Abstract
The Belle II experiment is expected to produce 50 times more data than the existing Belle experiment. Such huge data production requires not only scalability with respect to the storage service but also scalability regarding the metadata service.
There has already been a metadata service at the Belle experiment, but it is not proper for the Belle II experiment because it has scalability problems and it is not intended to be used in a distributed grid environment. To deal with these issues, we designed an advanced metadata service system based on AMCA, which provides efficient and scalable metadata searching.
We have built testbed sites to test the correctness, performance and scalability of the advanced metadata service system, and it has been proved to be able to provide efficient metadata searching for the Belle II experiment