Currently we're updating the request result upon completion only for BLK_PC requests. This makes it impossible for the upper layers to reliable detect the real cause for an I/O failure. By attaching the result and the sense to all requests we can update multipathing to make some more elaborate choices on how to handle I/O errors. This also solves a potential data corruption with multipathing and persistent reservations. When queue_if_no_path is active multipath will queue any I/O failure (including those failed with RESERVATION CONFLICT) until the reservation status changes. But by then I/O might have been ongoing on the other paths, thus the delayed submission will severely corrupt your data. Signed-off-by: Hannes Reinecke <hare@xxxxxxx> -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
