git.droids-corp.org / dpdk.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: edbe962) | patch
net/hns3: optimize Tx performance by mbuf fast free
authorChengwen Feng <fengchengwen@huawei.com>
Tue, 16 Nov 2021 01:22:11 +0000 (09:22 +0800)
committerFerruh Yigit <ferruh.yigit@intel.com>
Tue, 16 Nov 2021 15:39:20 +0000 (16:39 +0100)
commit3cc817c195cc8e3bf54b5cadd89c5c7776d3727e
treef460da4bd38573883d043dd1cc876f358d3b372ftree | snapshot
parentedbe962fa18d5133bae10f81bf6f13b43901a30bcommit | diff
net/hns3: optimize Tx performance by mbuf fast free

Currently the vector and simple xmit algorithm don't support multi_segs,
so if Tx offload support MBUF_FAST_FREE, driver could invoke
rte_mempool_put_bulk() to free Tx mbufs in this situation.

In the testpmd single core MAC forwarding scenario, the performance is
improved by 8% at 64B on Kunpeng920 platform.

Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
doc/guides/nics/features/hns3.ini diff | blob | history
drivers/net/hns3/hns3_rxtx.c diff | blob | history
drivers/net/hns3/hns3_rxtx.h diff | blob | history
drivers/net/hns3/hns3_rxtx_vec.h diff | blob | history
DPDK repo used for reviews