From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754989Ab1KQDzL (ORCPT ); Wed, 16 Nov 2011 22:55:11 -0500 Received: from mail-wy0-f174.google.com ([74.125.82.174]:58576 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754460Ab1KQDzJ (ORCPT ); Wed, 16 Nov 2011 22:55:09 -0500 Message-ID: <1321502104.3274.22.camel@edumazet-laptop> Subject: [RFC] tracepoint/jump_label overhead From: Eric Dumazet To: Mathieu Desnoyers Cc: linux-kernel , Ingo Molnar , Christoph Lameter Date: Thu, 17 Nov 2011 04:55:04 +0100 Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.1- Content-Transfer-Encoding: 7bit Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The general admitted claim of a tracepoint being on x86 a single instruction : jmp +0 Is not always true. For example in mm/slub.c, kmem_cache_alloc() void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); return ret; We can check compiler output and see that 4 extra instructions were added because s->objsize & s->size are evaluated. I noticed this in a perf session, because these 4 extra instructions added some noticeable latency/cost. c10e26a4: 8b 5d d8 mov -0x28(%ebp),%ebx c10e26a7: 85 db test %ebx,%ebx c10e26a9: 75 6d jne c10e2718 (doing the memset()) c10e26ab: 8b 76 0c mov 0xc(%esi),%esi // extra 1 c10e26ae: 8b 5d 04 mov 0x4(%ebp),%ebx // extra 2 c10e26b1: 89 75 f0 mov %esi,-0x10(%ebp) // extra 3 c10e26b4: 89 5d ec mov %ebx,-0x14(%ebp) // extra 4 c10e26b7: e9 00 00 00 00 jmp c10e26bc c10e26bc: 8b 45 d8 mov -0x28(%ebp),%eax c10e26bf: 83 c4 28 add $0x28,%esp c10e26c2: 5b pop %ebx c10e26c3: 5e pop %esi c10e26c4: 5f pop %edi c10e26c5: c9 leave A fix would be to not declare an inline function but a macro... #define trace_kmem_cache_alloc(...) \ if (static_branch(&__tracepoint_kmem_cache_alloc.key)) \ __DO_TRACE(&__tracepoint_kmem_cache_alloc, \ ... Anyone has some clever idea how to make this possible ? Thanks