On 04/30/2015 01:47 AM, Nicholas A. Bellinger wrote: > AFAICT from Robert + Alex's log this is the same type of scenario, and > I'm pretty sure I was hitting the same login timeout handler back then, > and was able to survive at least with iblock + scsi_debug backend. > > Give that ceph and enhancedio backend are involved, it's not completely > clear yet if this is a target specific issue or not.. > > Mike, what's the setup your able to reproduce with..? For the LIO crash part I was using scsi_debug and iblock. I just do a dd to the fc/iscsi device exported by LIO. Then on the LIO box I do echo blocked > /sys/block/sdXYZ/device/state to the scsi scsi_debug device exported by iblock. I then let the initiator side cmd timeout and the error handler to eventually drop the session. On the LIO box when I see "iSCSI Login timeout on Network Portal" I allow the device to start executing IO again. echo running > /sys/block/sdXYZ/device/state -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
