On 05/31/2011 02:35 PM, Ted Ts'o wrote:
On Tue, May 31, 2011 at 12:18:11PM +0200, Bernd Schubert wrote:
Out of interest, did anyone ever benchmark if dirindex provides any
advantages to readdir? And did those benchmarks include the
disadvantages of the present implementation (non-linear inode
numbers from readdir, so disk seeks on stat() (e.g. from 'ls -l') or
'rm -fr $dir')?
The problem is that seekdir/telldir is terminally broken (and so is
NFSv2 for using a such a tiny cookie) in that it fundamentally assumes
a linear data structure. If you're going to use any kind of
tree-based data structure, a 32-bit "offset" for seekdir/telldir just
doesn't cut it. We actually play games where we memoize the low
32-bits of the hash and keep track of which cookies we hand out via
seekdir/telldir so that things mostly work --- except for NFSv2, where
with the 32-bit cookie, you're just hosed.
Well, lets just ignore NFSv2, for NFS there are better working v3 and v4
alternatives. My real concern are ext3 and ext4, which have
#define pos2min_hash(pos) (0)
The reason why we have to iterate over the directory in hash tree
order is because if we have a leaf node split, half the directories
entries get copied to another directory entry, given the promises made
by seekdir() and telldir() about directory entries appearing exactly
once during a readdir() stream, even if you hold the fd open for weeks
or days, mean that you really have to iterate over things in hash
order.
Ah, I never looked into the dirindex implementation, I always thought
the dirindex blocks get updated and not real directory entries as well.
I'd have to look, since it's been too many years, but as I recall the
problem was that there is a common path for NFSv2 and NFSv3/v4, so we
don't know whether we can hand back a 32-bit cookie or a 64-bit
cookie, so we're always handing the NFS server a 32-bit "offset", even
though ew could do better. Actually, if we had an interface where we
could give you a 128-bit "offset" into the directory, we could
probably eliminate the duplicate cookie problem entirely. We just
send 64-bits worth of hash, plus the first two bytes of the of file
name.
Well, personally I'm more interested in user space, but I don't see any
difference between NFS, other kernel paths and user space. I think this
is used for everything:
/* Some one has messed with f_pos; reset the world */
if (info->last_pos != filp->f_pos) {
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
info->curr_hash = pos2maj_hash(filp->f_pos);
info->curr_minor_hash = pos2min_hash(filp->f_pos);
}
So with the above #define pos2min_hash(), info->curr_minor_hash is
always zero with no exception. Or do I miss something?
3) Disable dirindexing for readdirs
That won't work, since it will break POSIX compliance. Once again,
we're tied by the decisions made decades ago...
I really wonder if we couldn't set a flag somewhere to ignore posix for
applications that could handle it on their own. Pity that opendir
doesn't allow to set flags. An ioctl would be another choice.
Thanks,
Bernd
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
