ZFS UNMAP performance

[Eric van Gyzen]

On 03/12/2014 05:01, Bob Bishop wrote:
> Hi,
>
> On 12 Mar 2014, at 00:28, Danny Schales <dan at LaTech.edu> wrote:
>
>> On 3/11/2014 5:31 PM, Eric van Gyzen wrote:
>>>> Replying to myself...I note that the system is reporting that TRIM is
>>>> being used.  Is this normal for non-SSD systems?  There *is* SSD in the
>>>> system, but I'm pretty sure the system can't tell it's SSD (it's hidden
>>>> behind a Dell PERC card).  The number of trim.successes is roughly
>>>> equivalent to the number of deletes reported by gstat for the ISCSI LUN
>>>> devices.  Should the system be using TRIM for ISCSI LUNs?
>>> Sure, if the LUN (i.e. the storage controller) reports that it supports
>>> TRIM/UNMAP.  Note that this is completely unrelated to the type of disks
>>> that provide the LUN's backing store.
>>>
>>>> kstat.zfs.misc.zio_trim.bytes: 232845656064
>>>> kstat.zfs.misc.zio_trim.success: 30810983
>>>> kstat.zfs.misc.zio_trim.unsupported: 809
>>>> kstat.zfs.misc.zio_trim.failed: 0
>>>>
>>>> Danny
>>>>
>> Are there any risks to turning off TRIM to see if the performance
>> improves (other than the loss of space recovery)?
>>
>> Danny
> If the backing store really is SSD then turning off TRIM should hurt write performance eventually (and read to a lesser extent).

Correct.  If it's not SSD, though, the loss of space recovery should be
the only risk.  And I imagine your highest tier of storage is not SSD.

Eric