FreBSD 9.1 and ZFS v28 performances

[Ronald Klop]

On Wed, 20 Mar 2013 02:34:16 +0100, Bob Friesenhahn  
<bfriesen at simple.dallas.tx.us> wrote:

> On Mon, 18 Mar 2013, Davide D'Amico wrote:
>>>  While running the tests what sort of thing are you
>>> seeing from gstat, any disks maxing? If so primarily
>>> read or write?
>> Here the r/w pattern using zpool iostat 2:
>
> Using 'zpool iostat 2' is not likely to be very useful since zfs writes  
> all of is data in bursts and may wait up to 5 seconds to do so.
>
> If your benchmark uses synchronous writes and does continous updates,  
> then you should see zfs writing continiously to your zil device (or the  
> pool).
>
> Bob

Zpool iostat 2 still prints the per-second-speed. So it is the amount of  
data divided by 2. It is easier to reason about it if you use zpool iostat  
1.

Ronald.