- In this paper it is not mentioned in related work previous research in journaling in the block layer. Have that been done before?
* The idea is to build a log-structured filesystem for metadata only. locality of data and metadata is lost though. writes are improved by reads may worsen.
* Journal is fragmented and does not have a fixed size. Block allocation must talk to journaling mechanism.
* Since journal is fragmented, files will get fragmented as the journal fragments grow in size and number.
* While I do not agree with the principle of a fragmented, unbound metadata journal in practice, your design might be much
* Temporal locality is not clearly defined. Because blocks are accessed within a small window does not mean these are related. They may be accesses from two unrelated processes. You need more information to make determination of temporal locality.
* The figures are not well-explained; there are several concepts (e.g., modified block, unmodified block, durable temporal locality, etc. in Fig 5) which appear in the figure but not elaborated upon.
* Cleaning of the journal is required. During cleaning, metadata locations will need to change to make contiguous free space for commiting new transactions sequentially. Therefore, multiple writes of metadata are unavoidable. If you do need to copy metadata elsewhere you might as well copy these to their original static filesystem location.