Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 7 Jun 2005 21:40:05 +0200
From:      Pawel Jakub Dawidek <pjd@FreeBSD.org>
To:        Ivan Voras <ivoras@fer.hr>
Cc:        hackers@freebsd.org, scottl@FreeBSD.org, phk@FreeBSD.org
Subject:   Re: Google SoC idea
Message-ID:  <20050607194005.GG837@darkness.comp.waw.pl>
In-Reply-To: <42A475AB.6020808@fer.hr>
References:  <42A475AB.6020808@fer.hr>

next in thread | previous in thread | raw e-mail | index | archive | help

--AG6PiNxwwkUqaz46
Content-Type: text/plain; charset=iso-8859-2
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Mon, Jun 06, 2005 at 06:11:23PM +0200, Ivan Voras wrote:
+> I have an idea that I could implement through Google's "Summer of Code"=
=20
+> project, but as I have little experience with stuff it involves (kernel=
=20
+> programming / disks / filesystem optimization), so I expect any answer=
=20
+> from "It won't work" or "It's useless" to "It can't be done".  :)
+>=20
+> The idea is this: to implement sort of GEOM-layer disk data journaling=
=20
+> system. I imagine it to be a GEOM class using two "lower-level" devices:=
=20
+> one for data and one for the "journal" (this way, the journal device can=
=20
+> be on a fast and small disk). Such journaled device could be used to=20
+> host any filesystem, probably mounted with synchronoues-access, and it=
=20
+> will result in faster write access by keeping the writes sequential in=
=20
+> the "journal" device. Journal information will be commited to the data=
=20
+> disk periodically by a separate log-writer thread, or when it gets full.=
=20
+> The "data disk" will be consistent so it can be used without it's=20
+> "journal" part (after a clean disconnect/rebuild) if needed. At the=20
+> worst case, I think this will help performance in cases when there's a=
=20
+> burst of write activity followed by a period of IO idleness.
+>=20
+> I've made the above idea more-or-less from my head in one afternoon, so=
=20
+> it's perfectly possible that I'm missing some vital point or that it's=
=20
+> complete nonsense :)
+>=20
+> Does it make sense to do it this way? Is it worth applying for the SoC?

Not sure. Basically this is simlar what softupdate does, I think.
=46rom another point of view softupdates are only available for UFS.
You probably wants to hear scottl and phk opinions (CCed).

--=20
Pawel Jakub Dawidek                       http://www.wheel.pl
pjd@FreeBSD.org                           http://www.FreeBSD.org
FreeBSD committer                         Am I Evil? Yes, I Am!

--AG6PiNxwwkUqaz46
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (FreeBSD)

iD8DBQFCpfgVForvXbEpPzQRAulyAKDRdFAB5RebkoghErbCJRqidowyCgCg6j/V
Inrlfvv6F5+Hwq+VvjImM4Y=
=wc9J
-----END PGP SIGNATURE-----

--AG6PiNxwwkUqaz46--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050607194005.GG837>