Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 25 Jul 2010 14:22:17 +0700
From:      Edho P Arief <edhoprima@gmail.com>
To:        Adam Vande More <amvandemore@gmail.com>
Cc:        freebsd-stable <freebsd-stable@freebsd.org>, Dan Langille <dan@langille.org>
Subject:   Re: gpart -b 34 versus gpart -b 1024
Message-ID:  <AANLkTi=RGe7ygDYpF2u3BN4oPYSgyUUijOuLnz2q=XXY@mail.gmail.com>
In-Reply-To: <AANLkTinKEBb5S9REK3nn8GF3U=jRAtYMBBfsC5TB8Xj4@mail.gmail.com>
References:  <4C4BA50B.6050507@langille.org> <4C4BB672.3090109@langille.org>  <AANLkTinKEBb5S9REK3nn8GF3U=jRAtYMBBfsC5TB8Xj4@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, Jul 25, 2010 at 12:37 PM, Adam Vande More <amvandemore@gmail.com> w=
rote:
> On Sat, Jul 24, 2010 at 10:58 PM, Dan Langille <dan@langille.org> wrote:
>
>> =C2=A0 =C2=A0 =C2=A0 -------Sequential Output-------- ---Sequential Inpu=
t-- --Random--
>> =C2=A0 =C2=A0 =C2=A0 -Per Char- --Block--- -Rewrite-- -Per Char- --Block=
--- --Seeks---
>> =C2=A0 =C2=A0GB M/sec %CPU M/sec %CPU M/sec %CPU M/sec %CPU M/sec %CPU =
=C2=A0/sec %CPU
>> =C2=A0 =C2=A050 110.5 81.0 112.8 15.0 =C2=A062.8 =C2=A09.0 =C2=A072.9 48=
.5 139.7 =C2=A09.5 =C2=A0 144 =C2=A00.9
>>
>> Here, the results aren't much better either... =C2=A0am I not aligning t=
his
>> partition correctly? =C2=A0Missing something else? =C2=A0Or... are they =
both 4K block
>> aligned?
>
>
> The alignment doesn't apply to all drives, just the 4k WD's and some ssd'=
s.
>
> If they were misaligned, you would see a large difference in the tests. =
=C2=A0A
> few points one way or other in these is largely meaningless.
>
> That being said, if I were you I would set -b 2048(1 MB) as the default, =
the
> amount of space wasted is trivial and your partition will always be
> aligned. =C2=A0People following your tutorials may have a variety of diff=
erent
> drives and that setting is safe for all.
>

shouldn't it start at 2049? Starting at 2048 means it starts at 2048th
logical block which is 512 bytes off from physical block, doesn't it?


--=20
O< ascii ribbon campaign - stop html mail - www.asciiribbon.org



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTi=RGe7ygDYpF2u3BN4oPYSgyUUijOuLnz2q=XXY>