Re: [Scst-devel] Thin Provisioning and Ceph RBD's

[Vladislav B. <vs...@vl...>]

Hi,

Alex Gorbachev wrote on 07/27/2016 08:55 AM:
> Hi Vlad,
> 
> On Mon, Jul 25, 2016 at 10:44 PM, Vladislav Bolkhovitin <vs...@vl...> wrote:
>> Hi,
>>
>> I would suggest to rebuild SCST in the debug mode (after "make 2debug"), then before
>> calling the unmap command enable "scsi" and "debug" logging for scst and scst_vdisk
>> modules by 'echo add scsi >/sys/kernel/scst_tgt/trace_level; echo "add scsi"
>>> /sys/kernel/scst_tgt/handlers/vdisk_fileio/trace_level; echo "add debug"
>>> /sys/kernel/scst_tgt/handlers/vdisk_fileio/trace_level', then check, if for the unmap
>> command vdisk_unmap_range() is reporting running blkdev_issue_discard() in the kernel
>> logs.
>>
>> To double check, you might also add trace statement just before blkdev_issue_discard()
>> in vdisk_unmap_range().
> 
> With the debug settings on, I am seeing the below output - this means
> that discard is being sent to the backing (RBD) device, correct?

Correct. However, you can see some other code in vdisk_unmap_range() between this trace statement and actual blkdev_issue_discard() call, so, to be completely sure, I'd suggest you to add something like:

TRACE_DBG("Discarding (start_sector %lld, nr_sects %lld)", (unsigned long long)start_sector, (unsigned long long)nr_sects);

right before blkdev_issue_discard() for your kernel.
 
Vlad