| Age | Commit message (Collapse) | Author |
|---|
|
A double pointer is used in map__find() where a single pointer is enough
because the function doesn't affect the rbtree and the rbtree is locked.
Signed-off-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Saint-Etienne <eric.saintetienne@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1542969759-24346-1-git-send-email-eric.saint.etienne@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
When using the -x option, perf stat prints CSV-style output with one
event per line. For each event, it prints the count, the unit, the
event name, the cgroup, and a bunch of other event specific fields (such
as insn per cycles).
When you use CSV-style mode, you expect a normalized output where each
event is printed with the same number of fields regardless of what it is
so it can easily be imported into a spreadsheet or parsed.
For instance, if an event does not have a unit, then print an empty
field for it.
Although this approach was implemented for the unit, it was not for the
cgroup.
When mixing cgroup and non-cgroup events, then non-cgroup events would
not show an empty field, instead the next field was printed, make
columns not line up correctly.
This patch fixes the cgroup output issues by forcing an empty field
for non-cgroup events as soon as one event has cgroup.
Before:
<not counted> @ @cycles @foo @ 0 @100.00@@
2531614 @ @cycles @6420922@100.00@ @
foo cgroup lines up with time_running!
After:
<not counted> @ @cycles @foo @0 @100.00@@
2594834 @ @cycles @ @5287372 @100.00@@
Fields line up.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1541587845-9150-1-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Commit 0aa802a79469 ("perf stat: Get rid of extra clock display
function") introduced scale and unit for clock events. Thus,
perf_stat__update_shadow_stats() now saves scaled values of clock events
in msecs, instead of original nsecs. But while calculating values of
shadow stats we still consider clock event values in nsecs. This results
in a wrong shadow stat values. Ex,
# ./perf stat -e task-clock,cycles ls
<SNIP>
2.60 msec task-clock:u # 0.877 CPUs utilized
2,430,564 cycles:u # 1215282.000 GHz
Fix this by saving original nsec values for clock events in
perf_stat__update_shadow_stats(). After patch:
# ./perf stat -e task-clock,cycles ls
<SNIP>
3.14 msec task-clock:u # 0.839 CPUs utilized
3,094,528 cycles:u # 0.985 GHz
Suggested-by: Jiri Olsa <jolsa@redhat.com>
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: yuzhoujian@didichuxing.com
Fixes: 0aa802a79469 ("perf stat: Get rid of extra clock display function")
Link: http://lkml.kernel.org/r/20181116042843.24067-1-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
In debian/ubuntu its libssl-dev, but for fedora/RHEL/Centos/etc its
openssl-devel, fix it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 8ee4646038e4 ("perf build: Add libcrypto feature detection")
Link: https://lkml.kernel.org/n/tip-lnxqszts6aq2c9jy4b7mlnym@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The weak functions, strcmp_cpuid_str() and get_cpuid_str(), are defined
in pmu.c.
Most of the cpuid related functions, including *_cpuid_str()'s
declaration and platform specific definition, are in header.c/h.
To make the declaration and definition of all cpuid related functions in
a consistent place, move the weak functions to header.c.
There is no functional change.
Suggested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Link: http://lkml.kernel.org/r/20181121164939.13482-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Perf can take minutes to parse an image when -ffunction-section is used.
This is especially true with the kernel image when it is compiled this
way, which is the arm64 default since the patcheset "Enable deadcode
elimination at link time".
Perf organize maps using a rbtree. Whenever perf finds a new symbols, it
first searches this rbtree for the map it belongs to, by strcmp()'aring
section names. When it finds the map with the right name, it uses it to
add the symbol. With a usual image there aren't so many maps but when
using -ffunction-section there's basically one map per function. With
the kernel image that's north of 40,000 maps. For most symbols perf has
to parses the entire rbtree to eventually create a new map and add it.
Consequently perf spends most of the time browsing a rbtree that keeps
getting larger.
This performance fix introduces a secondary rbtree that indexes maps
based on the section name.
Signed-off-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Reviewed-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Reviewed-by: David Aldridge <david.aldridge@oracle.com>
Reviewed-by: Rob Gardner <rob.gardner@oracle.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1542822679-25591-1-git-send-email-eric.saint.etienne@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The Compiled Method Load Record (cmlr) is JDK specific interface to
access JVM stack info. This makes the jvmti agent code not compile under
another jdk, which does not support that.
Separating jvmti cmlr check into special feature check, and adding
HAVE_JVMTI_CMLR macro to indicate that.
Mark cmlr code in jvmti/libjvmti.c with HAVE_JVMTI_CMLR, so we can
compile it on system without cmlr support.
This change makes the jvmti compile with java-1.8.0-ibm package. It's
without the line numbers support, but the rest works.
Adding NO_JVMTI_CMLR compile variable for testing.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Gustavo Luiz Duarte <gduarte@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20181121154341.21521-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add JSON metrics (based on event list v1) for Cascadelake server
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/3ab97c73-c197-8555-1a35-b54636e667e6@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The perf tools cannot find the proper event list for the Cascadelake
server. Because the Cascadelake server and the Skylake server have the
same CPU model number, which are used by the perf tools to find the
event list.
The stepping for Skylake server is up to 4.
The stepping for Cascadelake server starts from 5.
The stepping can be used to distinguish between them.
The stepping is added in get_cpuid_str().
The stepping information for Skylake server is updated in mapfile.csv.
A x86 specific strcmp_cpuid_cmp() function is added to handle two CPUID
formats in mapfile.csv, "vendor-family-model-stepping" and
"vendor-family-model":
- If a cpuid-regular-expression from the mapfile.csv using the new
stepping format, a cpuid-string generated on the machine must include
stepping. Otherwise, it is a mismatch.
- If the cpuid-regular-expression using the old non-stepping format,
the stepping in the cpuid-string will be ignored.
The script, using environment string "PERF_CPUID" without stepping on
Skylake server, will be broken. If so, users must fix their scripts.
Committer notes:
Fixed this build error on centos:6 and debian:7:
arch/x86/util/header.c: In function 'is_full_cpuid':
arch/x86/util/header.c:82:39: error: declaration of 'cpuid' shadows a global declaration [-Werror=shadow]
arch/x86/util/header.c:12:1: error: shadowed declaration is here [-Werror=shadow]
arch/x86/util/header.c: In function 'strcmp_cpuid_str':
arch/x86/util/header.c:98:56: error: declaration of 'cpuid' shadows a global declaration [-Werror=shadow]
arch/x86/util/header.c:12:1: error: shadowed declaration is here [-Werror=shadow]
cc1: all warnings being treated as errors
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181114212416.15665-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
We already have function to check if a given event is either
SW_CPU_CLOCK or SW_TASK_CLOCK. Utilize it.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: yuzhoujian@didichuxing.com
Link: http://lkml.kernel.org/r/20181115095533.16930-1-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Depending on which functions are inlined in util/pmu.c, the snprintf()
calls in perf_pmu__parse_{scale,unit,per_pkg,snapshot}() might trigger a
warning:
util/pmu.c: In function 'pmu_aliases':
util/pmu.c:178:31: error: '%s' directive output may be truncated writing up to 255 bytes into a region of size between 0 and 4095 [-Werror=format-truncation=]
snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
^~
I found this when trying to build perf from Linux 3.16 with gcc 8.
However I can reproduce the problem in mainline if I force
__perf_pmu__new_alias() to be inlined.
Suppress this by using scnprintf() as has been done elsewhere in perf.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20181111184524.fux4taownc6ndbx6@decadent.org.uk
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The tool perf is useful for the performance analysis on the Hygon Dhyana
platform. But right now there is no Hygon support for it to analyze the
KVM guest os data. So add Hygon Dhyana support to it by checking vendor
string to share the code path of AMD.
Signed-off-by: Pu Wen <puwen@hygon.cn>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1542008451-31735-1-git-send-email-puwen@hygon.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Benchmark the various operations allowed for epoll_ctl(2). The idea is
to concurrently stress a single epoll instance doing add/mod/del
operations.
Committer testing:
# perf bench epoll ctl
# Running 'epoll/ctl' benchmark:
Run summary [PID 20344]: 4 threads doing epoll_ctl ops 64 file-descriptors for 8 secs.
[thread 0] fdmap: 0x21a46b0 ... 0x21a47ac [ add: 1680960 ops; mod: 1680960 ops; del: 1680960 ops ]
[thread 1] fdmap: 0x21a4960 ... 0x21a4a5c [ add: 1685440 ops; mod: 1685440 ops; del: 1685440 ops ]
[thread 2] fdmap: 0x21a4c10 ... 0x21a4d0c [ add: 1674368 ops; mod: 1674368 ops; del: 1674368 ops ]
[thread 3] fdmap: 0x21a4ec0 ... 0x21a4fbc [ add: 1677568 ops; mod: 1677568 ops; del: 1677568 ops ]
Averaged 1679584 ADD operations (+- 0.14%)
Averaged 1679584 MOD operations (+- 0.14%)
Averaged 1679584 DEL operations (+- 0.14%)
#
Lets measure those calls with 'perf trace' to get a glympse at what this
benchmark is doing in terms of syscalls:
# perf trace -m32768 -s perf bench epoll ctl
# Running 'epoll/ctl' benchmark:
Run summary [PID 20405]: 4 threads doing epoll_ctl ops 64 file-descriptors for 8 secs.
[thread 0] fdmap: 0x21764e0 ... 0x21765dc [ add: 1100480 ops; mod: 1100480 ops; del: 1100480 ops ]
[thread 1] fdmap: 0x2176790 ... 0x217688c [ add: 1250176 ops; mod: 1250176 ops; del: 1250176 ops ]
[thread 2] fdmap: 0x2176a40 ... 0x2176b3c [ add: 1022464 ops; mod: 1022464 ops; del: 1022464 ops ]
[thread 3] fdmap: 0x2176cf0 ... 0x2176dec [ add: 705472 ops; mod: 705472 ops; del: 705472 ops ]
Averaged 1019648 ADD operations (+- 11.27%)
Averaged 1019648 MOD operations (+- 11.27%)
Averaged 1019648 DEL operations (+- 11.27%)
Summary of events:
epoll-ctl (20405), 1264 events, 0.0%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
eventfd2 256 9.514 0.001 0.037 5.243 68.00%
clone 4 1.245 0.204 0.311 0.531 24.13%
mprotect 66 0.345 0.002 0.005 0.021 7.43%
openat 45 0.313 0.004 0.007 0.073 21.93%
mmap 88 0.302 0.002 0.003 0.013 5.02%
futex 4 0.160 0.002 0.040 0.140 83.43%
sched_setaffinity 4 0.124 0.005 0.031 0.070 49.39%
read 44 0.103 0.001 0.002 0.013 15.54%
fstat 40 0.052 0.001 0.001 0.003 5.43%
close 39 0.039 0.001 0.001 0.001 1.48%
stat 9 0.034 0.003 0.004 0.006 7.30%
access 3 0.023 0.007 0.008 0.008 4.25%
open 2 0.021 0.008 0.011 0.013 22.60%
getdents 4 0.019 0.001 0.005 0.009 37.15%
write 2 0.013 0.004 0.007 0.009 38.48%
munmap 1 0.010 0.010 0.010 0.010 0.00%
brk 3 0.006 0.001 0.002 0.003 26.34%
rt_sigprocmask 2 0.004 0.001 0.002 0.003 43.95%
rt_sigaction 3 0.004 0.001 0.001 0.002 16.07%
prlimit64 3 0.004 0.001 0.001 0.001 5.39%
prctl 1 0.003 0.003 0.003 0.003 0.00%
epoll_create 1 0.003 0.003 0.003 0.003 0.00%
lseek 2 0.002 0.001 0.001 0.001 11.42%
sched_getaffinity 1 0.002 0.002 0.002 0.002 0.00%
arch_prctl 1 0.002 0.002 0.002 0.002 0.00%
set_tid_address 1 0.001 0.001 0.001 0.001 0.00%
getpid 1 0.001 0.001 0.001 0.001 0.00%
set_robust_list 1 0.001 0.001 0.001 0.001 0.00%
execve 1 0.000 0.000 0.000 0.000 0.00%
epoll-ctl (20406), 1245480 events, 14.6%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
epoll_ctl 619511 1034.927 0.001 0.002 6.691 0.67%
nanosleep 3226 616.114 0.006 0.191 10.376 7.57%
futex 2 11.336 0.002 5.668 11.334 99.97%
set_robust_list 1 0.001 0.001 0.001 0.001 0.00%
clone 1 0.000 0.000 0.000 0.000 0.00%
epoll-ctl (20407), 1243151 events, 14.5%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
epoll_ctl 618350 1042.181 0.001 0.002 2.512 0.40%
nanosleep 3220 366.261 0.012 0.114 18.162 9.59%
futex 4 5.463 0.001 1.366 5.427 99.12%
set_robust_list 1 0.002 0.002 0.002 0.002 0.00%
epoll-ctl (20408), 1801690 events, 21.1%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
epoll_ctl 896174 1540.581 0.001 0.002 6.987 0.74%
nanosleep 4667 783.393 0.006 0.168 10.419 7.10%
futex 2 4.682 0.002 2.341 4.681 99.93%
set_robust_list 1 0.002 0.002 0.002 0.002 0.00%
clone 1 0.000 0.000 0.000 0.000 0.00%
epoll-ctl (20409), 4254890 events, 49.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
epoll_ctl 2116416 3768.097 0.001 0.002 9.956 0.41%
nanosleep 11023 1141.778 0.006 0.104 9.447 4.95%
futex 3 0.037 0.002 0.012 0.029 70.50%
set_robust_list 1 0.008 0.008 0.008 0.008 0.00%
madvise 1 0.005 0.005 0.005 0.005 0.00%
clone 1 0.000 0.000 0.000 0.000 0.00%
#
Committer notes:
Fix build on fedora:24-x-ARC-uClibc, debian:experimental-x-mips,
debian:experimental-x-mipsel, ubuntu:16.04-x-arm and ubuntu:16.04-x-powerpc
CC /tmp/build/perf/bench/epoll-ctl.o
bench/epoll-ctl.c: In function 'init_fdmaps':
bench/epoll-ctl.c:214:16: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
for (i = 0; i < nfds; i+=inc) {
^
bench/epoll-ctl.c: In function 'bench_epoll_ctl':
bench/epoll-ctl.c:377:16: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
for (i = 0; i < nthreads; i++) {
^
bench/epoll-ctl.c:388:16: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
for (i = 0; i < nthreads; i++) {
^
cc1: all warnings being treated as errors
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Link: http://lkml.kernel.org/r/20181106152226.20883-3-dave@stgolabs.net
[ Use inttypes.h to print rlim_t fields, fixing the build on Alpine Linux / musl libc ]
[ Check if eventfd() is available, i.e. if HAVE_EVENTFD is defined ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
This program benchmarks concurrent epoll_wait(2) for file descriptors
that are monitored with with EPOLLIN along various semantics, by a
single epoll instance. Such conditions can be found when using
single/combined or multiple queuing when load balancing.
Each thread has a number of private, nonblocking file descriptors,
referred to as fdmap. A writer thread will constantly be writing to the
fdmaps of all threads, minimizing each threads's chances of epoll_wait
not finding any ready read events and blocking as this is not what we
want to stress. Full details in the start of the C file.
Committer testing:
# perf bench
Usage:
perf bench [<common options>] <collection> <benchmark> [<options>]
# List of all available benchmark collections:
sched: Scheduler and IPC benchmarks
mem: Memory access benchmarks
numa: NUMA scheduling and MM benchmarks
futex: Futex stressing benchmarks
epoll: Epoll stressing benchmarks
all: All benchmarks
# perf bench epoll
# List of available benchmarks for collection 'epoll':
wait: Benchmark epoll concurrent epoll_waits
all: Run all futex benchmarks
# perf bench epoll wait
# Running 'epoll/wait' benchmark:
Run summary [PID 19295]: 3 threads monitoring on 64 file-descriptors for 8 secs.
[thread 0] fdmap: 0xdaa650 ... 0xdaa74c [ 328241 ops/sec ]
[thread 1] fdmap: 0xdaa900 ... 0xdaa9fc [ 351695 ops/sec ]
[thread 2] fdmap: 0xdaabb0 ... 0xdaacac [ 381423 ops/sec ]
Averaged 353786 operations/sec (+- 4.35%), total secs = 8
#
Committer notes:
Fix the build on debian:experimental-x-mips, debian:experimental-x-mipsel
and others:
CC /tmp/build/perf/bench/epoll-wait.o
bench/epoll-wait.c: In function 'writerfn':
bench/epoll-wait.c:399:12: error: format '%ld' expects argument of type 'long int', but argument 2 has type 'size_t' {aka 'unsigned int'} [-Werror=format=]
printinfo("exiting writer-thread (total full-loops: %ld)\n", iter);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~
bench/epoll-wait.c:86:31: note: in definition of macro 'printinfo'
do { if (__verbose) { printf(fmt, ## arg); fflush(stdout); } } while (0)
^~~
cc1: all warnings being treated as errors
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com> <jbaron@akamai.com>
Link: http://lkml.kernel.org/r/20181106152226.20883-2-dave@stgolabs.net
Link: http://lkml.kernel.org/r/20181106182349.thdkpvshkna5vd7o@linux-r8p5>
[ Applied above fixup as per Davidlohr's request ]
[ Use inttypes.h to print rlim_t fields, fixing the build on Alpine Linux / musl libc ]
[ Check if eventfd() is available, i.e. if HAVE_EVENTFD is defined ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
A new 'perf bench epoll' will use this, and to disable it for older
systems, add a feature test for this API.
This is just a simple program that if successfully compiled, means that
the feature is present, at least at the library level, in a build that
sets the output directory to /tmp/build/perf (using O=/tmp/build/perf),
we end up with:
$ ls -la /tmp/build/perf/feature/test-eventfd*
-rwxrwxr-x. 1 acme acme 8176 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.bin
-rw-rw-r--. 1 acme acme 588 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.d
-rw-rw-r--. 1 acme acme 0 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.make.output
$ ldd /tmp/build/perf/feature/test-eventfd.bin
linux-vdso.so.1 (0x00007fff3bf3f000)
libc.so.6 => /lib64/libc.so.6 (0x00007fa984061000)
/lib64/ld-linux-x86-64.so.2 (0x00007fa984417000)
$ grep eventfd -A 2 -B 2 /tmp/build/perf/FEATURE-DUMP
feature-dwarf=1
feature-dwarf_getlocations=1
feature-eventfd=1
feature-fortify-source=1
feature-sync-compare-and-swap=1
$
The main thing here is that in the end we'll have -DHAVE_EVENTFD in
CFLAGS, and then the 'perf bench' entry needing that API can be
selectively pruned.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-wkeldwob7dpx6jvtuzl8164k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Both futex and epoll need this call, and can cause build failure on
systems that don't have it pthread_attr_setaffinity_np().
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Link: http://lkml.kernel.org/r/20181109210719.pr7ohayuwqmfp2wl@linux-r8p5
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The iregs output was missing the newline at end as well as the leading
ABI output. This made it hard to compare the iregs and uregs values.
Instead, use a single function to output the register values and use it
for both, iregs and uregs, to ensure the output is consistent.
Before:
perf 7049 [-01] 1343.354347: 1 cycles:ppp:
ffffffffa7bc21ce perf_event_exec+0x18e (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7ead3 setup_new_exec+0xf3 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7cd7be5 load_elf_binary+0x395 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7e540 search_binary_handler+0x80 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f1aa __do_execve_file.isra.13+0x58a (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f561 do_execve+0x21 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f596 __x64_sys_execve+0x26 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7a041cb do_syscall_64+0x5b (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa840008c entry_SYSCALL_64+0x7c (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
AX:0x80000000 BX:0x0 CX:0x0 DX:0x7 SI:0xf DI:0x286 BP:0xffff95bc8213a460 SP:0xffffacbf0ba97d18 IP:0xffffffffa7bc21cd FLAGS:0x28e CS:0x10 SS:0x18 R8:0x2 R9:0x21440 R10:0x33816fb3b8c R11:0x1 R12:0xffff95bc8213a460 R13:0xffff95bc8213a400 R14:0xffff95bc8213a400 R15:0x1 ABI:2 AX:0xffffffffffffffda BX:0xffffffffffffffff CX:0x7f84ad85798b DX:0x560209699d50 SI:0x7ffe2c7a6820 DI:0x7ffe2c7a8c9b BP:0x7ffe2c7a20d0 SP:0x7ffe2c7a2058 IP:0x7f84ad85798b FLAGS:0x206 CS:0x33 SS:0x2b R8:0x7ffe2c7a2030 R9:0x7f84ae55f010 R10:0x8 R11:0x206 R12:0xffffffffffffffff R13:0xffffffffffffffff R14:0xffffffffffffffff R15:0xffffffffffffffff
perf 7049 [-01] 1343.354363: 1 cycles:ppp:
...
After:
perf 7049 [-01] 1343.354347: 1 cycles:ppp:
ffffffffa7bc21ce perf_event_exec+0x18e (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7ead3 setup_new_exec+0xf3 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7cd7be5 load_elf_binary+0x395 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7e540 search_binary_handler+0x80 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f1aa __do_execve_file.isra.13+0x58a (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f561 do_execve+0x21 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7c7f596 __x64_sys_execve+0x26 (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa7a041cb do_syscall_64+0x5b (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ffffffffa840008c entry_SYSCALL_64+0x7c (/lib/modules/4.20.0-rc1perf-devel-05115-gc0bc98f76e39-dirty/build/vmlinux)
ABI:2 AX:0x80000000 BX:0x0 CX:0x0 DX:0x7 SI:0xf DI:0x286 BP:0xffff95bc8213a460 SP:0xffffacbf0ba97d18 IP:0xffffffffa7bc21cd FLAGS:0x28e CS:0x10 SS:0x18 R8:0x2 R9:0x21440 R10:0x33816fb3b8c R11:0x1 R12:0xffff95bc8213a460 R13:0xffff95bc8213a400 R14:0xffff95bc8213a400 R15:0x1
ABI:2 AX:0xffffffffffffffda BX:0xffffffffffffffff CX:0x7f84ad85798b DX:0x560209699d50 SI:0x7ffe2c7a6820 DI:0x7ffe2c7a8c9b BP:0x7ffe2c7a20d0 SP:0x7ffe2c7a2058 IP:0x7f84ad85798b FLAGS:0x206 CS:0x33 SS:0x2b R8:0x7ffe2c7a2030 R9:0x7f84ae55f010 R10:0x8 R11:0x206 R12:0xffffffffffffffff R13:0xffffffffffffffff R14:0xffffffffffffffff R15:0xffffffffffffffff
perf 7049 [-01] 1343.354363: 1 cycles:ppp:
...
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181107223437.9071-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
While working on augmented syscalls I got into this error:
# trace -vv --filter-pids 2469,1663 -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
<SNIP>
libbpf: map 0 is "__augmented_syscalls__"
libbpf: map 1 is "__bpf_stdout__"
libbpf: map 2 is "pids_filtered"
libbpf: map 3 is "syscalls"
libbpf: collecting relocating info for: '.text'
libbpf: relo for 13 value 84 name 133
libbpf: relocation: insn_idx=3
libbpf: relocation: find map 3 (pids_filtered) for insn 3
libbpf: collecting relocating info for: 'raw_syscalls:sys_enter'
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=1
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=3
libbpf: relo for 9 value 28 name 178
libbpf: relocation: insn_idx=36
libbpf: relocation: find map 1 (__augmented_syscalls__) for insn 36
libbpf: collecting relocating info for: 'raw_syscalls:sys_exit'
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=0
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=2
bpf: config program 'raw_syscalls:sys_enter'
bpf: config program 'raw_syscalls:sys_exit'
libbpf: create map __bpf_stdout__: fd=3
libbpf: create map __augmented_syscalls__: fd=4
libbpf: create map syscalls: fd=5
libbpf: create map pids_filtered: fd=6
libbpf: added 13 insn from .text to prog raw_syscalls:sys_enter
libbpf: added 13 insn from .text to prog raw_syscalls:sys_exit
libbpf: load bpf program failed: Operation not permitted
libbpf: failed to load program 'raw_syscalls:sys_exit'
libbpf: failed to load object 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
bpf: load objects failed: err=-4009: (Incorrect kernel version)
event syntax error: 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
\___ Failed to load program for unknown reason
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
-e, --event <event> event/syscall selector. use 'perf list' to list available events
If I then try to use strace (perf trace'ing 'perf trace' needs some more work
before its possible) to get a bit more info I get:
# strace -e bpf trace --filter-pids 2469,1663 -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_PERF_EVENT_ARRAY, key_size=4, value_size=4, max_entries=4, map_flags=0, inner_map_fd=0, map_name="__bpf_stdout__", map_ifindex=0}, 72) = 3
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_PERF_EVENT_ARRAY, key_size=4, value_size=4, max_entries=4, map_flags=0, inner_map_fd=0, map_name="__augmented_sys", map_ifindex=0}, 72) = 4
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_ARRAY, key_size=4, value_size=1, max_entries=500, map_flags=0, inner_map_fd=0, map_name="syscalls", map_ifindex=0}, 72) = 5
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_HASH, key_size=4, value_size=1, max_entries=512, map_flags=0, inner_map_fd=0, map_name="pids_filtered", map_ifindex=0}, 72) = 6
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=57, insns=0x1223f50, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_enter", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = 7
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=18, insns=0x1224120, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=18, insns=0x1224120, license="GPL", log_level=1, log_size=262144, log_buf="", kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_KPROBE, insn_cnt=18, insns=0x1224120, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
event syntax error: 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
\___ Failed to load program for unknown reason
<SNIP similar output as without 'strace'>
#
I managed to create the maps, etc, but then installing the "sys_exit" hook into
the "raw_syscalls:sys_exit" tracepoint somehow gets -EPERMed...
I then go and try reducing the size of this new table:
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -47,6 +47,17 @@ struct augmented_filename {
#define SYS_OPEN 2
#define SYS_OPENAT 257
+struct syscall {
+ bool filtered;
+};
+
+struct bpf_map SEC("maps") syscalls = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct syscall),
+ .max_entries = 500,
+};
And after reducing that .max_entries a tad, it works. So yeah, the "unknown
reason" should be related to the number of bytes all this is taking, reduce the
default for pid_map()s so that we can have a "syscalls" map with enough slots
for all syscalls in most arches. And take notes about this error message,
improve it :-)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Edward Cree <ecree@solarflare.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-yjzhak8asumz9e9hts2dgplp@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
This change makes it much easier to easily distinguish between
consecutive samples by keeping the empty line between them, like we see
when we do not enable uregs output.
Before:
cpp-inlining 28298 [-01] 54837.342780: 3068085 cycles:pp:
7ffff7c96709 __hypot_finite+0xa9 (/usr/lib/libm-2.28.so)
...
ABI:2 AX:0x0 BX:0x40f56cf6 CX:0x294a3ae7 ...
cpp-inlining 28298 [-01] 54837.344493: 2881929 cycles:pp:
7ffff7c96696 __hypot_finite+0x36 (/usr/lib/libm-2.28.so)
...
ABI:2 AX:0x40d440c7 BX:0x40d440c7 CX:0x4d45e5da ...
After:
cpp-inlining 28298 [-01] 54837.342780: 3068085 cycles:pp:
7ffff7c96709 __hypot_finite+0xa9 (/usr/lib/libm-2.28.so)
...
ABI:2 AX:0x0 BX:0x40f56cf6 CX:0x294a3ae7 ...
cpp-inlining 28298 [-01] 54837.344493: 2881929 cycles:pp:
7ffff7c96696 __hypot_finite+0x36 (/usr/lib/libm-2.28.so)
...
ABI:2 AX:0x40d440c7 BX:0x40d440c7 CX:0x4d45e5da ...
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181107093705.16346-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
self pid filter"
Now that we have the "filtered_pids" logic in place, no need to do this
rough filter to avoid the feedback loop from 'perf trace's own syscalls,
revert it.
This reverts commit 7ed71f124284359676b6496ae7db724fee9da753.
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: https://lkml.kernel.org/n/tip-88vh02cnkam0vv5f9vp02o3h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Now that 'perf trace' fills in that "filtered_pids" BPF map, remove the
set of filtered pids used as an example to test that feature.
That feature works like this:
Starting a system wide 'strace' like 'perf trace' augmented session we
noticed that lots of events take place for a pid, which ends up being
the feedback loop of perf trace's syscalls being processed by the
'gnome-terminal' process:
# perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c
0.391 ( 0.002 ms): gnome-terminal/2469 read(fd: 17</dev/ptmx>, buf: 0x564b79f750bc, count: 8176) = 453
0.394 ( 0.001 ms): gnome-terminal/2469 read(fd: 17</dev/ptmx>, buf: 0x564b79f75280, count: 7724) = -1 EAGAIN Resource temporarily unavailable
0.438 ( 0.001 ms): gnome-terminal/2469 read(fd: 4<anon_inode:[eventfd]>, buf: 0x7fffc696aeb0, count: 16) = 8
0.519 ( 0.001 ms): gnome-terminal/2469 read(fd: 17</dev/ptmx>, buf: 0x564b79f75280, count: 7724) = 114
0.522 ( 0.001 ms): gnome-terminal/2469 read(fd: 17</dev/ptmx>, buf: 0x564b79f752f1, count: 7611) = -1 EAGAIN Resource temporarily unavailable
^C
So we can use --filter-pids to get rid of that one, and in this case what is
being used to implement that functionality is that "filtered_pids" BPF map that
the tools/perf/examples/bpf/augmented_raw_syscalls.c created and that 'perf trace'
bpf loader noticed and created a "struct bpf_map" associated that then got populated
by 'perf trace':
# perf trace --filter-pids 2469 -e tools/perf/examples/bpf/augmented_raw_syscalls.c
0.020 ( 0.002 ms): gnome-shell/1663 epoll_pwait(epfd: 12<anon_inode:[eventpoll]>, events: 0x7ffd8f3ef960, maxevents: 32, sigsetsize: 8) = 1
0.025 ( 0.002 ms): gnome-shell/1663 read(fd: 24</dev/input/event4>, buf: 0x560c01bb8240, count: 8112) = 48
0.029 ( 0.001 ms): gnome-shell/1663 read(fd: 24</dev/input/event4>, buf: 0x560c01bb8258, count: 8088) = -1 EAGAIN Resource temporarily unavailable
0.032 ( 0.001 ms): gnome-shell/1663 read(fd: 24</dev/input/event4>, buf: 0x560c01bb8240, count: 8112) = -1 EAGAIN Resource temporarily unavailable
0.040 ( 0.003 ms): gnome-shell/1663 recvmsg(fd: 46<socket:[35893]>, msg: 0x7ffd8f3ef950) = -1 EAGAIN Resource temporarily unavailable
21.529 ( 0.002 ms): gnome-shell/1663 epoll_pwait(epfd: 5<anon_inode:[eventpoll]>, events: 0x7ffd8f3ef960, maxevents: 32, sigsetsize: 8) = 1
21.533 ( 0.004 ms): gnome-shell/1663 recvmsg(fd: 82<socket:[42826]>, msg: 0x7ffd8f3ef7b0, flags: DONTWAIT|CMSG_CLOEXEC) = 236
21.581 ( 0.006 ms): gnome-shell/1663 ioctl(fd: 8</dev/dri/card0>, cmd: DRM_I915_GEM_BUSY, arg: 0x7ffd8f3ef060) = 0
21.605 ( 0.020 ms): gnome-shell/1663 ioctl(fd: 8</dev/dri/card0>, cmd: DRM_I915_GEM_CREATE, arg: 0x7ffd8f3eeea0) = 0
21.626 ( 0.119 ms): gnome-shell/1663 ioctl(fd: 8</dev/dri/card0>, cmd: DRM_I915_GEM_SET_DOMAIN, arg: 0x7ffd8f3eee94) = 0
21.746 ( 0.081 ms): gnome-shell/1663 ioctl(fd: 8</dev/dri/card0>, cmd: DRM_I915_GEM_PWRITE, arg: 0x7ffd8f3eeea0) = 0
^C
Oops, yet another gnome process that is involved with the output that
'perf trace' generates, lets filter that out too:
# perf trace --filter-pids 2469,1663 -e tools/perf/examples/bpf/augmented_raw_syscalls.c
? ( ): wpa_supplicant/1366 ... [continued]: select()) = 0 Timeout
0.006 ( 0.002 ms): wpa_supplicant/1366 clock_gettime(which_clock: BOOTTIME, tp: 0x7fffe5b1e430) = 0
0.011 ( 0.001 ms): wpa_supplicant/1366 clock_gettime(which_clock: BOOTTIME, tp: 0x7fffe5b1e3e0) = 0
0.014 ( 0.001 ms): wpa_supplicant/1366 clock_gettime(which_clock: BOOTTIME, tp: 0x7fffe5b1e430) = 0
? ( ): gmain/1791 ... [continued]: poll()) = 0 Timeout
0.017 ( ): wpa_supplicant/1366 select(n: 6, inp: 0x55646fed3ad0, outp: 0x55646fed3b60, exp: 0x55646fed3bf0, tvp: 0x7fffe5b1e4a0) ...
157.879 ( 0.019 ms): gmain/1791 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: , mask: 16789454) = -1 ENOENT No such file or directory
? ( ): cupsd/1001 ... [continued]: epoll_pwait()) = 0
? ( ): gsd-color/1908 ... [continued]: poll()) = 0 Timeout
499.615 ( ): cupsd/1001 epoll_pwait(epfd: 4<anon_inode:[eventpoll]>, events: 0x557a21166500, maxevents: 4096, timeout: 1000, sigsetsize: 8) ...
586.593 ( 0.004 ms): gsd-color/1908 recvmsg(fd: 3<socket:[38074]>, msg: 0x7ffdef34e800) = -1 EAGAIN Resource temporarily unavailable
? ( ): fwupd/2230 ... [continued]: poll()) = 0 Timeout
? ( ): rtkit-daemon/906 ... [continued]: poll()) = 0 Timeout
? ( ): rtkit-daemon/907 ... [continued]: poll()) = 1
724.603 ( 0.007 ms): rtkit-daemon/907 read(fd: 6<anon_inode:[eventfd]>, buf: 0x7f05ff768d08, count: 8) = 8
? ( ): ssh/5461 ... [continued]: select()) = 1
810.431 ( 0.002 ms): ssh/5461 clock_gettime(which_clock: BOOTTIME, tp: 0x7ffd7f39f870) = 0
^C
Several syscall exit events for syscalls in flight when 'perf trace' started, etc. Saner :-)
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: https://lkml.kernel.org/n/tip-c3tu5yg204p5mvr9kvwew07n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
This makes the augmented_syscalls support the --filter-pids and
auto-filtered feedback loop pids just like when working without BPF,
i.e. with just raw_syscalls:sys_{enter,exit} and tracepoint filters.
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: https://lkml.kernel.org/n/tip-zc5n453sxxm0tz1zfwwelyti@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Lookup for the first map named "filtered_pids" and, if augmenting
syscalls, i.e. if a BPF event is present and the
"__augmented_syscalls__" is present, then fill in that map with the pids
to filter, be it feedback loop ones (perf trace's pid, its father if it
is "sshd", more auto-filtered in the future) or the ones explicitely
stated in the tool command line via --filter-pids.
The code to actually fill in the map comes next.
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: https://lkml.kernel.org/n/tip-rhzytmw7qpe6lqyjxi1ded9t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
As we'll need that name for a new function to set filters for both
tracepoints and BPF maps for filtering pids.
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: https://lkml.kernel.org/n/tip-mdkck6hf3fnd21rz2766280q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
To better reflect that this is a tracepoint filter, as opposed, for
instance to map based BPF filters.
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: https://lkml.kernel.org/n/tip-9138svli6ddcphrr3ymy9oy3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Just to test filtering a bunch of pids, now its time to go and get that
hooked up in 'perf trace', right after we load the bpf program, if we
find a "pids_filtered" map defined, we'll populate it with the filtered
pids.
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: https://lkml.kernel.org/n/tip-1i9s27wqqdhafk3fappow84x@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
filter
When testing system wide tracing without filtering the syscalls called
by 'perf trace' itself we get into a feedback loop, drop for now those
two syscalls, that are the ones that 'perf trace' does in its loop for
writing the syscalls it intercepts, to help with testing till we get
that filtering in place.
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: https://lkml.kernel.org/n/tip-rkbu536af66dbsfx51sr8yof@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Will be used in the augmented_raw_syscalls.c to implement 'perf trace
--filter-pids'.
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: https://lkml.kernel.org/n/tip-9sybmz4vchlbpqwx2am13h9e@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Starting with a helper for a basic pid_map(), a hash using a pid as a
key.
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: https://lkml.kernel.org/n/tip-gdwvq53wltvq6b3g5tdmh0cw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Leftover from when we started augmented_raw_syscalls.c from
tools/perf/examples/bpf/augmented_syscalls.
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>
Fixes: e58a0322dbac ("perf examples bpf: Start augmenting raw_syscalls:sys_{start,exit}")
Link: https://lkml.kernel.org/n/tip-pmts9ls2skh8n3zisb4txudd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Just to show where we'll hook pid based filters, and what we use to
obtain the current pid, using a BPF getpid() equivalent.
Now we need to remove that hardcoded PID with a BPF hash map, so that we
start by filtering 'perf trace's own PID, implement the --filter-pid
functionality, etc.
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: https://lkml.kernel.org/n/tip-oshrcgcekiyhd0whwisxfvtv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Start with a getpid() function wrapping BPF_FUNC_get_current_pid_tgid,
idea is to mimic the system headers.
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: https://lkml.kernel.org/n/tip-zo8hv22onidep7tm785dzxfk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Introduced in:
ad8c0eaa0a41 ("tty/serial_core: add ISO7816 infrastructure")
Now 'perf trace' will be able to pretty-print the 'cmd' ioctl arg when
used in capable systems with software emitting those commands.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-7bds48dhckfnleie08mit314@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
When reporting on 'record' server we try to retrieve/use the mnt
namespace of the profiled tasks. We use following API with cookie to
hold the return namespace, roughly:
nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc)
setns(newns, 0);
...
new ns related open..
...
nsinfo__mountns_exit(struct nscookie *nc)
setns(nc->oldns)
Once finished we setns to old namespace, which also sets the current
working directory (cwd) to "/", trashing the cwd we had.
This is mostly fine, because we use absolute paths almost everywhere,
but it screws up 'perf diff':
# perf diff
failed to open perf.data: No such file or directory (try 'perf record' first)
...
Adding the current working directory to be part of the cookie and
restoring it in the nsinfo__mountns_exit call.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: 843ff37bb59e ("perf symbols: Find symbols in different mount namespace")
Link: http://lkml.kernel.org/r/20181101170001.30019-1-jolsa@kernel.org
[ No need to check for NULL args for free(), use zfree() for struct members ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
As the namespace support code will use this, which is not available in
some non _GNU_SOURCE libraries such as Android's bionic used in my
container build tests (r12b and r15c at the moment).
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: https://lkml.kernel.org/n/tip-x56ypm940pwclwu45d7jfj47@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Adam reported a record command crash for simple session like:
$ perf record -e cpu-clock ls
with following backtrace:
Program received signal SIGSEGV, Segmentation fault.
3543 ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
(gdb) bt
#0 perf_event__synthesize_event_update_unit
#1 0x000000000051e469 in perf_event__synthesize_extra_attr
#2 0x00000000004445cb in record__synthesize
#3 0x0000000000444bc5 in __cmd_record
...
We synthesize an update event that needs to touch the evsel id array,
which is not defined at that time. Fix this by forcing the id allocation
for events with their unit defined.
Reflecting possible read_format ID bit in the attr tests.
Reported-by: Yongxin Liu <yongxin.liu@outlook.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adam Lee <leeadamrobert@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201477
Fixes: bfd8f72c2778 ("perf record: Synthesize unit/scale/... in event update")
Link: http://lkml.kernel.org/r/20181112130012.5424-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/urgent improvements and fixes from Arnaldo Carvalho de Melo:
Intel PT SQL viewer: (Adrian Hunter)
- Fall back to /usr/local/lib/libxed.so
- Add Selected branches report
- Add help window
- Fix table find when table re-ordered
Intel PT debug log (Adrian Hunter)
- Add more event information
- Add MTC and CYC timestamps
perf record: (Andi Kleen)
- Support weak groups, just like with 'perf stat'
perf trace: (Arnaldo Carvalho de Melo)
- Start augmenting raw_syscalls:{sys_enter,sys_exit}: goal is to have a
generic, arch independent eBPF kernel component that is programmed with
syscall table details, what to copy, how many bytes, pid, arg filters from the
userspace via eBPF maps by the 'perf trace' tool that continues to use all its
argument beautifiers, just taking advantage of the extra pointer contents.
JVMTI: (Gustavo Romero)
- Fix undefined symbol scnprintf in libperf-jvmti.so
perf top: (Jin Yao)
- Display the LBR stats in callchain entries
perf stat: (Thomas Richter)
- Handle different PMU names with common prefix
arm64: Will (Deacon)
- Fix arm64 tools build failure wrt smp_load_{acquire,release}.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Andi reported following malfunction:
# perf record -e '{ref-cycles,cycles}:S' -a sleep 1
# perf script
non matching sample_id_all
That's because we disable sample_id_all bit for non-sampling group
members. We can't do that, because it needs to be the same over the
whole event list. This patch keeps it untouched again.
Reported-by: Andi Kleen <andi@firstfloor.org>
Tested-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180923150420.27327-1-jolsa@kernel.org
Fixes: e9add8bac6c6 ("perf evsel: Disable write_backward for leader sampling group events")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
This is the commit that porting the perf for nds32.
1.Raw event:
The raw events start with 'r'.
Usage:
perf stat -e rXYZ ./app
X: the index of performance counter.
YZ: the index(convert to hexdecimal) of events
Example:
'perf stat -e r101 ./app' means the counter 1 will count the instruction
event.
The index of counter and events can be found in
"Andes System Privilege Architecture Version 3 Manual".
Or you can perform the 'perf list' to find the symbolic name of raw events.
2.Perf mmap2:
Fix unexpected perf mmap2() page fault
When the mmap2() called by perf application,
you will encounter such condition:"failed to write."
With return value -EFAULT
This is due to the page fault caused by "reading" buffer
from the mapped legal address region to write to the descriptor.
The page_fault handler will get a VM_FAULT_SIGBUS return value,
which should not happens here.(Due to this is a read request.)
You can refer to kernel/events/core.c:perf_mmap_fault(...)
If "(vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))" is evaluated
as true, you will get VM_FAULT_SIGBUS as return value.
However, this is not an write request. The flags which indicated
why the page fault happens is wrong.
Furthermore, NDS32 SPAv3 is not able to detect it is read or write.
It only know either it is instruction fetch or data access.
Therefore, by removing the wrong flag assignment(actually, the hardware
is not able to show the reason), we can fix this bug.
3.Perf multiple events map to same counter.
When there are multiple events map to the same counter, the counter
counts inaccurately. This is because each counter only counts one event
in the same time.
So when there are multiple events map to same counter, they have to take
turns in each context.
There are two solution:
1. Print the error message when multiple events map to the same counter.
But print the error message would let the program hang in loop. The ltp
(linux test program) would be failed when the program hang in loop.
2. Don't print the error message, the ltp would pass. But the user need to
have the knowledge that don't count the events which map to the same
counter, or the user will get the inaccurate results.
We choose method 2 for the solution
Signed-off-by: Nickhu <nickhu@andestech.com>
Acked-by: Greentime Hu <greentime@andestech.com>
Signed-off-by: Greentime Hu <greentime@andestech.com>
|
|
Currently jvmti agent can not be used because function scnprintf is not
present in the agent libperf-jvmti.so. As a result the JVM when using
such agent to record JITed code profiling information will fail on
looking up scnprintf:
java: symbol lookup error: lib/libperf-jvmti.so: undefined symbol: scnprintf
This commit fixes that by reverting to the use of snprintf, that can be
looked up, instead of scnprintf, adding a proper check for the returned
value in order to print a better error message when the jitdump file
pathname is too long. Checking the returned value also helps to comply
with some recent gcc versions, like gcc8, which will fail due to
truncated writing checks related to the -Werror=format-truncation= flag.
Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
LPU-Reference: 1541117601-18937-2-git-send-email-gromero@linux.vnet.ibm.com
Link: https://lkml.kernel.org/n/tip-mvpxxxy7wnzaj74cq75muw3f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Guenter reported that using ARCH=x86_64 to build perf has regressed:
$ make -C tools/perf O=/tmp/build/perf ARCH=x86_64
make: Entering directory '/home/acme/git/perf/tools/perf'
BUILD: Doing 'make -j4' parallel build
HOSTCC /tmp/build/perf/fixdep.o
HOSTLD /tmp/build/perf/fixdep-in.o
LINK /tmp/build/perf/fixdep
Auto-detecting system features:
... dwarf: [ on ]
<SNIP>
... bpf: [ on ]
GEN /tmp/build/perf/common-cmds.h
make[2]: *** No rule to make target '/home/acme/git/perf/tools/arch/x86_64/include/uapi/asm//mman.h', needed by '/tmp/build/perf/trace/beauty/generated/mmap_flags_array.c'. Stop.
make[2]: *** Waiting for unfinished jobs....
PERF_VERSION = 4.19.gf6c23e3
make[1]: *** [Makefile.perf:207: sub-make] Error 2
make: *** [Makefile:70: all] Error 2
make: Leaving directory '/home/acme/git/perf/tools/perf'
$
This is because we must use $(SRCARCH) where we were using $(ARCH), so
that, just like the top level Makefile, we get this done:
# Additional ARCH settings for x86
ifeq ($(ARCH),i386)
SRCARCH := x86
endif
ifeq ($(ARCH),x86_64)
SRCARCH := x86
endif
Which is done in tools/scripts/Makefile.arch, so switch to use
$(SRCARCH).
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.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>
Fixes: fbd7458db757 ("perf beauty: Wire up the mmap flags table generator to the Makefile")
Link: https://lkml.kernel.org/r/20181105184612.GD7077@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
One cause of decoding errors is un-synchronized side-band data.
Timestamps are needed to debug such cases. TSC packet timestamps are
logged. Log also MTC and CYC timestamps.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/20181105073505.8129-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
More event information is useful for debugging, especially MMAP events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/20181105073505.8129-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
re-ordered
Table rows can be re-ordered by selecting a column to sort by. After
re-ordering, the "find" operation was highlighting the wrong row, fix
it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a window to display help. It is also possible to display the help
only, by using the option "--help-only" instead of a database name.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fetching data from the database can be slow. Add a report that provides
the ability to select a subset of branches.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
/usr/local/lib/libxed.so
Fall back to /usr/local/lib/libxed.so to cater for distributions that do
not have /usr/local/lib in the library path by default.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
'perf report' has supported the displaying of LBR stats (such as cycles,
predicted%) in callchain entry.
For example:
$ perf report --branch-history --stdio
--1.01%--intel_idle mwait.h:29
intel_idle cpufeature.h:164 (cycles:5)
intel_idle cpufeature.h:164 (predicted:76.4%)
intel_idle mwait.h:102 (cycles:41)
intel_idle current.h:15
While 'perf top' doesn't support that.
For example:
$ perf top -a -b --call-graph branch
- 13.86% 0.23% [kernel] [k] __x86_indirect_thunk_rax
- 13.65% __x86_indirect_thunk_rax
+ 1.69% do_syscall_64
+ 1.68% do_select
+ 1.41% ktime_get
+ 0.70% __schedule
+ 0.62% do_sys_poll
0.58% __x86_indirect_thunk_rax
Actually it's very easy to enable this feature in 'perf top'.
With this patch, the result is:
$ perf top -a -b --call-graph branch
$ - 13.58% 0.00% [kernel] [k] __x86_indirect_thunk_rax
$ - 13.57% __x86_indirect_thunk_rax (predicted:93.9%)
$ + 1.78% do_select (cycles:2)
$ + 1.68% perf_pmu_disable.part.99 (cycles:1)
$ + 1.45% ___sys_recvmsg (cycles:25)
$ + 0.81% unix_stream_sendmsg (cycles:18)
$ + 0.80% ktime_get (cycles:400)
$ 0.58% pick_next_task_fair (cycles:47)
$ + 0.56% i915_request_retire (cycles:2)
$ + 0.52% do_sys_poll (cycles:4)
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
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: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1540983995-20462-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
On s390 the CPU Measurement Facility for counters now supports
2 PMUs named cpum_cf (CPU Measurement Facility for counters) and
cpum_cf_diag (CPU Measurement Facility for diagnostic counters)
for one and the same CPU.
Running command
[root@s35lp76 perf]# ./perf stat -e tx_c_tend \
-- ~/mytests/cf-tx-events 1
Measuring transactions
TX_C_TABORT_NO_SPECIAL: 0 expected:0
TX_C_TABORT_SPECIAL: 0 expected:0
TX_C_TEND: 1 expected:1
TX_NC_TABORT: 11 expected:11
TX_NC_TEND: 1 expected:1
Performance counter stats for '/root/mytests/cf-tx-events 1':
2 tx_c_tend
0.002120091 seconds time elapsed
0.000121000 seconds user
0.002127000 seconds sys
[root@s35lp76 perf]#
displays output which is unexpected (and wrong):
2 tx_c_tend
The test program definitely triggers only one transaction, as shown
in line 'TX_C_TEND: 1 expected:1'.
This is caused by the following call sequence:
pmu_lookup() scans and installs a PMU.
+--> pmu_aliases() parses all aliases in directory
.../<pmu-name>/events/* which are file names.
+--> pmu_aliases_parse() Read each file in directory and create
an new alias entry. This is done with
+--> perf_pmu__new_alias() and
+--> __perf_pmu__new_alias() which also check for
identical alias names.
After pmu_aliases() returns, a complete list of event names
for this pmu has been created. Now function
pmu_add_cpu_aliases() is called to add the events listed in the json
| files to the alias list of the cpu.
+--> perf_pmu__find_map() Returns a pointer to the json events.
Now function pmu_add_cpu_aliases() scans through all events listed
in the JSON files for this CPU.
Each json event pmu name is compared with the current PMU being
built up and if they mismatch, the json event is added to the
current PMUs alias list.
To avoid duplicate entries the following comparison is done:
if (!is_arm_pmu_core(name)) {
pname = pe->pmu ? pe->pmu : "cpu";
if (strncmp(pname, name, strlen(pname)))
continue;
}
The culprit is the strncmp() function.
Using current s390 PMU naming, the first PMU is 'cpum_cf'
and a long list of events is added, among them 'tx_c_tend'
When the second PMU named 'cpum_cf_diag' is added, only one event
named 'CF_DIAG' is added by the pmu_aliases() function.
Now function pmu_add_cpu_aliases() is invoked for PMU 'cpum_cf_diag'.
Since the CPUID string is the same for both PMUs, json file events
for PMU named 'cpum_cf' are added to the PMU 'cpm_cf_diag'
This happens because the strncmp() actually compares:
strncmp("cpum_cf", "cpum_cf_diag", 6);
The first parameter is the pmu name taken from the event in
the json file. The second parameter is the pmu name of the PMU
currently being built.
They are different, but the length of the compare only tests the
common prefix and this returns 0(true) when it should return false.
Now all events for PMU cpum_cf are added to the alias list for pmu
cpum_cf_diag.
Later on in function parse_events_add_pmu() the event 'tx_c_end' is
searched in all available PMUs and found twice, adding it two
times to the evsel_list global variable which is the root
of all events. This results in a counter value of 2 instead
of 1.
Output with this patch:
[root@s35lp76 perf]# ./perf stat -e tx_c_tend \
-- ~/mytests/cf-tx-events 1
Measuring transactions
TX_C_TABORT_NO_SPECIAL: 0 expected:0
TX_C_TABORT_SPECIAL: 0 expected:0
TX_C_TEND: 1 expected:1
TX_NC_TABORT: 11 expected:11
TX_NC_TEND: 1 expected:1
Performance counter stats for '/root/mytests/cf-tx-events 1':
1 tx_c_tend
0.001815365 seconds time elapsed
0.000123000 seconds user
0.001756000 seconds sys
[root@s35lp76 perf]#
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Sebastien Boisvert <sboisvert@gydle.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: stable@vger.kernel.org
Fixes: 292c34c10249 ("perf pmu: Fix core PMU alias list for X86 platform")
Link: http://lkml.kernel.org/r/20181023151616.78193-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Implement a weak group fallback for 'perf record', similar to the
existing 'perf stat' support. This allows to use groups that might be
longer than the available counters without failing.
Before:
$ perf record -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}' -a sleep 1
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
/bin/dmesg | grep -i perf may provide additional information.
After:
$ ./perf record -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}:W' -a sleep 1
WARNING: No sample_id_all support, falling back to unordered processing
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 8.136 MB perf.data (134069 samples) ]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181001195927.14211-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
