On 11/30/2017 01:22 PM, Liu Bo wrote: >>>>>>> If the underlying protocal doesn't support retry and there >>>>>>> are some transient errors happening somewhere in our IO >>>>>>> stack, we'd like to give an extra chance for IO.
> Anyway, this is for a corner case, not for everyone, I think I need to > make it configurable so that at least we can provide some extra > robustness for people who super care about their data. Not sure I follow -- wouldn't such users prefer a transport like e.g. scsi that *does* perform retries (as well as other error recovery)? (Possibly they would also want features like mirroring & multipath, but in those scenarios doing additional retries from the filesystem is also unlikely to help much.) Ed -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
