Getting fnic I/O errors/lockups with FCPIO_SGL_INVALID in logs
Issue
- Running into trouble with the FCOE disks associated with Oracle filesystems. Access to the disks works OK until they start up Oracle Cluster SW. At that point, I/O access to the disks stall, and errors like the following are returned by the fnic driver:
kernel: scsi host1: hdr status = FCPIO_SGL_INVALID
Environment
- Red Hat Enterprise Linux 6
- Cisco UCSB-B200-M3
fnic: Cisco FCoE HBA Driver, ver 1.5.0.1
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.