Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 3 Nov 2013 14:28:18 -0800
From:      Tom Samplonius <tom@samplonius.org>
To:        Zenny <garbytrash@gmail.com>
Cc:        freebsd-stable@freebsd.org
Subject:   Re: HDD-manufacture induced ZFS limitations
Message-ID:  <7808D09C-D497-480B-AB88-FA300485B3CE@samplonius.org>
In-Reply-To: <CACuV5sB2JxFX16DYswh0SDo6AbCs3P0pdY0xwjnGT5Mi5%2BJDCw@mail.gmail.com>
References:  <CACuV5sB2JxFX16DYswh0SDo6AbCs3P0pdY0xwjnGT5Mi5%2BJDCw@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help

On Nov 3, 2013, at 1:07 AM, Zenny <garbytrash@gmail.com> wrote:

> Hi:
>=20
> PROBLEM
>=20
> I came across a very weird situation because HDD-manufacturer counts
> HDD space according to metric system instead of multiplication of 1024

  That is not weird or unusual.  For example, 72GB disks range from 72GB =
to 73.1GB (or so) in size.  It doesn't really have anything to do with =
the 1024 vs 1000 measurement issue.  Manufacturing variations result in =
a lot of different sizes.

  Major commercial storage vendors automatically round down to the =
nearest known increment.  This worked well for SCSI disks, as they =
always doubled in size each generation (9, 18, 36, 72, 144, etc.).  It =
doesn't work as well with SATA disks.

  Or down to the nearest whole GB, if it is not a known size.



Tom=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?7808D09C-D497-480B-AB88-FA300485B3CE>