From: Mark Knecht <markknecht@gmail.com>
To: gentoo-user@lists.gentoo.org
Subject: Re: [gentoo-user] 1-Terabyte drives - 4K sector sizes? -> bar performance so far
Date: Sun, 14 Feb 2010 19:17:21 -0800 [thread overview]
Message-ID: <5bdc1c8b1002141917tabba6a6g511e9aa8e68682bc@mail.gmail.com> (raw)
In-Reply-To: <20100215011740.GA27687@math.princeton.edu>
2010/2/14 Willie Wong <wwong@math.princeton.edu>:
> On Mon, Feb 15, 2010 at 01:48:01AM +0100, Frank Steinmetzger wrote:
<SNIP>
>>
>> action SS (1st) SS (2nd) SS+2 SS+4 SS+6 SS+8
>> -------------+----------+----------+----------+----------+----------+----------
>> untar portage 3m12.517 2m55.916 1m46.663 1m35.341 1m47.829 1m43.677
>> rm portage 4m11.109 3m54.950 3m18.820 3m11.378 3m21.804 3m12.433
>> cp 1GB file 0m21.383 0m13.558 0m14.920 0m12.813 0m13.407 0m13.681
>
> Instead of guessing using this rather imprecise metric, why not just
> look up the serial number of your drive and see what the physical
> sector size is? If you don't want to open your box, you can usually
> get the information from dmesg.
hdparm capital eye works very nicely:
gandalf ~ # hdparm -I /dev/sda
/dev/sda:
ATA device, with non-removable media
Model Number: WDC WD10EARS-00Y5B1
Serial Number: WD-WCAV55464493
Firmware Revision: 80.00A80
Transport: Serial, SATA 1.0a, SATA II Extensions,
SATA Rev 2.5, SATA Rev 2.6
Standards:
Supported: 8 7 6 5
Likely used: 8
<SNIP>
>
> Only caveat: don't trust the harddrive to report accurate geometry.
> This whole issue is due to the harddrives lying about their physical
> geometry to be compatible with older versions of Windows. So the
> physical sector size listed in dmesg may not be the real one. Which is
> why you are advised to look up the model number on the vendor's
> website yourself to determine the physical sector size.
>
> W
> --
> Willie W. Wong wwong@math.princeton.edu
Very true...
Since this thread started and you help (me at least1) understand what
I was dealing with I got in contact with Mark Lord - the developer and
maintainer of the hdparm program. I was interested in seeing if we
could get hdparm to recognize this aspect of the drive. He was very
interested and asked me to send along additional info which he then
analyzed and decided that, at least at this time, even drives that we
__know__ are 4K sector sizes are not implementing any way of reading
it from the drive's firmware which is supported, at least in the newer
SATA specs. With that he decided that even for his own new 4K drives
he cannot do anything except either assume they are 4K and partition
appropriately or look up specs specifically as you suggest.
Currently I'm partial to the idea that all my sector starting
addresses will end in '000'. It's easy to remember and at most that
wastes (I think) 512K bytes between sectors so it's not much in terms
of the overall disk space. Just a couple of megabyte on a drive with 4
partitions.
= Mark
next prev parent reply other threads:[~2010-02-15 3:18 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-07 16:27 [gentoo-user] 1-Terabyte drives - 4K sector sizes? -> bar performance so far Mark Knecht
2010-02-07 17:30 ` Alexander
2010-02-07 18:19 ` Volker Armin Hemmann
2010-02-07 19:26 ` Mark Knecht
2010-02-07 18:38 ` Mark Knecht
2010-02-07 19:16 ` Volker Armin Hemmann
2010-02-07 19:39 ` Willie Wong
2010-02-07 20:31 ` Mark Knecht
2010-02-07 21:59 ` Kyle Bader
2010-02-07 21:42 ` Mark Knecht
2010-02-08 2:08 ` Willie Wong
2010-02-08 17:10 ` Mark Knecht
2010-02-08 18:52 ` Valmor de Almeida
2010-02-08 20:34 ` Paul Hartman
2010-02-09 0:27 ` Neil Bothwick
2010-02-09 12:46 ` Stroller
2010-02-09 13:34 ` Neil Bothwick
2010-02-09 23:37 ` Iain Buchanan
2010-02-10 6:31 ` Volker Armin Hemmann
2010-02-10 7:11 ` Iain Buchanan
2010-02-10 8:37 ` Volker Armin Hemmann
2010-02-10 8:43 ` Volker Armin Hemmann
2010-02-09 13:35 ` Volker Armin Hemmann
2010-02-09 13:57 ` J. Roeleveld
2010-02-09 15:11 ` Stroller
2010-02-09 15:27 ` J. Roeleveld
2010-02-09 17:38 ` Stroller
2010-02-09 18:25 ` Mark Knecht
2010-02-09 19:29 ` J. Roeleveld
2010-02-09 15:43 ` Neil Bothwick
2010-02-09 17:17 ` Stroller
2010-02-09 20:30 ` Neil Bothwick
2010-02-09 18:03 ` Neil Walker
2010-02-09 19:37 ` J. Roeleveld
2010-02-09 23:52 ` Iain Buchanan
2010-02-10 1:16 ` Stroller
2010-02-10 6:59 ` Neil Walker
2010-02-10 7:31 ` Iain Buchanan
2010-02-10 1:28 ` Stroller
2010-02-10 11:14 ` J. Roeleveld
2010-02-10 16:37 ` Stroller
2010-02-10 17:26 ` J. Roeleveld
2010-02-10 20:48 ` Stroller
2010-02-10 0:11 ` Peter Humphrey
2010-02-10 6:48 ` Neil Walker
2010-02-09 17:33 ` Paul Hartman
2010-02-09 7:47 ` J. Roeleveld
2010-02-09 23:22 ` Iain Buchanan
2010-02-10 7:08 ` Alan McKinnon
2010-02-10 10:56 ` J. Roeleveld
2010-02-10 10:53 ` J. Roeleveld
2010-02-10 11:03 ` Volker Armin Hemmann
2010-02-10 11:17 ` J. Roeleveld
2010-02-10 11:24 ` Volker Armin Hemmann
2010-02-08 5:25 ` Valmor de Almeida
2010-02-08 19:57 ` Stroller
2010-02-09 0:05 ` Frank Steinmetzger
2010-02-09 0:37 ` Mark Knecht
2010-02-09 2:48 ` Frank Steinmetzger
2010-02-09 17:09 ` Frank Steinmetzger
2010-02-09 18:21 ` Mark Knecht
2010-02-09 21:13 ` Frank Steinmetzger
2010-02-09 22:17 ` J. Roeleveld
2010-02-09 22:54 ` Mark Knecht
2010-02-10 0:31 ` Iain Buchanan
2010-02-10 1:27 ` Mark Knecht
2010-02-10 7:06 ` Iain Buchanan
2010-02-09 16:31 ` Mark Knecht
2010-02-12 9:06 ` Mick
2010-02-12 12:14 ` Mark Knecht
2010-02-09 0:47 ` Stroller
2010-02-09 2:20 ` Willie Wong
2010-02-15 0:48 ` Frank Steinmetzger
2010-02-15 1:17 ` Willie Wong
2010-02-15 3:17 ` Mark Knecht [this message]
2010-02-15 18:03 ` Frank Steinmetzger
2010-02-15 23:53 ` Alex Schuster
2010-02-16 17:35 ` Frank Steinmetzger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5bdc1c8b1002141917tabba6a6g511e9aa8e68682bc@mail.gmail.com \
--to=markknecht@gmail.com \
--cc=gentoo-user@lists.gentoo.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox