Re: Regarding the basic use of perf top command
Hi, I think this should suffice https://perf.wiki.kernel.org/index.php/Tutorial#Live_analysis_with_perf_top Rest of the information is archived here http://lxr.linux.no/linux+v2.6.39/tools/perf/Documentation/ The value of 1000Hz means the frequency at which the system's timer is programmed to interrupt the kernel. It is a kernel configurable option. Thanks Vipin On 07/13/2011 10:59 AM, ankur dwivedi wrote: Hi, My question is regarding the basic use of perf top command in linux. The following is the snap shot of running a *perf top -e cache-misses* command from console: -- PerfTop: 76*irqs/sec* kernel:14.5% exact: 0.0% [1000Hz cache-misses], (all, 12 CPUs) -- *samples* *pcnt* functionDSO ___ _ ___ 48.00 36.9% get_page_from_freelist [kernel.kallsyms] 12.00 9.2% JS_CallTracer /usr/lib/xulrunner-1.9.2/libmozjs.so 12.00 9.2% JS_TraceChildren /usr/lib/xulrunner-1.9.2/libmozjs.so 8.00 6.2% dso__find_symbol/usr/bin/perf 7.00 5.4% native_flush_tlb_single [kernel.kallsyms] 6.00 4.6% _int_malloc /lib/libc-2.12.90.so http://libc-2.12.90.so What i want to know is the significance of different parameters here which are the following: 1. irqs/sec 2. samples 3. pcnt It also shows a value of 1000Hz. what is the meaning of that. I searched regarding these in the internet, but was unable to find a good explanation Thanks Ankur ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Linux Scheduler Statistics
Hi All, Posting it from my parallel question at LQ http://www.linuxquestions.org/questions/linux-kernel-70/proc-schedstats-statistics-890997/ I am trying to understand the statistics posted by /proc/schedstat. The documentation I could find on the subject was taken from here: Linux Scheduler Statistics http://eaglet.rain.com/rick/linux/sc...format-15.html I am running a FC14 2.6.35.6-45.fc14.x86_64 Below is a dump for my statistics version 15 timestamp 4356814703 cpu0 46540 0 96049852 39682767 50849563 28504181 6402127420973 1547256962507 55119801 domain0 ,,,,,,,0003 22495 21765 675 1037826 94 33 0 21765 5797 5345 416 1801124 55 0 1 5344 757236 702579 46725 114900414 9212 244 119 702460 44 13 31 0 0 0 0 0 0 375257 21494 0 domain1 ,,,,,,,000f 5593 4668 737 2285778 273 25 7 4661 5790 5750 34 266075 19 0 7 2801 374455 353235 19119 49007529 2851 30 4416 348819 17 4 13 0 0 0 0 0 0 93063 4192 0 ... Removed the rest of the cpu/domains Can somebody please explain me that why my cpu fields (2-4) are not zero as suggested in the document ? Am I doing something wrong ? or are the results different for x86 x86_64 boxes? Thanks. (P.S. I am running an i5 with 4 cores) Linux Boot process - somebody asked for it as I checked the archives http://www.opensourceproject.org.cn/article.php?id=182 Read Appendix A Thanks, Vipin Jain ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
