Hello ZFS community, I do not have a so strong love towards *probability*. And even less love when probability caracterize true, solid and tangible stuff that I''ve to administer. I start doing some math.. don''t get scared : I''m not going to show you the little scribbles that I''ve done. But I''m looking for some good materials: - online tools to calculate in an analytic or numeric manner different topology - best practice on raid topology : what is the best: - zfs pool tank1 raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 - zfs pool tank1 raidz raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 - ... and other things that I even not thought about Any thought Ced. -- Cedric BRINER Geneva - Switzerland
cedric briner wrote:> Hello ZFS community, > > I do not have a so strong love towards *probability*. And even less love > when probability caracterize true, solid and tangible stuff that I''ve to > administer. > > I start doing some math.. > don''t get scared : I''m not going to show you the little scribbles that > I''ve done. > > But I''m looking for some good materials: > - online tools to calculate in an analytic or numeric manner different > topology > - best practice on raid topology : what is the best: > - zfs pool tank1 raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 > - zfs pool tank1 raidz raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 > - ... and other things that I even not thought about > > Any thoughtI''ve put together some graphs to show various possible configurations. The models are also explained (except for the ditto blocks, which is in the pipeline, hopefully in the next few days) See http://blogs.sun.com/relling -- richard
Richard Elling wrote:> cedric briner wrote: >> Hello ZFS community, >> >> I do not have a so strong love towards *probability*. And even less >> love when probability caracterize true, solid and tangible stuff that >> I''ve to administer. >> >> I start doing some math.. >> don''t get scared : I''m not going to show you the little scribbles that >> I''ve done. >> >> But I''m looking for some good materials: >> - online tools to calculate in an analytic or numeric manner different >> topology >> - best practice on raid topology : what is the best: >> - zfs pool tank1 raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 >> - zfs pool tank1 raidz raidz 1 2 3 raidz 4 5 6 raidz 7 8 9 >> - ... and other things that I even not thought about >> >> Any thought > > I''ve put together some graphs to show various possible configurations. > The models are also explained (except for the ditto blocks, which is > in the pipeline, hopefully in the next few days) > See http://blogs.sun.com/rellingThis is good news to me ! I''ll be checking in the next few days your blog. thanks ! Ced.> -- richard >-- Cedric BRINER Geneva - Switzerland