[zfs-discuss] RAIDZ-2 disk space

Gionatan Danti g.danti at assyoma.it
Thu Apr 5 17:50:12 EDT 2018


Il 05-04-2018 23:08 Gandalf Corvotempesta via zfs-discuss ha scritto:
> Some questions: why linux is seeing dissk as 447GB (based on fdisk
> output) and not as 480GB ?

Because HDD/SSD vendors use the convention GB = 10^3 bytes, while Linux 
and basically all other operating systems define GB = 2^30 bytes (see 
GiB). So, 480 GB = 447 GiB. Bonus info: flash chips are often produced 
in multiple of power of 2 - this means that your SSD really has *at 
least* 480 GiB, probably more; however, the exceeding flash is used as 
an (hidden) spare ares for data correction and background garbage 
collection.

> The 647GB available, can be used fully or should I reserve about 20%
> for ZFS? (i've read somewhere that is not suggested to fill ZFS
> totally)

With recent developments, the "soft-limit" to not pass should be around 
95%. Passing it will cause a very noticeable performance drop.

Regards.

-- 
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