educative.io

GFS: why small file can have a few chunks?

“Large chunk size (64MB) in GFS has its disadvantages while reading. Since a small file will have one or a few chunks, the ChunkServers storing those chunks can become hotspots if a lot of clients are accessing the same file.”

one chunk is 64MB, and why a small file can have a few chunks?

Thank you!

Hi @Clara, thanks for reaching us.
Here the small file is meant as a file having a relatively smaller size, it can be less than 64 MB or greater than 64 MB.
The count of chunks can be found by dividing the file size by 64 MB. So that’s why we can have only one chunk if the file size is less than 64MB and can have a few chunks if the file size is greater than 64 MB; for example, if the size of the file is 230 MB then we have 4 chunks.