On 28 Apr 2000, Andi Kleen wrote:
> Chris Mason <mason@suse.com> writes:
>
> >
> > --- diff/linux-2.3.99-pre6/fs/buffer.c Fri Apr 28 12:09:15 2000
> > +++ linux/fs/buffer.c Thu Apr 27 20:52:49 2000
> > @@ -336,10 +336,11 @@
> >
> > /* sync the superblock to buffers */
> > sb = inode->i_sb;
> > - wait_on_super(sb);
> > + lock_super(sb) ;
> > if (sb->s_op && sb->s_op->write_super)
> > sb->s_op->write_super(sb);
>
> Iirc the wait_on_super instead of lock_super was intentional here, because
> some programs (Oracle?) did spend excessive time being blocked on the
> super block lock.
>
Hmm, that makes sense I can see it being a slow down for ext2 if oracle or
mail servers pound on fsync (in reiserfs, they block on the commit).
I'm not sure I understand why need the locking in sync_supers if we don't
need it in fsync though.
-chris
-
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 : Sun Apr 30 2000 - 21:00:15 EST