hardware_TrimIntegrity: Compare read speed before/after trim.
Use FIO to measure 4K random read QD32 performance before / after
trim in hardware_TrimIntegrity. Device that doing trim properly
should report some speed difference because we don't need to
access NAND when read from trimmed LBA.
TEST=Tested in falco.
Tested passed. Result shows that median read latency is 4x better.
Tested-by: Puthikorn Voravootivat <firstname.lastname@example.org>
Reviewed-by: Grant Grundler <email@example.com>
Commit-Queue: Puthikorn Voravootivat <firstname.lastname@example.org>
2 files changed