J. Haritsa, M. Carey, M. Livny, Value-based scheduling in real-time database systems, Technical Report TR 1204, Department of Computer Science, University of Wisconsin, Madison, 1991.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....0 C (A) Maximizing throughput 0 D 0 C (B) Minimizing mean resptime 0 D D 0 C C (C) Hybrid version Figure 4.2: Illustration of service yield functions. In certain sense, our definition of service yield is similar to the concept of value in value based real time database systems [50, 52]. One major dis67 tinction is that real time systems are usually sized to handle transient heavy load [50] For Internet services, however, the client request rates tend to be bursty and over provisioning system resources for a service site to accommodate the potential peak will not be ....

....Figure 4.2: Illustration of service yield functions. In certain sense, our definition of service yield is similar to the concept of value in value based real time database systems [50, 52] One major dis67 tinction is that real time systems are usually sized to handle transient heavy load [50]. For Internet services, however, the client request rates tend to be bursty and over provisioning system resources for a service site to accommodate the potential peak will not be cost effective [13, 23, 27] More detailed discussions on scheduling schemes to achieve high aggregate service yield ....

[Article contains additional citation context not shown here]

J. R. Haritsa, M. J. Carey, and M. Livny. Value-Based Scheduling in Real-Time Database Systems. VLDB Journal, 2:117--152, 1993.

....QoS curve steadily declines from its maximum and eventually drops below the slopeslack technique at about 260 partitions. 7 Related Work There has been extensive research on scheduling tasks under real time performance expectations both in operating systems [14, 16, 17, 20] and database systems [3, 11, 12, 18, 19]. To the best of our knowledge, Aurora s scheduling approach that combines priority assignment and dynamic scheduling plan consauction is the first comprehensive proposal for scheduling continuous queries over real time data streams and QoS expectations. Our solutions no doubt borrow a lot from ....

....of excess load in a way that least degrades the QoS. This allows our scheduling algorithm to focus only on undefioad situations. We note here that Haritsa et al. 12] proposed an extension of EDF that is designed to handle overloads through adaptive admission control. Real time database systems [3, 11, 12, 15, 18, 19] attempt to satisfy deadlines associates with each incoming transaction, with the goal of minimizing the number of transactions that miss their deadlines. These systems commonly support short running, independent transactions, whereas Aurora deals with long running continuous queries over ....

[Article contains additional citation context not shown here]

J. R. Haritsa, M. J. Carey, and M. Livny. Value-Based Scheduling in Real-Time Database Systems. VLDB Journal.' Very Large Data Bases, 2(2): 117-152, 1993.

....that our logical versioning scheme can easily be extended to handle the case when transactions have associate deadlines. Each transaction is assigned a priority based on its deadline (if transactions have values, then these can be incorporated into the priority assignment as described in [HSRT89, HCL93] Since read only transactions do not obtain locks, they are never involved in conflicts, and so are irrelevant from a concurrency control perspective. Updaters, however, do obtain locks and may be involved in conflicts. These conflicts can be resolved in favor of the transaction with the higher ....

....our work. Our work on making read only transactions completely non blocking and their execution times more predictable is complementary to the time cognizant transaction processing schemes proposed in the real time database systems literature [SZ88, AGM88, AGM89, HCL90b, HCL90a, HSRT89, HSRT91, HCL93, Ram93] Our use of main memory technology and version based concurrency control schemes enable transaction running times to be estimated more accurately. Consequently, scheduling algorithms can generate better schedules, that is, schedules in which more transactions meet their deadlines. ....

[Article contains additional citation context not shown here]

J. Haritsa, M. Carey, and M. Livny. Value-based scheduling in real-time database systems. VLDB Journal, 2(2):117--152, 1993.

....before. The deadline assignment method used in our RTDBS model is described later in this section. The transaction deadlines are soft; i.e. each transaction is executed to completion even if it misses its deadline. Criticalness and deadline are two independent characteristics of RTDB transactions [21, 23]. A close deadline does not necessarily imply more criticalness. The transaction manager at the originating site of a transaction T assigns a real time priority to transaction T based on its criticalness (C T ) deadline (D T ) and arrival time (A T ) The priority of transaction T is ....

J.R.Haritsa, M.J.Carey, M.Livny, "Value-Based Scheduling in Real-Time Database Systems", Technical Report No.1024, Dept. of Computer Science, University of Wisconsin-Madison, 1991.

....increases when the system uses earliest deadline first or least slack first algorithm for transaction priority assignment. Both priority assignment policies have the weakness that they can assign the highest priority to a transaction that has already missed or is about to miss its deadline [Abbo88, Hari91]. Finally, there is another problem related with priority assignment policy. If the policy changes transaction priority dynamically and allows priority reversal between transactions [Hari90b] repeated conflicts between a pair of transactions may be resolved in some cases in favor of one ....

Haritsa, J. R., Miron Livny, Michael J. Carey, "Value-Based Scheduling in Real-Time Database Systems," Technical Report TR1024, Department of Computer Science, University of Wisconsin, May 1991.

....their priorities in descending deadline order. In the least slack first (LSF) AGM88a] policy, the transaction with the shortest slack time is executed first. The slack time is an estimate of how long we can delay the execution of transaction and still meet its deadline. In the highest value (HV) HCL91] policy, transaction priorities are assigned acording to the transaction value attribute. The priority ceiling protocol with dynamic adjustment (PCP DA) LSH97] uses a priority ceiling protocol with dynamic adjustment of serialization order to enhance the system schedulability in hard RTDBs. ....

J. Haritsa, M. Carey, and M. Livny. Value-based scheduling in real-time database systems. Tech. Rep. CS-TR-91-1024, University of Winconsin, Madison, 1991.

....cause a portion or all of the current version to be lost [138] In the remainder of this section, we discuss the issues related to processing real time transactions. Evaluations of the techniques discussed, if any, are invariably by either a testbed system, e.g. 87] or through simulation, e.g. [3, 76, 215]. One exception is the approximate analysis of real time DBs [79] where an analytical approach is used to approximate the steady state fraction of real time transactions that complete successfully. 6.2.1 Processing Transactions with Hard Deadlines All transactions with hard deadlines must ....

....of transactions. 6.2.2 Processing Transactions with Soft Deadlines Transaction Priority Assignment Policies: Priorities and values for real time transactions are used for conflict resolution and CPU scheduling. The literature contains various transaction priority or value assignment algorithms [26, 75, 76, 86, 91, 134] and their evaluations [3, 1, 86] Some of these policies are Earliest deadline first, Highest value first, Least slack time first (where slack time is the maximum amount of time that a transaction can spend without executing, and still complete within its deadline) ....

Haritsa, J. R., Carey, M. J., and Livny, M., "Value-Based Scheduling in Real-Time Database Systems," VLDB Journal 2, 2, 1993.

....the most important intra systems that can be used in real time systems. Real time database systems (RTDBS) have transactions that should be executed with timing constraints. In general, a timing constraint is expressed in the form of a deadline until which the user wants to complete the transaction[8,12,14]. Conventional database systems differ from real time database systems in that they do not take into account timing constraints. Applications of real time database systems, such as computer aided manufacturing, military command and control, traffic control and process control, are being ....

J. R. Haritsa, M. J. Carey, and M. Linvy. Value-based scheduling in real-time database systems. VLDB Journal, 2(2):117--152, 1993.

....databases. Key words: concurrency, databases, real time systems 1 Introduction Real time database systems have transactions that should be executed with timing constraints. In general, a timing constraint is expressed in the form of a deadline until which the user wants to complete the transaction[1,5]. Conventional database systems differ from real time database systems in that they do not take into account timing constraints. In conventional database systems, the performance objective is to minimize average response time and maximize the throughput. The primary performance goal in real time ....

....performance objective is to minimize average response time and maximize the throughput. The primary performance goal in real time database systems, on the other hand, is to maximize the number of transactions that Preprint submitted to Elsevier Preprint 18 January satisfy their timing constraints[5]. In contrast to a conventional database system whose transactions are executed with equal priority, a real time database system must schedule the transactions based on individual transaction s priority, e.g. deadline. In particular, a priority comprises information such as the absolute deadline, ....

J. R. Haritsa, M. J. Carey, and M. Linvy. Value-based scheduling in real-time database systems. VLDB Journal, 2(2):117--152, 1993.

.... [Bestavros and Braoudakis 1994] Biyabani et al. 1988] Buchmann et al. 1989] Chakravarthy et al. 1994a] Chakravarthy et al. 1994b] Chen Lin 1990] David et al. 1994] DiPippo Wolfe 1993] Goyal et al. 1995] Haritsa et al. 1990a] Haritsa et al. 1990b] Haritsa et al. 1992] [Haritsa et al. 1993], Hong et al. 1993] Huang et al. 1989] Huang et al. 1991a] Huang et al. 1991b] Huang et al. 1992] Kim et al. 1990] Kim Srivastava 1991] Kuo Mok 1992] Lam et al. 1995] Lee Son 1993] Lee Son 1994] Lee Son 1995] Lin Son 1990] Sha et al. 1988] Sha et al. 1990] ....

J.R. Haritsa, M.J. Carey, M. Livny `Value-Based Scheduling in Real-Time Database Systems', International Journal on Very Large Data Bases, vol.2, no.2, 1993, pp.117-152.

....deadline imply that it has a low value. Transactions with similar values may have different deadlines, while those with similar deadlines may have different values. Performance analysis studies that incorporated transaction values include those of Huang et al. Huan89, Huan91] and Haritsa et al.[Hari91]. In [Huan89] several PCC based algorithms are investigated for resource scheduling and data conflict resolution. This work is extended in [Huan91] to include OCC based methods. Both consider a soft RTDBS where transaction values, after missing their deadlines, decrease at a rate inversely ....

....and data conflict resolution. This work is extended in [Huan91] to include OCC based methods. Both consider a soft RTDBS where transaction values, after missing their deadlines, decrease at a rate inversely proportional to the values that these transactions had before their deadlines. In [Hari91] the special case in which all transactions have step shaped value functions the system is operating under a firm deadlines assumption is investigated. Our work differs from the work of Huang et al. in that we do not relate the value that a transaction has before its deadline to the rate with ....

Jayant R. Haritsa, Michael J. Carey, and Miron Linvy. "Value-based scheduling in real-time database systems." Technical Report Computer Sciences Technical Report #1024, University of WisconsinMadison, May 1991.

....groups there is a mandatory top group. A service from this top group, although mandatory, may be replaced by a guaranteed non rescindable service. This constitutes a minor mode change. Value based real time scheduling has been investigated in the real time database (RTDB) area. For example, in [13, 11, 33, 12] transactions have both values and deadlines. Scheduling algorithms were developed and evaluated that choose priority by considering various combinations of value and deadline. Usually, total value is the performance metric and no value is accrued if deadlines are missed. Also in the real time ....

J. Haritsa, M. Carey, and M. Livny. Value-based scheduling in real-time database systems. Technical Report TR 1204, Dept. CS, Univ. of Wisconsin, Madison, 1991.

....with later deadlines. 11 Update locks are acquired when a data page intended for modification is first read, i.e. lock upgrades are not modeled. 12 For applications with transactions of varying criticalities, the value cognizant priority assignment mechanisms proposed in the literature (e.g. [25]) can be utilized. G. Concurrency Control For transaction concurrency control, we use an extended version of the centralized 2PL High Priority (2PL HP) protocol proposed in [1] 13 The basic 2PL HP protocol, which is based on the classical strict two phase locking protocol (2PL) 14] operates ....

J. Haritsa, M. Carey, and M. Livny, "Value-based Scheduling in Real-Time Database Systems," Intl. Journal on Very Large Data Bases, vol. 2, no. 2, April 1993.

....deadlines. A long term operating region where the KillPercent 7 Pinned buffers are, of course, not eligible to be replaced. 8 For applications with transactions of varying criticalities, one of the value cognizant priority assignment mechanisms proposed in the literature can be utilized see [11] for a detailed study of this issue, including a value based extension of AED called Hierarchical Earliest Deadline [11] is high is obviously unrealistic for a viable RTDBS. Exercising the system to high miss levels (as in our experiments) however, provides valuable information on the response ....

.... 8 For applications with transactions of varying criticalities, one of the value cognizant priority assignment mechanisms proposed in the literature can be utilized see [11] for a detailed study of this issue, including a value based extension of AED called Hierarchical Earliest Deadline [11]. is high is obviously unrealistic for a viable RTDBS. Exercising the system to high miss levels (as in our experiments) however, provides valuable information on the response of the protocols to brief periods of stress loading. All the KillPercent graphs of this paper show mean values that have ....

J. Haritsa, M. Carey, and M. Livny, "Value-based Scheduling in Real-Time Database Systems," Intl. Journal on Very Large Data Bases, vol. 2, no. 2, April 1993.

....the RTDBS is to maximize the value realized by the in time transactions. Minimizing the number of late transactions is a secondary concern in this environment. A fundamental problem here is how to establish a priority ordering among transactions that are distinguished by both values and deadlines [Biya88, Hari91a]. In particular, it is not clear what tradeoff should be established between transaction values and deadlines in generating the priority ordering. We present here an extension of the AED algorithm, called Hierarchical Earliest Deadline (HED) for integrating the value and deadline characteristics ....

....and minimizing the number of missed deadlines becomes a secondary concern. A fundamental problem when transactions are characterized by both value and deadline is how to construct a priority ordering, since this requires a tradeoff to be established between these two orthogonal characteristics. In [Hari91a], several priority mappings that establish different, but fixed, tradeoffs between value and deadline were investigated. It was found that one of two mappings either Earliest Deadline (ED) or Highest Value (HV) which implement extreme tradeoffs almost always provided the best performance. ....

Haritsa, J., Carey, M., Livny, M., "Value-Based Scheduling in Real-Time Database Systems," Tech. Report 1024, Univ. of Wisconsin, Madison, May 1991.

No context found.

J. Haritsa, M. Carey, M. Livny, Value-based scheduling in real-time database systems, Technical Report TR 1204, Department of Computer Science, University of Wisconsin, Madison, 1991.

No context found.

J. R. Haritsa, M. J. Carey, and M. Livny. Value-Based Scheduling in Real-Time Database Systems. VLDB Journal, 2:117--152, 1993.

No context found.

J. R. Haritsa, M. J. Carey, and M. Livny. Value-Based Scheduling in Real-Time Database Systems. VLDB Journal, 2(2):117--152, 1993.

No context found.

J.R. Haritsa, M.J. Carey, and M. Livny. Value-Based Scheduling in Real-Time Database Systems. Technical Report 1204, Department of Computer Science, University of Wisconsin-Madison (1991).

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