From mboxrd@z Thu Jan 1 00:00:00 1970 From: Steven Rostedt Date: Tue, 13 Apr 2010 21:52:21 +0000 Subject: Re: [PATCH 7/7] sparc64: Add function graph tracer support. Message-Id: <1271195542.7962.92.camel@localhost> List-Id: References: <20100412.234300.212396783.davem@davemloft.net> In-Reply-To: <20100412.234300.212396783.davem@davemloft.net> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: sparclinux@vger.kernel.org On Tue, 2010-04-13 at 14:34 -0700, David Miller wrote: > From: Rostedt > Neener, neener: > :-p > 101) | run_local_timers() { > 115) + 24.063 us | raise_softirq(); > 69) | run_local_timers() { > 85) + 23.623 us | hrtimer_run_queues(); > 103) | run_local_timers() { > 66) + 71.749 us | } > 91) | run_local_timers() { > 106) + 23.184 us | raise_softirq(); > 65) + 29.117 us | raise_softirq(); > 68) + 23.843 us | hrtimer_run_queues(); > 112) + 23.623 us | hrtimer_run_queues(); > 105) + 24.063 us | hrtimer_run_queues(); > 17) + 25.161 us | raise_softirq(); > 82) + 24.282 us | hrtimer_run_queues(); > 100) + 72.628 us | } > > BTW, one thing that drives me nuts on this machine is that catting the > 'trace' file takes several seconds to start up. Is it calling > stop_machine() or something else which very expensive with high cpu > counts? No, in does not call stop_machine, but it stops all tracing on all cpus. I wonder what is happening :-/ It does allocate an "iterator" that has per cpu descriptors. Does "trace_pipe" give you the same issues? -- Steve