On Mon, 21 Feb 2000, Alexander Viro wrote:
>> >BTW, _where_ can one call ext2_put_inode() without the big lock?
>>
>> shrink_icache_memory -> ... -> sync_one -> ... -> iput -> ext2_put_inode
>
>Oh, crap... Yes, now one can. Which doesn't make it a good idea, BTW.
If I would be acquiring the big kernel lock in inode.c you would now
complain me that I am not allowing SMP threaded fs to scale (and I would
agree with you and that's why I didn't do that in first place).
>Why doing sync_all_inodes() here? Instead of just skipping locked ones,
>that is.
locked != dirty. If you want to make progress with slow bdflush syncs
you'd better try to free inodes once they are not dirty.
Andrea
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Wed Feb 23 2000 - 21:00:30 EST