- 14 Nov, 2016 11 commits
-
-
Jin Yao authored
Create some branch counters in per callchain list entry. Each counter is for a branch flag. For example, predicted_count counts all the *predicted* branches. The counters get updated by processing the callchain cursor nodes. It also provides functions to retrieve or print the values of counters in callchain list. Besides the counting for branch flags, it also counts and returns the average number of iterations. Signed-off-by:
Yao Jin <yao.jin@linux.intel.com> Acked-by:
Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linux-kernel@vger.kernel.org Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/1477876794-30749-4-git-send-email-yao.jin@linux.intel.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Jin Yao authored
Create a new flag show_branchflag_count in symbol_conf. The flag is used to control if showing the branch flag counting information. The flag depends on if the perf.data has branch data and if user chooses the "branch-history" option in perf report command line. Signed-off-by:
-
Jin Yao authored
Since the branch ip has been added to call stack for easier browsing, this patch adds more branch information. For example, add a flag to indicate if this ip is a branch, and also add with the branch flag. Then we can know if the cursor node represents a branch and know what the branch flag it has. The branch history code has a loop detection pass that removes loops. It would be nice for knowing how many loops were removed then in next steps, we can compute out the average number of iterations. For example: Before remove_loops(), entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x300, to = 0x250 entry3: from = 0x300, to = 0x250 entry4: from = 0x700, to = 0x800 After remove_loops() entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x700, to = 0x800 The original entry2 and entry3 are removed. So the number of iterations (from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1). iterations = removed number + 1; average iteractions = Sum(iteractions) / number of samples This formula ignores other cases, for example, iterations cross multiple buffers and one buffer contains 2+ loops. Because in practice, it's good enough. Signed-off-by:
-
Taeung Song authored
To write config items to a particular config file, we should know where is each config section and item from. Current setting functionality of perf-config use autogenerating way by overwriting collected config items to a config file. For example, when collecting config items from user and system config files (i.e. ~/.perfconfig and $(sysconf)/perfconfig), perf_config_set can contain both user and system config items. So we should know where each value is from to avoid merging user and system config items on user config file. Signed-off-by:
Taeung Song <treeze.taeung@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Nambong Ha <over3025@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Wookje Kwon <aweee0@gmail.com> Link: http://lkml.kernel.org/r/1478241862-31230-7-git-send-email-treeze.taeung@gmail.comSigned-off-by:
-
Taeung Song authored
Add setting feature that can add config variables with their values to a config file (i.e. user or system config file) or modify config key-value pairs in a config file. For the syntax examples: perf config [<file-option>] [section.name[=value] ...] e.g. You can set the ui.show-headers to false with # perf config ui.show-headers=false If you want to add or modify several config items, you can do like # perf config annotate.show_nr_jumps=false kmem.default=slab Committer notes: Testing it: $ perf config -l top.children=true report.children=false $ $ perf config top.children=false $ perf config -l top.children=false report.children=false $ $ perf config kmem.default=slab $ perf config -l top.children=false report.children=false kmem.default=slab $ Signed-off-by: -
Taeung Song authored
You can show the values for several config items as below: # perf config report.queue-size call-graph.record-mode but it is necessary to more precisely check arguments, before passing them to show_spec_config(). This validation function would be also used when parsing config key-value pairs arguments in the near future. Committer notes: Testing it: $ perf config bla. The config variable does not contain a variable name: bla. $ perf config .bla The config variable does not contain a section name: .bla $ perf config bla.bla $ Signed-off-by: -
Taeung Song authored
Add a functionality getting specific config key-value pairs. For the syntax examples, perf config [<file-option>] [section.name ...] e.g. To query config items 'report.queue-size' and 'report.children', do # perf config report.queue-size report.children Signed-off-by: -
Jiri Olsa authored
Now when jvmti compilation is plugged into Makefile.perf, there's no need for this makefile. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Acked-by:
Stephane Eranian <eranian@google.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: William Cohen <wcohen@redhat.com> Link: http://lkml.kernel.org/r/20161112121016.GA17194@kravaSigned-off-by:
-
Jiri Olsa authored
Compile jvmti agent as part of the perf build. The agent library is called libperf-jvmti.so and is installed in default place together with other files: $ make libperf-jvmti.so BUILD: Doing 'make -j4' parallel build ... CC jvmti/libjvmti.o CC jvmti/jvmti_agent.o LD jvmti/jvmti-in.o LINK libperf-jvmti.so $ make DESTDIR=/tmp/krava/ install-bin ... $ find /tmp/krava/ | grep libperf /tmp/krava/lib64/libperf-jvmti.so /tmp/krava/lib64/libperf-gtk.so Signed-off-by: -
Jiri Olsa authored
Adding support to detect jvmti support. It is not plugged into the FEATURE_TESTS machinery, because it's quite rare and will be used separately from perf via feature_check call. Signed-off-by:
-
Jiri Olsa authored
Adding support to remove options from final CFLAGS for both object file and build target. It's now possible to remove CFLAGS options like: CFLAGS_REMOVE_krava.o += -Wstrict-prototypes Committer notes: This comes from the kernel's kbuild infrastructure, the subset that is supported in tools/ is being documented at tools/build/Documentation/Build.txt. Signed-off-by:
-
- 11 Nov, 2016 1 commit
-
-
Arnaldo Carvalho de Melo authored
Since the unprivileged sched switch event was added in perf, PT doesn't need need perf_event_paranoid=-1 anymore for per cpu decoding. Add a note stating that that is only needed for kernels < 4.2. Reported-by:
Adrian Hunter <adrian.hunter@intel.com> Fixes: 45ac1403 ("perf: Add PERF_RECORD_SWITCH to indicate context switches") Link: http://lkml.kernel.org/n/tip-x2ybghpqxxn3zu0m8o7qi42r@git.kernel.orgSigned-off-by:
-
- 08 Nov, 2016 1 commit
-
-
Rabin Vincent authored
Since 841e3558 ("perf callchain: Recording 'dwarf' callchains do not need DWARF unwinding support"), --call-graph dwarf is allowed in 'perf record' even without unwind support. A couple of other places don't reflect this yet though: the help text should list dwarf as a valid record mode and the dump_size config should be respected too. Signed-off-by:
Rabin Vincent <rabinv@axis.com> Cc: He Kuang <hekuang@huawei.com> Fixes: 841e3558 ("perf callchain: Recording 'dwarf' callchains do not need DWARF unwinding support") Link: http://lkml.kernel.org/r/1470837148-7642-1-git-send-email-rabin.vincent@axis.comSigned-off-by:
-
- 28 Oct, 2016 9 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-20161028' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core perf/core improvements and fixes from Arnaldo Carvalho de Melo: New features: - Support matching by topic in 'perf list' (Andi Kleen) User visible: - Apply cpu color only when there was activity in 'perf sched map' (Namhyung Kim) - Always show the task's COMM in 'perf sched map -v' (Namhyung Kim) - Fix hierarchy column counts in the perf hist browser (top, report), avoiding showing nothing after pressing the RIGHT key a number of times (Namhyung Kim) Infrastructure: - Support cascading options in libsubcmd and use it to share common options in 'perf sched' subcommands (Namhyung Kim) - Avoid worker cacheline bouncing in 'perf bench futex' (Davidlohr Bueso) - Sanitize numeric parameters in 'perf bench futex' (Davidlohr Bueso) - Update copies of kernel files (Arnaldo Carvalho de Melo) - Fix scripting (perl, python) setup to avoid leaks (Arnaldo Carvalho de Melo) - Add missing object file to the python binding linkage list (Arnaldo Carvalho de Melo) Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
Arnaldo Carvalho de Melo authored
In ac12f676 ("perf tools: Implement branch_type event parameter") we started using the parse_branch_str() function from one of the files used in the python binding, which caused this entry in 'perf test' to fail: # perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 16667 Traceback (most recent call last): File "<stdin>", line 1, in <module> ImportError: /tmp/build/perf/python/perf.so: undefined symbol: parse_branch_str test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! # I must've commited some mistake when running 'perf test' to send the pull request for the perf-core-for-mingo-20161024 tag, to have let this regression to pass, sigh. Just add tools/perf/util/parse-branch-options.c and switch from using ui__warning(), that is not available in the python binding, use pr_warning() instead, which is good enough for this case. Now: # perf test python 16: Try 'import perf' in python, checking link problems : Ok # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Fixes: ac12f676 ("perf tools: Implement branch_type event parameter") Link: http://lkml.kernel.org/n/tip-9kn1ct1cx9ppwqlmzl6z0xhs@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing one more set of die() calls. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-6pyil685m5i2tugg56gcy0tg@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Both register_perl_scripting() and register_python_scripting() allocate this variable, fix it by checking if it already was. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 7e4b21b8 ("perf/scripts: Add Python scripting engine") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Introduced in commit f9afc619 ("x86: Wire up protection keys system calls") This will make 'perf trace' aware of them on x86_64. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-s1ta2ttv2xacecqogmd3a9p1@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To get the defines introduced in the commit e8c24d3a ("x86/pkeys: Allocation/free syscalls") Silencing this perf build warning: Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel Need to change 'perf trace' to beautify those syscalls, as soon as booting with a kernel with it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-yev9rexu02cl7cjeozzmrl9t@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Ignore export.h and EXPORT_SYMBOL in: 784d5699 ("x86: move exports to actual definitions") We're not dragging this stuff, not useful in tools/ This silences the following warnings while building perf: Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel Warning: tools/arch/x86/lib/memset_64.S differs from kernel Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-h9vw3pe0fq79zmyqsfr0s0mo@git.kernel.orgSigned-off-by:
-
Andi Kleen authored
Add support in perf list topic to only show events belonging to a specific vendor events topic. For example the following works now: % perf list frontend List of pre-defined events (to be used in -e): stalled-cycles-frontend OR idle-cycles-frontend [Hardware event] stalled-cycles-frontend OR cpu/stalled-cycles-frontend/ [Kernel PMU event] frontend: dsb2mite_switches.count [Decode Stream Buffer (DSB)-to-MITE switches] dsb2mite_switches.penalty_cycles [Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles] dsb_fill.exceed_dsb_lines [Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines] icache.hit [Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches] ... Signed-off-by: -
Namhyung Kim authored
Joonwoo reported that there's a mismatch between timestamps in script and sched commands. This was because of difference in printing the timestamp. Factor out the code and share it so that they can be in sync. Also I found that sched map has similar problem, fix it too. Committer notes: Fixed the max_lat_at bug introduced by Namhyung's original patch, as pointed out by Joonwoo, and made it a function following the scnprintf() model, i.e. returning the number of bytes formatted, and receiving as the first parameter the object from where the data to the formatting is obtained, renaming it from: char *timestamp_in_usec(char *bf, size_t size, u64 timestamp) to int timestamp__scnprintf_usec(u64 timestamp, char *bf, size_t size) Reported-by:
Joonwoo Park <joonwoop@codeaurora.org> Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20161024020246.14928-3-namhyung@kernel.orgSigned-off-by:
-
- 25 Oct, 2016 7 commits
-
-
Namhyung Kim authored
I'd like to see the name of tasks with perf sched map, but it only shows name of new tasks and then use short names after all. This is not good for long running tasks since it's hard for users to track the short names. This patch makes it show the names (except the idle task) when -v option is used. Probably we may make it as default behavior. Signed-off-by:
-
Namhyung Kim authored
Applying cpu color always doesn't help readability IMHO. Instead it might be better to applying the color when there's an activity on those CPUs. Signed-off-by:
-
Namhyung Kim authored
The -i and -v options can be used in subcommands so enable cascading the sched_options. This fixes the following inconvenience in 'perf sched': $ perf sched -i perf.data.sched map ... (it works well) ... $ perf sched map -i perf.data.sched Error: unknown switch `i' Usage: perf sched map [<options>] --color-cpus <cpus> highlight given CPUs in map --color-pids <pids> highlight given pids in map --compact map output in compact mode --cpus <cpus> display given CPUs in map With this patch, the second command line works with the perf.data.sched data file. Signed-off-by: -
Namhyung Kim authored
Sometimes subcommand have common options and it can only handled in the upper level command unless it duplicates the options. This patch adds a parent field and fallback to the parent if the given argument was not found in the current options. Signed-off-by:
-
Namhyung Kim authored
The perf report/top on TUI supports horizontal scrolling using LEFT and RIGHT keys. But it calculate the number of columns incorrectly when hierarchy mode is enabled so that keep pressing RIGHT key can make the output disappeared. In the hierarchy mode, all sort keys are collapsed into a single column, so it needs to be applied when calculating column numbers. Reported-and-Tested-by:
Markus Trippelsdorf <markus@trippelsdorf.de> Signed-off-by:
-
Davidlohr Bueso authored
This gets rid of oddities such as: perf bench futex hash -t -4 perf: calloc: Cannot allocate memory Runtime (and many more) are equally busted, i.e. run for bogus amounts of time. Just use the abs, instead of, for example errorring out. Committer note: After the patch: $ perf bench futex hash -t -4 # Running 'futex/hash' benchmark: Run summary [PID 10178]: 4 threads, each operating on 1024 [private] futexes for 10 secs. [thread 0] futexes: 0x34f9fa0 ... 0x34faf9c [ 4702208 ops/sec ] [thread 1] futexes: 0x34fb140 ... 0x34fc13c [ 4707020 ops/sec ] [thread 2] futexes: 0x34fc2e0 ... 0x34fd2dc [ 4711526 ops/sec ] [thread 3] futexes: 0x34fd480 ... 0x34fe47c [ 4709683 ops/sec ] Averaged 4707609 operations/sec (+- 0.04%), total secs = 10 $ Signed-off-by:
Davidlohr Bueso <dbueso@suse.de> Tested-by:
-
Davidlohr Bueso authored
Sebastian noted that overhead for worker thread ops (throughput) accounting was producing 'perf' to appear in the profiles, consuming a non-trivial (i.e. 13%) amount of CPU. This is due to cacheline bouncing due to the increment of w->ops. We can easily fix this by just working on a local copy and updating the actual worker once done running, and ready to show the program summary. There is no danger of the worker being concurrent, so we can trust that no stale value is being seen by another thread. This also gets rid of the unnecessary cache alignment hack; its not worth it. Reported-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by:
-
- 24 Oct, 2016 11 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-20161024' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: New features: - Dynamicly change verbosity level by pressing 'V' in the 'perf top/report' hists TUI browser (Alexis Berlemont) - Implement 'perf trace --delay' in the same fashion as in 'perf record --delay', to skip sampling workload initialization events (Alexis Berlemont) - Make vendor named events case insensitive in 'perf list', i.e. 'perf list LONGEST_LAT' works just the same as 'perf list longest_lat' (Andi Kleen) - Show instruction bytes and lenght in 'perf script' for Intel PT and BTS (Andi Kleen, Adrian Hunter) E.g: % perf record -e intel_pt// foo % perf script --itrace=i0ns -F ip,insn,insnlen ffffffff8101232f ilen: 5 insn: 0f 1f 44 00 00 ffffffff81012334 ilen: 1 insn: 5b ffffffff81012335 ilen: 1 insn: 5d ffffffff81012336 ilen: 1 insn: c3 ffffffff810123e3 ilen: 1 insn: 5b ffffffff810123e4 ilen: 2 insn: 41 5c ffffffff810123e6 ilen: 1 insn: 5d ffffffff810123e7 ilen: 1 insn: c3 ffffffff810124a6 ilen: 2 insn: 31 c0 ffffffff810124a8 ilen: 9 insn: 41 83 bc 24 a8 01 00 00 01 ffffffff810124b1 ilen: 2 insn: 75 87 - Allow enabling the perf_event_attr.branch_type attribute member: (Andi Kleen) perf record -e sched:sched_switch,cpu/cpu-cycles,branch_type=any/ ... - Add unwinding support for jitdump (Stefano Sanfilippo) Fixes: - Use raw_syscall:sys_enter timestamp in 'perf trace' (Arnaldo Carvalho de Melo) Infrastructure: - Allow jitdump to be built without libdwarf (Maciej Debski) - Sync x86's syscall table tools/ copy (Arnaldo Carvalho de Melo) - Fixes to avoid calling die() in library fuctions already propagating other errors (Arnaldo Carvalho de Melo) - Improvements to allow libtraceevent to be properly installed in distro packages (Jiri Olsa) - Removing coresight miscellaneous debug output (Mathieu Poirier) - Cache align the 'perf bench futex' worker struct (Sebastian Andrzej Siewior) Documentation: - Minor improvements on the documentation of event parameters (Andi Kleen) - Add jitdump format specification document (Stephane Eranian) Spelling fixes: - Fix typo "No enough" to "Not enough" (Alexander Alemayhu) Signed-off-by:
-
Mathieu Poirier authored
Printing the full path of the selected link is obviously not needed, hence removing. Signed-off-by:
Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1476913323-6836-1-git-send-email-mathieu.poirier@linaro.orgSigned-off-by:
-
Andi Kleen authored
Make the 'perf list' glob matching for vendor events case insensitive. This allows to use the upper case vendor events with perf list too. Now the following works: % perf list LONGEST_LAT ... cache: longest_lat_cache.miss [Core-originated cacheable demand requests missed LLC] longest_lat_cache.reference [Core-originated cacheable demand requests that refer to LLC] Signed-off-by: -
Arnaldo Carvalho de Melo authored
Instead of the one when another syscall takes place while another is being processed (in another CPU, but we show it serialized, so need to "interrupt" the other), and also when finally showing the sys_enter + sys_exit + duration, where we were showing the sample->time for the sys_exit, duh. Before: # perf trace sleep 1 <SNIP> 0.373 ( 0.001 ms): close(fd: 3 ) = 0 1000.626 (1000.211 ms): nanosleep(rqtp: 0x7ffd6ddddfb0) = 0 1000.653 ( 0.003 ms): close(fd: 1 ) = 0 1000.657 ( 0.002 ms): close(fd: 2 ) = 0 1000.667 ( 0.000 ms): exit_group( ) # After: # perf trace sleep 1 <SNIP> 0.336 ( 0.001 ms): close(fd: 3 ) = 0 0.373 (1000.086 ms): nanosleep(rqtp: 0x7ffe303e9550) = 0 1000.481 ( 0.002 ms): close(fd: 1 ) = 0 1000.485 ( 0.001 ms): close(fd: 2 ) = 0 1000.494 ( 0.000 ms): exit_group( ) [root@jouet linux]# Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-ecbzgmu2ni6glc6zkw8p1zmx@git.kernel.org Fixes: 752fde44 ("perf trace: Support interrupted syscalls") Signed-off-by: -
Arnaldo Carvalho de Melo authored
Not used at all, we need just the entry_time to calculate the syscall duration. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-js6r09zdwlzecvaei7t4l3vd@git.kernel.orgSigned-off-by:
-
Sebastian Andrzej Siewior authored
It popped up in perf testing that the worker consumes some amount of CPU. It boils down to the increment of `ops` which causes cache line bouncing between the individual threads. This patch aligns the struct by 256 bytes to ensure that not a cache line is shared among CPUs. 128 byte is the x86 worst case and grep says that L1_CACHE_SHIFT is set to 8 on s390. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We already have handling for errors when processing PERF_RECORD_ events, so instead of calling die() when not being able to alloc, propagate the error, so that the normal UI exit sequence can take place, the user be warned and possibly the terminal be properly reset to a sane mode. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-r90je3c009a125dvs3525yge@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
It already returns whatever strbuf_(grow|addch)() returns in case of failure, so just return -ENOSPC in the only case where it was die()ing. When it returns, its only caller will call die() anyway, so no need to be so eager, die later. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-as05b7mbogprlwi8iarwns8e@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Instead of having all tests perform alloc/free, do it in the code that calls the do_cycles() and do_gettimeofday() functions. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-lywj4mbdb1m9x1z9asivwuuy@git.kernel.orgSigned-off-by:
-
Alexis Berlemont authored
In the perf wiki todo-list[1], there is an entry regarding initial-delay and 'perf trace'; the following small patch tries to fulfill this point. It has been generated against the branch tip/perf/core. It has only been implemented in the "trace__run" case. Ex.: $ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1 ... fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0 ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0 fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0 write(6, "\0", 1) = 1 close(6) = 0 nanosleep({0, 5000000}, NULL) = 0 # DELAY OF 5 MS BEFORE ENABLING THE EVENTS ioctl(3, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(4, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(5, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(7, PERF_EVENT_IOC_ENABLE, 0) = 0 ... [1]: https://perf.wiki.kernel.org/index.php/TodoSigned-off-by:Alexis Berlemont <alexis.berlemont@gmail.com> Suggested-and-Tested-by:
-
Alexis Berlemont authored
Here is a small patch which tries to fulfill a point in the perf todo list: * Make pressing 'V' multiple times to go on cycling thru various verbosity levels in 'perf top', so that info that is present in 'perf top -v' can be obtained without having to restart the tool (acme). After a small grep in the code, the max verbosity level seems 3; so, we cycle at 4; I did not dare define a MAX_VERBOSE_LEVEL constant. Signed-off-by:
-
