From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alex Williamson Subject: Re: [RFC PATCH 0/3] Weight-balanced binary tree + KVM growable memory slots using wbtree Date: Tue, 22 Feb 2011 18:56:19 -0700 Message-ID: <1298426179.1668.35.camel@x201> References: <1298386481.5764.60.camel@x201> <20110222183822.22026.62832.stgit@s20.home> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org, mtosatti@redhat.com, xiaoguangrong@cn.fujitsu.com To: avi@redhat.com Return-path: In-Reply-To: <20110222183822.22026.62832.stgit@s20.home> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Tue, 2011-02-22 at 11:54 -0700, Alex Williamson wrote: > This series introduces a new weight-balanced binary tree (wbtree) for > general use. It's largely leveraged from the rbtree, copying it's > rotate functions, while introducing different rebalance and erase > functions. This tree is particularly useful for managing memory > ranges, where it's desirable to have the most likely targets (the > largest ranges) at the top of each subtree. > > Patches 2 & 3 go on to convert the KVM memory slots to a growable > array and make use of wbtree for efficient managment. Trying to > exercise the worst case for this data structure, I ran netperf > TCP_RR on an emulated rtl8139 NIC connected directly to the host > via a tap. Both qemu-kvm and the netserver on the host were > pinned to optimal CPUs with taskset. This series resulted in > a 3% improvement for this test. Marcelo asked about kernbench with ept=0 on this series. Using a 4-way, 10G guest with pinned vcpus, build in tmpfs, 10x optimal run, I got: before (stdev) after (stdev) % --------+-----------------+----------------+------- Elapsed | 42.809 (0.19) | 42.305 (0.23) | -1.18 User | 115.709 (0.22) | 114.720 (0.31) | -0.85 System | 41.605 (0.14) | 40.924 (0.20) | -1.64 %cpu | 366.9 (1.45) | 367.6 (1.51) | 0.19 context | 7272.3 (68.6) | 7249.5 (97.8) | -0.31 sleeps | 14826.2 (110.6) | 14798.5 (63.0) | -0.19 So, a small but measurable gain. Also, sorry for forgetting to address Marcelo's comments from the original version of patch 2/3, I'll pick them up in the next round. Thanks, Alex