Thanks Martin. Sorry for the wait; it took a while for the user to respond. They don't have scsi devs but rather nvme devs. The sg_vpd command failed b/c there was no bl page available. I asked them to provide the supported vpd pages that are there. I do have some nvme data though from a sosreport. I'll send you that in a separate email. Thanks again. On Tue, Jun 20, 2023 at 11:20 AM Martin K. Petersen <martin.petersen@xxxxxxxxxx> wrote: > > > John, > > > 1) Set a 64M limit as you've suggested in the past. It seems more > > prudent to tune the value upward for the few devices that can actually > > handle a 2TiB discard rather than tune downward for the large > > majority. > > This makes the assumption that smaller always equals faster. However, > some devices track allocations in very large units. And as a result, > sending smaller discards will result in *slower* performance for those > devices. In addition, for doings things like the full block device sweep > we do during mkfs, it is often imperative that we issue large sequential > ranges. > > Please provide the VPD pages from the device in question. > > -- > Martin K. Petersen Oracle Linux Engineering >
