nvmf: Don't assume the first core is core 0 when scheduling poll groups

Change-Id: I883ffacca26be0d4fc0a3cfdac5a9c0391b7585e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453013
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This commit is contained in:
Ben Walker 2019-05-03 11:16:04 -07:00 committed by Jim Harris
parent 3555e24505
commit 97d35377c5

View File

@ -158,7 +158,7 @@ nvmf_tgt_get_pg(struct spdk_nvmf_qpair *qpair)
struct spdk_nvme_transport_id trid;
struct nvmf_tgt_host_trid *tmp_trid = NULL, *new_trid = NULL;
int ret;
uint32_t core = 0;
uint32_t core = spdk_env_get_first_core();
switch (g_spdk_nvmf_tgt_conf->conn_sched) {
case CONNECT_SCHED_HOST_IP: