A. P. Buchmann et al. Time-critical database scheduling: A framework for integrating realtime scheduling and concurrency control. In Proc. of Int. Conf. on Data Engineering, pages 470--480, 1989.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....basic building blocks of operating systems and RTDBSs is thus necessary. The functions of a RTDBS that should be supported by the underlying 22 operating system include priority based CPU and IO scheduling, concurrency control and recovery, buffer management, and data management. Buchmann et al. [9] proposed a system architecture for the integration of functions from operating systems and RTDBSs. The architecture provides an interface between the operating system s scheduler and the RTDBS s concurrency control module. The priority scheduling function provided by the operating system is used ....

A.P. Buchmann, D.R. McCarthy, M. Shu, U. Dayal `Time-Critical Database Scheduling: A Framework for Integrating Real-Time Scheduling and Concurrency Control', Proceedings of the 5th International Conference on Data Engineering, 1989, pp.470-480.

....inequalities of Equation (2.1) are satisfied. Prior RTDBS research investigates three primary strategies for improving the 5 performance and predictability of database transactions: 1. use memory based databases [9, 11, 37, 41] 2. schedule transactions according to task priorities or deadlines [1, 6, 33, 43, 42], 3. reduce delays and uncertainties associated with concurrency control [6, 9, 13, 15, 20, 30, 31, 35, 36, 39, 48] To this list, we add: 4. avoid the overhead associated with a client server architecture, and 5. run transactions in parallel on shared memory multiprocessors. Some real time ....

....strategies for improving the 5 performance and predictability of database transactions: 1. use memory based databases [9, 11, 37, 41] 2. schedule transactions according to task priorities or deadlines [1, 6, 33, 43, 42] 3. reduce delays and uncertainties associated with concurrency control [6, 9, 13, 15, 20, 30, 31, 35, 36, 39, 48]. To this list, we add: 4. avoid the overhead associated with a client server architecture, and 5. run transactions in parallel on shared memory multiprocessors. Some real time database systems have been developed for main memory which can dramatically enhance performance and predictability by ....

[Article contains additional citation context not shown here]

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal, "Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control," in Proc. IEEE Int'l Conf. on Data Engineering, pp. 470--480, February 1989.

....interchangeably. 147 148 8. 2 Grouping Subtransactions: Relaxing Atomicity In what follows, we consider lock based CC protocols (specifically an adapted version of strict 2PL) There are several approaches to the concurrency control of nested (tree structured) transactions [Moss 85] Some [Buc 89] has chosen to take some subtransactions as individual transactions (open nested structure) Therefore if a node fails, its failure does not affect the other parts (no rollback) Or, partial results of subtransactions can be viewed by other transactions. But for the atomicity of the transaction, ....

A. Buchmann, D.R. McCarthy, M. Hsu, "Time-Critical Database Scheduling: A Framework for Integrating Real-Time Scheduling and Concurrency Control", Proceedings of the 5th Conference on Data Engineering, 1989.

....systems with those from real time systems is not feasible. The reason for this situation is that the two environments, database systems and real time systems, have different assumptions and objectives, which result in an impedance mismatch between them (for a detailed discussion on this issue, see [Buch89] and [Rama92] Therefore, meeting the timing constraints of real time database systems demands new approaches to data and transaction management. Typically, a real time system is an embedded computer system, which is used in a large system to provide control and computation functions. An embedded ....

.... Hou89, Huan89, Huan91b, Huan91c, Kort90, Kort90b, Kuo92, Lee93, Lee93b, Lee93c, Lee93d, Lin90, Liu88, Marz89, O Nei92, Pu92, Rajk89, Sha88, Son90, Son92, Song90, Stan88, Vrbs88] The subjects addressed in these papers include the modeling of real time transactions and real time database systems [Abbo88, Buch89, Care89, Daya88, Hari90, Huan89, Kort90, Liu88, Sha88, Stan88], scheduling of real time transactions [Abbo88, Abbo89, Huan89, Stan88, Sha88] concurrency control and data conflict resolution [Abbo88, Abbo89, Agra92, Buch89, Hari90, Hari90b, Huan89, Huan91b, Huan91c, Lee93, Lee93b, Lee93c, Lee93d, Lin90, Sha88, Son90, Son90b, Song90, You93] processing of ....

[Article contains additional citation context not shown here]

Buchmann, A., D. McCarthy, M. Hsu, and U. Dayal, "Time-Critical Database Scheduling: A Framework for Integrating Real-Time Scheduling and Concurrency Control," Proceedings of the 5th Data Engineering Conference, February 1989.

....to proceed at the risk of having to restart them in case these suspected conflicts materialize. For RTDBMS, maximum concurrency (or throughput) ceases to be an expressive measure of performance. Rather, the number of timely commited transactions becomes the decisive performance measure [9]. Most real time concurrency control schemes considered in the literature [1, 3, 31, 15, 29, 27, 28] are based on Two Phase Locking (2PL) which is a PCC strategy. Despite its Speculative Concurrency Control 145 widespread use in commercial systems, 2PL s long and unpredictable blocking times ....

A. P. Buchmann, D. C. McCarthy, M. Hsu, and U. Dayal. "Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency controls." In Proceedings of the 5th International Conference on Data Engineering, Los Angeles, California, February 1989.

....whether the probabilities that an estimated time for some execution will actually deviate from the actual time taken, is small. With the current technology, the answer is negative, and hence, it is futile to attempt to provide any certain guarantees with regard to the execution times (e.g. see [BMHD89] However, that does not resolve the issues that are faced by a time constrained scenario. Further, note that meeting the time constraints on transactions is comparatively simple as regards the invocation times which we state without further explanation and research efforts are in ....

....issues that are faced by a time constrained scenario. Further, note that meeting the time constraints on transactions is comparatively simple as regards the invocation times which we state without further explanation and research efforts are in progress to address these issues (e.g. see [BMHD89, C 89] We regard the problem of meeting the invocation times accurately as being resolved except for crisis situations that are discussed in [KSS90] However, the constraints on the execution times with regard to the value functions accrued, are quite difficult to meet. In our context, ....

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In Proceedings of the Fifth International Conference on Data Engineering, Los Angeles, pages 470--480, February 1989.

.... systems; Database management; Architecture; Intelligent memory 1 Introduction Applications that require real time functionality are difficult to implement using standard hardware and software systems [Sta88] This is also the case with a real time database (RTDB) management system [AGM88, AGM89, BMHD89, C 89, DLW90, HCL90, KSS90, Sin88, Son88, SZ88] which straddles the areas of a high performance database management system (DBMS) and a real time system (RTS) A general RTDB application may be regarded as a reactive process control system [Sin88] The world external to the computer system ....

A.P. Buchmann, D.R. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In Proceedings of the Fifth International Conference on Data Engineering, Los Angeles, pages 470--480, February 1989.

....management techniques at least in their current form. Among the obstacles to using transaction management technology in real time systems are: ffl High variance in access time for a data object that makes it difficult to place a reasonable bound on transaction response times (e.g. see [BMHD89, KSS90] ffl Concurrency control requirement of achieving high overall throughput do not permit the incorporation of real time constraints on the execution of individual transactions (e.g. see [BMHD89, Son88] ffl Standard recovery techniques that guarantee the atomic execution of a ....

.... that makes it difficult to place a reasonable bound on transaction response times (e.g. see [BMHD89, KSS90] ffl Concurrency control requirement of achieving high overall throughput do not permit the incorporation of real time constraints on the execution of individual transactions (e.g. see [BMHD89, Son88] ffl Standard recovery techniques that guarantee the atomic execution of a transaction by restricting other transactions (e.g. delaying access to uncommitted data) are not suited for the characteristics of real time applications (e.g. see [Sin88, LKS91b] The above problems are ....

[Article contains additional citation context not shown here]

A.P. Buchmann, D.R. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In Proceedings of the Fifth International Conference on Data Engineering, Los Angeles, pages 470--480, February 1989. 17

.... requirements but also operate under timing constraints [36, 37, 50, 69] The algorithms and protocols that must be integrated 23 include: cpu scheduling, concurrency control, conflict resolution, transaction restart, transaction wakeup, deadlock, buffer management, and disk I O scheduling [21, 23, 25, 26, 50, 100]. Each of these algorithms or protocols should directly address the real time constraints. To date, work on real time databases has investigated a centralized, secondary storage real time database [1, 2, 3] As is usually required in traditional database systems, work so far has required that all ....

A. Buchmann, et. al., "Time-Critical Database Scheduling: A Framework For Integrating Real-Time Scheduling and Concurrency Control," Data Engineering Conference, February 1989.

....of magnitude slower than CPU speeds, the improvement of I O efficiency is extremely important to the performance of a real time system. This motivates our interest in examining the real time disk scheduling problem. Although extensive work has been done on issues like real time CPU scheduling [6, 17, 1, 14] and real time communications [15, 18, 8, 13] interestingly enough, very few papers have dealt with I O disk scheduling problem in a real time environment. This is, in part, because the problem is difficult, and because in many real time systems disks are not accessed under time constraints. ....

Buchmann, A.P. et. al., "Time-Critical Database Scheduling: A Framework For Integrating Real-Time Scheduling and Concurrency Control," Data Engineering Conference, Feb. 1989.

....requirements on reaction time. For instance, a user may query the database for information and request the result within a certain amount of time. Given the added dimension of time on transactions, one of the interesting areas of study in real time databases is that of transaction scheduling [BMHD89]. Not only must the schedules meet timing constraints, thus meeting the temporal consistency requirements, they must also maintain the logical (traditional) consistency of the data in the database. Typically, there are two types timing constraints on transactions: absolute timing constraints and ....

A.P. Buchmann, D.R. McCarthy, M. Hsu, and U.Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In The Fifth International Conference on Data Engineering, Feb. 1989.

....their decisions on the tasks priorities. The priorities themselves are based on some of the attributes associated with these tasks [1, 22, 11] Typically, each task in a real time system has an arrival time, an estimated worst case execution time, a particular level of importance, and a deadline [4, 17], among other various attributes, many of which will be discussed in more details later in this study. Scheduling algorithms differ in their assignment of priorities. That is, different scheduling policies use different attributes in deriving the corresponding priorities [11] which obviously ....

....whether we are dealing with soft or firm deadlines, we believe that there are other performance issues that must be considered in order to accurately reflect the scheduler s behavior under various operating environments. The performance metrics presented in this section have been mentioned in [4, 10, 22]; however, in the rest of this section, we discuss them in more details along with their role in the schedulability and functionality of the entire system. Value Sum: As we mentioned earlier, every task within the system has a particular level of importance. In order to account for the ....

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal, "Time-Critical Database Scheduling: A Framework For Integrating Real-time Scheduling And Concurrency Control", Proceedings of IEEE Real-time Systems Symposium, 1989.

.... out in evaluating the performance of concurrency control and the impact of real time constraints in RTDBS [AGM88, AGM89, HSTR89, Son91] Buchmann et al. presented a framework for integrating real time scheduling and concurrency control and a summary of real time concurrency control algorithms [BMHD89]. Several priority ceiling based protocols were proposed; these protocols provide bounded blocking times imposed by accessing data objects and schedulability tests for scheduling a set of periodic tasks in uniprocessor RTDBS [SRSC91, Nak93] Haritsa et al. proposed a priority based optimistic ....

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In Proceedings of Data Engineering, pages 470--480, 1989.

....[Gra92] on RTDBS of which the most active is developing transaction scheduling algorithms for soft and firm real time transactions. The scheduler of a RTDBS is responsible for assigning priorities [HJC93, HSRT91, LL73, SZ88] and resolving access conflicts among transactions based on priorities [AGM89, BMH89, HCL90b, KS91, KM92, KM93, LS93, LS90, Sha88]. Among them several approaches [AGM88, HCL90b, HSRT91, LS93, LLH95] are specifically studied for firm RTDBS and several OCC variants have been proposed, and showed the problems of 2PL HP for firm deadline transactions. However, 2PL and 2PL HP yield better performance than OCC or OCC variants for ....

A. Buchmann, D.R. McCarthy, and M. Hsu. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In Proceedings of the Fifth Conference on Data Engineering, pages 470--480, Feb 1989.

....of dynamically arriving transactions that have deadlines. It assumes that transactions operate on a disk resident database, where only a small fraction of accessed data can be cached in memory. Although considerable research has been done recently on processing transactions with time constraints [1, 2, 4, 10, 13, 14, 15, 16, 20] for the most part, this work has not directly tackled the problems introduced by the various sources of unpredictability (discussed in Section 2) Whereas concurrency control protocols have been proposed to execute transactions taking their time constraints into account, most of them do not ....

....starts making changes to the data whether the transaction will meet its deadline. Because of this, transactions may be aborted when their deadlines expire and this in turn can have adverse effects on other ongoing transactions. Perhaps the only exceptions are the ideas discussed in [21] and [4]. Both consider transactions whose execution times as well as data requirements are assumed to be known a priori. Reference [21] considers periodic transactions operating on a main memory database. In [4] an approach is suggested where the system creates schedules that take into account the data ....

[Article contains additional citation context not shown here]

A.P. Buchmann, D.R. McCarthy, M. Chu, and U. Dayal, "Time-Critical Database Scheduling: A Framework for Integrating Real-Time Scheduling and Concurrency Control", Proceedings of the Conference on Data Engineering, 1989.

....1995 (RTDBS) which are designed to cope with rare highload conditions, rather than normal average load conditions. RTDBS are engineered not to guarantee a particular throughput, but to ensure that in the rare event of a highly loaded system, transactions complete before their set deadlines [BMHD89]. These design goals often lead to a computing environment with far more resources than what would be necessary to sustain average loads, thus vanishing the advantage of PCC over OCC algorithms. In particular, OCC algorithms become attractive since computing resources wasted due to restarts do not ....

A. P. Buchmann, D. C. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency controls. In Proceedings of the 5th International Conference on Data Engineering, Los Angeles, California, February 1989.

....architectures. None of the prior work in RTDBSs considers the possibility of application tasks executing transactions themselves. Transaction and I O Scheduling Several researchers have investigated transaction and I O scheduling algorithms that support different real time needs and priorities [1, 12, 62, 83, 76]. Some commercial database systems support priority based transaction scheduling [25, 64] By servicing high priority tasks first, the database can provide faster and more predictable performance for transactions submitted by high priority tasks. In this case, low priority tasks experience ....

.... [70, 79] or symmetric updates [71] Priority inheritance protocols can also be used to reflect task priorities in distributed transaction execution [67] Some researchers suggest that serializability should not be used as the primary correctness criterion for real time concurrency control [12, 21, 56]. Lin [48, 49] suggests that, for real time applications, data inconsistent with the external world can be worse than internally inconsistent data. He calls the correspondence between a database and the state of the external world external consistency. External consistency is lost if the ....

[Article contains additional citation context not shown here]

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal, "Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control," in Proc. IEEE Int'l Conf. on Data Engineering, pp. 470--480, February 1989.

No context found.

Buchmann, A., Dayal, U., McCarthy, D. and Hsu, M.: 1989, Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control, Proceedings Fifth International Conference on Data Engineering, IEEE, Los Angeles.

No context found.

A. P. Buchmann et al. Time-critical database scheduling: A framework for integrating realtime scheduling and concurrency control. In Proc. of Int. Conf. on Data Engineering, pages 470--480, 1989.

No context found.

Buchmann, A. et al., "Time-Critical Database Scheduling: A Framework for Integrating Real-Time Scheduling and Concurrency Control," 5th Data Engineering Conference, Feb. 1989.

No context found.

A. P.Buchmann, D. C. McCarthy, M. Hsu, and U. Dayal. "Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency controls." In Proceedings of the 5th International Conference on Data Engineering, Los Angeles, California, February 1989.

No context found.

A. P. Buchmann, D. C. McCarthy, M. Hsu, and U. Dayal. "Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency controls. " In Proceedings of the 5th International Conference on Data Engineering, Los Angeles, California, February 1989.

No context found.

A.P. Buchmann, D.R. McCarthy, M. Hsu, and U. Dayal. Time-critical database scheduling: A framework for integrating real-time scheduling and concurrency control. In The Fifth International Conference on Data Engineering,February 1989.

No context found.

Buchmann, A.P., D.R. McCarthy, M. Hsu, and U. Dayal, "Time-Critical Database Scheduling: A Framework For Integrating Real-Time Scheduling and Concurrency Control," Data Engineering Conference, Feb. 1989.

No context found.

A. P. Buchmann, D. R. McCarthy, M. Hsu, and U. Dayal, "Time-Critical Database Scheduling: A Framework For Integrating Real-time Scheduling And Concurrency Control", Proceedings of IEEE Real-time Systems Symposium, 1989.

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