Commit 9b5dabff authored May 12, 2022 by Or Gerlitz Committed by Tomasz Zawadzki May 25, 2022

nvme/rdma: Always use spdk allocation scheme



Use the conventional huge-pages based spdk allocation scheme for the initiator
data-structures unconditionally.

Change-Id: I5baee7614e3ac9b5497b3d771dfddfbaa7fdf65b
Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12687


Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

parent 895300d8

lib/nvme/nvme_rdma.c

+2 −10

Original line number	Diff line number	Diff line
		@@ -404,22 +404,14 @@ nvme_rdma_calloc(size_t nmemb, size_t size)
		return NULL;
		}

		if (!g_nvme_hooks.get_rkey) {
		return calloc(nmemb, size);
		} else {
		return spdk_zmalloc(nmemb * size, 0, NULL, SPDK_ENV_SOCKET_ID_ANY, SPDK_MALLOC_DMA);
		}
		}

		static inline void
		nvme_rdma_free(void *buf)
		{
		if (!g_nvme_hooks.get_rkey) {
		free(buf);
		} else {
		spdk_free(buf);
		}
		}

		static int nvme_rdma_ctrlr_delete_io_qpair(struct spdk_nvme_ctrlr *ctrlr,
		struct spdk_nvme_qpair *qpair);

Admin message