zfs discuss - Oct 2010 - Swapping disks in pool to facilitate pool growth

Hi Guys,

We are a running a Solaris 10 production server being used for backup
services within our DC. We have 8 500GB drives in a zpool and we wish to
swap them out 1 by 1 for 1TB drives.

I would like to know if it is viable to add larger disks to zfs pool to grow
the pool size and then remove the smaller disks?

I would assume this would degrade the pool and require it to resilver?

Any advice would be gratefully received.

Kind regards

Kevin
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20101007/4ea717dd/attachment.html>

On 07/10/2010 11:22, Kevin Walker wrote:
> We are a running a Solaris 10 production server being used for backup
> services within our DC. We have 8 500GB drives in a zpool and we wish to
> swap them out 1 by 1 for 1TB drives.
>
> I would like to know if it is viable to add larger disks to zfs pool to
> grow the pool size and then remove the smaller disks?
This is covered in the documentation:

docs.sun.com Home
	> Oracle Solaris 10 System Administrator Collection
	> Oracle Solaris ZFS Administration Guide
	> 1.  Oracle Solaris ZFS File System (Introduction)
		> What''s New in ZFS?
		> ZFS Device Replacement Enhancements

http://docs.sun.com/app/docs/doc/819-5461/githb?l=en&a=view
> I would assume this would degrade the pool and require it to resilver?
A resilver is required without it there is no way to get your data on to 
the new drives.

Wither the pool is degraded or not depends on wither you dettach an 
existing side of a two way mirror to do the replacement with the larger 
drive or if you create a three way mirror first and then dettach one of 
the size of the original two way mirror.

-- 
Darren J Moffat

> From: zfs-discuss-bounces at opensolaris.org [mailto:zfs-discuss-
> bounces at opensolaris.org] On Behalf Of Kevin Walker
> 
> We are a running a Solaris 10 production server being used for backup
> services within our DC. We have 8 500GB drives in a zpool and we wish
> to swap them out 1 by 1 for 1TB drives.
> 
> I would like to know if it is viable to add larger disks to zfs pool to
> grow the pool size and then remove the smaller disks?
> 
> I would assume this would degrade the pool and require it to resilver?
Because it''s a raidz, yes it will be degraded each time you remove one
disk.
You will not be using "attach" and "detach."  You will be
using "replace"

Because it''s a raidz, each resilver time will be unnaturally long. 
Raidz
resilver code is inefficient.  Just be patient and let it finish each time
before you replace the next disk.  Performance during resilver will be
exceptionally poor.  Exceptionally.

Because of the inefficient raidz resilver code, do everything within your
power to reduce IO on the system during the resilver.  Of particular
importance:  Don''t create snapshots while the system is resilvering. 
This
will exponentially increase the resilver time.  (I''m exaggerating by
saying
"exponentially," don''t take it literally.  But in reality, it
*is*
significant.)

Because you''re going to be degrading your redundancy, you *really* want
to
ensure all the disks are good before you do any degrading.  This means,
don''t begin your "replace" until after you''ve
completed a scrub.

On Thu, Oct 7, 2010 at 12:22 AM, Kevin Walker <indigoskywalker at
gmail.com> wrote:
> I would like to know if it is viable to add larger disks to zfs pool to
grow
> the pool size and then remove the smaller disks?
>
> I would assume this would degrade the pool and require it to resilver?
You can do a zfs replace without removing the the original disks as
well if you have additional ports available. This will prevent the
array from becoming degraded during the resilver.

You may be able to replace more than one drive at the same time this
way. I''ve never tried it, and you should test before attempting to do
so.

-B

-- 
Brandon High : bhigh at freaks.com

On Oct 27, 2010, at 21:17, Brandon High wrote:
> You may be able to replace more than one drive at the same time this
> way. I''ve never tried it, and you should test before attempting to
do
> so.
If the OP doesn''t have a test system available, it may be possible to  
try this multi-replace experiment using plain files as the backing  
store (created with mkfile).

On Wed, Oct 27, 2010 at 3:56 PM, David Magda <dmagda at ee.ryerson.ca>
wrote:
> If the OP doesn''t have a test system available, it may be possible
to try
> this multi-replace experiment using plain files as the backing store
> (created with mkfile).
.. or via a VirtualBox, VMWare, or other virtualization instance.

-B

-- 
Brandon High : bhigh at freaks.com