Abstract: The present invention provides a computer-implemented method, computer system and computer program product for data compression. According to the computer-implemented method, one or more data blocks on a data source to be replicated to a data target may be detected. Then, compression performance of a first compression dictionary may be evaluated. The first compression dictionary may be previously used to compress existing data on the data target. If the compression performance is lower than a preset performance threshold, a second compression dictionary may be generated based on the existing data on the data target. The data target may be updated based on the existing data and the one or more data blocks using the second compression dictionary.

Abstract: Partial reloading of source data in data synchronization. Determining whether a source partition of source data in a source database is to be reloaded into target data in a target database, the source partition corresponding to a target partition of the target data. In accordance with a determination that the source partition is to be reloaded, one or more processors determine to load the source partition from the source database into the target database as a reference partition, the reference partition being separated from the target data in the target database and being assigned with a reference partition identity. In accordance with a determination that the loading of the source partition is completed, one or more processors determine to attach the reference partition to the target data.