Add a new flag field while opening a tracepoint perf counter:
-e tracepoint_subsystem:tracepoint_name:flags
This is intended to be generic although for now it only supports the
r[e[c[o[r[d]]]]] flag:
./perf record -e workqueue:workqueue_insertion:record
./perf record -e workqueue:workqueue_insertion:r
will have the same effect: enabling the raw samples record for
the given tracepoint counter.
In the future, we may want to support further flags, separated
by commas.
Signed-off-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>
LKML-Reference: <1250152039-7284-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It is better than showing the map addr, this way at least we
know that we can't get the symtabs because the DSO was deleted
(system update) while an app still used such DSO.
Yeah, don't do that, but if you do, you'll figure it out
quicker this way.
[acme@doppio linux-2.6-tip]$ perf report | head -15
# Samples: 3796
#
# Overhead Command Shared Object Symbol
# ........ ....... ................................................................... ......
#
23.55% pidgin /lib64/libglib-2.0.so.0.2000.4.#prelink#.Pd98lu (deleted) [.] 0x00000000038844
21.55% pidgin /lib64/libpthread-2.10.1.so.#prelink#.AFwK8Q (deleted) [.] 0x0000000000a42d
10.85% pidgin [kernel] [.] vread_hpet
7.85% pidgin /lib64/libgobject-2.0.so.0.2000.4.#prelink#.o1vpU7 (deleted) [.] 0x00000000014de8
3.35% pidgin /lib64/libc-2.10.1.so (deleted) [.] 0x0000000007a875
3.19% pidgin /lib64/libdbus-1.so.3.4.0.#prelink#.6mwgZP (deleted) [.] 0x0000000001d254
3.06% pidgin /usr/lib64/libgtk-x11-2.0.so.0.1600.5.#prelink#.511hAl (deleted) [.] 0x000000002334e7
2.90% pidgin /usr/lib64/libgdk-x11-2.0.so.0.1600.5.#prelink#.5qlMo1 (deleted) [.] 0x00000000037b2d
1.84% pidgin [kernel] [k] do_sys_poll
1.45% pidgin /usr/lib64/libX11.so.6.2.0.#prelink#.iR59Rx (deleted) [.] 0x0000000004c751
[acme@doppio linux-2.6-tip]$
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Luis Claudio R. Gonçalves <lclaudio@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090811200436.GA3478@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In old binutils we can't access bfd_demangle(), use
cplus_demangle() just like oprofile.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Luis Claudio R. Gonçalves <lclaudio@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090811192211.GG18061@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Sometimes we get callchain branches that have a rate under the
limit given by the user.
Say you launched:
perf record -f -g -a ./hackbench 10
perf report -g fractal,10.0
And you got:
2.33% hackbench [kernel] [k] _spin_lock_irqsave
|
|--78.57%-- remove_wait_queue
| poll_freewait
| do_sys_poll
| sys_poll
| sysenter_dispatch
| 0xf7ffa430
| 0x1ffadea3c
|
|--7.14%-- __up_read
| up_read
| do_page_fault
| page_fault
| 0xf7ffa430
| 0xa0df710000000a
...
It is abnormal to get a 7.14% branch whereas we passed a 10%
filter.
The problem is that we round down the minimum threshold. This
happens mostly when we have very low number of events. If the
total amount of your branch is 4 and you have a subranch of 3
events, filtering to 90% will be computed like follows:
limit = 4 * 0.9;
The result is about 3.6, but the cast to integer will round
down to 3. It means that our filter is actually of 75%
We must then explicitly round up the minimum threshold.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: acme@redhat.com
Cc: peterz@infradead.org
Cc: efault@gmx.de
LKML-Reference: <20090809024235.GA10146@nowhere>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If we recorded with -g option to record the callchain, right now
we require a -g option to perf report as well - and people reported
this as unnecessary complication: the user already specified -g
once, no need to require it a second time.
So if the recording includes call-chains, display the callchain by
default from perf report.
( The user can override this default using "-g none" option from
perf report. )
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-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>
LKML-Reference: <1249690585-9145-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When the callchain tree comes to insert an empty backtrace, it
raises a spurious warning about the fact we are inserting an
empty. This is spurious because the radix tree assumes it did
something wrong to reach this state. But it didn't, we just met
an empty callchain that has to be ignored.
This happens occasionally with certain types of call-chain
recordings. If it happens it's a big nuisance as perf report
output starts with thousands of warning lines.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-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>
LKML-Reference: <1249690585-9145-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While toying with perf, I've noticed that perf record can
easily enter a busy loop when doing something as silly as:
$ perf record -A ls
Yeah, do_read here really wants to read a known size, not being
able to should die(), not busy-loop ;)
That was the cause for the bug.
Signed-off-by: Pierre Habouzit <pierre.habouzit@intersec.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Stop perf list from displaying tracepoints without an id file,
those are special tracepoints that are not interfaced to
perfcounters so listing them is erroneous and passing them as
events will produce no output.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Used with perf report --verbose:
[acme@doppio linux-2.6-tip]$ perf report -v | head -16
5.17% firefox /usr/lib64/xulrunner-1.9.1/libxul.so 0x00000000005d8eee f [.] imgContainer::DrawFrameTo(gfxIImageFrame*, gfxIImageFrame*, nsRect&)
2.56% firefox /lib64/libpthread-2.10.1.so 0x0000000000008e02 d [.] __pthread_mutex_lock_internal
1.94% firefox /usr/lib64/xulrunner-1.9.1/libxul.so 0x0000000000d0af8f f [.] SearchTable
1.75% firefox [kernel] 0xffffffffff60013b k [.] vread_hpet
1.63% firefox /lib64/libpthread-2.10.1.so 0x000000000000a404 d [.] __pthread_mutex_unlock
1.47% firefox /usr/lib64/xulrunner-1.9.1/libmozjs.so 0x00000000000482ea f [.] js_Interpret
1.42% firefox /usr/lib64/xulrunner-1.9.1/libmozjs.so 0x000000000003eda3 f [.] JS_CallTracer
1.24% firefox [kernel] 0xffffffff8102ca4a k [k] read_hpet
1.16% firefox [kernel] 0xffffffff810f3dd4 k [k] fget_light
1.11% firefox /usr/lib64/xulrunner-1.9.1/libmozjs.so 0x00000000000567ff f [.] js_TraceObject
0.98% firefox /usr/lib64/firefox-3.5.2/firefox 0x000000000000dd23 b [.] arena_ralloc
[acme@doppio linux-2.6-tip]$
The new field is just after the symbol address. To help in
figuring out symbol resolution bugs.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Brice Goglin reported:
> I can easily sort them by thread id, but I don't know how to match
> my 4 events with each group of 4 lines.
Also report the counter id and the time running/enabled
stats (in case the counter got time-shared).
Reported-by: Brice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Brice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Brice Goglin reported that only the first result from a
multi-counter perf record --stat run is accurate, the
rest looks bogus.
A silly mistake made us re-read the first attribute for
every recorded attribute.
Reported-by: Brice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Brice Goglin <Brice.Goglin@inria.fr>
Cc: paulus@samba.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The callchain fractal mode builds each new total hits in a new
branch of profiling by using the parent's hits of the current
branch plus the hits of the children.
This is wrong, the total hits of a branch should be made of the
sum of every children hits, we must ignore the parent hits in
this scope.
This patch also fixes another mistake with the hit counting.
Now the rates are correct.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: 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: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In some cases distros have binaries and debuginfo in weird places:
[root@doppio tuna]# ls -la /usr/lib64/{xulrunner-1.9.1/xulrunner-stub,firefox-3.5.2/firefox}
-rwxr-xr-x 1 root root 90024 2009-08-03 19:45 /usr/lib64/firefox-3.5.2/firefox
-rwxr-xr-x 1 root root 90024 2009-08-03 18:23 /usr/lib64/xulrunner-1.9.1/xulrunner-stub
[root@doppio tuna]# sha1sum /usr/lib64/{xulrunner-1.9.1/xulrunner-stub,firefox-3.5.2/firefox}
19a858077d263d5de22c9c5da250d3e4396ae739 /usr/lib64/xulrunner-1.9.1/xulrunner-stub
19a858077d263d5de22c9c5da250d3e4396ae739 /usr/lib64/firefox-3.5.2/firefox
[root@doppio tuna]# rpm -qf /usr/lib64/{xulrunner-1.9.1/xulrunner-stub,firefox-3.5.2/firefox}
xulrunner-1.9.1.2-1.fc11.x86_64
firefox-3.5.2-2.fc11.x86_64
[root@doppio tuna]# ls -la /usr/lib/debug/{usr/lib64/xulrunner-1.9.1/xulrunner-stub,usr/lib64/firefox-3.5.2/firefox}.debug
ls: cannot access /usr/lib/debug/usr/lib64/firefox-3.5.2/firefox.debug: No such file or directory
-rwxr-xr-x 1 root root 403608 2009-08-03 18:22 /usr/lib/debug/usr/lib64/xulrunner-1.9.1/xulrunner-stub.debug
Seemingly we don't have a .symtab when we actually can find it
if we use the .note.gnu.build-id ELF section put in place by
some distros. Use it and find the symbols we need.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since the C++ demangling isn't needed for everybody and
bfd/iberty aren't widely/easily available on all machines, make
it optional.
It also allows you to forcefully disable demangling by using
NO_DEMANGLE=1 and otherwise tries to detect libbfd/libiberty
combinations that result in a compiling demangler.
Reported-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
LKML-Reference: <20090801082048.GX12579@kernel.dk>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Check whether index is within bounds before testing the element.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Cc: a.p.zijlstra@chello.nl
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4A757BCF.40101@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch fixes a spelling error that has resulted from copy
and pasting. The location of the error was found using a
semantic patch but the semantic patch was not trying to find
these errors. After looking things over it seemed logical that
this change was needed. Please review it and then include the
patch if it is in fact the correct change.
Signed-off-by: Stoyan Gaydarov <sgayda2@uiuc.edu>
Signed-off-by: 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: <1248949529-20891-1-git-send-email-sgayda2@uiuc.edu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
vmlinux meets the criteria for symbol adjustment, which breaks vmlinux generated symbols.
Fix this by exempting vmlinux. This is a bit fragile in that someone could change the
kernel dso's name, but currently that name is also hardwired.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1248091298.18702.18.camel@marge.simson.net>
If "/sys/kernel/debug" is not a debugfs mount point, search for the debugfs
filesystem in /proc/mounts, but also allows the user to specify
'--debugfs-dir=blah' or set the environment variable: 'PERF_DEBUGFS_DIR'
Signed-off-by: Jason Baron <jbaron@redhat.com>
[ also made it probe "/debug" by default ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090721181629.GA3094@redhat.com>
Add support to 'perf list' and 'perf stat' for kernel tracepoints. The
implementation creates a 'for_each_subsystem' and 'for_each_event' for
easy iteration over the tracepoints.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <426129bf9fcc8ee63bb094cf736e7316a7dcd77a.1248190728.git.jbaron@redhat.com>
for some reason, this structure gets compiled as 36 bytes in some files
(the ones that alloacte it) but 40 bytes in others (the ones that use it).
The cause is an off_t type that gets a different size in different
compilation units for some yet-to-be-explained reason.
But the effect is disasterous; the size/offset members of the struct
are at different offsets, and result in mostly complete garbage.
The parser in perf is so robust that this all gets hidden, and after
skipping an certain amount of samples, it recovers.... so this bug
is not normally noticed.
.... except when you want every sample to be exact.
Fix this by just using an explicitly sized type.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4A655917.9080504@linux.intel.com>
The strlist__entry method allows accessing strlists like an
array, will be used in the 'perf report' to access the first
entry.
We now keep the nr_entries so that we can check if we have just
one entry, will be used in 'perf report' to improve the output
by showing just at the top when we have just, say, one DSO.
While at it use nr_entries to optimize strlist__is_empty by not
using the far more costly rb_first based implementation.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1247325517-12272-2-git-send-email-acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Auto-adjust column width of perf report output to the
longest occuring string length.
Example:
[acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13
12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr
8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc
8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len
8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp
6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch
5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type
[acme@doppio pahole]$
[acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10
21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc
20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp
16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch
[acme@doppio pahole]$
Also add these extra options to control the new behaviour:
-w, --field-width
Force each column width to the provided list, for large terminal
readability.
-t, --field-separator:
Use a special separator character and don't pad with spaces, replacing
all occurances of this separator in symbol names (and other output) with
a '.' character, that thus it's the only non valid separator.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20090711014728.GH3452@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The cache events contain '$' which will hit shell variable
expansion. To avoid confusion change this to 'cache', ie
L1-d$-loads becomes L1-dcache-loads.
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Jaswinder Singh Rajput <jaswinder@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20090706120131.GB4391@kryten>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The current callchain displays the overhead rates as absolute:
relative to the total overhead.
This patch provides relative overhead percentage, in which each
branch of the callchain tree is a independant instrumentated object.
This provides a 'fractal' view of the call-chain profile: each
sub-graph looks like a profile in itself - relative to its parent.
You can produce such output by using the "fractal" mode
that you can abbreviate via f, fr, fra, frac, etc...
./perf report -s sym -c fractal
Example:
8.46% [k] copy_user_generic_string
|
|--52.01%-- generic_file_aio_read
| do_sync_read
| vfs_read
| |
| |--97.20%-- sys_pread64
| | system_call_fastpath
| | pread64
| |
| --2.81%-- sys_read
| system_call_fastpath
| __read
|
|--39.85%-- generic_file_buffered_write
| __generic_file_aio_write_nolock
| generic_file_aio_write
| do_sync_write
| reiserfs_file_write
| vfs_write
| |
| |--97.05%-- sys_pwrite64
| | system_call_fastpath
| | __pwrite64
| |
| --2.95%-- sys_write
| system_call_fastpath
| __write_nocancel
[...]
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The cumul hits are the number of hits of every childs of a node
plus the hits of the current nodes, required for percentage
computing of a branch.
Theses numbers are calculated during the sorting of the branches of
the callchain tree using a depth first postfix traversal, so that
cumulative hits are propagated in the right order.
But if we plan to implement percentages relative to the parent and not
absolute percentages (relative to the whole overhead), we need to know
the cumulative hits of the parent before computing the children
because the relative minimum acceptable number of entries (ie: minimum
rate against the cumulative hits from the parent) is the basis to
filter the children against a given rate.
Then we need to handle the cumul hits on the fly to prepare the
implementation of relative overhead rates.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246772361-9960-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ingo Molnar wrote:
> i just bisected a 'perf report' bug that would cause us to not
> resolve all user-space symbols in a 'git gc' run to:
>
> f5812a7a33 is first bad commit
> commit f5812a7a33
> Author: Arnaldo Carvalho de Melo <acme@redhat.com>
> Date: Tue Jun 30 11:43:17 2009 -0300
>
> perf_counter tools: Adjust only prelinked symbol's addresses
Rename ->prelinked to ->adjust_symbols and making what was done
only for prelinked libraries also to ET_EXEC binaries, such as
/usr/bin/git:
[acme@doppio pahole]$ readelf -h /usr/bin/git | grep Type
Type: EXEC (Executable file)
[acme@doppio pahole]$
And after installing the 'git-debuginfo' package, I get correct results:
[acme@doppio linux-2.6-tip]$ perf report --sort comm,dso,symbol -d /usr/bin/git | head -20
#
# (1139614 samples)
#
# Overhead Command Shared Object Symbol
# ........ ................ ......................... ......
#
34.98% git /usr/bin/git [.] send_sideband
33.39% git /usr/bin/git [.] enter_repo
6.81% git /usr/bin/git [.] diff_opt_parse
4.95% git /usr/bin/git [.] is_repository_shallow
3.24% git /usr/bin/git [.] odb_mkstemp
1.39% git /usr/bin/git [.] output
1.34% git /usr/bin/git [.] xmmap
1.25% git /usr/bin/git [.] receive_pack_config
1.16% git /usr/bin/git [.] git_pathdup
0.90% git /usr/bin/git [.] read_object_with_reference
0.86% git /usr/bin/git [.] show_patch_diff
0.85% git /usr/bin/git 0x00000000095e2e
0.69% git /usr/bin/git [.] display
[acme@doppio linux-2.6-tip]$
I'll check what are the last cases where we can't resolve symbols, like
this 0x00000000095e2e later.
And I guess this will fix the problems Mike were seeing too:
[acme@doppio linux-2.6-tip]$ readelf -h ../build/perf/vmlinux | grep Type
Type: EXEC (Executable file)
[acme@doppio linux-2.6-tip]$
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Among perf annotate, perf report and perf top, we can find the
common colored printing of percents according to the following
rules:
High overhead = > 5%, colored in red
Mid overhead = > 0.5%, colored in green
Low overhead = < 0.5%, default color
Factorize these multiple checks in a single function named
percent_color_fprintf() and also provide a get_percent_color()
for sites which print percentages and other things at the same
time.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246558475-10624-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Callchains output may become a burden on a trace because even
rarely hit site are exposed. This can be too much information.
Let the user set a threshold as a minimum percent of hits using
the new pattern for the -c option:
-c mode,min_percent
Example:
$ perf report -s sym -c flat,4
8.25% [k] copy_user_generic_string
4.19%
copy_user_generic_string
generic_file_aio_read
do_sync_read
vfs_read
sys_pread64
system_call_fastpath
pread64
5.39% [k] search_by_key
4.63% 0x00000000009e0a
2.36% [k] memcpy_c
[...]
$ perf report -s sym -c graph,2
8.25% [k] copy_user_generic_string
|
|--4.31%-- generic_file_aio_read
| do_sync_read
| vfs_read
| |
| --4.19%-- sys_pread64
| system_call_fastpath
| pread64
|
--3.24%-- generic_file_buffered_write
__generic_file_aio_write_nolock
generic_file_aio_write
do_sync_write
reiserfs_file_write
vfs_write
|
--3.14%-- sys_pwrite64
system_call_fastpath
__pwrite64
5.39% [k] search_by_key
|
--2.23%-- reiserfs_update_sd_size
4.63% 0x00000000009e0a
2.36% [k] memcpy_c
[...]
You can also omit it and it will default to 0.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246558475-10624-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently, the printing of callchains is done in a single
vertical level, this is the "flat" mode:
8.25% [k] copy_user_generic_string
4.19%
copy_user_generic_string
generic_file_aio_read
do_sync_read
vfs_read
sys_pread64
system_call_fastpath
pread64
This patch introduces a new "graph" mode which provides a
hierarchical output of factorized paths recursively sorted:
8.25% [k] copy_user_generic_string
|
|--4.31%-- generic_file_aio_read
| do_sync_read
| vfs_read
| |
| |--4.19%-- sys_pread64
| | system_call_fastpath
| | pread64
| |
| --0.12%-- sys_read
| system_call_fastpath
| __read
|
|--3.24%-- generic_file_buffered_write
| __generic_file_aio_write_nolock
| generic_file_aio_write
| do_sync_write
| reiserfs_file_write
| vfs_write
| |
| |--3.14%-- sys_pwrite64
| | system_call_fastpath
| | __pwrite64
| |
| --0.10%-- sys_write
[...]
The command line has then changed.
By providing the -c option, the callchain will output in the
flat mode by default.
But you can override it:
perf report -c graph
or
perf report -c flat
You can also pass the abreviated mode:
perf report -c g
or
perf report -c gra
will both make use of the graph mode.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is no predefined macro to create an option that can have
a custom value or a default one if none is given.
This patch provides a new helper OPT_CALLBACK_DEFAULT() which
defines such kind of option.
For example, considering an option -c, we want to get the
default value in the following cases:
perf command -c -d
perf command -d -c
And the foo value when it's given:
perf command -c foo -d
perf command -d -c foo
That's also why PARSE_OPT_LASTARG_DEFAULT is extended here to
support default values whatever the position of the option, not
only in the end.
Should it now be renamed to PARSE_OPT_ARG_DEFAULT ?
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: git@vger.kernel.org
LKML-Reference: <1246550301-8954-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Iterating through children of a node in the callchain tree
shows something that may be quite confusing at a first glance.
The head is the children field of the parent and the list nodes
are in the brothers field of the children.
This is because the childs are linked to the parent as a list
of "brothers" using the "children" list of the parent as a
head:
---------------
| Parent (head) |-------------------------------------
--------------- |
| |
children |
| |
----------- ----------- |
| 1st child |---brother---| 2nd child |---brother-----
----------- -----------
This makes the following strange pattern often occuring:
list_for_each_entry(child, &parent->children, brothers) {
// do something with children
}
Abstract it to chain_for_each_child() to factorize and simplify
this pattern.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246550301-8954-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf_counter tools: Make symbol loading consistently return number of loaded symbols.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246514758.13293.42.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The copy we were using came from another copy I did for the dwarves
(pahole) package, that came from the kernel years ago.
The only function that is used by the perf tools and that isn't in the
kernel is list_del_range, that I'm leaving in the perf tools only for
now.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20090701174608.GA5823@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The tools/perf/util/rbtree.c copy already drifted by three
csets:
4b324126e04c6011781116c047add3
So remove the copy and use the lib/rbtree.c directly, sharing
the source code while still generating a separate object file,
since tools/perf uses a far more agressive -O6 switch.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090701152837.GG15682@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Enable -Wextra. This found a few real bugs plus a number
of signed/unsigned type mismatches/uncleanlinesses. It
also required a few annotations
All things considered it was still worth it so lets try with
this enabled for now.
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: Ingo Molnar <mingo@elte.hu>
This reworks the parser for event descriptors to make it more
consistent in what it accepts. It is now structured as a
recursive descent parser for the following grammar:
events ::= event ( ("," | space) space* event )*
event ::= ( raw_event | numeric_event | symbolic_event |
generic_hw_event ) [ event_modifier ]
raw_event ::= "r" hex_number
numeric_event ::= number ":" number
number ::= decimal_number | "0x" hex_number | "0" octal_number
symbolic_event ::= string_from_event_symbols_array
generic_hw_event::= cache_type ( "-" ( cache_op | cache_result ) )*
event_modifier ::= ":" ( "u" | "k" | "h" )+
with the extra restriction that you can have at most one
cache_op and at most one cache_result.
We pass the current string pointer by reference (i.e. as a
const char **) to the various parsing functions so that they
can advance the pointer to indicate how much they consumed.
They return 0 if they didn't recognize the thing at the pointer
or 1 if they did (and advance the pointer past it).
This also fixes parse_aliases to take the longest matching
alias from the table, not the first one. Otherwise "l1-data"
would match the "l1-d" alias and the "ata" would not be
consumed.
This allows event modifiers indicating what processor modes to
count in to be applied to any event, not just numeric events,
and adds a ":h" modifier to indicate counting in hypervisor
mode. Specifying ":u" now sets both exclude_kernel and
exclude_hv, and so on. Multiple modes can be specified, e.g.
":uk" will count in user or hypervisor mode (i.e. only
exclude_kernel will be set).
Signed-off-by: Paul Mackerras <paulus@samba.org>
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: <19018.53826.843815.189847@cargo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The symbol resolving has of course revealed some bugs in the
callchain tree handling. This patch fixes some of them,
including:
- inherit the children from the parents while splitting a node
- fix list range moving
- fix indexes setting in callchains
- create a child on the current node if the path doesn't match in
the existent children (was only done on the root)
- compare using symbols when possible so that we can match a function
using any ip inside by referring to its start address.
The practical effects are:
- remove double callchains
- fix upside down or any random order of callchains
- fix wrong paths
- fix bad hits and percentage accounts
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246419315-9968-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix a confusion while giving the size of a callchain list
during its allocation. We are using the wrong structure size.
Signed-off-by: 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: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1246419315-9968-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
So that we can filter by dso. Symbols in other dsos won't be
accounted for.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1246399282-20934-2-git-send-email-acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
I.e. we can't handle these two kinds of files in the same way:
1) prelinked system library:
[acme@doppio pahole]$ readelf -s /usr/lib64/libdw-0.141.so | egrep 'FUNC.+GLOBAL.+dwfl_report_elf'
278: 00000030450105a0 261 FUNC GLOBAL DEFAULT 12 dwfl_report_elf@@ELFUTILS_0.122
2) not prelinked library with debug information from a -debuginfo package:
[acme@doppio pahole]$ readelf -s /usr/lib/debug/usr/lib64/libdw-0.141.so.debug | egrep 'FUNC.+GLOBAL.+dwfl_report_elf'
629: 00000000000105a0 261 FUNC GLOBAL DEFAULT 12 dwfl_report_elf
[acme@doppio pahole]$
Now the numbers I got for a pahole perf run are in line with
the numbers I get from oprofile.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090630144317.GB12663@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Vince Weaver reported that there's a handful of #ifdef __MINGW32__
sections in the code.
Remove them as they are in essence dead code - as unlike upstream
Git, the perf tool is unlikely to be ported to Windows.
Reported-by: Vince Weaver <vince@deater.net>
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 <mingo@elte.hu>
We plan to display the callchains depending on some user-configurable
parameters.
To gather the callchains stats from the recorded stream in a fast way,
this patch introduces an ad hoc radix tree adapted for callchains and also
a rbtree to sort these callchains once we have gathered every events
from the stream.
Signed-off-by: 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>
LKML-Reference: <1246026481-8314-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add 'l1d' and 'l1i' aliases again as shortcuts - just dont make them
the primary display alias.
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1245945462.9157.11.camel@hpdv5.satnam>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Frederic Weisbecker