NFS hard semantics wanted: how to?

2010-12-22 Thread torn5
Hello open-iscsi people I am approaching iscsi, and I am currently doing some "reliability" tests. In particular I would like to be able to reboot the target machine without the initiators to lose data. Like NFS hard mounts. If the target goes down: 1) I want the device to be frozen so that ap

NFS hard semantics wanted: how to?

2010-12-22 Thread torn5
Hello open-iscsi people I am approaching iscsi, and I am currently doing some "reliability" tests. In particular I would like to be able to reboot the target machine without the initiators to lose data. Like NFS hard mounts. If the target goes down: 1) I want the device to be frozen so that ap

Re: NFS hard semantics wanted: how to?

2010-12-30 Thread torn5
On 12/22/2010 07:09 PM, Mike Christie wrote: On 12/22/2010 05:57 AM, torn5 wrote: Hello open-iscsi people I am approaching iscsi, and I am currently doing some "reliability" tests. In particular I would like to be able to reboot the target machine without the initiators to lose

Open-iscsi does not honour queue_depth

2011-01-05 Thread torn5
Hello all I am doing a test right now, I have about 200 outstanding commands (cat /sys/block/devicename/inflight) at any time, I tried to go into /sys/block/devicename/inflight/device and set queue_depth to 1, the file is now set correctly to 1 and it previously was 1024, but open-iscsi does n

Re: Open-iscsi does not honour queue_depth

2011-01-05 Thread torn5
On 01/05/2011 10:14 PM, Mike Christie wrote: On 01/05/2011 03:05 PM, Mike Christie wrote: does not care about it and I still have about 200 inflight commands at any time. Isn't the queue_depth the max number of inflight commands? Not exactly. A problem is that queue_depth is a scsi layer limi

Re: [PATCH RFC] iser: support for reporting the current portal (address/port)

2011-01-24 Thread torn5
On 01/14/2011 08:27 AM, Mike Christie wrote: > > Hey, > > I was working on this patch. It seems to work for iser and cxgbi in > the normal case. iscsi_tcp is broken with it (there is debugging stuff > in iscsi_tcp.c so do not look at it for review purposes). > Excuse the stupid question: how can y

Create device before target is available

2013-01-28 Thread torn5
Hi, in a recovery from power loss situation, the target host might restart slower than initiator hosts. Is there a way in open-iscsi to start and create devices in blocked mode even if target is not available yet? (to be used together with long recovery timeouts...) Thanks in advance T. -- Yo

Re: Create device before target is available

2013-01-28 Thread torn5
On 01/28/13 18:34, Mike Christie wrote: On 01/26/2013 08:45 AM, torn5 wrote: Is there a way in open-iscsi to start and create devices in blocked mode even if target is not available yet? (to be used together with long recovery timeouts...) I think so - sort of. If you were to set

Re: Create device before target is available

2013-01-29 Thread torn5
On 01/28/13 21:59, Mike Christie wrote: On 01/28/2013 02:55 PM, torn5 wrote: Mike, thanks for your reply I actually need the blockdevice to be available (in blocked mode) just after starting the initiator, even if the initiator wasn't able to connect yet. Ah ok. That might not be possibl