From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Monjalon Subject: Re: Performances are not scale with multiple ports Date: Tue, 28 May 2013 11:22:44 +0200 Message-ID: <201305281122.44387.thomas.monjalon@6wind.com> References: Mime-Version: 1.0 Content-Type: Text/Plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: dev-VfR2kkLFssw@public.gmane.org To: Shinae Woo Return-path: In-Reply-To: List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" Hello, 28/05/2013 04:26, Shinae Woo : > ./build/l2fwd -cf -n3 -- -p3 > ./build/l2fwd -cf -n3 -- -pf > > But both cases, the aggregated performance are not scale. [..] > The question is that > 1. How I can achieve each port receiving full 14.88Mpps ? > What might be the bottleneck in current environment? > 2. Why the performance using multiple ports is not scale? > I guess doubling ports shows the doubling the receiving performance, > but it shows not. I am curious about what is limiting the packet > receivng performance. In order to scale with line-rate performance, you probably have to adjust the configuration to your hardware. Several parameters should be considered: - PCIe bus (is it fast enough ?) - NUMA sockets (copy between NUMA nodes could slow forwarding) - CPU threads (classic SMP is better than hyperthreading) To make it short, you could check your PCI bus and your CPU configuration. For the latter, /proc/cpuinfo should provide enough information with fields "physical id" and "core id". -- Thomas