HAST + ZFS + NFS + CARP

[InterNetX - Juergen Gotteswinter]

i see so much pain upcoming when $something goes wrong, even the smallest piece
will end up in drama
 
zfs has been designed as a pragmatic stupid simpel solid solution, why whould
one rape this concept with such complexity :(
 

> Miroslav Lachman <000.fbsd at quip.cz> hat am 4. Juli 2016 um 14:56 geschrieben:
>
>
> Julien Cigar wrote on 07/04/2016 14:25:
>
> > another option I had in mind is to export ZVOL through iSCSI:
> > - on serverA: $> zpool create storage mirror /dev/ada1 /dev/ada2
> > - on serverB: $> zpool create storage mirror /dev/ada1 /dev/ada2
> >
> > create a 50G dedicated redundant storage for serverC:
> > - on serverA: $> zfs create -V 50G storage/serverc
> > - on serverB: $> zfs create -V 50G storage/serverc
> >
> > iSCSI export /dev/zvol/storage/serverc from serverA and serverB and
> > create a ZFS dataset on serverC:
> > - on serverC: $> zpool create storage mirror /dev/ivol1 /dev/ivol2
> >
> > (where ivol1 is the volume from serverA and ivol2 the volume from
> > serverB)
> >
> > create, for example, a dataset for the dovecot service
> > - on serverC: $> zfs create -o compress=lz4 storage/dovecot
>
> I think it will be painfully slow. ZFS on top of ZFS throught iSCSI...
> too much layering, too much delays.
>
> Miroslav Lachman
> _______________________________________________
> freebsd-fs at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-fs
> To unsubscribe, send any mail to "freebsd-fs-unsubscribe at freebsd.org"