Block I/O layer semantics

From: Thanos Makatos
Date: Tue Jun 15 2010 - 08:30:38 EST


I want to learn whether there are exact semantics offered by the Linux
block I/O layer. Specifically, I would like to know the following:
1. Can a write request bypass a read request (both in flight) that
access the same sector number? Does the I/O scheduler has anything to
do with it? I suppose it is legal since both these requests are
concurrent, however I can't find it anywhere clearly documented. And,
as a consequence:
2. A read request must return the contents of the last completed
write, right? (Obviously this shouldn't happen, still need a
confirmation, through..)

Thank you.

P.S: Please CC me on your reply - I haven't subscribed to the list.

Thanos Makatos
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at