>>>>> "Hugh" == Hugh Dickins <hugh.dickins@xxxxxxxxxxxxx> writes: Hugh> You mentioned an "-o discard" mount option before: so I think what Hugh> we ought to be doing is an option to swapon. But you can imagine Hugh> that I'd prefer to avoid that too, if we can work this out without Hugh> it. The main problem we have is that the devices currently supporting TRIM are doing a piss poor job at it. We have pretty good vendor guarantees that discards are going to be essentially free on SCSI-class hardware. But in the ATA space things are currently being driven by early adopters / tweakers that care more about benchmarketing and feature checklists. Whether things actually work as intended is mostly irrelevant. I think we'll need to give things a little bit of time for decent ATA TRIM implementations to materialize. And then we can switch to an "assume it works, blacklist bad eggs" approach. Until then I think we need to make discard an explicit opt-in feature. -- Martin K. Petersen Oracle Linux Engineering -- 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
