Lines Matching refs:perf

4 supports broadly the same options as the linux-tools perf, but also supports
20 The Linux kernel wraps these hardware counters into hardware perf events. In
43 5. Simpleperf reads samples from the mapped buffers and generates perf.data.
45 The report command reads a "perf.data" file and any shared libraries used by
178 When monitoring perf counters, we can also use --interval option to decide the print
196     # open the collected new.html in browser and perf counters will be shown up
205     # to perf.data.
259 By default, simpleperf stores records in perf.data in current directory. We can
266 simpleperf report is used to report based on perf.data generated by simpleperf
270 perf.data and executable binaries used by the monitored program, filter out
277 perf event is cpu-cycles, the overhead can be seen as the percentage of cpu
280     # Reports perf.data, using only records sampled in libsudo-game-jni.so,
297 By default, simpleperf reads perf.data in current directory. We can use -i
358 Simpleperf works similar to linux-tools-perf, but it has following improvements:
368 perf.data. So we can profile for a longer time with limited space on device.'
382 to profile processes running device, and generate perf.data.
386 bin/windows.They can be used to parse perf.data on host.
392 perf.data on host. It is configured by app_profiler.config.
395 annotate.py is used to annotate source files using perf.data. It is configured
397 report.py reports perf.data in a GUI window.
398 simpleperf_report_lib.py is used to enumerate samples in perf.data. Internally
399 it uses libsimpleperf_report.so to parse perf.data. It can be used to translate
400 samples in perf.data to other forms. One example using simpleperf_report_lib.py
417 file: perf.data, and run simpleperf to report perf.data. Below are the steps.
450 ### 4. Record perf.data
454     angler:/data/data/com.example.sudogame $ls -lh perf.data
455     -rw-rw-rw- 1 u0_a93 u0_a93 2.6M 2017-01-01 09:26 perf.data
460 ### 5. Report perf.data
461 There are different ways to report perf.data. Below shows some examples.
509 in perf.data (otherwise, simpleperf can’t find it). In this case, it is
660 #### 2. Record perf.data
665 #### 3. Report perf.data
733 runs simpleperf to generate perf.data, and pulls perf.data and binaries from
751 It pulls generated perf.data on host, and collects binaries from device in
761 simpleperf_report_lib.py provides an interface reading samples from perf.data.
766     $python report_sample.py >out.perf
767     $stackcollapse-perf.pl out.perf >out.folded
779 annotate.py reads perf.data and binaries in binary_cache. Then it knows which