The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add comm_str_lock to protect comm_str rb tree.
The lock is only needed for multithreaded code, so using mutex wrappers
provided by perf tool.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-3-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add two locks to protect namespaces_list and comm_list.
The lock is only needed for multithreaded code, so using mutex wrappers
provided by perf tool.
Not all the comm_list/namespaces_list accessing are protected, e.g.
thread__exec_comm. Because the multithread code for perf top event
synthesizing does not touch them. They don't need a lock.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-2-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
On s390x perf test 1 failed. It turned out that commit 4a084ecfc8
("perf report: Fix module symbol adjustment for s390x") was incorrect.
The previous implementation in dso__load_sym() is also suitable for
s390x.
Therefore this patch undoes commit 4a084ecfc8.
Signed-off-by: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Zvonko Kosic <zvonko.kosic@de.ibm.com>
Fixes: 4a084ecfc8 ("perf report: Fix module symbol adjustment for s390x")
LPU-Reference: 20170915071404.58398-1-tmricht@linux.vnet.ibm.com
Link: http://lkml.kernel.org/n/tip-5ani7ly57zji7s0hmzkx416l@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The build of kernel v4.14-rc1 for i686 fails on RHEL 6 with the error
in tools/perf:
util/syscalltbl.c:157: error: expected ';', ',' or ')' before '__maybe_unused'
mv: cannot stat `util/.syscalltbl.o.tmp': No such file or directory
Fix it by placing/moving:
#include <linux/compiler.h>
outside of #ifdef HAVE_SYSCALL_TABLE block.
Signed-off-by: Akemi Yagi <toracat@elrepo.org>
Cc: Alan Bartlett <ajb@elrepo.org>
Link: http://lkml.kernel.org/r/oq41r8$1v9$1@blaine.gmane.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
With --call-graph option, perf report can display call chains using
type, min percent threshold, optional print limit and order. And the
default call-graph parameter is 'graph,0.5,caller,function,percent'.
Before this patch, 'perf report --call-graph' shows incorrect debug
messages as below:
# perf report --call-graph
Invalid callchain mode: 0.5
Invalid callchain order: 0.5
Invalid callchain sort key: 0.5
Invalid callchain config key: 0.5
Invalid callchain mode: caller
Invalid callchain mode: function
Invalid callchain order: function
Invalid callchain mode: percent
Invalid callchain order: percent
Invalid callchain sort key: percent
That is because in function __parse_callchain_report_opt(),each field of
the call-graph parameter is passed to parse_callchain_{mode,order,
sort_key,value} in turn until it meets the matching value.
For example, the order field "caller" is passed to
parse_callchain_mode() firstly and obviously it doesn't match any mode
field. Therefore parse_callchain_mode() will shows the debug message
"Invalid callchain mode: caller", which could confuse users.
The patch fixes this issue by moving the warning out of the function
parse_callchain_{mode,order,sort_key,value}.
Signed-off-by: Mengting Zhang <zhangmengting@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/1506154694-39691-1-git-send-email-zhangmengting@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Yet another fix for probing the max attr.precise_ip setting: it is not
enough settting attr.exclude_kernel for !root users, as they _can_
profile the kernel if the kernel.perf_event_paranoid sysctl is set to
-1, so check that as well.
Testing it:
As non root:
$ sysctl kernel.perf_event_paranoid
kernel.perf_event_paranoid = 2
$ perf record sleep 1
$ perf evlist -v
cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ...
Now as non-root, but with kernel.perf_event_paranoid set set to the
most permissive value, -1:
$ sysctl kernel.perf_event_paranoid
kernel.perf_event_paranoid = -1
$ perf record sleep 1
$ perf evlist -v
cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ...
$
I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel,
non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel.
In both cases, use the highest available precision: attr.precise_ip = 3.
Reported-and-Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: d37a369790 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p")
Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Andi reported a performance drop in single threaded perf tools such as
'perf script' due to the growing number of locks being put in place to
allow for multithreaded tools, so wrap the POSIX threads rwlock routines
with the names used for such kinds of locks in the Linux kernel and then
allow for tools to ask for those locks to be used or not.
I.e. a tool may have a multithreaded phase and then switch to single
threaded, like the upcoming patches for the synthesizing of
PERF_RECORD_{FORK,MMAP,etc} for pre-existing processes to then switch to
single threaded mode in 'perf top'.
The init routines will not be conditional, this way starting as single
threaded to then move to multi threaded mode should be possible.
Reported-by: Andi Kleen <ak@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170404161739.GH12903@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The -M metric group parser threw away the events of earlier groups when
multiple groups were specified. Fix this here by not overwriting the
string incorrectly.
Now this works correctly:
% perf stat -M Summary,SMT --metric-only -a sleep 1
Performance counter stats for 'system wide':
Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization SMT_2T_Utilization Kernel_Utilization CoreIPC CORE_CLKS
900907376.0 2.7 2398954144.0 0.1 0.0 0.2 0.2 0.1 0.4 2080822855.5
while previously it would only show the SMT metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170914205735.18431-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When a PMU is missing print a better error message mentioning
the missing PMU.
% mkdir empty
% mount --bind empty /sys/devices/msr
% perf stat -M Summary true
event syntax error: '{inst_retired.any,cycles}:W,{cpu_clk_unhalted.thread}:W,{inst_retired.any}:W,{cpu_clk_unhalted.ref_tsc,msr/tsc/}:W,{fp_comp_ops_exe.sse_scalar..'
\___ Cannot find PMU `msr'. Missing kernel support?
It still cannot find the right column for aliases, but it's already a vast improvement.
v2: Check asprintf
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170913215006.32222-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In some cases we already have calculated the hash bucket, so reuse it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-800zehjsyy03er4s4jf0e99v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To process any events, it needs to find the thread in the machine first.
The machine maintains a rb tree to store all threads. The rb tree is
protected by a rw lock.
It is not a problem for current perf which serially processing events.
However, it will have scalability performance issue to process events in
parallel, especially on a heavy load system which have many threads.
Introduce a hashtable to divide the big rb tree into many samll rb tree
for threads. The index is thread id % hashtable size. It can reduce the
lock contention.
Committer notes:
Renamed some variables and function names to reduce semantic confusion:
'struct threads' pointers: thread -> threads
threads hastable index: tid -> hash_bucket
struct threads *machine__thread() -> machine__threads()
Cast tid to (unsigned int) to handle -1 in machine__threads() (Kan Liang)
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1505096603-215017-2-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
There are no usage outside util.c and this is the only remaining reason
for fcntl.h to be included in util.h, to get the loff_t definition in
Alpine Linux, so make it static.
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-2dzlsao7k6ihozs5karw6kpx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When there isn't a config file (e.g. ~/.perfconfig) or it has nothing,
the config set wasn't created.
If the config set does not exist, a config file can't be autogenerated.
So allow creating a empty config set in the above case,
then we can support the config file autogeneration.
Before:
$ rm -f ~/.perfconfig
$ perf config --user report.children=false
$ cat ~/.perfconfig
cat: /root/.perfconfig: No such file or directory
But I think it should work even if there isn't a config file.
After:
$ rm -f ~/.perfconfig
$ perf config --user report.children=false
$ cat ~/.perfconfig
# this file is auto-generated.
[report]
children = false
NOTE:
As a result, if perf_config_set__init() fails, it looks as if the config
set isn't freed. But it isn't a problem. Because the config set will be
freed by perf_config_set__delete() at the end of cmd_config().
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1504754336-9824-1-git-send-email-treeze.taeung@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In perf_event__synthesize_threads() perf goes through all proc files
serially by readdir.
scandir() does a snapshoot of /proc, which is multithreading friendly.
It's possible that some threads which are added during event synthesize.
But the number of lost threads should be small. They should not impact
the final analysis.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1504806954-150842-3-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adding the size values '[current/total]' into progress bar, to show more
detailed progress of data reading.
Adding new ui_progress__init_size function to specify we want to display
the size.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170908120510.22515-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
USER_REGS can currently only collected implicitely with call graph
recording. Sometimes it is useful to see them separately, and filter
them. Add a new --user-regs option to record that is similar to
--intr-regs, but acts on user regs.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170905170029.19722-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some of the metrics formulas (like GFLOPs) need to know how long the
measurement period is. Support an internal event called duration_time,
which reports time in second. It maps to the dummy event, but is special
cased for statistics to report the walltime duration.
So far it is not printed, but only used internally for metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-10-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We don't need to use ctx to look up events for saved values. The
context is already part of the evsel pointer, which is the primary key.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-9-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add code to perf list to print metric groups, and metrics
that don't have an event name. The metricgroup code collects
the eventgroups and events into a rblist, and then prints
them according to the configured filters.
The metricgroups are printed by default, but can be
limited by perf list metric or perf list metricgroup
% perf list metricgroup
..
Metric Groups:
DSB:
DSB_Coverage
[Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
FLOPS:
GFLOPs
[Giga Floating Point Operations Per Second]
Frontend:
IFetch_Line_Utilization
[Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions]
Frontend_Bandwidth:
DSB_Coverage
[Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
Memory_BW:
MLP
[Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)]
v2: Check return value of asprintf to fix warning on FC26
Fix key in lookup/addition for the groups list
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-8-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add generic support for standalone metrics specified in JSON files to
perf stat. A metric is a formula that uses multiple events to compute a
higher level result (e.g. IPC).
Previously metrics were always tied to an event and automatically
enabled with that event. But now change it that we can have standalone
metrics. They are in the same JSON data structure as events, but don't
have an event name.
We also allow to organize the metrics in metric groups, which allows a
short cut to select several related metrics at once.
Add a new -M / --metrics option to perf stat that adds the metrics or
metric groups specified.
Add the core code to manage and parse the metric groups. They are
collected from the JSON data structures into a separate rblist. When
computing shadow values look for metrics in that list. Then they are
computed using the existing saved values infrastructure in stat-shadow.c
The actual JSON metrics are in a separate pull request.
% perf stat -M Summary --metric-only -a sleep 1
Performance counter stats for 'system wide':
Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization
317614222.0 1392930775.0 0.0 0.0 0.2 0.1
1.001497549 seconds time elapsed
% perf stat -M GFLOPs flops
Performance counter stats for 'flops':
3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%)
14 fp_comp_ops_exe.sse_scalar_double (66.65%)
0 fp_comp_ops_exe.sse_packed_double (66.67%)
0 fp_comp_ops_exe.sse_packed_single (66.70%)
0 simd_fp_256.packed_double (66.70%)
0 simd_fp_256.packed_single (66.67%)
0 duration_time
3.238372845 seconds time elapsed
v2: Add missing header file
v3: Move find_map to pmu.c
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Extract the code to get the per cpu JSON alias into a separate function
for reuse. No behavior changes.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-6-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Print the generic metric header even when the expression evaluation
failed. Otherwise an expression that fails on the first collections due
to division by zero may suddenly reappear later without an header.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The 'perf stat' shadow metric printing already supports generic metrics.
Factor out the code doing that into a separate function that can be
re-used in a later patch.
No behavior changes.
v2: Fix indentation
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170831194036.30146-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Setting up groups can be complicated due to the complicated scheduling
restrictions of different PMUs.
User tools usually don't understand all these restrictions.
Still in many cases it is useful to set up groups and they work most of
the time. However if the group is set up wrong some members will not
report any value because they never get scheduled.
Add a concept of a 'weak group': try to set up a group, but if it's not
schedulable fallback to not using a group. That gives us the best of
both worlds: groups if they work, but still a usable fallback if they
don't.
In theory it would be possible to have more complex fallback strategies
(e.g. try to split the group in half), but the simple fallback of not
using a group seems to work for now.
So far the weak group is only implemented for perf stat, not for record.
Here's an unschedulable group (on IvyBridge with SMT on)
% perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1
73,806,067 branches
4,848,144 branch-misses # 6.57% of all branches
14,754,458 l1d.replacement
24,905,558 l2_lines_in.all
<not supported> l2_rqsts.all_code_rd <------- will never report anything
With the weak group:
% perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1
125,366,055 branches (80.02%)
9,208,402 branch-misses # 7.35% of all branches (80.01%)
24,560,249 l1d.replacement (80.00%)
43,174,971 l2_lines_in.all (80.05%)
31,891,457 l2_rqsts.all_code_rd (79.92%)
The extra event scheduled with some extra multiplexing
v2: Move fallback code to separate function.
Add comment on for_each_group_member
Adjust to new perf_evsel__close interface
v3: Fix debug print out.
Committer testing:
Before:
# perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1
Performance counter stats for 'system wide':
<not counted> branches
<not counted> branch-misses
<not counted> l1d.replacement
<not counted> l2_lines_in.all
<not supported> l2_rqsts.all_code_rd
1.002147212 seconds time elapsed
# perf stat -e '{branches,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1
Performance counter stats for 'system wide':
83,207,892 branches
11,065,444 l1d.replacement
28,484,024 l2_lines_in.all
12,186,179 l2_rqsts.all_code_rd
1.001739493 seconds time elapsed
After:
# perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}':W -a sleep 1
Performance counter stats for 'system wide':
543,323,909 branches (80.01%)
27,100,512 branch-misses # 4.99% of all branches (80.02%)
50,402,905 l1d.replacement (80.03%)
67,385,892 l2_lines_in.all (80.01%)
21,352,885 l2_rqsts.all_code_rd (79.94%)
1.001086658 seconds time elapsed
#
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20170831194036.30146-2-andi@firstfloor.org
[ Add a "'perf stat' only, for now" comment in the man page, suggested by Jiri ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Do not carry the perf.data file descriptor into the workload process and
close it when perf executes the workload.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170908084621.31595-2-jolsa@kernel.org
[ Add definitions for O_CLOEXEC for older systems ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Peter reported that when he explicitely asked for multiple events with
the same name on the command line it got coalesced into just one line,
i.e.:
# perf stat -e cycles -e cycles -e cycles usleep 1
Performance counter stats for 'usleep 1':
3,269,652 cycles
0.000884123 seconds time elapsed
#
And while there is the --no-merges option to disable that auto-merging,
this is a blunt change in behaviour for such explicit request, so change
the code so that this auto merging is done only when handling the multi
PMU aliases with the same name that introduced this coalescing,
restoring the previous behaviour for the explicit case:
# perf stat -e cycles -e cycles -e cycles usleep 1
Performance counter stats for 'usleep 1':
1,472,837 cycles
1,472,837 cycles
1,472,837 cycles
0.001764870 seconds time elapsed
#
Reported-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 430daf2dc7 ("perf stat: Collapse identically named events")
Link: http://lkml.kernel.org/r/20170831184122.GK4831@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a new sort option "phys_daddr" for --mem-mode sort. With this
option applied, perf can sort and report by sample's physical address.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504026672-7304-3-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Support new sample type PERF_SAMPLE_PHYS_ADDR for physical address.
Add new option --phys-data to record sample physical address.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504026672-7304-2-git-send-email-kan.liang@intel.com
[ Added missing printing in evsel.c patch sent by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
With two new methods, one to find the first match, returning its syscall
id and its index in whatever internal database it keeps the syscall
into, then one to find the next match, if any.
Implemented only on arches where we actually read the syscall table from
the kernel sources, i.e. x86-64 for now, all the others use the libaudit
method for which this returns -1, i.e. just stubs were added, with the
actual implementation using whatever libaudit functions for matching
that may be available.
Cc: Adrian Hunter <adrian.hunter@intel.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-i0sj4rxk1a63pfe9gl8z8irs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The branch history code has a loop detection function. With this, we can
get the number of iterations by calculating the removed loops.
While it would be nice for knowing the average cycles of iterations.
This patch adds up the cycles in branch entries of removed loops and
save the result to the next branch entry (e.g. branch entry A).
Finally it will display the iteration number and average cycles at the
"from" of branch entry A.
For example:
perf record -g -j any,save_type ./div
perf report --branch-history --no-children --stdio
--22.63%--main div.c:42 (RET CROSS_2M)
compute_flag div.c:28 (cycles:2 iter:173115 avg_cycles:2)
|
--10.73%--compute_flag div.c:27 (RET CROSS_2M)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M)
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1502111115-18305-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
On x86, the plt header size is as same as the plt entry size, and can be
identified from shdr's sh_entsize of the plt.
But we can't assume that the sh_entsize of the plt shdr is always the
plt entry size in all architecture, and the plt header size may be not
as same as the plt entry size in some architecure.
On ARM, the plt header size is 20 bytes and the plt entry size is 12
bytes (don't consider the FOUR_WORD_PLT case) that refer to the binutils
implementation. The plt section is as follows:
Disassembly of section .plt:
000004a0 <__cxa_finalize@plt-0x14>:
4a0: e52de004 push {lr} ; (str lr, [sp, #-4]!)
4a4: e59fe004 ldr lr, [pc, #4] ; 4b0 <_init+0x1c>
4a8: e08fe00e add lr, pc, lr
4ac: e5bef008 ldr pc, [lr, #8]!
4b0: 00008424 .word 0x00008424
000004b4 <__cxa_finalize@plt>:
4b4: e28fc600 add ip, pc, #0, 12
4b8: e28cca08 add ip, ip, #8, 20 ; 0x8000
4bc: e5bcf424 ldr pc, [ip, #1060]! ; 0x424
000004c0 <printf@plt>:
4c0: e28fc600 add ip, pc, #0, 12
4c4: e28cca08 add ip, ip, #8, 20 ; 0x8000
4c8: e5bcf41c ldr pc, [ip, #1052]! ; 0x41c
On AARCH64, the plt header size is 32 bytes and the plt entry size is 16
bytes. The plt section is as follows:
Disassembly of section .plt:
0000000000000560 <__cxa_finalize@plt-0x20>:
560: a9bf7bf0 stp x16, x30, [sp,#-16]!
564: 90000090 adrp x16, 10000 <__FRAME_END__+0xf8a8>
568: f944be11 ldr x17, [x16,#2424]
56c: 9125e210 add x16, x16, #0x978
570: d61f0220 br x17
574: d503201f nop
578: d503201f nop
57c: d503201f nop
0000000000000580 <__cxa_finalize@plt>:
580: 90000090 adrp x16, 10000 <__FRAME_END__+0xf8a8>
584: f944c211 ldr x17, [x16,#2432]
588: 91260210 add x16, x16, #0x980
58c: d61f0220 br x17
0000000000000590 <__gmon_start__@plt>:
590: 90000090 adrp x16, 10000 <__FRAME_END__+0xf8a8>
594: f944c611 ldr x17, [x16,#2440]
598: 91262210 add x16, x16, #0x988
59c: d61f0220 br x17
NOTES:
In addition to ARM and AARCH64, other architectures, such as
s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa also need to consider
this issue.
Signed-off-by: Li Bin <huawei.libin@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: David Tolnay <dtolnay@gmail.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: zhangmengting@huawei.com
Link: http://lkml.kernel.org/r/1496622849-21877-1-git-send-email-huawei.libin@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The commit 9aaf5a5f47 ("perf probe: Check kprobes blacklist when
adding new events"), 'perf probe' supports checking the blacklist of the
fuctions which can not be probed. But the checking condition is wrong,
that the end_addr of the symbol which is the start_addr of the next
symbol can't be included.
Committer notes:
IOW make it match its kernel counterpart in kernel/kprobes.c:
bool within_kprobe_blacklist(unsigned long addr)
Each entry have as its end address not its end address, but the first
address _outside_ that symbol, which for related functions, is the first
address of the next symbol, like these from kernel/trace/trace_probe.c:
0xffffffffbd198df0-0xffffffffbd198e40 print_type_u8
0xffffffffbd198e40-0xffffffffbd198e90 print_type_u16
0xffffffffbd198e90-0xffffffffbd198ee0 print_type_u32
0xffffffffbd198ee0-0xffffffffbd198f30 print_type_u64
0xffffffffbd198f30-0xffffffffbd198f80 print_type_s8
0xffffffffbd198f80-0xffffffffbd198fd0 print_type_s16
0xffffffffbd198fd0-0xffffffffbd199020 print_type_s32
0xffffffffbd199020-0xffffffffbd199070 print_type_s64
0xffffffffbd199070-0xffffffffbd1990c0 print_type_x8
0xffffffffbd1990c0-0xffffffffbd199110 print_type_x16
0xffffffffbd199110-0xffffffffbd199160 print_type_x32
0xffffffffbd199160-0xffffffffbd1991b0 print_type_x64
But not always:
0xffffffffbd1997b0-0xffffffffbd1997c0 fetch_kernel_stack_address (kernel/trace/trace_probe.c)
0xffffffffbd1c57f0-0xffffffffbd1c58b0 __context_tracking_enter (kernel/context_tracking.c)
Signed-off-by: Li Bin <huawei.libin@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: zhangmengting@huawei.com
Fixes: 9aaf5a5f47 ("perf probe: Check kprobes blacklist when adding new events")
Link: http://lkml.kernel.org/r/1504011443-7269-1-git-send-email-huawei.libin@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Prior to this patch, make scripts tested for CLANG with ifeq ($(CC),
clang), failing to detect CLANG binaries with different names. Fix it by
testing for the existence of __clang__ macro in the list of compiler
defined macros.
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Paul Turner <pjt@google.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170827075442.108534-5-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
There's no big value on displaying counts for every event ID, which is
one per every CPU. Rather than that, displaying the whole sum for the
event.
$ perf record -c 100000 -e cycles:u -s test
$ perf report -T
Before:
# PID TID cycles:u cycles:u cycles:u cycles:u ... [20 more columns of 'cycles:u']
3339 3339 0 0 0 0
3340 3340 0 0 0 0
3341 3341 0 0 0 0
3342 3342 0 0 0 0
Now:
# PID TID cycles:u
3339 3339 19678
3340 3340 18744
3341 3341 17335
3342 3342 26414
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-10-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We need to make sure the array of value pointers are zero initialized,
because we use them in realloc later on and uninitialized non zero value
will cause allocation error and aborted execution.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-9-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Bailing out in case the allocation failed, not the other way round.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-8-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We are taking wrong index (+1) for first thread, which leaves thread
with index 0 unused and uninitialized.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-7-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adding dump_read function to gather all the dump output of read
function. Adding output of enabled and running times and id if enabled
(3 new lines with '...' prefix below).
$ perf record -s ...
$ perf report -D
958358311769 0x91f8 [0x40]: PERF_RECORD_READ: 3339 3339 cycles:u 0
... time enabled : 958358313731
... time running : 958358313731
... id : 80
Committer note:
Do not use 'read' as a variable name as it breaks the build on older
systems, such as RHEL6:
CC /tmp/build/perf/util/session.o
cc1: warnings being treated as errors
util/session.c: In function 'dump_read':
util/session.c:1132: error: declaration of 'read' shadows a global declaration
/usr/include/bits/unistd.h:35: error: shadowed declaration is here
mv: cannot stat `/tmp/build/perf/util/.session.o.tmp': No such file or directory
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-6-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Set read_format for what we expect to get from read event generated by
perf_event_attr::inherit_stat.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824162737.7813-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Skylake introduced new mem_remote bit in union perf_mem_data_src [1].
It applies to any other memory level to express Remote unknown level, as
is reported by Skylake.
Adding this extra check to c2c_decode_stats to properly decode remote
HITMs on Skylake.
[1] http://lkml.kernel.org/r/20170816222156.19953-4-andi@firstfloor.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170824085732.28481-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fix misprint CAP_IOC_LOCK -> CAP_IPC_LOCK. This capability have nothing
to do with raw tracepoints. This part is about bypassing mlock limits.
Sysctl kernel.perf_event_paranoid = -1 allows raw and ftrace function
tracepoints without CAP_SYS_ADMIN.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/150322916080.129746.11285255474738558340.stgit@buzz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add decoding for the new "lvlx" and "snoopx" meminfo fields added
earlier to the kernel so that "perf mem report" and other tools can
print it properly.
v2: Merge with persistent memory patch.
Switch to new bit encoding for each combination.
v3: Switch to generic lvlnum field.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170816222156.19953-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Avoid adding redundant events while parsing an expression. When we add
an "other" event check first if it already exists.
v2: Fix perf test failure.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170811232634.30465-10-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some of the upcoming metrics need more than 8 events. Increase the maximum
number the parser supports.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170811232634.30465-9-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Enhance the expression parser for more complex metric formulas.
- Support python style IF ELSE operators
- Add an #SMT_On magic variable for formulas that depend on the SMT
status.
Example: 4 *( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles
- Support MIN/MAX operations
Example: min(1 , IDQ.MITE_UOPS / ( UPI * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )
This is useful to fix up problems caused by multiplexing.
- Support | & ^ operators
- Minor cleanups and fixes
- Support an \ escape for operators. This allows to specify event names
like c2-residency
- Support @ as an alternative for / to be able to specify pmus without
conflicts with operators (like msr/tsc/ as msr@tsc@)
Example: (cstate_core@c3\\-residency@ / msr@tsc@) * 100
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170811232634.30465-8-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add an smt_on() function to return if SMT is enabled or disabled. Used
in the next patch.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170811232634.30465-7-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf stat -e cpu/uops_executed.core,cmask=1/
would be detected as a BPF source event because the .c matches the .c
source BPF pattern.
v2:
Originally I tried to use lex lookahead, but it doesn't seem to work.
This now extends the BPF pattern to match longer events, but then does
an extra check in the C code to reject BPF matches that do not end with
.c/.o/.obj
This uses REJECT, which makes the flex scanner slower, but that
shouldn't be a big problem for the perf events.
Committer testing:
# perf trace -e write -e /home/acme/bpf/tracepoint.c cat /etc/passwd > /dev/null
0.000 ( 0.006 ms): cat/18485 write(fd: 1, buf: 0x7f59eebe1000, count: 3494 ) ...
0.006 ( ): raw_syscalls:sys_enter:NR 1 (1, 7f59eebe1000, da6, 22, 7f59eebe0010, 0))
0.008 ( ): perf_bpf_probe:_write:(ffffffff9626b2c0))
0.000 ( 0.010 ms): cat/18485 ... [continued]: write()) = 3494
#
It continues doing what was expected, i.e. identifying
/home/acme/bpf/tracepoint.c as a BPF event and activates the clang
machinery to build an eBPF object and then uses sys_bpf() to hook it up
to the raw_syscalls:sys_enter tracepoint, etc.
Andi forgot to add Wang to the CC list, fix it.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170811232634.30465-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
