+1
−8
Loading
This was added in patch 07526d85, back in March 2018. This was before DPDK supported dynamic hugepage allocations. Presumably this flag was added to reduce the amount of memory lost due to mempool buffers that would otherwise span an IOVA boundary (mostly typical with IOMMU off and we are relying on physical addresses). Removing it simplifies any code in SPDK that uses mempool buffers for DMA operations, since it doesn't have to worry about splitting buffers that span an IOVA boundary - DPDK has already done it for us. Signed-off-by:Jim Harris <james.r.harris@intel.com> Change-Id: I49f6c1407fad02acae7e07c9dd00cb0449bd3554 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12277 Community-CI: Mellanox Build Bot Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Tested-by:
SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by:
Changpeng Liu <changpeng.liu@intel.com> Reviewed-by:
Aleksey Marchuk <alexeymar@mellanox.com>