Nicholas A. Bellinger wrote:
> On Sun, 2008-06-29 at 01:36 -0500, Mike Christie wrote:
>> Nicholas A. Bellinger wrote:
>>> Hi Mike!
>> Hey, looks like you doing some more cool stuff. Don't you have a job 
>> where you have to hack on boring stuff like the rest of us :)
> What Jerome said. :-)
>>> On Sat, 2008-06-28 at 15:33 -0500, Mike Christie wrote:
>>>> What version of open-iscsi and kernel are you using? And are you using 
>>>> the kernel modules with open-iscsi or the ones that come with the kernel?
>>> Whoops, forgot to include that tid-bit:
>>> open-iscsi: 2.0.730-1etch1
>>> kernel: I am using v2.6.22.19-kdb, and Jerome is using
>>> v2.6.22-4-vserver-amd64
>> Ah if your disk are using write back cache then you are going to hit 
>> some problems. So if you see this in /var/log/messages when you loging:
>> kernel: sd 9:0:0:1: [sdb] Write cache: enabled,
>> then later when you run iscsiadm to log out you see:
>> kernel: sd 9:0:0:1: [sdb] Synchronizing SCSI cache
>> Then you are going to hit problems due to the scsi sysfs interface 
>> changing on us. iscsiadm is going to hang. IO is going to hang. You 
>> basically have to reboot the box by hand.
> Yep, so the LIO-CORE does NOT emulate Write Cache Enable (although there

Oh. There are some other issues that we can hit with IO getting failed 
and applications hanging waiting for IO to be sent but it gets lost. Try 
the newer code where all that should be fixed.

> is some Read Cache code :-) bit in the caching mode page in the virtual
> storage object case (IBLOCK, FILE, etc).  We are using the LIO-Core
> IBLOCK plugin for export DRBD's struct block_device, which uses the
> generic emulation of MODE_SENSE*, which leaves buf[2] untouched in
> caching mode page.  
> For the PSCSI subsystem plugin, these mode pages obviously come from the
> underlying hardware.  I even recall that libata does emulate this down
> to SATA/PATA bits for us. (thanks jgarzik and co)  
> On a related note, did you and Tomo ever get around to implement
> write/read caching emulation in STGT for virtual devices..?  Its

I am not sure the exact status. We use the buffer cache normally and so 
I think we always report that we support write caching. I think someone 
just sent patches to turn it off.

> definately something that is on my long term list for doing generically
> amoungst virtual devices in LIO-Core v3.x.
> Many thanks for your most valuable of time,

No problem.

> --nab
> > 

You received this message because you are subscribed to the Google Groups 
"open-iscsi" group.
To post to this group, send email to
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at

Reply via email to