The Linux Foundation Collaboration Summit is an exclusive, invitation-only summit gathering core kernel developers, distribution maintainers, ISVs, end users, system vendors and other community organizations for plenary sessions and workgroup meetings to meet face-to-face to tackle and solve the most pressing issues facing Linux today. If your company is not a member of The Linux Foundation and you are interested in joining please visit our website to learn more about how you can become a Corporate Member.
Disk-mirroring is a standard feature of basically every OS today. However, these solutions cover built-in disks only.For remotely connected disks eg via FibreChannel or iSCSI the situation changes.
Normally every I/O error is being treated as an fatal error, requiring manual interaction to replace the disk.With remote or SAN-attached disks transient I/O errors might occur, requiring a more careful I/O handling. This is especially true on mainframe, where the standard 'DASD' driver might undergo a rather lengthy recovery routine on errors.
In this talk I will give an overview on the challenges when implementing such a solution and present the 'md_monitor' program for handling transient I/O errors on MD mirror setups.