Now, each bdevperf_job gets it's own bdevperf_thread. Scheduling the jobs onto cores is left to the underlying event framework in the normal case. In the multi-thread case, cpumasks are set on the jobs' threads to ensure they're distributed appropriately. Change-Id: I55f1a44b4262d715954b3a63bf00b8d2321fafca Signed-off-by: Ben Walker <benjamin.walker@intel.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1512 Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Jim Harris <james.r.harris@intel.com> Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com> |
||
---|---|---|
.. | ||
.gitignore | ||
bdevperf.c | ||
bdevperf.py | ||
Makefile |