Forza, > Does the mpt3sas driver or the HBA controller not follow the > /sys/block/<dev>/device/timeout value? Discard operations have different timeouts than regular filesystem read/write I/O. > Any thoughts other than trying to avoid using discards/fstrim? I did > reach out to Broadcom for support, and they claim it is a fault in the > fstrim code and that on FreeBSD they had fixed this. Not sure how > relevant that statement is though. Since this HBA performs SCSI->ATA translation in firmware, Linux has very little control over what's going on. We issue discard commands constrained by the drive limits reported to us by the HBA. I recommend making sure you run the latest HBA firmware. You can also try setting discard_max_bytes in sysfs for the block device in question to a smaller value. -- Martin K. Petersen Oracle Linux Engineering
