Bulk allocation of multiple mbufs increased more than ~2% and less
than 8% throughput on single core (1.8 GHz), based on usage for example
1: Testpmd case: Two null devices with copy 8% improvement.
testpmd -c 0x3 -n 4 --socket-mem 1024,1024
--vdev 'eth_null0,size=64,copy=1' --vdev 'eth_null1,size=64,copy=1'
-- -i -a --coremask=0x2 --txrst=64 --txfreet=64 --txd=256
--rxd=256 --rxfreet=64 --burst=64 --txpt=64 --txq=1 --rxq=1 --numa
2. Ovs switch case: 2% improvement.
$VSCTL add-port ovs-br dpdk1 -- set Interface dpdk1 type=dpdk \
options:dpdk-devargs=eth_null0,size=64,copy=1
$VSCTL add-port ovs-br dpdk2 -- set Interface dpdk2 type=dpdk \
options:dpdk-devargs=eth_null1,size=64,copy=1
Signed-off-by: Mallesh Koujalagi <malleshx.koujalagi@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
return 0;
packet_size = h->internals->packet_size;
+ if (rte_pktmbuf_alloc_bulk(h->mb_pool, bufs, nb_bufs) != 0)
+ return 0;
+
for (i = 0; i < nb_bufs; i++) {
- bufs[i] = rte_pktmbuf_alloc(h->mb_pool);
- if (!bufs[i])
- break;
bufs[i]->data_len = (uint16_t)packet_size;
bufs[i]->pkt_len = packet_size;
bufs[i]->port = h->internals->port_id;
return 0;
packet_size = h->internals->packet_size;
+ if (rte_pktmbuf_alloc_bulk(h->mb_pool, bufs, nb_bufs) != 0)
+ return 0;
+
for (i = 0; i < nb_bufs; i++) {
- bufs[i] = rte_pktmbuf_alloc(h->mb_pool);
- if (!bufs[i])
- break;
rte_memcpy(rte_pktmbuf_mtod(bufs[i], void *), h->dummy_packet,
packet_size);
bufs[i]->data_len = (uint16_t)packet_size;