request stream, preferably using a graph where each vertex of the graph represents a requested data unit and each edge represents that a destination unit is requested shortly after a source unit the frequency of this occurrence. The most frequently requested data units are also determined from the request stream. The determined data is copied into the reorganization region and reorganized according to the determined sequences and most frequently requested units. The reorganized data might then be used to service future requests for data.

The present invention discloses a method, apparatus, and article of manufacture for implementing a locking structure for supporting parity protection in a RAID clustered environment. When updating parity, the parity is locked so that other nodes cannot access or modify the parity. Accordingly, the parity is locked, read, generated, written, and unlocked by a node. An enhanced protocal may combine the lock and read functions and the write and unlock functions. Further, the SCSI RESERVE and RELEASE commands may be utlized to lock/unlock the parity data. By locking the parity in this maner, overhead is mininized and does not increase as the number of nodes increases.

Method and apparatus for supporting parity protection in a RAID clustered environment

A computer-implemented method for clustering related data pages in close physical proximity to each other on a magnetic disk drive or other storage device. The method includes identifying relationships between the pages, with the relationships being established not simply by time of page access, but rather by user access patterns. The pages are clustered based on the relationships. To undertake the clustering, the pages and references can be represented and analyzed as respective vertices and edges in edge graphs.

System and method for reorganizing data on a disk drive to improve spatial locality

A method of writing to cache in a clustered environment. A first node in a storage cluster receives a request to write data from a user application. The first node determines if the data is owned by a remote node. If the data is owned by a remote node, the data in the remote node may be invalidated, if necessary. Such invalidation may not be necessary if a global cache directory is utilized. Thereafter, the data is written in a cache of the first node. Additionally, the data is written in a cache of a partner node of the first node. Confirmation of the cache write in the partner node is then received in the first node.

Method and apparatus for improving write performance in a cluster-based file system

The present invention is system and method for determining information that is to be prefetched in a multi-stream environment which can detect sequential streams from among the aggregate reference stream and yet requires relatively little memory to operate, which is uniquely adapted for use in a multi-stream environment, in which multiple data accessing streams are performing sequential accesses to information independently of each other. A reference address referencing stored information is received. A matching run is found. A count corresponding to the run is updated. If the count exceeds a predetermined threshold, an amount of information to prefetch is determined. If a predetermined fraction of the determined amount of information to prefetch must still be retrieved, the determined amount of information is retrieved. A matching run may be found by searching a stack comprising a plurality of entries to find an entry corresponding to the reference address. Each of the plurality of entries may be associated with a maximum accessed address, a forward range, and a backward range, and the searching step may comprise searching the plurality of stack entries in one direction starting at an end of the stack and determining whether the reference address is between (maximum accessed address&minus;backward range) and (maximum accessed address&plus;forward range) for each stack entry until a matching stack entry is found.

Growing community of inventors

Saratoga, CA, United States of America

Honesty Cheng Young