How to check whethera disk supports 32-bit IO

How to check whethera disk supports 32-bit IO

[query]

Hi All ,


    I want to know enable 32-bit IO-support on my SATA hard drive
using hdparm . But before I enable 32-bit support , I want to know
whether my hard drive supports 32-bit IO or not.

    I tried the -I option with hdparm , but it is not telling clearly
whether it supports 32-bit or not.

    The following is the output from the hard drive of my system (hdparm -I ) .

    =====
   Commands/features:
	Enabled	Supported:
	   *	NOP cmd
	   *	READ BUFFER cmd
	   *	WRITE BUFFER cmd
	   *	Host Protected Area feature set
	   *	Look-ahead
	   *	Write cache
	   *	Power Management feature set
		Security Mode feature set
	   *	SMART feature set
	   *	FLUSH CACHE EXT command
	   *	Mandatory FLUSH CACHE command
	   *	Device Configuration Overlay feature set
	   *	48-bit Address feature set
(is it telling that the disk supports 48-bit IO)
		Automatic Acoustic Management feature set
		SET MAX security extension
	   *	DOWNLOAD MICROCODE cmd
	   *	General Purpose Logging feature set
	   *	SMART self-test
	   *	SMART error logging
      =====

   Tried smartctl with the -a option  also , but no luck .

   Any help will be highly appreciated  in determining the IO speed of
the disk .


Thanks
-Bz

Re: How to check whethera disk supports 32-bit IO

[Glynn Clements]

query wrote:

>     I want to know enable 32-bit IO-support on my SATA hard drive
> using hdparm . But before I enable 32-bit support , I want to know
> whether my hard drive supports 32-bit IO or not.

The term "32-bit I/O" relates to communication between the CPU and a
PCI IDE controller. The concept isn't meaningful for an on-board
controller.

As for communication between the controller and the drive, a parallel
ATA interface is 16-bit, while SATA is serial.

> 	   *	48-bit Address feature set
> (is it telling that the disk supports 48-bit IO)

No, it's stating that the drive supports 48-bit LBA addresses. The
original IDE standard used 28-bit addresses which limit the size of
the drive to 137GB (2^28 512-byte sectors).

-- 
Glynn Clements <glynn@gclements.plus.com>

Re: How to check whethera disk supports 32-bit IO

[query]

On Tue, May 18, 2010 at 7:13 PM, Glynn Clements
<glynn@gclements.plus.com> wrote:

Thanks for the clarification .  Need some further clarification...
>
> query wrote:
>
>>     I want to know enable 32-bit IO-support on my SATA hard drive
>> using hdparm . But before I enable 32-bit support , I want to know
>> whether my hard drive supports 32-bit IO or not.
>
> The term "32-bit I/O" relates to communication between the CPU and a
> PCI IDE controller.

"The hdpam man page say "32-bit" refers to data transfers across a PCI
or VLB bus to the interface  card  only ". So , here does the
interface card is referring to the CPU.

> The concept isn't meaningful for an on-board controller.

By On-board controller do you mean to say hardware RAID device or SCSI
devices and we don't have  to set IO parameter
in such devices.



>
> As for communication between the controller and the drive, a parallel
> ATA interface is 16-bit, while SATA is serial.
>
>>          *    48-bit Address feature set
>> (is it telling that the disk supports 48-bit IO)
>
> No, it's stating that the drive supports 48-bit LBA addresses. The
> original IDE standard used 28-bit addresses which limit the size of
> the drive to 137GB (2^28 512-byte sectors).

With 48-bit addressing the limit is 144 petabytes . So , does that
mean we can install hard drive of  capacity  144 petabytes
if disks of such size are available and the BIOS supports it. Can BIOS
put a restriction on the maximum capacity of hard drive we
can install .


Thanks again .
Bz

>
> --
> Glynn Clements <glynn@gclements.plus.com>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-admin" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: How to check whethera disk supports 32-bit IO

[Glynn Clements]

query wrote:

> >>     I want to know enable 32-bit IO-support on my SATA hard drive
> >> using hdparm . But before I enable 32-bit support , I want to know
> >> whether my hard drive supports 32-bit IO or not.
> >
> > The term "32-bit I/O" relates to communication between the CPU and a
> > PCI IDE controller.
> 
> "The hdpam man page say "32-bit" refers to data transfers across a PCI
> or VLB bus to the interface  card  only ". So , here does the
> interface card is referring to the CPU.

"Interface card" means a card that plugs into a PCI or VLB slot (VLB =
VESA Local Bus, an alternative standard for expansion cards which
superseded ISA but was itself superseded by PCI).

> > The concept isn't meaningful for an on-board controller.
> 
> By On-board controller do you mean to say hardware RAID device or SCSI
> devices and we don't have  to set IO parameter
> in such devices.

I mean an IDE controller that's built into the Southbridge.

In any case, you won't find a SATA controller using 16-bit transfers.

> > As for communication between the controller and the drive, a parallel
> > ATA interface is 16-bit, while SATA is serial.
> >
> >>          *    48-bit Address feature set
> >> (is it telling that the disk supports 48-bit IO)
> >
> > No, it's stating that the drive supports 48-bit LBA addresses. The
> > original IDE standard used 28-bit addresses which limit the size of
> > the drive to 137GB (2^28 512-byte sectors).
> 
> With 48-bit addressing the limit is 144 petabytes . So , does that
> mean we can install hard drive of  capacity  144 petabytes
> if disks of such size are available and the BIOS supports it. Can BIOS
> put a restriction on the maximum capacity of hard drive we

The practical limit is the fact that the largest drives currently
available are around 3 terabytes.

The BIOS is only relevant to booting from a drive; a modern OS such as
Linux or Windows doesn't use the BIOS to access the drive.

In the past, BIOSes were limited to 528MB or 8.46GB or 137GB. This
meant that if you wanted to boot from the drive, you had to ensure
that the bootloader and kernel were stored in the region accessible to
the BIOS (typically by creating a separate boot partition at the
beginning of the disk). Once the kernel was loaded, it would be able
to access the entire drive.

For a (long) list of such historical limiations, see:

	http://www.pcguide.com/ref/hdd/bios/size.htm

-- 
Glynn Clements <glynn@gclements.plus.com>
--
To unsubscribe from this list: send the line "unsubscribe linux-admin" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html