diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-11-14 16:56:32 +0900 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-11-14 16:56:32 +0900 |
commit | fcd7476f9e03a36e709e0807198d47a826cc4e3a (patch) | |
tree | 1a9017988a864fae9ec62fd9e08e18cdc42d06cf /tools/perf/Documentation/perf-trace.txt | |
parent | d320e203bad4cfcef3613e83a52f8c70a77e8a60 (diff) | |
parent | d969135aae1434547f41853f0e8eaa622e8b8816 (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"A number of fixes:
- Fix segfault on perf trace -i perf.data, from Namhyung Kim.
- Fix segfault with --no-mmap-pages, from David Ahern.
- Don't force a refresh during progress update in the TUI, greatly
reducing startup costs, fix from Patrick Palka.
- Fix sw clock event period test wrt not checking if using >
max_sample_freq.
- Handle throttle events in 'object code reading' test, fix from
Adrian Hunter.
- Prevent condition that all sort keys are elided, fix from Namhyung
Kim.
- Round mmap pages to power 2, from David Ahern.
And a number of late arrival changes:
- Add summary only option to 'perf trace', suppressing the decoding
of events, from David Ahern
- 'perf trace --summary' formatting simplifications, from Pekka
Enberg.
- Beautify fifth argument of mmap() as fd, in 'perf trace', from
Namhyung Kim.
- Add direct access to dynamic arrays in libtraceevent, from Steven
Rostedt.
- Synthesize non-exec MMAP records when --data used, allowing the
resolution of data addresses to symbols (global variables, etc), by
Arnaldo Carvalho de Melo.
- Code cleanups by David Ahern and Adrian Hunter"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
tools lib traceevent: Add direct access to dynamic arrays
perf target: Shorten perf_target__ to target__
perf tests: Handle throttle events in 'object code reading' test
perf evlist: Refactor mmap_pages parsing
perf evlist: Round mmap pages to power 2 - v2
perf record: Fix segfault with --no-mmap-pages
perf trace: Add summary only option
perf trace: Simplify '--summary' output
perf trace: Change syscall summary duration order
perf tests: Compensate lower sample freq with longer test loop
perf trace: Fix segfault on perf trace -i perf.data
perf trace: Separate tp syscall field caching into init routine to be reused
perf trace: Beautify fifth argument of mmap() as fd
perf tests: Use lower sample_freq in sw clock event period test
perf tests: Check return of perf_evlist__open sw clock event period test
perf record: Move existing write_output into helper function
perf record: Use correct return type for write()
perf tools: Prevent condition that all sort keys are elided
perf machine: Simplify synthesize_threads method
perf machine: Introduce synthesize_threads method out of open coded equivalent
...
Diffstat (limited to 'tools/perf/Documentation/perf-trace.txt')
-rw-r--r-- | tools/perf/Documentation/perf-trace.txt | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 7b0497f95a7..fae38d9a44a 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -93,9 +93,15 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --comm:: Show process COMM right beside its ID, on by default, disable with --no-comm. +-s:: --summary:: - Show a summary of syscalls by thread with min, max, and average times (in - msec) and relative stddev. + Show only a summary of syscalls by thread with min, max, and average times + (in msec) and relative stddev. + +-S:: +--with-summary:: + Show all syscalls followed by a summary by thread with min, max, and + average times (in msec) and relative stddev. --tool_stats:: Show tool stats such as number of times fd->pathname was discovered thru |