Alexander Viro writes:
> Trond, I'm not asking about implementation - the question being what
> semantics do you want for nfs_zap_caches() wrt user-mapped pages.
Ok, looking through sendmail, and then db2, the situation is
created by the db2 library. If the process does the following:
1. creates NFS file
2. sets file size by lseek + write
3. maps it
4. fcntl locks the file (writes above data back to file)
5. write to the mapping (makes pages dirty)
6. fcntl unlocks it (dirty page data is NOT written back)
7. closes it
8. unlinks it
9. some time later unmaps it (causes dirty data to be written back)
Note that (6) doesn't act as a barrier to synchronise writes in this case,
but it does for any normal write()s. Surely NFS should cause any dirty
data associated with the file to be written back to the server no matter
what?
Although Linus' fix seems to prevent the problem, I get the feeling that it
is a sticky plaster over a much bigger problem.
_____
|_____| ------------------------------------------------- ---+---+-
| | Russell King rmk@arm.linux.org.uk --- ---
| | | | http://www.arm.linux.org.uk/personal/aboutme.html / / |
| +-+-+ --- -+-
/ | THE developer of ARM Linux |+| /|\
/ | | | --- |
+-+-+ ------------------------------------------------- /\\\ |
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Oct 23 2000 - 21:00:17 EST