Lh*lh: a Scalable High Performance Data Structure for Switched Multicomputers Lh*lh: a Scalable High Performance Data Structure for Switched Multicomputers
نویسندگان
چکیده
LH lh is a new data structure for scalable high performance hash les on the increasingly popular switchedmulticomputers i e MIMDmulti processor machines with distributed RAM memory and without shared memory An LH lh le scales up gracefully over available processors and the distributed memory easily reaching Gbytes Address calcu lus does not require any centralized component that could lead to a hot spot Access times to the le can be under a millisecond and the le can be used in parallel by several client processors We show the LH lh design and report on the performance analysis This includes experiments on the Parsytec GC PowerPlus multicomputer with up to Power PCs and MB of distributed RAM per node We prove the e ciency of the method and justify various algorithmic choices that were made LH lh opens a new perspective for high performance appli cations especially for the database management of new types of data and in real time environments This work has been supported by the Swedish National Board for Industrial and Technical Development NUTEK and Center for Industrial Information Technol ogy CENIIT This report has been accepted to EDBT Extended Database Technology in Avinon France March LH lh A Scalable High Performance Data Structure for Switched Multicomputers Jonas S Karlsson Email jonka ida liu se Witold Litwin Email litwin cidmac dauphine fr Tore Risch Email torri ida liu se
منابع مشابه
LH*LH: A scalable High Performance Data Structure for Switched Multicomputers
Abs t r ac t . LH*LH is a new data structure for scalable high-performance hash files on the increasingly popular switched multicomputers, i.e., MIMD multiprocessor machines with distributed RAM memory and without shared memory. An LH*LH file scales up gracefully over available processors and the distributed memory, easily reaching Gbytes. Address calculus does not require any centralized compo...
متن کاملRP * : A Family of Order - Preserving Scalable Distributed Data Structures
Hash-based scalable distributed data structures (SDDSs), like LH* and DDH, for networks of interconnected computers (multicomputers) were shown to open new perspectives for file management. We propose a family of ordered SDDSs, called RP*, providing for ordered and dynamic files on multicomputers, and thus for more efficient processing of range queries and of ordered traversals of files. The ba...
متن کاملIH* : A New Hash-Based Multidimensional SDDS
Classic one-dimensional data structures are very important. Nevertheless, the new data management systems (CAD, Web,..) need new access methods that support efficiently spatial operations on multi-attributes (multidimensional ) data files. Scalable Distributed Data Structures (SDDS) is a new class of data structures conceived specially for multicomputers: collection of PCs and workstations inte...
متن کاملRP*: A Family of Order Preserving Scalable Distributed Data Structures
Hash-based scalable distributed data structures (SDDSs), like LH* and DDH, for networks of intcmonnected ampllters (multicomputers) were shown to open new perspectives for fik management. We prcpose a family of ordered SDDSs, called P, providing for ordered and dynamic files on mutticomputers, and thus for more etlicknt pmeessing of range queries and of ordered traversak of files The basic algo...
متن کاملg : a High - availability Scalable Distributed Data Structure by Record Grouping
LH*g is a high-availability extension of the LH* Scalable Distributed Data Structure. An LH*g file scales up with constant key search and insert performance, while surviving any single-site unavailability (failure). Highavailability is achieved through new principle of record grouping. A group is a logical structure of up to k records, where k is a file parameter. Every group contains a parity ...
متن کامل