Date: Thu, 30 Jun 2016 16:00:40 +0200 From: Fabian Keil <freebsd-listen@fabiankeil.de> To: freebsd-hackers@freebsd.org Subject: Re: ggatel(8) extension for binding multiple files Message-ID: <20160630160040.279fc306@fabiankeil.de> In-Reply-To: <nl2eii$ukl$1@ger.gmane.org> References: <nl2eii$ukl$1@ger.gmane.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--Sig_/LuxbYHEM76xLGs6Q6PdZ1HH
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
Julian Hsiao <julian@hsiao.email> wrote:
> I've been working on extending ggatel(8) to support binding multiple files
> to one device, similar to how sparse bundles work on OS X. You could
> simulate the functionality with ggatel(8) / md(4) + gconcat(8), but this
> scales poorly when you have 10^5 files. I've got a working prototype that
> passes some simple tests I wrote. I also tried using it as backing store
> for UFS and ZFS, copied /usr/{src,obj} over, and ran make build world (wi=
th
> ZFS followed by zpool scrub).
>=20
> To use it, instead of passing a file to ggatel(8) as the last argument,
> pass a directory with files numerically named in hex (i.e. 0, 1, 2 ..., 9,
> a, b, ..., e, f, 10, 11, ...).
>=20
> So, I think it's a good time to gauge the community's interest in this
> feature and whether it'd be possible to merge it to trunk.
In what situation do you think this is preferable to simply using
a single sparse file or zvol as backing store?
Even using gvirstor sounds like less maintenance hassle to me.
> Known issues:
[...]
> - Both ggatel(8) and md(4) implement BIO_DELETE by zeroing the requested
> range. However, this interacts poorly with ZFS since it BIO_DELETEs
> the entire device at pool creation. I know there is a ZFS sysctl to
> disable the behavior, but I think the device should just not advertise
> support if it had to fake it anyway, so I didn't implement it.
In ElectroBSD, ggated writes zeros for BIO_DELETEs[0] and as far as I'm
concerned this interacts rather well with ZFS as ZFS will convert the
zeros back to BIO_DELETEs (if any compression is enabled) and thus the
intended effect is achieved.
I suspect that the reason why it may perform poorly with ggatel is that
IIRC ggatel does not use a request queue and worker threads and thus
performs poorly in general (compared to ggatec/ggated).
Fabian
[0] Patch 042 in:
https://www.fabiankeil.de/sourcecode/electrobsd/ElectroBSD-r295083-0c7f4d6.=
diff
(The patch set is out of date, but the ggate[cd]-related patches should sti=
ll apply.)
--Sig_/LuxbYHEM76xLGs6Q6PdZ1HH
Content-Type: application/pgp-signature
Content-Description: OpenPGP digital signature
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iEYEARECAAYFAld1JggACgkQBYqIVf93VJ2AsQCcDsQbrwAiLzaYrbVfjCOQ/Ulq
gH0An2Y2+JaCmMLfkPXivVtfI0wo6bb1
=HZon
-----END PGP SIGNATURE-----
--Sig_/LuxbYHEM76xLGs6Q6PdZ1HH--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160630160040.279fc306>