Date: Sat, 20 Feb 2010 01:07:58 +0100 From: Pawel Jakub Dawidek <pjd@FreeBSD.org> To: Garrett Cooper <yanefbsd@gmail.com> Cc: freebsd-fs@freebsd.org Subject: Re: HAST (Highly Available Storage) now in HEAD. Message-ID: <20100220000758.GI1617@garage.freebsd.pl> In-Reply-To: <7d6fde3d1002191541k51ab8526ub18a7c05484112f5@mail.gmail.com> References: <20100219200725.GA1617@garage.freebsd.pl> <7d6fde3d1002191511h4caac149tf39dcc37cf750afe@mail.gmail.com> <20100219233744.GG1617@garage.freebsd.pl> <7d6fde3d1002191541k51ab8526ub18a7c05484112f5@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--aznLbwQ42o7LEaqN Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Feb 19, 2010 at 03:41:41PM -0800, Garrett Cooper wrote: > On Fri, Feb 19, 2010 at 3:37 PM, Pawel Jakub Dawidek <pjd@freebsd.org> wr= ote: > > On Fri, Feb 19, 2010 at 03:11:44PM -0800, Garrett Cooper wrote: > >> =A0 =A0 Very cool stuff. How many nodes max are you targeting for this > >> service [...] > > > > Currently HAST is intended for use only with High Availability clusters, > > not for performance clusters and is limited to exactly two nodes - one > > primary node, which has access to shared storage and one secondary node, > > which just receives updates from primary. User's applications should > > only work on primary node. >=20 > I was looking forward a bit more than what's setup today TBH, but that's = ok... What exactly were you expecting? Even if HAST would be able to operate in multi-master mode, I don't think we have any file system that can take advantage of such configuration. Also note that DRBD, which is on the market for a long time already can operate also only in primary-secondary configuration for production uses. Eventhough it supports primary-primary configuration, it is not recommended for production use AFAIK. If you describe your needs, we might be able to figure something out. > [...] Is the data being checksummed / > verified somewhere to ensure integrity at all (I would think so / hope > so...)? You mean on-disk on on-wire? There is initial code in HAST to checksum data on-wire, but not yet finished. Checksumming data on-disk is not planed for HAST, it can be done using different GEOM classes, like geli. The most sense currently makes putting ZFS on HAST, because with UFS switching between the nodes will take a long time thanks to fsck. And once you are using ZFS you get checksumming for free (on both disk and wire). --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --aznLbwQ42o7LEaqN Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAkt/J94ACgkQForvXbEpPzT6GwCg1Gh616DCpk6pO57WxivB18My MdkAoJ2YeStG/1ueLYCaQaVwY2OkEm3t =MeYL -----END PGP SIGNATURE----- --aznLbwQ42o7LEaqN--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20100220000758.GI1617>