I have a zpool of five 1.5TB disks in raidz1. They are on c?t?d?p0 devices - using the full disk, not any slice or partition, because the pool was created in zfs-fuse in linux and no partition tables were ever created. (for the full saga of my move from that to opensolaris, anyone who missed out on the fun can read the thread http://www.mail-archive.com/zfs-discuss@opensolaris.org/msg34813.html - but I will try to include all relevant information so that's not necessary). When I had gotten things working in opensolaris, and done a scrub, I had gotten some errors on one disk and so I offlined it, overwrote the whole disk with random-looking data, and read the data back to check that the disk was behaving. it was, and I resilvered, and things have seemed fine since.
I just noticed, though (some time later, with things working correctly in the meantime), that I now have a EFI partition table on the disk that I resilvered. none of the others have any partition table. This confuses me greatly, for a few reasons. One, why did zfs create a partition table? I thought it only did that when you gave it a shorthand disk in the form c?t?d? with no slice or partition number - I did replace giving it the full path /dev/dsk/c9t4d0p0. Doesn't this mean that zfs must actually be using s0 of the drive, not p0? c9t4d0p0 is what shows up in the zpool status, along with p0 devices for the other four drives. Two, given that this one disk has a EFI partition table - including 8MB reserved slice 8 - the actual device that zfs is using is more than 8MB smaller than the other four. How am I using a raidz1 with unequally sized devices? Since this has been running without a problem for a few weeks now, I'm not actually concerned about it being a problem - just rather confused. Can anybody explain what's up with this? Thanks, -Ethan
_______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
