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
