Jim Gray, editor. The Benchmark Handbook for Database and Transaction Processing Systems, Second Edition, Morgan Kaufmann Publishers, Inc., San Francisco, CA, 1993.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....do not satisfy, followed by a brief comparison between these three benchmarks, in Section 6. In the conclusion, we state our contributions and what needs to be done in the near future. 5 XML Benchmark Desiderata A useful domain specific benchmark should be relevant, portable, scalable and simple [13]. Domain specificity is accomplished in XBench by the definition of a specific database and workload design for a given application domain. Each of these are developed using an identical methodology, thus producing a family of benchmarks. In addition to these general principles, the following ....

J. Gray, The Benchmark Handbook for Database and Transaction Processing Systems. San Mateo, California: Morgan Kaufmann Publishers, Inc., 1991.

....the ease of implementing remote communication with the CORBA platform may mislead software engineers to use remote invocations excessively. As a result, the responsiveness of the software may drop significantly. To improve the performance of middleware based distributed systems, benchmarking [OMG99a, Gra91] and performance heuristics [Kh98a] can provide useful hints for the development work. They help developers to find promising technologies and architectures but, unfortunately, they do not give any quantitative estimates for the performance of the resulting system. In addition, such techniques ....

....layers get merged. In both cases, service demand estimates can be either deduced from the operation descriptions, or they can be measured from a benchmark or a prototype. See [Jai91] for a discussion on making measurements, Smi90] for obtaining estimates by analyzing the software structure, and [Gra91] for using benchmarks. There are two practical ways to represent service demands. In the first approach, they are expressed directly by using the execution time that has been obtained, say, from measurements made for a prototype system. The advantage of this approach is the simplicity of ....

Gray, Jim (Ed.), The Benchmark Handbook for Database and Transaction Processing Systems, Morgan Kaufmann Publishers, San Mateo, CA, USA, 1991.

....i.e. the interarrival time is exponentially distributed. The widely accepted (and thus usually omitted) justification is that Poisson streams have been found to be a good approximation for the arrival of jobs submitted independently by a large number of users [Kleinrock 75] Gross, Harris 85] Gray 91] Most studies also assume that the transaction service times are exponentially distributed, but a justification for this assumption is usually missing. A possible justification is that the time required to process a transaction at a database site is mainly determined by the disk service time, ....

....is not to compare different database systems but to analyze different configurations, replication schemata, and workload patterns in distributed databases, as well as their effects on the system performance. The database schema of the DR DebitCredit follows the original DebitCredit banking schema [Gray 91] The main extensions of the DR DebitCredit are an additional read only transaction in the workload, an arbitrarily adjustable selectivity of these queries, an arbitrarily adjustable ratio of read to update and local to remote transactions, 2 dimensional variations of the replication schema, and ....

Jim Gray: "The Benchmark Handbook for Database and Transaction Processing Systems", Morgan Kaufmann, 1991.

....management systems (DBMS) SPEC CPU 2002 for computer systems, and the TREC Ad Hoc Retrieval Task for information retrieval systems. 2. 1 TPC A TM The full name for TPC A is the Transaction Processing Council (TPC) Benchmark TM A for Online Transaction Processing including a LAN or WAN network[8]. It evolved from the DebitCredit test originally published in 1984. This effort was spearheaded by Jim Gray but had so many contributors from industry and academia that the author on the paper was given as Anon et al. This paper struck a chord in the database community. Researchers began to ....

....and seminars are essential. 4.3 Desiderata for Successful Benchmarks In this section, we present seven requirements or properties of successful benchmarks. These can be used as design goals when creating a benchmark or as dimensions for evaluating an existing one. We took work by Gray [8] and Feather et al. 6] and expanded on them, based on our own observations of successful benchmarks. The first two properties, accessibility and affordability, are primarily concerned with the packaging and delivery of the benchmark. The last five, clarity, relevance, solvability, portability, ....

Jim Gray, "The Benchmark Handbook: For Database and Transaction Processing Systems," San Mateo, CA: Morgan Kaufman Publishers, Inc, 1991.

.... and the European IST project DBench [5] there is still a significant gap between i)the level of recognition attached to robustness benchmarks and fattit injection based dependability benchmarking, and ii) the wide offer and broad agreement that characterize performance benchmarks (e.g. see [6]) Much effort is needed before the same standing can eventually be achieved. In practice, basic attributes such as workload, faultload, measurements and measures precisely characterize a dependability benchmark. Clearly, the determination of a representativefaultload is one of the key issues for ....

J. Gray (Ed.), The Benchmark Handbook for Database and Transaction Processing Systems, San Francisco, CA, USA: Morgan Kaufmann Publishers, 1993.

....for testing the major components of the database system. There have been many successors to this approach which improved on it. Current accepted transaction processing benchmarks, TPC Benchmarks, are mainly based on determining the transaction per second (TPS) processing rate for sets of queries [4], 8] They are loosely based on debit and credit banking applications. The primary purpose of any database benchmarking tool This material is based upon work supported by the National Science Foundation under Grant No. IIS 9979458 is to determine reasonable ways to compare the performance of ....

J. Gray, editor. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann Publishers, Inc., San Mateo, CA, USA, second edition, 1993.

....using synthetic data, in this paper it is shown that, at least in some cases, one can generate spatio temporal data sets that simulate real world behavior. Much work has been done towards data generation for benchmarks in prototype and commercial non spatio temporal databases [3] 6] 7] 9] [10], 14] 16] 19] These generated data can be used to test different implementations under various operating conditions. In STDBs, the work on the generation of test data is limited and only a few innovative papers have appeared in the literature. In Theodoridis et al. 21] the authors present a ....

J. Gray (ed.). The Benchmark Handbook for Database and Transaction Processing Systems, Morgan Kaufmann, 2nd edition, 1993.

....design, implementation, and evaluation. More details on this automatic tuning method can be found in [51] 52] 53] The tuning problem that we are considering here arises in transaction processing systems when transactions execute concurrently (e.g. in an order entry application like TPC C [34]) A trans action consists of multiple data access steps, which are combined into a unit of work for which the system ensures the so called ACID properties: atomicity, consistency preservation, isolation, and durability [35] 37] To guarantee these properties, virtually all commercial database ....

....of many underconfigured systems, due to underrated load growth. To illustrate the importance of tuning the memory mangement for the workload dynamics, consider a system with a load of 10,000 page accesses per second (which is approximately equivalent to 100 TPC C NewOrder transactions per second [34]) Assume that we have enough memory to achieve a buffer hit ratio of 0.8 in steady state. This results in a disk I O load of 0.2 10,000 = 2,000 disk I Os per second. Assume that we have 50 disks, and that the load is perfectly balanced over all disks. Then each disk has to service 40 I Os per ....

J. Gray (Ed.). The Benchmark Handbook for Database and Transaction Processing Systems, 2nd Edition 7 Morgan Kaufmann (1993).

....RR guidelines. 5. 2 Quantifying Availability and the Effects of Recursive Restartability A major contribution of the transaction concept was the emergence of a model, TP systems, that allowed different implementations of data management systems to be directly compared (e.g. using TPC benchmarks [18]) We are seeking an analogous model that characterizes applications possessing RR properties, and that can serve in quantifying availability. Availability benchmarking has been of interest only for the past decade [32, 5] It is considerably more difficult than performance benchmarking, because ....

J. Gray. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufman, 2 edition, 1993.

....in [1] 12] In [18] several storage strategies and mapping schemes for XML data using a relational database are explored. Domain specific database benchmarks for OLTP (TPC C) decision support (TPC H, TPC R, APB 1) information retrieval, spatial data management (Sequoia) etc. are available [20]. In this paper we concentrate solely on the query processing capabilities of the systems we test. XMach 1, XMark and XOO7 are the three benchmarks currently available that test XML systems for their query processing abilities. For detailed information about the data and schema used by these ....

J. Gray. The Benchmark Handbook: For Database and Transaction Processing Systems. Morgan Kaufmann, 2nd edition, 1993.

....simple optimization has proven very effective in many environments; it was quickly incorporated into Sequent s algorithm because of its greatly improved handling of bulk data transfers. 1 Recently, the Transaction Processing Council published the TPC A online transaction processing benchmark [Gra91], which is now in common use by database software and platform vendors. This benchmark is a very important development, because it provides a precise and realistic definition of an important application that requires large numbers of connections. In particular, the TPC A benchmark allows objective ....

Jim Gray. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann, 1991.

....[Bun97] In [FK99] several storage strategies and mapping schemes for XML data using a relational database are explored. Domain specific database benchmarks for OLTP (TPC C) decision support (TPC H, TPC R, 6 APB 1) information retrieval, spatial data management (Sequoia) etc. are available [Gra93] TPC] In this paper we concentrate solely on the query processing capabilities of the systems we test. XMach 1, XMark and XOO7 are the three benchmarks currently available that test XML systems for their query processing abilities. 4.1 XMach 1 has has Document ha Title Chapter has has ....

J. Gray. The Benchmark Handbook: For Database and Transaction Processing Systems. Morgan Kaufmann, 2nd edition, 1993.

....free memory may become exhausted. When mature generations are also collected, the size of a data structure should have a direct impact on the overall performance. Because our measurements did not take this cumulative cost of copying into account, we ran a main memory variant of the TPC B benchmark [14] to investigate the effect of the collection of mature generations using Patricia trees, path and width compressed quaternary tries, and path , width and levelcompressed tries. In the tests we did not find any significant deviations from our earlier results. We have not included balanced trees ....

J. Gray, editor. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann Publishers, San Matea (CA), USA, 1993.

No context found.

Gray, J. (ed.), The Benchmark Handbook for Database and Transaction Processing Systems, Morgan Kaufmann, San Mateo, 1991.

No context found.

Jim Gray, editor. The Benchmark Handbook for Database and Transaction Processing Systems, Second Edition, Morgan Kaufmann Publishers, Inc., San Francisco, CA, 1993.

No context found.

J. Gray. Benchmark handbook: for database and transaction processing systems. Morgan Kaufmann, 1992.

No context found.

J. Gray. The Benchmark Handbook For Database and Transaction Processing Systems. Morgan Kaufmann, 1991.

No context found.

J. Gray. Benchmark handbook: for database and transaction processing systems. Morgan Kaufmann, 1992.

No context found.

Jim Gray. Benchmark Handbook: For Database and Transaction Processing Systems. Morgan Kaufmann Publishers Inc., 1992.

No context found.

J. Gray. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann Publishers, Inc., 2nd edition, 1993.

No context found.

Jim Gray. Benchmark Handbook: For Database and Transaction Processing Systems. Morgan Kaufmann Publishers Inc., 1992.

No context found.

Jim Gray. The benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann Publishers, New York, 1993.

No context found.

J. Gray, editor. The Benchmark Handbook for Database and Transaction Processing Systems. Morgan Kaufmann Publishers, San Francisco, 2. edition, 1993.

No context found.

J. Gray, editor. The Benchmark handbook for database and transaction processing systems, second edition. Morgan Kaufmann, 1993.

No context found.

Gray, J. N., The Benchmark Handbook for Database and Transaction Processing Systems, Morgan-Kaufmann, 1991.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC