How DiskANN index built in milvus?

[ucasfl]

For DiskANN, it build index with static binary data, so in milvus, how it works? When insert data, does it generate specific binary data on disk, then building the index?

[chasingegg]

In milvus there are growing data(newly inserted data) and sealed data, and diskann will be built on the static sealed data

[ucasfl]

For static sealed data, are you keep it as the same format that DiskANN needed?

The input data over which to build an index, in .bin format. The first 4 bytes represent number of points as an integer. 
The next 4 bytes represent the dimension of data as an integer. The following n*d*sizeof(T) bytes contain the contents of 
the data one data point in time. sizeof(T) is 1 for byte indices, and 4 for float indices. This will be read by the program as 
int8_t for signed indices, uint8_t for unsigned indices or float for float indices.

https://github.com/microsoft/DiskANN/blob/main/workflows/SSD_index.md

[chasingegg]

Yes

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. Rotten issues close after 30d of inactivity. Reopen the issue with /reopen.