FreeBSD 9 and gmirror /geom raid

[Rainer Duffner]

Am Thu, 8 Mar 2012 11:35:48 GMT
schrieb Martin Simmons <martin at lispworks.com>:

> >>>>> On Thu, 08 Mar 2012 05:58:11 +0100, Davide D'Amico said:
> > 
> > Il 08/03/12 00:02, Freddie Cash ha scritto:
> > > On Wed, Mar 7, 2012 at 6:14 AM, Davide D'Amico
> > > <davide.damico at contactlab.com>  wrote:
> > >> Hi, I have a server DELL R210 with two sata drives:
> > >> ada0 at ahcich0 bus 0 scbus0 target 0 lun 0
> > >> ada0:<SAMSUNG HE253GJ 1AJ30001>  ATA-8 SATA 2.x device
> > >> ada0: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
> > >> ada0: Command Queueing enabled
> > >> ada0: 238418MB (488281250 512 byte sectors: 16H 63S/T 16383C)
> > >> ada0: Previously was known as ad4
> > >> ada1 at ahcich1 bus 0 scbus1 target 0 lun 0
> > >> ada1:<SAMSUNG HE253GJ 1AJ30001>  ATA-8 SATA 2.x device
> > >> ada1: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
> > >> ada1: Command Queueing enabled
> > >> ada1: 238418MB (488281250 512 byte sectors: 16H 63S/T 16383C)
> > >> ada1: Previously was known as ad6
> > >>
> > >> Previously (8.x) - when I didn't use a hw raid - I used to
> > >> install freebsd in a drive (i.e. ad4), boot from it and then:
> > >>
> > >> # sysctl kern.geom.debugflags=16
> > >> # gmirror label -v -b round-robin data ad4
> > >> # gmirror insert data ad6
> > >> // Modification to /etc/fstab
> > >> // reboot
> > >>
> > >> How could accomplish to the same task with 9.0-RELEASE?
> > > http://people.freebsd.org/~rse/mirror/
> > >
> > Hi Freddie, and thanks for your link.
> > 
> > I followed that procedure until 9.0-RELEASE but the new installer
> > uses GPT as the default partition schema, which seems incompatible
> > with gmirror.
> > 
> > I noticed in the handbook 
> > (http://www.freebsd.org/doc/handbook/geom-mirror.html):
> > "The following procedure is also incompatible with the default 
> > installation settings of FreeBSD 9./X/which use the newGPTpartition 
> > scheme. GEOM will overwriteGPTmetadata, causing data loss and
> > possibly an unbootable system."
> > 
> > So I think that the old procedure is no more useful.
> 
> I think the problem with the old procedure is that it mirrors the
> whole disk. This fails because both gmirror and GPT store data in the
> last few blocks of the disk.
> 
> If you create gmirror(s) at the GPT partition level instead, then it
> should be safe.


maybe like this:

http://blather.michaelwlucas.com/archives/1071

Haven't tried it, but I may need it at some point...