[zfs-discuss] which would be faster

[Tim Cook]

So I have 8 drives total. 

5x500GB seagate 7200.10
3x300GB seagate 7200.10

I'm trying to decide, would I be better off just creating two separate pools?

pool1 = 5x500gb raidz
pool2= 3x300gb raidz

or would I be better off creating one large pool, with two raid sets?  I'm 
trying to figure out if it would be faster this way since it should be striping 
across the two pools (from what I understand).  On the other hand, the pool of 
3 disks is obviously going to be much slower than the pool of 5.

In a perfect world I'd just benchmark both ways, but due to some constraints, 
that may not be possible.  Any insight?
 
 
This message posted from opensolaris.org
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss

Re: [zfs-discuss] which would be faster

[Al Hopper]

On Tue, 20 Nov 2007, Tim Cook wrote:

 So I have 8 drives total.

 5x500GB seagate 7200.10
 3x300GB seagate 7200.10

 I'm trying to decide, would I be better off just creating two separate pools?

 pool1 = 5x500gb raidz
 pool2= 3x300gb raidz

... reformatted ...

 or would I be better off creating one large pool, with two raid 
 sets?  I'm trying to figure out if it would be faster this way since 
 it should be striping across the two pools (from what I understand). 
 On the other hand, the pool of 3 disks is obviously going to be much 
 slower than the pool of 5.

 In a perfect world I'd just benchmark both ways, but due to some 
 constraints, that may not be possible.  Any insight?


Hi Tim,

Let me give you a 3rd option for your consideration.  In general, 
there is no one-pool-fits-all-workloads solution.  On a 10 disk 
system here, we ended up with a:

5 disk raidz1 pool
2 disk mirror pool
3 disk mirror pool

Each have their strengths/weaknesses.  The raidz set is ideal for 
large file sequential access type workloads - but the IOPS are 
limited to the IOPS of a single drive.  The 3-way mirror is 
ideal for a workload with a high read to write ratio - which describes 
many real-world type workloads (e.g. software development) - since ZFS 
will load balance read ops amoung all members of the mirror set.  So 
read IOPS is 3x the IOPS rating of a single disk.

I would suggest/recommend you configure a 5 disk raidz1 pool (with the 
500Gb disks) and a 2nd pool using a 3-way mirror.  You can then match 
pool/filesystems to the best fit with your different workloads.

Remember the incredibly useful blogs at: http://blogs.sun.com/relling/ 
(Thank you Richard) to determine the relative reliability/failure 
rates of different ZFS configs.

PS: If we had to do it over, I'd probably go with a 6-disk raidz2, 
in place of the 5-disk raidz1 - due to the much higher relibility of 
that config.

Regards,

Al Hopper  Logical Approach Inc, Plano, TX.  [EMAIL PROTECTED]
Voice: 972.379.2133 Fax: 972.379.2134  Timezone: US CDT
OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007
http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
Graduate from sugar-coating school?  Sorry - I never attended! :)
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss

Re: [zfs-discuss] which would be faster

[Rob Logan]

  On the other hand, the pool of 3 disks is obviously
  going to be much slower than the pool of 5

while today that's true, someday io will be
balanced by the latency of vdevs rather than
the number... plus two vdevs are always going
to be faster than one vdev, even if one is slower
than the other.

so do 4+1 and 2+1 in the same pool rather than
separate pools. this will let zfs balance
the load (always) between the two vdevs rather than
you trying the balance the load between pools.

Rob

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