8cd855f3a7
I think the main point of having unused qpairs in the perf application is to simulate the performance drag of having active qpairs sitting idle on an application. If we don't poll these unused I/O qpairs, there is no real performance effect (in terms of cache evictions, wasted cycles or otherwise). Signed-off-by: Seth Howell <seth.howell@intel.com> Change-Id: Ie67223eae57a9bfbfaa703a401b0960f88552e11 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2008 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Mellanox Build Bot Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com> Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com> Reviewed-by: Jim Harris <james.r.harris@intel.com> Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com> |
||
|---|---|---|
| .. | ||
| .gitignore | ||
| Makefile | ||
| perf.c | ||
| README.md | ||
Compiling perf on FreeBSD
To use perf test on FreeBSD over NVMe-oF, explicitly link userspace library of HBA. For example, on a setup with Mellanox HBA,
LIBS += -lmlx5