Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Andreas Dilger <adilger@dilger.ca>
Message-Id: <6E4DE257-4220-4B5B-B3D0-B67C7BC69BB5@dilger.ca>
Content-Type: multipart/signed;
 boundary="Apple-Mail=_9ABD2FFE-ADCA-4E79-B98F-629817F7E7A3";
 protocol="application/pgp-signature"; micalg=pgp-sha256
Mime-Version: 1.0 (Mac OS X Mail 10.3 \(3273\))
Subject: Re: How capacious and well-indexed are ext4, xfs and btrfs
 directories?
Date:   Thu, 20 May 2021 23:13:28 -0600
In-Reply-To: <206078.1621264018@warthog.procyon.org.uk>
Cc:     Theodore Ts'o <tytso@mit.edu>,
        "Darrick J. Wong" <djwong@kernel.org>, Chris Mason <clm@fb.com>,
        Ext4 Developers List <linux-ext4@vger.kernel.org>,
        xfs <linux-xfs@vger.kernel.org>,
        linux-btrfs <linux-btrfs@vger.kernel.org>,
        linux-cachefs@redhat.com,
        linux-fsdevel <linux-fsdevel@vger.kernel.org>,
        NeilBrown <neilb@suse.com>
To:     David Howells <dhowells@redhat.com>
References: <206078.1621264018@warthog.procyon.org.uk>
Precedence: bulk


--Apple-Mail=_9ABD2FFE-ADCA-4E79-B98F-629817F7E7A3
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
	charset=us-ascii

On May 17, 2021, at 9:06 AM, David Howells <dhowells@redhat.com> wrote:
> With filesystems like ext4, xfs and btrfs, what are the limits on =
directory
> capacity, and how well are they indexed?
>=20
> The reason I ask is that inside of cachefiles, I insert fanout =
directories
> inside index directories to divide up the space for ext2 to cope with =
the
> limits on directory sizes and that it did linear searches (IIRC).
>=20
> For some applications, I need to be able to cache over 1M entries =
(render
> farm) and even a kernel tree has over 100k.
>=20
> What I'd like to do is remove the fanout directories, so that for each =
logical
> "volume"[*] I have a single directory with all the files in it.  But =
that
> means sticking massive amounts of entries into a single directory and =
hoping
> it (a) isn't too slow and (b) doesn't hit the capacity limit.

Ext4 can comfortably handle ~12M entries in a single directory, if the
filenames are not too long (e.g. 32 bytes or so).  With the "large_dir"
feature (since 4.13, but not enabled by default) a single directory can
hold around 4B entries, basically all the inodes of a filesystem.

There are performance knees as the index grows to a new level (~50k, =
10M,
depending on filename length)

As described elsewhere in the thread, allowing concurrent create and =
unlink
in a directory (rename probably not needed) would be invaluable for =
scaling
multi-threaded workloads.  Neil Brown posted a prototype patch to add =
this
to the VFS for NFS:

=
https://lore.kernel.org/lustre-devel/8736rsbdx1.fsf@notabene.neil.brown.na=
me/

Maybe it's time to restart that discussion?

Cheers, Andreas


--Apple-Mail=_9ABD2FFE-ADCA-4E79-B98F-629817F7E7A3
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
	filename=signature.asc
Content-Type: application/pgp-signature;
	name=signature.asc
Content-Description: Message signed with OpenPGP

-----BEGIN PGP SIGNATURE-----
Comment: GPGTools - http://gpgtools.org
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=A2zI
-----END PGP SIGNATURE-----

--Apple-Mail=_9ABD2FFE-ADCA-4E79-B98F-629817F7E7A3--