From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH V2 1/3] lib: introduce some memory copy macros and functions Date: Thu, 02 Sep 2010 10:55:58 +0200 Message-ID: <877hj4o76p.fsf@basil.nowhere.org> References: <4C7F3A2A.2000007@cn.fujitsu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Peter Zijlstra , Ingo Molnar , Andrew Morton , "Theodore Ts'o" , Linux Kernel , Linux Ext4 , Linux Btrfs To: miaox@cn.fujitsu.com Return-path: In-Reply-To: <4C7F3A2A.2000007@cn.fujitsu.com> (Miao Xie's message of "Thu, 02 Sep 2010 13:46:18 +0800") List-ID: Miao Xie writes: > Changes from V1 to V2: > - change the version of GPL from version 2.1 to version 2 > > the kernel's memcpy and memmove is very inefficient. But the glibc version is > quite fast, in some cases it is 10 times faster than the kernel version. So I Can you elaborate on which CPUs and with what workloads you measured that? The kernel memcpy is optimized for copies smaller than a page size for example (kernel very rarely does anything on larger than 4k), the glibc isn't. etc. There are various other differences. memcpy and memmove are very different. AFAIK noone has tried to optimize memmove() before because traditionally it wasn't used for anything performance critical in the kernel. Has that that changed? memcpy on the other hand while not perfect is actually quite optimized for typical workloads. One big difference between the kernel and glibc is that kernel is often cache cold, so you e.g. the cost of a very large code footprint memcpy/memset is harder to amortize. Microbenchmarks often leave out that crucial variable. I have some systemtap scripts to measure size/alignment distributions of copies on a kernel, if you have a particular workload you're interested in those could be tried. Just copying the glibc bloat uncritical is very likely the wrong move at least. -Andi -- ak@linux.intel.com -- Speaking for myself only.