Never update primary keys in synchronized tables. Updating primary keys defeats the purpose of a primary key because the key is the only way to identify the same row in different databases (remote and consolidated) and the only way to detect conflicts.
Conflicts are not the same as errors. When conflicts can occur, you should define a process to compute the correct values, or at least to log the conflict. Conflict handling is an integral part of a well-designed application.
During the download stage of a synchronization, no conflicts arise in the remote database. If a downloaded row contains a new primary key, the values are inserted into a new row. If the primary key matches that of a pre-existing row, the values in the row are updated.
User1 starts with an inventory of ten items, and then sells three and updates the Remote1 inventory value to seven items. User2 sells four items and updates the Remote2 inventory to six. When Remote1 synchronizes, the consolidated database is updated to seven. When Remote2 synchronizes, a conflict is detected because the value of the inventory is no longer ten. To resolve this conflict programmatically, you need three row values:
The current value in the consolidated database.
The new row value that Remote2 uploaded.
The old row value that Remote2 obtained during the last synchronization.
In this case, the business logic could use the following to calculate the new inventory value and resolve the conflict:
current consolidated - (old remote - new remote) -> 7 - (10-6) = 3
For other examples of how to handle conflicts, see:
|Discuss this page in DocCommentXchange.
Send feedback about this page using email.
|Copyright © 2009, iAnywhere Solutions, Inc. - SQL Anywhere 11.0.1|