- 23 Oct, 2009 4 commits
-
-
Arnaldo Carvalho de Melo authored
We were using eprintf in some places, that looks at a global 'verbose' level, and at other places passing a 'v' parameter to specify the verbosity level, unify it by introducing pr_{err,warning,debug,etc}, just like in the kernel. Signed-off-by:Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256153646-10097-1-git-send-email-acme@redhat.com> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
Frederic Weisbecker authored
Wrapping the kernel headers is dangerous when it comes to arch headers. Once we wrap asm/types.h, it will also replace the glibc asm/types.h, not only the kernel one. This results in build errors on some machines. Drop this wrapper and do its work from linux/types.h wrapper, also the glibc asm/types.h can already handle most of the type definition it was doing (typedef __u64, __u32, etc...). Todo: Check the others asm/*.h wrappers to prevent from other conflicts. Reported-by:
Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-3-git-send-email-fweisbec@gmail.com> Signed-off-by:
-
Frederic Weisbecker authored
Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: -
Frederic Weisbecker authored
While recursively printing the branches of each callchains, we forget to display the root. It is never printed. Say we have: symbol f1 f2 | -------- f3 | f4 | ---------f5 f6 Actually we never see that, instead it displays: symbol | --------- f3 | f4 | --------- f5 f6 However f1 is always the same than "symbol" and if we are sorting by symbols first then "symbol", f1 and f2 will be well aligned like in the above example, so displaying f1 looks redundant here. But if we are sorting by something else first (dso, comm, etc...), displaying f1 doesn't look redundant but rather necessary because the symbol is not well aligned anymore with its callchain: comm dso symbol f1 f2 | --------- [...] And we want the callchain to be obvious. So we fix the bug by printing the root branch, but we also filter its first entry if we are sorting by symbols first. Reported-by:Anton Blanchard <anton@samba.org> Signed-off-by:
-
- 21 Oct, 2009 2 commits
-
-
Steven Rostedt authored
The second argument in the strtok_r() function is not to be used generically and can have different implementations. Currently the function parsing of the perf trace code uses the second argument to copy data from. This can crash the tool or just have unpredictable results. The correct solution is to use strsep() which has a defined result. I also added a check to see if the result was correct, and will break out of the loop in case it fails to parse as expected. Reported-by:
Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <20091020232034.237814877@goodmis.org> Signed-off-by:
-
Steven Rostedt authored
When using gdb to debug perf, it is practically impossible to use when perf is compiled with -O6. For developers, this patch adds the DEBUG feature to the make command line so that a developer can easily remove the optimization flag. LKML-Reference: <1255590330.8392.446.camel@twins> Signed-off-by:
-
- 20 Oct, 2009 10 commits
-
-
Arnaldo Carvalho de Melo authored
We need to use map->unmap_ip() here too to match section relative symbol address to the absolute address needed to match objdump -dS addresses. Reported-by:
Mike Galbraith <efault@gmx.de> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
If the user doesn't pass a symbol name to annotate, it will annotate all the symbols that have hits, in order, just like 'perf report -s comm,dso,symbol'. This is a natural followup patch to the one that uses output_hists to find the symbols with hits. The common case is to annotate the first few entries at the top of a perf report, so lets type less characters. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We have this sym_priv_size mechanism for attaching private areas to struct symbol entries but annotate wasn't using it, adding private areas to struct symbol in addition to a ->priv pointer. Scrap all that and use the sym_priv_size mechanism. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We need this because we get section relative addresses when reading the symtabs, but when a tool like 'perf annotate' needs to match these address to what 'objdump -dS' produces we need the address + section back again. So in annotate now we look at the 'struct hist_entry' instances (that weren't really being used) so that we iterate only over the symbols that had some hit and get the map where that particular hit happened so that we can get the right address to match with annotate. Verified that at least: perf annotate mmap_read_counter # Uses the ~/bin/perf binary perf annotate --vmlinux /home/acme/git/build/perf/vmlinux intel_pmu_enable_all on a 'perf record perf top' session seems to work. Signed-off-by:
-
Arjan van de Ven authored
During the Kernel Summit demo of perf/ftrace/timechart, there was a feature request to have a process filter for timechart so that you can zoom into one or a few processes that you are really interested in. This patch adds basic support for this feature, the -p (--process) option now can select a PID or a process name to be shown. Multiple -p options are allowed, and the combined set will be included in the output. Signed-off-by:
Arjan van de Ven <arjan@linux.intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <20091020070939.7d0fb8a7@infradead.org> Signed-off-by:
-
Ingo Molnar authored
Merge reason: Queue up dependent patch. Signed-off-by: -
Arjan van de Ven authored
[from KS feedback] Currently, scheduler delays are shown in a mostly transparent, light yellow color. This color is rather hard to see on several screens, especially projectors. This patch changes the color of the scheduler delays to be a much more "hard" yellow that survived the kernel summit projector. Reported-by:
Linus Torvalds <torvalds@osdl.org> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <20091020064731.20ae126a@infradead.org> Signed-off-by:
-
Arjan van de Ven authored
The timechart wakeup arrows currently show no process information when the waker/wakee are processes that are not actually chosen to be shown on the timechart. This patch fixes this oversight, by looking through all processes (after giving preference to visible processes) as well as falling back to just showing the PID if no name for the process can be resolved. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Build dependencies were not properly mapped out. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
To cure a bunch of: In file included from util/include/linux/bitmap.h:1, from util/header.h:8, from builtin-trace.c:7: util/include/../../../../include/linux/bitmap.h:8:26: error: linux/string.h: No such file or directory make: *** [builtin-trace.o] Error 1 make: *** Waiting for unfinished jobs.... Signed-off-by:
-
- 19 Oct, 2009 9 commits
-
-
Ingo Molnar authored
Count branches first, cache-misses second. The reason is that on x86 branches are not counted by all counters on all CPUs. Before: Performance counter stats for 'ls': 0.756653 task-clock-msecs # 0.802 CPUs 0 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 250 page-faults # 0.330 M/sec 2375725 cycles # 3139.781 M/sec 1628129 instructions # 0.685 IPC 19643 cache-references # 25.960 M/sec 4608 cache-misses # 6.090 M/sec 342532 branches # 452.694 M/sec <not counted> branch-misses 0.000943356 seconds time elapsed After: Performance counter stats for 'ls': 1.056734 task-clock-msecs # 0.859 CPUs 0 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 259 page-faults # 0.245 M/sec 3345932 cycles # 3166.295 M/sec 3074090 instructions # 0.919 IPC 616928 branches # 583.806 M/sec 39279 branch-misses # 6.367 % 21312 cache-references # 20.168 M/sec 3661 cache-misses # 3.464 M/sec 0.001230551 seconds time elapsed (also prettify the printout of branch misses, in case it's getting scaled.) Cc: Tim Blechmann <tim@klingt.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by: -
Ingo Molnar authored
Clean up the array definition to be vertically aligned. No functional effects. Cc: Tim Blechmann <tim@klingt.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by: -
Tim Blechmann authored
Adds performance event information about branches and branch misses to the default output of perf stat. Signed-off-by:
Tim Blechmann <tim@klingt.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by:
-
Randy Dunlap authored
Check for libelf headers and glibc headers separately so that the error message correctly identifies which package installation is missing/needed. Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Cc: paulus@samba.org Cc: a.p.zijlstra@chello.nl Cc: efault@gmx.de Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <4ADBCCE8.3060300@oracle.com> Signed-off-by:
-
Tim Blechmann authored
Add delay_secs sanity check to handle_keypress, this fixes a division by zero crash. Signed-off-by:
-
Frederic Weisbecker authored
Use DECLARE_BITMAP instead of an open coded array for our bitmap of featured sections. This makes the array an unsigned long instead of a u64 but since we use a 256 bits bitmap, the array size shouldn't vary between different boxes. Signed-off-by:
-
Frederic Weisbecker authored
This provides a new set of bitmasked headers. A new field is added in the perf headers that implements a bitmap storing optional features present in the perf.data file. The layout can be pictured like this: (Usual perf headers)(Features bitmap)[Feature 0][Feature n][Feature 255] If the bit n is set, then the feature n is used in this file. They are all set in order. This brings a backward and forward compatibility. The trace_info section has moved into such optional features, this is the first and only one for now. This is backward compatible with the .32 file version although it doesn't support the previous separate trace.info file. And finally it doesn't support the current interim development version. Signed-off-by:
-
Frederic Weisbecker authored
Use the kernel bitmap library for internal perf tools uses. Signed-off-by:
-
Anton Blanchard authored
When we count both branches and branch-misses it is useful to print out the percentage of branch-misses: # perf stat -e branches -e branch-misses /bin/true Performance counter stats for '/bin/true': 401684 branches # 0.000 M/sec 23301 branch-misses # 5.801 % Signed-off-by:
-
- 17 Oct, 2009 1 commit
-
-
Julia Lawall authored
In each case, if the NULL test on thread is needed, then the dereference should be after the NULL test. A simplified version of the semantic match that detects this problem is as follows (http://coccinelle.lip6.fr/): // <smpl> @match exists@ expression x, E; identifier fld; @@ * x->fld ... when != \(x = E\|&x\) * x == NULL // </smpl> Signed-off-by:
Julia Lawall <julia@diku.dk> LKML-Reference: <Pine.LNX.4.64.0910170842500.9213@ask.diku.dk> Signed-off-by:
-
- 16 Oct, 2009 1 commit
-
-
Ingo Molnar authored
We released the first version of perf with 0.0.1 in v2.6.31, time to double our version number to 0.0.2 ;-) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by:
-
- 15 Oct, 2009 13 commits
-
-
Ingo Molnar authored
Now that we can filter based on fields via perf record, people will start using filter expressions and will expect them to be obvious. The primary way to see which fields are available is by looking at the trace output, such as: gcc-18676 [000] 343.011728: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.012727: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.032692: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.033690: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.034687: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.035686: irq_handler_entry: irq=0 handler=timer cc1-18677 [000] 343.036684: irq_handler_entry: irq=0 handler=timer While 'irq==0' filters work, the 'handler==<x>' filter expression does not work: $ perf record -R -f -a -e irq:irq_handler_entry --filter handler=timer sleep 1 Error: failed to set filter with 22 (Invalid argument) The problem is that while an 'irq' field exists and is recognized as a filter field - 'handler' does not exist - its name is 'name' in the output. To solve this, we need to synchronize the printout and the field names, wherever possible. In cases where the printout prints a non-field, we enclose that information in square brackets, such as: perf-1380 [013] 724.903505: softirq_exit: vec=9 [action=RCU] perf-1380 [013] 724.904482: softirq_exit: vec=1 [action=TIMER] This way users can use filter expressions more intuitively: all fields that show up as 'primary' (non-bracketed) information is filterable. This patch harmonizes the field names for all irq, bkl, power, sched and timer events. We might in fact think about dropping the print format bit of generic tracepoints altogether, and just print the fields that are being recorded. Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: -
Ingo Molnar authored
Américo Wang noticed that we have a locking imbalance in the error paths of ftrace_profile_set_filter(), causing potential leakage of event_mutex. Also clean up other error codepaths related to event_mutex while at it. Plus fix an initialized variable in the subsystem filter code. Reported-by:
Américo Wang <xiyou.wangcong@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <2375c9f90910150247u5ccb8e2at58c764e385ffa490@mail.gmail.com> Signed-off-by:
-
Li Zefan authored
Add a new option "--filter <filter_str>" to perf record, and it should be right after "-e trace_point": #./perf record -R -f -e irq:irq_handler_entry --filter irq==18 ^C # ./perf trace perf-4303 ... irq_handler_entry: irq=18 handler=eth0 init-0 ... irq_handler_entry: irq=18 handler=eth0 init-0 ... irq_handler_entry: irq=18 handler=eth0 init-0 ... irq_handler_entry: irq=18 handler=eth0 init-0 ... irq_handler_entry: irq=18 handler=eth0 See Documentation/trace/events.txt for the syntax of filter expressions. Signed-off-by:Li Zefan <lizf@cn.fujitsu.com> Acked-by:
Peter Zijlstra <peterz@infradead.org> Acked-by:
-
Li Zefan authored
- Add an ioctl to allocate a filter for a perf event. - Free the filter when the associated perf event is to be freed. - Do the filtering in perf_swevent_match(). Signed-off-by:
-
Li Zefan authored
"==" will always do a full match, and "~" will do a glob match. In the future, we may add "=~" for regex match. Signed-off-by:
-
Li Zefan authored
Change: for_each_pred for_each_subsystem To: for_each_subsystem for_each_pred This change also prepares for later patches. Signed-off-by:
-
Ingo Molnar authored
Merge reason: to add event filter support we need the following commits from the tracing tree: 3f6fe06d: tracing/filters: Unify the regex parsing helpers 1889d209: tracing/filters: Provide basic regex support 737f453f: tracing/filters: Cleanup useless headers Signed-off-by:
-
Steven Rostedt authored
The (char *) for all the static strings was a fix for the symptom and not the disease. The real issue was that the function prototypes needed to be declared "const char *". Signed-off-by:
Steven Rostedt <srostedt@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <20091014194400.635935008@goodmis.org> Signed-off-by:
-
Steven Rostedt authored
The opterators '-' and '+' are not handled in the trace print format. To do: '++' and '--'. Signed-off-by:
-
Steven Rostedt authored
Add the irqs disabled, preemption count, need resched, and other info that is shown in the latency format of ftrace. # perf trace -l perf-16457 2..s2. 53636.260344: kmem_cache_free: call_site=ffffffff811198f perf-16457 2..s2. 53636.264330: kmem_cache_free: call_site=ffffffff811198f perf-16457 2d.s4. 53636.300006: kmem_cache_free: call_site=ffffffff810d889 Signed-off-by: -
Steven Rostedt authored
The ftrace output events can have either arguments or no arguments. The parser needs to be able to handle both. Signed-off-by:
-
Steven Rostedt authored
The bprintk parsing was broken in more ways than one. The file parsing was incorrect, and the words used by the arguments are always 4 bytes aligned, even on 64-bit machines. Signed-off-by:
-
Steven Rostedt authored
Even though an event may fail to parse, we should not kill the entire report. The trace should still be able to show what it can. If an event fails to parse, a warning is printed, and the output continues. Signed-off-by:
-
