H. Hsiao, "Performance and availability in database machines with replicated data," Computer Sciences Technical Report#963, University of Wisconsin-Madison, 1990. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
A Performance Study of Three High Availability Data.. - Hsiao, Dewitt (1993) (11 citations) Self-citation (Hsiao) (Correct)
....processes. 4. I. Model validation In order to evaluate the accuracy of the results produced by the simulation model, we first configured the model to reflect, as accurately as possible, the characteristics of Gamma and then ran a number of experiments without replication. As described in [14], the model predicted the actually measured performance of Gamma with less than a 10 margin of error. 4.2. Experimental design Typically, system throughput and average response time are the two key metrics used to evaluate a system. However, since our model simulates a closed system, response ....
H. Hsiao, "Performance and availability in database machines with replicated data," Computer Sciences Technical Report#963, University of Wisconsin-Madison, 1990.
A Performance Study of Three High Availability Data.. - Hsiao, DeWitt (1991) (11 citations) Self-citation (Hsiao) (Correct)
....the array in order to satisfy a single disk request. In such cases, the failed disk array will be restricted to serve only one request at a time and its performance will degrade significantly. The availability of a system or data file is greatly influenced by the way data files are placed on disks [Hsia90b] and the time needed to recover or restore a failed disk node. The longer the recovery time is the higher the probability that a second failure will render data unavailable. With an identical copy approach, data can be copied from the intact disk(s) to the new disk after the broken disk has been ....
....processes. 4.1. Model Validation In order to evaluate the accuracy of the results produced by the simulation model, we first configured the model to reflect, as accurately as possible, the characteristics of Gamma, and then ran a number of experiments without replication. As described in [Hsia90b], the model predicted the actually measured performance of Gamma with less than a 10 margin of error. 4.2. Experimental Design Typically, system throughput and average response time are the two key metrics used to evaluate a system. However, since our model simulates a closed system, response ....
Hsiao, H., "Performance and Availability in Database Machines with Replicated Data," Computer Sciences Technical Report #963, University of Wisconsin-Madison, August, 1990.
Towards Practical Multiversion Locking Techniques For On-Line.. - Bober (1993) (3 citations) (Correct)
No context found.
Hsiao, H., Performance and Availability in Database Machines with Replicated Data, Ph.D. Thesis, Computer Sciences Department, University of Wisconsin-Madison, Sept. 1990.
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