[zfs-discuss] ZFS on RAID-5 array

Gionatan Danti g.danti at assyoma.it
Thu Apr 12 19:04:12 EDT 2018


Il 12-04-2018 19:30 Gordan Bobic via zfs-discuss ha scritto:
> Right up to the point when the disk starts feeding you garbage instead
> of errors (yes, it happens). At that point the controller won't be
> able to tell if that happened without reading the whole stripe, which
> is exactly what ZFS does anyway, and any theoretical performance
> advantage disappears.

Enterprise SAS controllers and disks can use the Data Integrity Field to 
checksum both data and location of each written LBA (see here[1] and 
here[2]). That said, such controllers and disks are more expensive than 
their SATA equivalent.

[1] https://access.redhat.com/solutions/41548
[2] https://en.wikipedia.org/wiki/Data_Integrity_Field

-- 
Danti Gionatan
Supporto Tecnico
Assyoma S.r.l. - www.assyoma.it
email: g.danti at assyoma.it - info at assyoma.it
GPG public key ID: FF5F32A8


More information about the zfs-discuss mailing list