+1
−0
+2
−3
Loading
Add a num_connected_qpairs variable to the spdk_nvme_transport_poll_group structure and use it in poll_group_process_completions() in the RDMA transport. This is helpful to reduce the overhead of nvme_rdma_poll_group_process_completions() for large scale configuration. Signed-off-by:Shuhei Matsumoto <smatsumoto@nvidia.com> Change-Id: If19db4d59983024aa2fcec50ca2c1f17d0f3338c Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/18842 Reviewed-by:
Ben Walker <ben@nvidia.com> Community-CI: Mellanox Build Bot Tested-by:
SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by:
Aleksey Marchuk <alexeymar@nvidia.com>