From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rick Jones Subject: Re: [PATCH] vhost: Make it more scalable by creating a vhost thread per device. Date: Fri, 09 Apr 2010 10:13:08 -0700 Message-ID: <4BBF6024.6060809@hp.com> References: <1270229480.13897.8.camel@w-sridhar.beaverton.ibm.com> <1270488911.27874.43.camel@w-sridhar.beaverton.ibm.com> <1270771542.31186.397.camel@w-sridhar.beaverton.ibm.com> <4BBE716B.7050904@hp.com> <1270827580.25555.13.camel@w-sridhar.beaverton.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: "Michael S. Tsirkin" , Tom Lendacky , netdev , "kvm@vger.kernel.org" To: Sridhar Samudrala Return-path: Received: from g6t0186.atlanta.hp.com ([15.193.32.63]:38205 "EHLO g6t0186.atlanta.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751265Ab0DIRNL (ORCPT ); Fri, 9 Apr 2010 13:13:11 -0400 In-Reply-To: <1270827580.25555.13.camel@w-sridhar.beaverton.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: Sridhar Samudrala wrote: > On Thu, 2010-04-08 at 17:14 -0700, Rick Jones wrote: > >>>Here are the results with netperf TCP_STREAM 64K guest to host on a >>>8-cpu Nehalem system. >> >>I presume you mean 8 core Nehalem-EP, or did you mean 8 processor Nehalem-EX? > > > Yes. It is a 2 socket quad-core Nehalem. so i guess it is a 8 core > Nehalem-EP. > >>Don't get me wrong, I *like* the netperf 64K TCP_STREAM test, I lik it a lot!-) >>but I find it incomplete and also like to run things like single-instance TCP_RR >>and multiple-instance, multiple "transaction" (./configure --enable-burst) >>TCP_RR tests, particularly when concerned with "scaling" issues. > > > Can we run multiple instance and multiple transaction tests with a > single netperf commandline? Do you count a shell for loop as a single command line? > Is there any easy way to get consolidated throughput when a netserver on > the host is servicing netperf clients from multiple guests? I tend to use a script such as: ftp://ftp.netperf.org/netperf/misc/runemomniagg2.sh which presumes that netperf/netserver have been built with: ./configure --enable-omni --enable-burst ... and uses the CSV output format of the omni tests. When I want sums I then turn to a spreadsheet, or I suppose I could turn to awk etc. The TCP_RR test can be flipped around request size for response size etc, so when I have a single sustem under test, I initiate the netperf commands on it, targetting netservers on the clients. If I want inbound bulk throughput I use the TCP_MAERTS test rather than the TCP_STREAM test. happy benchmarking, rick jones