From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752428AbeESLqd (ORCPT ); Sat, 19 May 2018 07:46:33 -0400 Received: from terminus.zytor.com ([198.137.202.136]:56153 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752053AbeESLq3 (ORCPT ); Sat, 19 May 2018 07:46:29 -0400 Date: Sat, 19 May 2018 04:46:08 -0700 From: tip-bot for Jin Yao Message-ID: Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, ak@linux.intel.com, mingo@kernel.org, peterz@infradead.org, tglx@linutronix.de, jolsa@kernel.org, alexander.shishkin@linux.intel.com, kan.liang@linux.intel.com, yao.jin@linux.intel.com, acme@redhat.com Reply-To: alexander.shishkin@linux.intel.com, jolsa@kernel.org, kan.liang@linux.intel.com, yao.jin@linux.intel.com, acme@redhat.com, linux-kernel@vger.kernel.org, hpa@zytor.com, ak@linux.intel.com, mingo@kernel.org, peterz@infradead.org, tglx@linutronix.de In-Reply-To: <1526569118-14217-2-git-send-email-yao.jin@linux.intel.com> References: <1526569118-14217-2-git-send-email-yao.jin@linux.intel.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:perf/core] perf annotate: Record the min/max cycles Git-Commit-ID: 48659ebf37e5d9d23bda6dbf032bdbe9708929f1 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 48659ebf37e5d9d23bda6dbf032bdbe9708929f1 Gitweb: https://git.kernel.org/tip/48659ebf37e5d9d23bda6dbf032bdbe9708929f1 Author: Jin Yao AuthorDate: Thu, 17 May 2018 22:58:37 +0800 Committer: Arnaldo Carvalho de Melo CommitDate: Fri, 18 May 2018 16:31:41 -0300 perf annotate: Record the min/max cycles Currently perf has a feature to account cycles for LBRs For example, on skylake: perf record -b ... perf report or perf annotate And then browsing the annotate browser gives average cycle counts for program blocks. For some analysis it would be useful if we could know not only the average cycles but also the min and max cycles. This patch records the min and max cycles. Signed-off-by: Jin Yao Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1526569118-14217-2-git-send-email-yao.jin@linux.intel.com [ Switch from max/min to min/max ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 14 +++++++++++++- tools/perf/util/annotate.h | 4 ++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 5d74a30fe00f..4fcfefea3bc2 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -760,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes, ch[offset].num_aggr++; ch[offset].cycles_aggr += cycles; + if (cycles > ch[offset].cycles_max) + ch[offset].cycles_max = cycles; + + if (ch[offset].cycles_min) { + if (cycles && cycles < ch[offset].cycles_min) + ch[offset].cycles_min = cycles; + } else + ch[offset].cycles_min = cycles; + if (!have_start && ch[offset].have_start) return 0; if (ch[offset].num) { @@ -953,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) if (ch->have_start) annotation__count_and_fill(notes, ch->start, offset, ch); al = notes->offsets[offset]; - if (al && ch->num_aggr) + if (al && ch->num_aggr) { al->cycles = ch->cycles_aggr / ch->num_aggr; + al->cycles_max = ch->cycles_max; + al->cycles_min = ch->cycles_min; + } notes->have_cycles = true; } } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index f28a9e43421d..d50363d56f73 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -105,6 +105,8 @@ struct annotation_line { int jump_sources; float ipc; u64 cycles; + u64 cycles_max; + u64 cycles_min; size_t privsize; char *path; u32 idx; @@ -186,6 +188,8 @@ struct cyc_hist { u64 start; u64 cycles; u64 cycles_aggr; + u64 cycles_max; + u64 cycles_min; u32 num; u32 num_aggr; u8 have_start;