Commit a0da65f4 authored by Ziye Yang's avatar Ziye Yang Committed by Jim Harris
Browse files

bdevperf: adjust the bdevperf task number. 



According to my analysis, the exact number is not
related with core number, which should be calucated
as g_target_count * g_queue_depth. Since each
target will be run I/O by differnet cores.

And it would solve the task number not enough issue.

Change-Id: I483f4609341766123f95b39bff057e95a9d19531
Signed-off-by: default avatarZiye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/386801


Tested-by: default avatarSPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: default avatarHailiang Wang <hailiangx.e.wang@intel.com>
Reviewed-by: default avatarDaniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: default avatarBen Walker <benjamin.walker@intel.com>
Reviewed-by: default avatarJim Harris <james.r.harris@intel.com>
parent 618c8f90

test/lib/bdev/bdevperf/bdevperf.c

+6 −1
Original line number Diff line number Diff line
@@ -569,10 +569,15 @@ bdevperf_run(void *arg1, void *arg2) 
	 *  the min buffer alignment.  Some backends such as AIO have alignment restrictions

	 *  that must be accounted for.

	 */

	task_pool = rte_mempool_create("task_pool", 4096 * spdk_env_get_core_count(),

	task_pool = rte_mempool_create("task_pool", g_target_count * g_queue_depth,

				       sizeof(struct bdevperf_task),

				       64, 0, NULL, NULL, task_ctor, NULL,

				       SOCKET_ID_ANY, 0);

	if (!task_pool) {

		SPDK_ERRLOG("Cannot allocate %d tasks\n", g_target_count * g_queue_depth);

		spdk_app_stop(1);

		return;

	}



	printf("Running I/O for %d seconds...\n", g_time_in_sec);

	fflush(stdout);