On 2/9/2024 12:02 AM, lon...@linuxonhyperv.com wrote: > From: Long Li <lon...@microsoft.com> > > Instead of allocating mbufs one by one during RX, use > rte_pktmbuf_alloc_bulk() to allocate them in a batch. > > With this patch, there are no measurable performance improvements in > benchmarks. However, this patch should improve CPU cycles and reduce > potential locking conflicts in real-world applications. > > Signed-off-by: Long Li <lon...@microsoft.com> >
Applied to dpdk-next-net/main, thanks.