Adrian Hunter [Thu, 7 Jan 2016 09:13:59 +0000 (10:13 +0100)]
perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
'perf record' uses perf_evsel__open() to open events and passes the
evsel->cpus and evsel->threads. Many tests and some tools instead use
perf_evlist__open() which passes instead evlist->cpus and
evlist->threads.
Make perf_evlist__open() follow the 'perf record' behaviour so that a
consistent approach is taken.
Namhyung Kim [Thu, 7 Jan 2016 11:41:53 +0000 (20:41 +0900)]
perf report: Show random usage tip on the help line
Currently perf report only shows a help message "For a higher level
overview, try: perf report --sort comm,dso" unconditionally (even if
the sort keys were used). Add more help tips and show randomly.
Load tips from ${prefix}/share/doc/perf-tip/tips.txt file.
Jiri Olsa [Thu, 7 Jan 2016 09:14:04 +0000 (10:14 +0100)]
perf tools: Do not show trace command if it's not compiled in
The trace command still appears in help message when you run simple
'perf' command.
It's because the generate-cmdlist.sh does not care about the
HAVE_LIBAUDIT_SUPPORT dependency of trace command and puts it into
generated common_cmds array.
Wrapping trace command under HAVE_LIBAUDIT_SUPPORT dependency, which
will exclude it from common_cmds array if HAVE_LIBAUDIT_SUPPORT is not
set.
Namhyung Kim [Sun, 29 Nov 2015 14:24:17 +0000 (23:24 +0900)]
perf report: Change default to use event group view
The event group view feature is to see related events together. To use
the group view, events should be recorded as a group with a dedicated
syntax of surrounding events by braces (-e '{ evt1, evt2, ... }').
Also 'perf report' also requires the --group option to enable it.
However it's almost always beneficial to use the group view to see the
group events as it's more expressive. And I think it's more natural to
see events together if they are recorded as a group.
Thus this patch changes the default value to enable it. If users don't
want to see like it and keep the original behavior, they can set the
report.group config variable to false and/or use --no-group option in
the 'perf report' command line.
Namhyung Kim [Tue, 5 Jan 2016 03:06:00 +0000 (12:06 +0900)]
perf top: Decay periods in callchains
It missed to decay periods in callchains when decaying hist entries.
This resulted in more than 100 percent overhead in callchains in the
fractal style output.
The commit that introduced it should've moved it to the same place, plus
the 'tools/' prefix, but instead moved it to a bogus tools/lib/util/
directory, being the only file there.
Move it to tools/lib/find_bit.c, picking the name for the file where
these routines live since:
8f6f19dd5143 ("lib: move find_last_bit to lib/find_next_bit.c")
Next step is to make tools/lib/find_bit.c to differ from lib/find_bit.c
just in removing what is not used by tools/.
perf tests: No need to set attr.sample_freq for tracking !PERF_RECORD_SAMPLE
We were asking for a 4kHz sample_freq, making the test fail needlessly
when the system reduced /proc/sys/kernel/perf_event_max_sample_rate
below that.
Before:
# perf test -vv dummy
23: Test using a dummy software event to keep tracking :
--- start ---
test child forked, pid 32421
------------------------------------------------------------
perf_event_attr:
type 1
size 112
config 0x9
{ sample_period, sample_freq } 4000
sample_type IP|TID|ID|PERIOD
<SNIP>
sys_perf_event_open failed, error -22
Unable to open dummy and cycles event
test child finished with -2
---- end ----
Test using a dummy software event to keep tracking: Skip
#
[root@zoo ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
1000
After:
[root@zoo ~]# perf test dummy
23: Test using a dummy software event to keep tracking : Ok
This patch fixes a bug in __perf_pmu__new_alias() whereby the
alias->snapshot field was not initialized to false. This led to random
alias->snapshot value for an alias and was breaking some measurements
such as:
$ perf stat -a -e uncore_imc/data_reads/ -I 1000 sleep 100
Because the event ended up being treated as snapshot mode, when it is
not.
Jiri Olsa [Tue, 5 Jan 2016 21:09:05 +0000 (22:09 +0100)]
perf stat record: Keep sample_type 0 for pipe session
For pipe sessions we need to keep sample_type zero, because script's
perf_evsel__check_attr is triggered by sample_type != 0, and the check
would fail on stat session.
I was tempted to keep it zero unconditionally, but the pipe session is
sufficient. In perf.data session we are guarded by HEADER_STAT feature.
Namhyung Kim [Tue, 5 Jan 2016 10:58:35 +0000 (19:58 +0900)]
perf tools: Add all matching dynamic sort keys for field name
When a perf.data file has multiple events, it's likely to be similar
(tracepoint) events. In that case, they might have same field name so
add all of them to sort keys instead of bailing out.
Jiri Olsa [Wed, 23 Dec 2015 17:58:31 +0000 (18:58 +0100)]
tools build feature: Move dwarf post unwind choice output into perf
We decide what dwarf unwind to choose way after the Makefile.feature
makefile is included. The $(dwarf-post-unwind) is not even set at that
time. For the same reason it was never included in FEATURE-DUMP file.
Moving it into perf VF=1 verbose display.
$ make VF=1
BUILD: Doing 'make -j4' parallel build
Auto-detecting system features:
... dwarf: [ on ]
...
... LIBUNWIND_DIR:
... LIBDW_DIR:
... DWARF post unwind library: libunwind
...
Namhyung Kim [Tue, 22 Dec 2015 17:07:10 +0000 (02:07 +0900)]
perf tools: Make 'trace' or 'trace_fields' sort key default for tracepoint events
When an evlist contains tracepoint events only, use 'trace' sort key as
default. If --raw-trace option was given, use 'trace_fields' instead.
This will make users more convenient to see trace result.
Namhyung Kim [Tue, 22 Dec 2015 17:07:09 +0000 (02:07 +0900)]
perf tools: Add 'trace_fields' dynamic sort key
The 'trace_fields' sort key is similar as 'trace' sort key, but it shows
each fields separately. Each event will get different columns as their
fields.
Namhyung Kim [Tue, 22 Dec 2015 17:07:08 +0000 (02:07 +0900)]
perf tools: Skip dynamic fields not defined for current event
When there are multiple events, each dynamic sort key is defined just
for one event. In this case other events will always show "N/A" for
those fields. But they are meaningless and consume precious screen
width.
Let's skip those undefined dynamic fields.
$ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1
Namhyung Kim [Tue, 22 Dec 2015 17:07:06 +0000 (02:07 +0900)]
perf tools: Support shortcuts for events in dynamic sort keys
The dynamic sort key requires event name but specifying full event name
is rather inconvenient. This patch adds more ways to identify the event
in a more compact way.
1. If session has just one event, event name can be omitted.
2. Events can be accessed by index preceded by a percent sign.
3. A part of the name can be used, if it's not ambiguous. The partial
name should not contain ':' in it.
4. Full system + event name is still used, it should contain ':'.
Namhyung Kim [Tue, 22 Dec 2015 17:07:05 +0000 (02:07 +0900)]
perf report/top: Add --raw-trace option
The --raw-trace option allows disabling pretty printing by the event's
print_fmt or plugin. Besides that, each dynamic sort key now can
receive a 'raw' suffix separated by '/' to ask for the raw trace of a
specific field.
Namhyung Kim [Tue, 22 Dec 2015 17:07:04 +0000 (02:07 +0900)]
perf tools: Add 'trace' sort key
The 'trace' sort key is to show tracepoint event output using either
print fmt or plugin. For example sched_switch event (using plugin) will
show output like below:
# perf record -e sched:sched_switch -a usleep 10
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.197 MB perf.data (69 samples) ]
#
$ perf report -s trace --stdio
...
# Overhead Trace output
# ........ ...................................................
#
9.48% swapper/0:0 [120] R ==> transmission-gt:17773 [120]
9.48% transmission-gt:17773 [120] S ==> swapper/0:0 [120]
9.04% swapper/2:0 [120] R ==> transmission-gt:17773 [120]
8.92% transmission-gt:17773 [120] S ==> swapper/2:0 [120]
5.25% swapper/0:0 [120] R ==> kworker/0:1H:109 [100]
5.21% kworker/0:1H:109 [100] S ==> swapper/0:0 [120]
1.78% swapper/3:0 [120] R ==> transmission-gt:17773 [120]
1.78% transmission-gt:17773 [120] S ==> swapper/3:0 [120]
1.53% Xephyr:6524 [120] S ==> swapper/0:0 [120]
1.53% swapper/0:0 [120] R ==> Xephyr:6524 [120]
1.17% swapper/2:0 [120] R ==> irq/33-iwlwifi:233 [49]
1.13% irq/33-iwlwifi:233 [49] S ==> swapper/2:0 [120]
Note that the 'trace' sort key works only for tracepoint events. If
it's used to other type of events, just "N/A" will be printed.
Namhyung Kim [Tue, 22 Dec 2015 17:07:03 +0000 (02:07 +0900)]
perf tools: Try to show pretty printed output for dynamic sort keys
Each tracepoint event has format string for print to improve
readability. Try to parse the output and match the field name. If it
finds one, use that for the result. If not, fallbacks to the original
output.
For example, sort on kmem:kmalloc.gfp_flags looks like below:
(Note: libtraceevent plugins are not installed on my system. They might
affect the output below)
Namhyung Kim [Tue, 22 Dec 2015 17:07:02 +0000 (02:07 +0900)]
perf tools: Add dynamic sort key for tracepoint events
The existing sort keys are less useful for tracepoint events in that
they are always sampled at the same place, the function where the
tracepoint is located.
For example, a 'perf report' on sched:sched_switch event looks like the
following:
In fact, tracepoints have meaningful information in their fields but
there's no way to use in 'perf report' currently. The dynamic sort keys
are introduced in this patc to overcome this limitation.
The sched:sched_switch events have following fields:
With dynamic sort keys, you can use <event.field> as a sort key. Those
dynamic keys are checked and created on demand. For instance, below is
to sort by next_pid field output on the same data file:
Namhyung Kim [Tue, 22 Dec 2015 17:07:01 +0000 (02:07 +0900)]
perf tools: Pass evlist to setup_sorting()
This is a preparation to support dynamic sort keys for tracepoint
events. Dynamic sort keys can be created for specific fields in trace
events so it needs the event information.
Namhyung Kim [Tue, 22 Dec 2015 17:07:01 +0000 (02:07 +0900)]
perf top: Create the evlist sooner
This is a preparation to support dynamic sort keys for tracepoint
events. Dynamic sort keys can be created for specific fields in trace
events so it needs the event information, so we need to pass the evlist
to the sort routines, create it sooner so that the next patch can do
that.
Namhyung Kim [Wed, 23 Dec 2015 13:08:41 +0000 (22:08 +0900)]
tools lib traceevent: Factor out and export print_event_field[s]()
The print_event_field() and print_event_fields() functions print basic
information of a given field or event without the print format. They'll
be used by dynamic sort keys later.
Committer note:
Rename it to pevent_print_field[s]() to get proper namespacing, as
discussed with Steven Rostedt.
Namhyung Kim [Tue, 22 Dec 2015 17:06:58 +0000 (02:06 +0900)]
perf hist: Pass struct sample to __hists__add_entry()
This is a preparation to add more info into the hist_entry. Also it
already passes too many argument, so passing sample directly will reduce
the overhead of the function call.
Vince Weaver [Wed, 9 Dec 2015 16:34:45 +0000 (11:34 -0500)]
perf/x86/amd: Remove l1-dcache-stores event for AMD
This is a long standing bug with the l1-dcache-stores generic event on
AMD machines. My perf_event testsuite has been complaining about this
for years and I'm finally getting around to trying to get it fixed.
The data_cache_refills:system event does not make sense for l1-dcache-stores.
Maybe this was a typo and it was meant to be for l1-dcache-store-misses?
In any case, the values returned are nowhere near correct for l1-dcache-stores
and in fact the umask values for the event have completely changed with
fam15h so it makes even less sense than ever. So just remove it.
Harish Chegondi [Mon, 7 Dec 2015 22:32:32 +0000 (14:32 -0800)]
perf/x86/intel/uncore: Add Knights Landing uncore PMU support
Knights Landing uncore performance monitoring (perfmon) is derived from
Haswell-EP uncore perfmon with several differences. One notable difference
is in PCI device IDs. Knights Landing uses common PCI device ID for
multiple instances of an uncore PMU device type. In Haswell-EP, each
instance of a PMU device type has a unique device ID.
Knights Landing uncore components that have performance monitoring units
are UBOX, CHA, EDC, MC, M2PCIe, IRP and PCU. Perfmon registers in EDC, MC,
IRP, and M2PCIe reside in the PCIe configuration space. Perfmon registers
in UBOX, CHA and PCU are accessed via the MSR interface.
For more details, please refer to the public document:
Harish Chegondi [Mon, 7 Dec 2015 22:32:31 +0000 (14:32 -0800)]
perf/x86/intel/uncore: Remove hard coding of PMON box control MSR offset
Call uncore_pci_box_ctl() function to get the PMON box control MSR offset
instead of hard coding the offset. This would allow us to use this
snbep_uncore_pci_init_box() function for other PCI PMON devices whose box
control MSR offset is different from SNBEP_PCI_PMON_BOX_CTL.
Harish Chegondi [Mon, 7 Dec 2015 22:28:18 +0000 (14:28 -0800)]
perf/x86/intel: Add perf core PMU support for Intel Knights Landing
Knights Landing core is based on Silvermont core with several differences.
Like Silvermont, Knights Landing has 8 pairs of LBR MSRs. However, the
LBR MSRs addresses match those of the Xeon cores' first 8 pairs of LBR MSRs
Unlike Silvermont, Knights Landing supports hyperthreading. Knights Landing
offcore response events config register mask is different from that of the
Silvermont.
This patch was developed based on a patch from Andi Kleen.
For more details, please refer to the public document:
Kan Liang [Thu, 3 Dec 2015 21:00:11 +0000 (16:00 -0500)]
perf/x86/intel/uncore: Add Broadwell-EP uncore support
The uncore subsystem for Broadwell-EP is similar to Haswell-EP.
There are some differences in pci device IDs, box number and
constraints. This patch extends the Broadwell-DE codes to support
Broadwell-EP.
This patch updates the PEBS support for Intel Atom to provide
an alias for the cycles:pp event used by perf record/top by default
nowadays.
On Atom, only INST_RETIRED:ANY supports PEBS, so we use this event
instead with a large cmask to count cycles. Given that Core2 has
the same issue, we use the intel_pebs_aliases_core2() function for Atom
as well.
This patches fixes the LBR kernel crashes on Intel Atom.
The kernel was assuming that if the CPU supports 64-bit format
LBR, then it has an LBR_SELECT MSR. Atom uses 64-bit LBR format
but does not have LBR_SELECT. That was causing NULL pointer
dereferences in a couple of places.
perf/x86: Fix filter_events() bug with event mappings
This patch fixes a bug in the filter_events() function.
The patch fixes the bug whereby if some mappings did not
exist, e.g., STALLED_CYCLES_FRONTEND, then any event after it
in the attrs array would disappear from the published list of
events in /sys/devices/cpu/events. This could be verified
easily on any system post SNB (which do not publish
STALLED_CYCLES_FRONTEND):
$ ./perf stat -e cycles,ref-cycles true
Performance counter stats for 'true':
1,217,348 cycles
<not supported> ref-cycles
The problem is that in filter_events() there is an assumption
that the argument (attrs) is organized in increasing continuous
event indexes related to the event_map(). But if we remove the
non-supported events by shifing the position in the array, then
the lookup x86_pmu.event_map() needs to compensate for it, otherwise
we are looking up the wrong index. This patch corrects this problem
by compensating for the deleted events and with that ref-cycles
reappears (here shown on Haswell):
$ perf stat -e ref-cycles,cycles true
Performance counter stats for 'true':
4,525,910 ref-cycles
1,064,920 cycles
0.002943888 seconds time elapsed
Andi Kleen [Fri, 4 Dec 2015 11:50:52 +0000 (03:50 -0800)]
perf/x86: Use INST_RETIRED.PREC_DIST for cycles: ppp
Add a new 'three-p' precise level, that uses INST_RETIRED.PREC_DIST as
base. The basic mechanism of abusing the inverse cmask to get all
cycles works the same as before.
PREC_DIST is available on Sandy Bridge or later. It had some problems
on Sandy Bridge, so we only use it on IvyBridge and later. I tested it
on Broadwell and Skylake.
PREC_DIST has special support for avoiding shadow effects, which can
give better results compare to UOPS_RETIRED. The drawback is that
PREC_DIST can only schedule on counter 1, but that is ok for cycle
sampling, as there is normally no need to do multiple cycle sampling
runs in parallel. It is still possible to run perf top in parallel, as
that doesn't use precise mode. Also of course the multiplexing can
still allow parallel operation.
Andi Kleen [Fri, 4 Dec 2015 11:50:32 +0000 (03:50 -0800)]
perf/x86: Use INST_RETIRED.TOTAL_CYCLES_PS for cycles:pp for Skylake
I added UOPS_RETIRED.ALL by mistake to the Skylake PEBS event list for
cycles:pp. But the event is not documented for Skylake, and has some
issues.
The recommended replacement for cycles:pp is to use
INST_RETIRED.ANY+pebs as a base, similar to what CPUs before Sandy
Bridge did. This new event is called INST_RETIRED.TOTAL_CYCLES_PS. The
event is not really new, but has been already used by perf before
Sandy Bridge for the original cycles:p
Note the SDM doesn't document that event either, but it's being
documented in the latest version of the event list on:
https://download.01.org/perfmon/SKL
This patch does:
- Remove UOPS_RETIRED.ALL from the Skylake PEBS event list
- Add INST_RETIRED.ANY to the Skylake PEBS event list, and an table entry to
allow cmask=16,inv=1 for cycles:pp
- We don't need an extra entry for the base INST_RETIRED event,
because it is already covered by the catch-all PEBS table entry.
- Switch Skylake to use the Core2 PEBS alias (which is
INST_RETIRED.TOTAL_CYCLES_PS)
Andi Kleen [Thu, 3 Dec 2015 21:22:20 +0000 (13:22 -0800)]
perf/x86: Allow zero PEBS status with only single active event
Normally we drop PEBS events with a zero status field. But when
there is only a single PEBS event active we can assume the
PEBS record is for that event. The PEBS buffer is always flushed
when PEBS events are disabled, so there is no risk of mishandling
state PEBS records this way.
Peter Zijlstra [Thu, 3 Dec 2015 17:35:21 +0000 (18:35 +0100)]
perf/core: Collapse more IPI loops
This patch collapses the two 'hard' cases, which are
perf_event_{dis,en}able().
I cannot seem to convince myself the current code is correct.
So starting with perf_event_disable(); we don't strictly need to test
for event->state == ACTIVE, ctx->is_active is enough. If the event is
not scheduled while the ctx is, __perf_event_disable() still does the
right thing. Its a little less efficient to IPI in that case,
over-all simpler.
For perf_event_enable(); the same goes, but I think that's actually
broken in its current form. The current condition is: ctx->is_active
&& event->state == OFF, that means it doesn't do anything when
!ctx->active && event->state == OFF. This is wrong, it should still
mark the event INACTIVE in that case, otherwise we'll still not try
and schedule the event once the context becomes active again.
This patch implements the two function using the new
event_function_call() and does away with the tricky event->state
tests.
Peter Zijlstra [Tue, 15 Dec 2015 12:49:05 +0000 (13:49 +0100)]
perf: Fix race in swevent hash
There's a race on CPU unplug where we free the swevent hash array
while it can still have events on. This will result in a
use-after-free which is BAD.
Simply do not free the hash array on unplug. This leaves the thing
around and no use-after-free takes place.
When the last swevent dies, we do a for_each_possible_cpu() iteration
anyway to clean these up, at which time we'll free it, so no leakage
will occur.
Which is a WARN_ON_ONCE() indicating that cpuctx->task_ctx is not
what we expected it to be.
This is because context switches can swap the task_struct::perf_event_ctxp[]
pointer around. Therefore you have to either disable preemption when looking
at current, or hold ctx->lock.
Fix perf_event_enable_on_exec(), it loads current->perf_event_ctxp[]
before disabling interrupts, therefore a preemption in the right place
can swap contexts around and we're using the wrong one.
Ingo Molnar [Fri, 18 Dec 2015 08:46:17 +0000 (09:46 +0100)]
Merge tag 'perf-core-for-mingo-3' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull new perf tool feature from Arnaldo Carvalho de Melo:
" User visible changes:
- Generate perf.data files from 'perf stat', to tap into the scripting
capabilities perf has instead of defining a 'perf stat' specific scripting
support to calculate event ratios, etc. Simple example:
This patchset abandons the idea of new formula language and rather adds support
to:
- store stat data into perf.data file
- add python support to process stat events
Basically it allows to store stat data into perf.data and post process it with
python scripts in a similar way we do for sampling data.
The stat data are stored in new stat, stat-round, stat-config user events.
stat - stored for each read syscall of the counter
stat round - stored for each interval or end of the command invocation
stat config - stores all the config information needed to process data
so report tool could restore the same output as record
The python script can now define 'stat__<eventname>_<modifier>' functions
to get stat events data and 'stat__interval' to get stat-round data.
See CPI script example in scripts/python/stat-cpi.py."
Also a few other changes:
User visible changes:
- Make command line options always available, even when they
depend on some feature being enabled, warning the user about
use of such options (Wang Nan)
- Support --vmlinux in perf record, useful, so far, for eBPF,
where we will set up events that will be used in the record
session (He Kuang)
- Automatically disable collecting branch flags and cycles with
--call-graph lbr. This allows avoiding a bunch of extra MSR
reads in the PMI on Skylake. (Andi Kleen)
Infrastructure changes:
- Dump the stack when a 'perf test -v ' entry segfaults, so far we
would have to run it under gdb with 'set follow-fork-mode child'
set to get a proper backtrace (Arnaldo Carvalho de Melo)
- Initialize the refcnt in 'struct thread' to 1 and fixup its
users accordingly, so that we try to have the same refcount
model accross the perf codebase (Arnaldo Carvalho de Melo)
- More prep work for moving the subcmd infrastructure out of
tools/perf/ and into tools/lib/subcmd/ to be used by other
tools/ living utilities (Josh Poimboeuf)
- Fix 'perf test' hist testcases when kptr_restrict is on (Namhyung Kim)
Ingo Molnar [Fri, 18 Dec 2015 08:40:13 +0000 (09:40 +0100)]
Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/urgent tooling fix from Arnaldo Carvalho de Melo:
User visible changes:
- Fix 'perf list' segfault due to lack of support for PERF_CONF_SW_BPF_OUTPUT
in an array used just for printing available events, robustify the code
involved (Arnaldo Carvalho de Melo)
Ingo Molnar [Fri, 18 Dec 2015 08:37:51 +0000 (09:37 +0100)]
Merge tag 'perf-core-for-mingo-2.1' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements from Arnaldo Carvalho de Melo:
User visible changes:
- Add record.build-id config option to 'perf record', to allow configuring
in the ~/.perfconfig file if and how build-ids should be processed, allowing
a permanent setting for options such as -B and -N: (Namhyung Kim)
$ perf record -h -B -N
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-B, --no-buildid do not collect buildids in perf.data
-N, --no-buildid-cache do not update the buildid cache
$
Infrastructure changes:
- Move code for options parsing and subcommand handling from tools/perf/
to tools/lib/subcmd/, so that it can be used by other tools/ living
utilities (Josh Poimboeuf)
Jiri Olsa [Thu, 5 Nov 2015 14:40:59 +0000 (15:40 +0100)]
perf stat report: Process stat and stat round events
Adding processing of stat and stat round events.
The stat data com in stat events, using generic function
process_stat_round_event to store data under perf_evsel object.
The stat-round events comes each interval or as last event in non
interval mode. The function process_stat_round_event process stored data
for each perf_evsel object and print it out.
Jiri Olsa [Thu, 5 Nov 2015 14:40:50 +0000 (15:40 +0100)]
perf stat record: Add pipe support for record command
Allowing storing stat record data into pipe, so report tools
(report/script) could read data directly from record.
Committer note:
Before this patch:
$ perf stat record -o - usleep 1 | perf report -i -
incompatible file format (rerun with -v to learn more)
$ perf stat record -o - usleep 1 | perf script -i -
incompatible file format (rerun with -v to learn more)
$ ls -la perf.data
ls: cannot access perf.data: No such file or directory
$
After:
$ perf stat record -o - usleep 1 | perf report -i -
# To display the perf.data header info, please use
# --header/--header-only options.
#
Error:
The - file has no samples!
$ perf stat record -o - usleep 1 | perf script -i -
Display of symbols requested but neither sample IP nor sample address
is selected. Hence, no addresses to convert to symbols.
0 [0x80]: failed to process type: 64
$ ls -la perf.data
ls: cannot access perf.data: No such file or directory
$
Jiri Olsa [Thu, 5 Nov 2015 14:40:46 +0000 (15:40 +0100)]
perf stat record: Add record command
Add 'perf stat record' command support. It creates simple (header only)
perf.data file ATM.
The record command could be specified anywhere among stat options. All
stat command options are valid for stat record command with '-o' option
exception. If specified for record command it denotes the perf data file
name.
Committer note:
Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
while avoiding that older tools show confusing messages, for instance,
with sample_type = 0, we get:
$ oldperf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
non matching sample_type
$
While with sample_type set to PERF_SAMPLE_IDENTIFIER, after we re-run 'perf
stat record usleep' we get:
$ oldperf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
task-clock
context-switches
cpu-migrations
page-faults
cycles
stalled-cycles-frontend
stalled-cycles-backend
instructions
branches
branch-misses
$
Which at least shows the names of the events in the perf.data file.
Additionally, such files, when passed to 'perf report' will produce:
$ oldperf report --stdio
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
Warning:
Kernel address maps (/proc/{kallsyms,modules}) were restricted.
Check /proc/sys/kernel/kptr_restrict before running 'perf record'.
As no suitable kallsyms nor vmlinux was found, kernel samples
can't be resolved.
Samples in kernel modules can't be resolved as well.
Error:
The perf.data file has no samples!
# To display the perf.data header info, please use --header/--header-only options.
#
$
Which is confusing and can be solved by just adding the kernel mmap record,
which will also remove that warning about the data size field being equal to
zero, after generating the mmap record:
Jiri Olsa [Sun, 25 Oct 2015 14:51:43 +0000 (15:51 +0100)]
perf tools: Introduce stat perf.data header feature
Introducing the 'stat' feature to mark a perf.data as created by the
'perf stat record' command. It contains no data.
It's needed so that the report tools (report/script) can differentiate
sampling data from counting data, because they need to be treated in a
different way.
In the future it might be used to store the version of the stat storage
system used.
projects / linux.git / log