zfs discuss - Mar 2010 - ZFS and 4kb sector Drives (All new western digital GREEN Drives?)

Does zfs handle 4kb sectors properly or does it always assume 512b sectors?

If it does, we could manually create a slice properly aligned and set zfs to use
it...






--
 The sender of this email subscribes to Perimeter E-Security''s email
 anti-virus service. This email has been scanned for malicious code and is
 believed to be virus free. For more information on email security please
 visit: http://www.perimeterusa.com/services/messaging
 This communication is confidential, intended only for the named recipient(s)
 above and may contain trade secrets or other information that is exempt from
 disclosure under applicable law. Any use, dissemination, distribution or
 copying of this communication by anyone other than the named recipient(s) is
 strictly prohibited. If you have received this communication in error, please
 delete the email and immediately notify our Command Center at 203-541-3444.

 Thanks 
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100326/918c8269/attachment.html>

Yes, it does.

Bottone, Frank ??:
>
> Does zfs handle 4kb sectors properly or does it always assume 512b 
> sectors?
>
> If it does, we could manually create a slice properly aligned and set 
> zfs to use it?
>
>
> --
>  The sender of this email subscribes to Perimeter E-Security''s
email
>  anti-virus service. This email has been scanned for malicious code and is
>  believed to be virus free. For more information on email security please
>  visit: http://www.perimeterusa.com/services/messaging 
>  This communication is confidential, intended only for the named
recipient(s)
>  above and may contain trade secrets or other information that is exempt
from
>  disclosure under applicable law. Any use, dissemination, distribution or
>  copying of this communication by anyone other than the named recipient(s)
is
>  strictly prohibited. If you have received this communication in error,
please
>  delete the email and immediately notify our Command Center at
203-541-3444.
>
>  Thanks
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> zfs-discuss mailing list
> zfs-discuss at opensolaris.org
> http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
>

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 26.03.2010 16:55, Bottone, Frank wrote:
> Does zfs handle 4kb sectors properly or does it always assume 512b sectors?
> 
>  
> 
> If it does, we could manually create a slice properly aligned and set
> zfs to use it?
A real simple patch would be to attempt alignment with 4096 every time
(since 4096 is a multiple of 512 there really wouldn''t be a performance
penalty here). This would mean that things are optimal on _ALL_ disks.
(and allow those of us using more advanced diskcontrollers to set the
strip-size (strip size, not stripe size) to 4K as well)

//Svein

- -- 
- --------+-------------------+-------------------------------
  /"\   |Svein Skogen       | svein at d80.iso100.no
  \ /   |Solberg ?stli 9    | PGP Key:  0xE5E76831
   X    |2020 Skedsmokorset | svein at jernhuset.no
  / \   |Norway             | PGP Key:  0xCE96CE13
        |                   | svein at stillbilde.net
 ascii  |                   | PGP Key:  0x58CD33B6
 ribbon |System Admin       | svein-listmail at stillbilde.net
Campaign|stillbilde.net     | PGP Key:  0x22D494A4
        +-------------------+-------------------------------
        |msn messenger:     | Mobile Phone: +47 907 03 575
        |svein at jernhuset.no | RIPE handle:    SS16503-RIPE
- --------+-------------------+-------------------------------
         If you really are in a hurry, mail me at
               svein-mobile at stillbilde.net
 This mailbox goes directly to my cellphone and is checked
        even when I''m not in front of my computer.
- ------------------------------------------------------------
                     Picture Gallery:
          https://gallery.stillbilde.net/v/svein/
- ------------------------------------------------------------
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.12 (MingW32)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/

iEYEARECAAYFAkus2cMACgkQSBMQn1jNM7YHeACgoxq5z6Eylrfn9IeIer+epJPs
ylwAoKgxYWRaT7IQ+JTjeTQk8goCBcFT
=TB1W
-----END PGP SIGNATURE-----

Awesome!

Just when I thought zfs couldn?t get any better...



-----Original Message-----
From: Larry.Liu at Sun.COM [mailto:Larry.Liu at Sun.COM] 
Sent: Friday, March 26, 2010 11:58 AM
To: Bottone, Frank
Cc: zfs-discuss at opensolaris.org
Subject: Re: [zfs-discuss] ZFS and 4kb sector Drives (All new western digital
GREEN Drives?)

Yes, it does.

Bottone, Frank ??:
>
> Does zfs handle 4kb sectors properly or does it always assume 512b 
> sectors?
>
> If it does, we could manually create a slice properly aligned and set 
> zfs to use it?
>
>
> --
>  The sender of this email subscribes to Perimeter E-Security''s
email
>  anti-virus service. This email has been scanned for malicious code and is
>  believed to be virus free. For more information on email security please
>  visit: http://www.perimeterusa.com/services/messaging 
>  This communication is confidential, intended only for the named
recipient(s)
>  above and may contain trade secrets or other information that is exempt
from
>  disclosure under applicable law. Any use, dissemination, distribution or
>  copying of this communication by anyone other than the named recipient(s)
is
>  strictly prohibited. If you have received this communication in error,
please
>  delete the email and immediately notify our Command Center at
203-541-3444.
>
>  Thanks
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> zfs-discuss mailing list
> zfs-discuss at opensolaris.org
> http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
>   






--
 The sender of this email subscribes to Perimeter E-Security''s email
 anti-virus service. This email has been scanned for malicious code and is
 believed to be virus free. For more information on email security please
 visit: http://www.perimeterusa.com/services/messaging
 This communication is confidential, intended only for the named recipient(s)
 above and may contain trade secrets or other information that is exempt from
 disclosure under applicable law. Any use, dissemination, distribution or
 copying of this communication by anyone other than the named recipient(s) is
 strictly prohibited. If you have received this communication in error, please
 delete the email and immediately notify our Command Center at 203-541-3444.

 Thank

On Mar 26, 2010, at 8:58 AM, Svein Skogen wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
> 
> On 26.03.2010 16:55, Bottone, Frank wrote:
>> Does zfs handle 4kb sectors properly or does it always assume 512b
sectors?
>> 
>> 
>> 
>> If it does, we could manually create a slice properly aligned and set
>> zfs to use it?
> 
> A real simple patch would be to attempt alignment with 4096 every time
> (since 4096 is a multiple of 512 there really wouldn''t be a
performance
> penalty here). This would mean that things are optimal on _ALL_ disks.
> (and allow those of us using more advanced diskcontrollers to set the
> strip-size (strip size, not stripe size) to 4K as well)
Two thoughts:

1. the "performance impact" may not be very great, but I''m
sure there are
exceptions in the consumer-grade market

2. people will be disappointed with the reduced compressibility of their data

 -- richard

ZFS storage and performance consulting at http://www.RichardElling.com
ZFS training on deduplication, NexentaStor, and NAS performance
Las Vegas, April 29-30, 2010 http://nexenta-vegas.eventbrite.com

For the time being, the EARS series of drives actually present 512 byte sectors
to the o/s through emulation in firmware.

The drive I tested was WD20EARS (2TB WD Caviar Green Advanced Format drives):

MDL: WD20EARS-00S81
DATE: 29 DEC 2009
DCM: HBRNHT2BB
DCX: 6019S1W87
LBA: 3907029168

The LBA above is key -. this s the unmber of sectors presented by the
drive''s firmware to the host o/s. Combinations of jumpers, and runnign
the WD alignment utility only appears to reorganise how the ECC is stored in 4k
blocks physically on disk, but the drive still presents each 4K physicaly dick
block as 8 x 512byte logical blocks to the host.

I have logged a support request with WD to see if they may be releasing firmware
that will present the 4k blocks natively. As an individual user, i actually
doubt that WD will ever respond. I can only hope that quite a few others
(00''s / 000''s) of other people also log similar requests and
that WD may release appropriate firmware.

Would be grateful to hear of any others and their testing experiences with other
series of advanced format drives from WD.

The drives works perfectly on 64bit kernel, but not on 32bit osol kernels. I
purchased the drive just to test on 32bit kernel - mainly as there are quite a
lot of soho NAS devices that may be able to use our Velitium Embedded Kit for
OpenSolaris with drives larger than 1TB.

It would be nice if the 32bit osol kernel support 48bit LBA (similar to linux,
not sure if 32bit BSD supports 48bit LBA ), then the drive would probably work -
perhaps later in the year we will have time to work on a patch to support 48bit
lba on the 32bit osol kernels...

Darren Mackay
http://www.sikkra.com
http://sourceforge.net/projects/velitium/
-- 
This message posted from opensolaris.org

> It would be nice if the 32bit osol kernel support
> 48bit LBA 
Is already supported, for may years (otherwise
disks with a capacity >= 128GB could not be
used with Solaris) ...
> (similar to linux, not sure if 32bit BSD
> supports 48bit LBA ), then the drive would probably
> work - perhaps later in the year we will have time to
> work on a patch to support 48bit lba on the 32bit
> osol kernels...
I think that - as a start - you have to eliminate the use
of the (signed 32-bit long on 32-bit kernel) daddr_t data
type in the kernel, and switch everything to 64 bit
diskaddr_t, and fix all device drivers that are currently
using daddr_t (including getting 3rd party device drivers
fixed).
-- 
This message posted from opensolaris.org

On Fri, Mar 26, 2010 at 05:57:31PM -0700, Darren Mackay
wrote:
> not sure if 32bit BSD supports 48bit LBA
Solaris is the only otherwise-modern OS with this daft limitation.

--
Dan.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 194 bytes
Desc: not available
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100327/0741bba7/attachment.bin>

On Sat, Mar 27, 2010 at 08:47:26PM +1100, Daniel Carosone
wrote:
> On Fri, Mar 26, 2010 at 05:57:31PM -0700, Darren Mackay wrote:
> > not sure if 32bit BSD supports 48bit LBA
> 
> Solaris is the only otherwise-modern OS with this daft limitation.
Ok, it''s not due to LBA48, but the 1Tb limitation is still daft.

There are some limits you''ll encounter in BSD, such as if you use the
wrong disklabel format - but not in the basic disk drivers. 

--
Dan.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 194 bytes
Desc: not available
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100327/c9c9ac7e/attachment.bin>

On 27.03.2010 11:01, Daniel Carosone wrote:
> On Sat, Mar 27, 2010 at 08:47:26PM +1100, Daniel Carosone wrote:
>> On Fri, Mar 26, 2010 at 05:57:31PM -0700, Darren Mackay wrote:
>>> not sure if 32bit BSD supports 48bit LBA
>>
>> Solaris is the only otherwise-modern OS with this daft limitation.
> 
> Ok, it''s not due to LBA48, but the 1Tb limitation is still daft.
> 
> There are some limits you''ll encounter in BSD, such as if you use
the
> wrong disklabel format - but not in the basic disk drivers. 
And, if you use the cheaper cards containing SiI-chips, you may find
that _SOME_ manufacturers saved a penny per year by not connecting all
the wires, so LBA48 simply don''t work. Don''t ask how many gray
hairs
tracking down THAT one caused me. (disks that worked absolutely fine
until you passed a certain block. Then *wham!* corruptions-galore.)

//Svein

-- 
--------+-------------------+-------------------------------
  /"\   |Svein Skogen       | svein at d80.iso100.no
  \ /   |Solberg ?stli 9    | PGP Key:  0xE5E76831
   X    |2020 Skedsmokorset | svein at jernhuset.no
  / \   |Norway             | PGP Key:  0xCE96CE13
        |                   | svein at stillbilde.net
 ascii  |                   | PGP Key:  0x58CD33B6
 ribbon |System Admin       | svein-listmail at stillbilde.net
Campaign|stillbilde.net     | PGP Key:  0x22D494A4
        +-------------------+-------------------------------
        |msn messenger:     | Mobile Phone: +47 907 03 575
        |svein at jernhuset.no | RIPE handle:    SS16503-RIPE
--------+-------------------+-------------------------------
         If you really are in a hurry, mail me at
               svein-mobile at stillbilde.net
 This mailbox goes directly to my cellphone and is checked
        even when I''m not in front of my computer.
------------------------------------------------------------
                     Picture Gallery:
          https://gallery.stillbilde.net/v/svein/
------------------------------------------------------------

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 196 bytes
Desc: OpenPGP digital signature
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100327/ccd60db5/attachment.bin>

I''m not entirely convinced there is no problem here.... I had a WD EADS
1.5TB die, the warranty replacement drive was a EARS. So, first foray into
4k sectors.

I had 8x EADS in a raidz set, had replaced the broken one with a 1.5TB
Seagate 7200rpm - which was obviously faster.

Just replacing back, and here is the iostat for the new EARS drive:
http://pastie.org/889572

<http://pastie.org/889572>Those asvc_t''s are atrocious. As is the
op/s
throughput. All the other drives spend the vast majority of the time idle,
waiting for the new EARS drive to write out data.

This is after isolating another issue to my Dell PERC 5/i''s - they
apparently don''t talk nicely with the EARS drives either. Streaming
writes
would push data for two seconds and pause for ten. Random writes ... give
up.
On the Intel chipset''s SATA - streaming writes are acceptable, but
random
writes are as per the above url.

Format tells me that the partition starts at sector 256.But given that ZFS
writes variable size blocks, that really shouldn''t matter.

When plugged the EARS into a P45-based motherboard running Windows, HDTune
presents a normal looking streaming writes graph, and the average seek time
is 14ms - the drive seems healthy.

Any thoughts?

On 27 March 2010 21:05, Svein Skogen <svein at stillbilde.net> wrote:
> On 27.03.2010 11:01, Daniel Carosone wrote:
> > On Sat, Mar 27, 2010 at 08:47:26PM +1100, Daniel Carosone wrote:
> >> On Fri, Mar 26, 2010 at 05:57:31PM -0700, Darren Mackay wrote:
> >>> not sure if 32bit BSD supports 48bit LBA
> >>
> >> Solaris is the only otherwise-modern OS with this daft limitation.
> >
> > Ok, it''s not due to LBA48, but the 1Tb limitation is still
daft.
> >
> > There are some limits you''ll encounter in BSD, such as if you
use the
> > wrong disklabel format - but not in the basic disk drivers.
>
> And, if you use the cheaper cards containing SiI-chips, you may find
> that _SOME_ manufacturers saved a penny per year by not connecting all
> the wires, so LBA48 simply don''t work. Don''t ask how many
gray hairs
> tracking down THAT one caused me. (disks that worked absolutely fine
> until you passed a certain block. Then *wham!* corruptions-galore.)
>
> //Svein
>
> --
> --------+-------------------+-------------------------------
>  /"\   |Svein Skogen       | svein at d80.iso100.no
>  \ /   |Solberg ?stli 9    | PGP Key:  0xE5E76831
>   X    |2020 Skedsmokorset | svein at jernhuset.no
>  / \   |Norway             | PGP Key:  0xCE96CE13
>        |                   | svein at stillbilde.net
>  ascii  |                   | PGP Key:  0x58CD33B6
>  ribbon |System Admin       | svein-listmail at stillbilde.net
> Campaign|stillbilde.net     | PGP Key:  0x22D494A4
>        +-------------------+-------------------------------
>        |msn messenger:     | Mobile Phone: +47 907 03 575
>        |svein at jernhuset.no | RIPE handle:    SS16503-RIPE
> --------+-------------------+-------------------------------
>         If you really are in a hurry, mail me at
>               svein-mobile at stillbilde.net
>  This mailbox goes directly to my cellphone and is checked
>        even when I''m not in front of my computer.
> ------------------------------------------------------------
>                     Picture Gallery:
>          https://gallery.stillbilde.net/v/svein/
> ------------------------------------------------------------
>
>
> _______________________________________________
> zfs-discuss mailing list
> zfs-discuss at opensolaris.org
> http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100327/44c4073c/attachment.html>