Re: [zfs-discuss] Question on 4k sectors

2012-07-23 Thread Bob Friesenhahn

On Mon, 23 Jul 2012, Anonymous Remailer (austria) wrote:


The question was relative to some older boxes running S10 and not planning
to upgrade the OS, keeping them alive as long as possible...


Recent Solaris 10 kernel patches are addressing drives with 4k 
sectors.  It seems that Solaris 10 will work with drives with 4k 
sectors so Solaris 10 users will not be stuck.


Bob
--
Bob Friesenhahn
bfrie...@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/
GraphicsMagick Maintainer,http://www.GraphicsMagick.org/
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-23 Thread Anonymous Remailer (austria)

You wrote:

> 2012-07-23 18:37, Anonymous wrote:
> > Really, it would be so helpful to know which drives we can buy with
> > confidence and which should be avoided...is there any way to know from the
> > manufacturers web sites or do you have to actually buy one and see what it
> > does? Thanks to everyone for the info.
> 
> I think that vendors' marking like 512e may give a clue on
> their support of "emulated 512-byte sectors", whatever they
> would mean by that for a specific model line.

Yeah but buying through the mail it's awfully difficult to see the vendor
markings until it's too late ;)

> I believe you can roughly be certain that all 3Tb HDDs except
> Hitachi use 4Kb native sectors, and 4Tb disks are all 4Kb.
> If these disks don't expose such sector sizing to the OS
> properly, you can work around that in several ways, including,
> as of recent illumos changes, an override config file for the
> SCSI driver.

The question was relative to some older boxes running S10 and not planning
to upgrade the OS, keeping them alive as long as possible...

> The main problem with "avoiding" 4kb drives seems to be just
> the cases where you want to replace a single disk in an older
> pool built with 512b-native sectored drives.

Right, that's what we're concerned with.

> For new pools (or rather new complete top-level VDEVs) this does not
> matter much, except that your overheads with small data blocks can get
> noticeably bigger.

Understood.

> There were statements on this list that drives emulating 512b
> sectors (whether they announce it properly or not) are not
> all inherently evil - this emulation by itself may be of some
> concern regarding performance, but not one of reliability.
> Then again, firmware errors are possible in any part of the
> stack, of both older and newer models ;)

I haven't seen any post suggesting 512b emulation didn't have very adverse
effects on performance. Given how touchy ZFS seems to be I don't want to
give him any excuses! Thanks for your post.
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-23 Thread Jim Klimov

2012-07-23 18:37, Anonymous wrote:

Really, it would be so helpful to know which drives we can buy with
confidence and which should be avoided...is there any way to know from the
manufacturers web sites or do you have to actually buy one and see what it
does? Thanks to everyone for the info.


I think that vendors' marking like 512e may give a clue on
their support of "emulated 512-byte sectors", whatever they
would mean by that for a specific model line.

I believe you can roughly be certain that all 3Tb HDDs except
Hitachi use 4Kb native sectors, and 4Tb disks are all 4Kb.
If these disks don't expose such sector sizing to the OS
properly, you can work around that in several ways, including,
as of recent illumos changes, an override config file for the
SCSI driver.

The main problem with "avoiding" 4kb drives seems to be just
the cases where you want to replace a single disk in an older
pool built with 512b-native sectored drives. For new pools
(or rather new complete top-level VDEVs) this does not matter
much, except that your overheads with small data blocks can
get noticeably bigger.

There were statements on this list that drives emulating 512b
sectors (whether they announce it properly or not) are not
all inherently evil - this emulation by itself may be of some
concern regarding performance, but not one of reliability.
Then again, firmware errors are possible in any part of the
stack, of both older and newer models ;)

HTH,
//Jim


___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-23 Thread Anonymous
"Hans J. Albertsson"  wrote:

> I think the problem is with disks that are 4k organised, but report 
> their blocksize as 512.
> 
> If the disk reports it's blocksize correctly as 4096, then ZFS should 
> not have a problem.
> At least my 2TB Seagate Barracuda disks seemed to report their 
> blocksizes as 4096, and my zpools on those machines have ashift set to 
> 12, which is correct, since 2¹² = 4096

Thanks, this is good to know. Is there any way, looking at manufacturers
data sheets for drives, whether they report their blocksize correctly? From
Seagate and WD that list the number of sectors, it's trivial to determine
what sectors the disk is using. But is this number what the disk is really
organized in or is it the number the disk reports?! It is very confusing...

So far we seem to rely on reports from people on the list, which is good for
us but bad for guys who wasted money on drives that don't work as they
should (the drives that don't report actual sector sector size correctly).

Really, it would be so helpful to know which drives we can buy with
confidence and which should be avoided...is there any way to know from the
manufacturers web sites or do you have to actually buy one and see what it
does? Thanks to everyone for the info.

___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-19 Thread Freddie Cash
On Thu, Jul 19, 2012 at 5:29 AM, Hans J. Albertsson
 wrote:
> I think the problem is with disks that are 4k organised, but report their
> blocksize as 512.
>
> If the disk reports it's blocksize correctly as 4096, then ZFS should not
> have a problem.
> At least my 2TB Seagate Barracuda disks seemed to report their blocksizes as
> 4096, and my zpools on those machines have ashift set to 12, which is
> correct, since 2¹² = 4096
>
> You cannot mix 512 and 4096 byte blocksize disks in one pool, at least not
> in a mirror. All disks in a single pool should have the same blocksize.
>
> There is a hacked version of zpool for OpenIndiana that has a blocksize
> option to the create subcommand. I don't know if other OSes have similar
> fixes.

FreeBSD includes the gnop(8) command which can be used to create
pseudo-devices that declare any size of sectors you want.  This can be
used to create ashift=12 vdevs on top of 512B, pseudo-512B, or 4K
drives.

# gnop -S 4096 da{0,1,2,3,4,5,6,7}
# zpool create pool raidz2 da{0,1,2,3,4,5,6,7}.nop
# zpool export pool
# gnop destroy da{0,1,2,3,4,5,6,7}.nop
# zpool import -d /dev pool

-- 
Freddie Cash
fjwc...@gmail.com
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-19 Thread Hans Rosenfeld
On Thu, Jul 19, 2012 at 02:29:38PM +0200, Hans J. Albertsson wrote:
> I think the problem is with disks that are 4k organised, but report 
> their blocksize as 512.
> 
> If the disk reports it's blocksize correctly as 4096, then ZFS should 
> not have a problem.
> At least my 2TB Seagate Barracuda disks seemed to report their 
> blocksizes as 4096, and my zpools on those machines have ashift set to 
> 12, which is correct, since 2¹² = 4096
> 
> You cannot mix 512 and 4096 byte blocksize disks in one pool, at least 
> not in a mirror. All disks in a single pool should have the same blocksize.

Ashift is a vdev property. As far as I know you can have several vdevs
with different ashifts in one pool.

Besides, it is possible to mix 512 and 4096 byte blocksizes in a mirror
vdev (and likely also in other vdev configurations), if and only if you
start with the 4096 byte blocksize disk. That is, you can attach 512
byte blocksize disks to ashift=12 vdevs, but you can't attach a 4096
byte blocksize disk to an ashift=9 vdev.

And even that is not entirely true: some implementation of ZFS might
choose to just warn about it or not care at all, while others will
refuse to create or import such a pool.


Hans


-- 
%SYSTEM-F-ANARCHISM, The operating system has been overthrown
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] Question on 4k sectors

2012-07-19 Thread Hans J. Albertsson
I think the problem is with disks that are 4k organised, but report 
their blocksize as 512.


If the disk reports it's blocksize correctly as 4096, then ZFS should 
not have a problem.
At least my 2TB Seagate Barracuda disks seemed to report their 
blocksizes as 4096, and my zpools on those machines have ashift set to 
12, which is correct, since 2¹² = 4096


You cannot mix 512 and 4096 byte blocksize disks in one pool, at least 
not in a mirror. All disks in a single pool should have the same blocksize.


There is a hacked version of zpool for OpenIndiana that has a blocksize 
option to the create subcommand. I don't know if other OSes have similar 
fixes.
Such a hacked zpool might not be useful for the root pool at install 
time, at least it would require some subterfuge to make the installation 
use the correct blocksize, since the process is a bit too far automated.



On 2012-07-19 14:00, zfs-discuss-requ...@opensolaris.org wrote:

Message: 2
Date: Wed, 18 Jul 2012 16:44:37 +0200 (CEST)
From: Dave U. Random
To:zfs-discuss@opensolaris.org
Subject: [zfs-discuss] Question on 4k sectors
Message-ID:
<07c48c7b7d3a7e568976704a375af...@anonymitaet-im-inter.net>

Hi. Is the problem with ZFS supporting 4k sectors or is the problem mixing
512 byte and 4k sector disks in one pool, or something else? I have seen
alot of discussion on the 4k issue but I haven't understood what the actual
problem ZFS has with 4k sectors is. It's getting harder and harder to find
large disks with 512 byte sectors so what should we do? TIA...


___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss