From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnaldo Carvalho de Melo Subject: Re: Perf event for Wall-time based sampling? Date: Thu, 18 Sep 2014 16:31:52 -0300 Message-ID: <20140918193152.GL2770@kernel.org> References: <2221771.b2oSN5LR6X@milian-kdab2> <2297882.Vc1x1zOfA6@milian-kdab2> <20140918155745.GH2770@kernel.org> <45528931.El8SOGvs6Z@milian-kdab2> <20140918191713.GK2770@kernel.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mail.kernel.org ([198.145.19.201]:47108 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756244AbaIRTb5 (ORCPT ); Thu, 18 Sep 2014 15:31:57 -0400 Content-Disposition: inline In-Reply-To: <20140918191713.GK2770@kernel.org> Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: Milian Wolff Cc: linux-perf-users , Namhyung Kim , Ingo Molnar , Joseph Schuchart Em Thu, Sep 18, 2014 at 04:17:13PM -0300, Arnaldo Carvalho de Melo escreveu: > Em Thu, Sep 18, 2014 at 06:37:47PM +0200, Milian Wolff escreveu: > > This was also why I asked my initial question, which I want to repeat once > > more: Is there a technical reason to not offer a "timer" software event to > > perf? I'm a complete layman when it comes to Kernel internals, but from a user > > point of view this would be awesome: > > > perf record --call-graph dwarf -e sw-timer -F 100 someapplication > > > This command would then create a timer in the kernel with a 100Hz frequency. > > Whenever it fires, the callgraphs of all threads in $someapplication are > > sampled and written to perf.data. Is this technically not feasible? Or is it > > simply not implemented? What you want is a sysrq-t that goes all the way to userspace, right? Try: echo t > /proc/sysrq dmesg i.e. probably you want that when a thread goes to sleep, we can take a sample with callchains, no? With a 'ping 127.0.0.1' running, I get this for its process: [19255.244315] ping S ffff88043e213100 0 6754 6548 0x00000080 [19255.244316] ffff880231693a80 0000000000000082 ffff88040ffb1940 0000000000013100 [19255.244317] ffff880231693fd8 0000000000013100 ffff880423c88000 ffff88040ffb1940 [19255.244318] ffffffff81efb1c0 ffff880231693ab0 00000001012131d1 ffffffff81efb1c0 [19255.244319] Call Trace: [19255.244321] [] schedule+0x29/0x70 [19255.244322] [] schedule_timeout+0x151/0x270 [19255.244325] [] __skb_recv_datagram+0x426/0x4d0 [19255.244328] [] skb_recv_datagram+0x32/0x40 [19255.244330] [] raw_recvmsg+0x7d/0x1b0 [19255.244331] [] inet_recvmsg+0x6c/0x80 [19255.244333] [] sock_recvmsg+0x9a/0xd0 [19255.244345] [] __sys_recvmsg+0x42/0x80 [19255.244346] [] SyS_recvmsg+0x12/0x20 [19255.244348] [] system_call_fastpath+0x16/0x1b No? Trying to collect dwarf callchains after installing iputils-debuginfo (where /bin/ping symtab is)... > > I'm experimenting with a libunwind based profiler, and with some ugly signal > > hackery I can now grab backtraces by sending my application SIGUSR1. Based on > > Humm, can't you do the same thing with perf? I.e. you send SIGUSR1 to > your app with the frequency you want, and then hook a 'perf probe' into > your signal... /me tries some stuff, will get back with results... > > > that, I can probably create a profiling tool that fits my needs. I just wonder > > why one cannot do the same with perf. > > - Arnaldo