++ b/tools/perf/testsuite/common/init.sh
@@ -0,0 +1,50 @@
+#
+# init.sh
+# Author: Michael Petlan <mpet...@redhat.com>
+#
+# Description:
+#
+# This file should be used for initialization of basic functions
+# for checking, reporting results etc.
+#
+#
+
?
Michael
Michael Petlan (3):
tools/perf/testsuite: Init commit
tools/perf/testsuite: Adding a skeleton for future testcases
tools/perf/testsuite: Adding a set of testcases for perf-stat
tools/perf/testsuite/base_skeleton/cleanup.sh | 16 +++
tools/perf/testsuite/base_skeleton/settings.sh
100755
index 000..d02b8ca
--- /dev/null
+++ b/tools/perf/testsuite/base_stat/cleanup.sh
@@ -0,0 +1,20 @@
+#
+# cleanup.sh of perf stat test
+# Author: Michael Petlan <mpet...@redhat.com>
+#
+# Description:
+# FIXME
+#
+#
+
+. ../common/settings.sh
+. ../
of SKELETON test
+# Author: Michael Petlan <mpet...@redhat.com>
+#
+# Description:
+# FIXME
+#
+#
+
+. ../common/settings.sh
+. ../common/patterns.sh
+. ../common/init.sh
+. ./settings.sh
+
+print_overall_results 0
+exit 0
diff --git a/tools/perf/testsuite/base_skeleton/settings
the
full path when necessary.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/util/annotate.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0fc8d7a..cbf0fdb 100644
--- a/tools/perf/util/annotate.c
+++ b/tool
into the annotating mechanism.
This patch addresses it and enables perf-annotate to print the full
paths as well.
Tested with latest git version.
Regards,
Michael
Michael Petlan (1):
perf annotate: Support of full source file paths for srcline fix
tools/perf/util/annotate.c | 1 +
1 file
On Thu, 2015-11-12 at 10:02 -0500, Yuanfang Chen wrote:
> And the case can be reduced to
>
> perf stat -e \{r1000248,r148\} -- sleep 1
>
> Performance counter stats for 'sleep 1':
>
> 7008 r1000248
> r148
>
>1.001885804 seconds time elapsed
>
perf stat -e
On Tue, 2015-11-03 at 12:45 -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Nov 03, 2015 at 03:24:43AM +, 平松雅巳 / HIRAMATU，MASAMI escreveu:
> > Hi Michael,
> >
> > From: Michael Petlan [mailto:mpet...@redhat.com]
> > >
> > >Hi Masami Hiramatsu,
> >
iramatsu" <masami.hiramatsu...@hitachi.com>
> Para: "Michael Petlan" <mpet...@redhat.com>, linux-perf-users@vger.kernel.org
> CC: "Arnaldo Carvalho de Melo" <a...@kernel.org>
> Enviados: Jueves, 22 de Octubre 2015 14:16:15
> Asunto: [
On Wed, 2015-09-02 at 16:43 +, Joakim Tjernlund wrote:
> on PPC I do:
> # > perf record -a /root/a.out
>
> then
> #> perf report -v
> ...
> 50.36%a.out /root/a.out
> 0x2c4 d [.] main
>
> compare the address 0x2c4 with
> #> nm -a
$?
41
After:
# perf buildid-list -k
39356d74e96e02346fe0ec1f3f162b6c522bac62
# echo $?
0
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/builtin-buildid-list.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/b
of course x86_64.
In the current state, it searches for the "testsuite" directory in
`pwd`, when not found, the testcase is skipped. --> Maybe we should
think about some packaging, standard locations or whatever.
Thoughts?
Regards,
Michael
Michael Petlan (2):
per
the perf's directory).
In case the testsuite is not found, the testcase is skipped. If this is
not the desired behaviour, some packaging will be needed.
Usage:
./perf test suite
or
./perf test suite -v
(for the verbose output)
Signed-off-by: Michael Petlan <mpet...@redhat.
On Sun, 2015-12-06 at 16:53 +0100, Jiri Olsa wrote:
> I can't get this applied on latest acme's perf/core
>
Hi, I send patches that apply to latest Linus' tree:
https://github.com/torvalds/linux.git
Should I use some different tree? Arnaldo's? What is the URL
of the proper tree I should send
On Thu, 2015-12-03 at 14:26 +, Patrick Agrain wrote:
> Hello,
>
> perf record no samples in perf.data on an IBM x3250M5.
> perf stat is OK (in that way that it displays some stats).
1) Which stats are displayed? Do the basic events from "perf list hw"
work?
perf stat -e cycles -- sleep 1
vent]
major-faults [Software event]
minor-faults [Software event]
page-faults OR faults [Software event]
task-clock [Software event]
Signed-off-by: Michael Petlan
check_*.pl
- various scripts for checking output
- might be extended by some more advanced checking
tools and techniques
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
.../testsuite/common/check_all_lines_matched.pl| 38 +++
.../
the perf's directory).
In case the testsuite is not found, the testcase is skipped. If this is
not the desired behaviour, some packaging will be needed.
Usage:
./perf test suite
or
./perf test suite -v
(for the verbose output)
Signed-off-by: Michael Petlan <mpet...@redhat.
first.
Example:
cd testsuite/base_annotate
./setup.sh
./test_basic.sh
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_annotate/cleanup.sh | 22 +++
.../perf/testsuite/base_annotate/examples/Makefile | 13 ++
tools/perf/testsuite/base_annotate/ex
This commit adds tests for perf probe tool. Some of the tests are based
on Masami Hiramatsu's perf-probe tests.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_probe/cleanup.sh | 22 ++
tools/perf/testsuite/base_probe/examples/Makefile
This commit adds tests for perf buildid-list tool. It is a placeholder
for future perf buildid-cache tests as well.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_buildid/cleanup.sh | 20 ++
tools/perf/testsuite/base_buildid/settings.sh
This commit adds tests for perf trace tools.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_trace/cleanup.sh | 19 +++
tools/perf/testsuite/base_trace/settings.sh| 10 ++
tools/perf/testsuite/base_trace/setup.sh | 16 +++
..
This commit adds tests for perf stat tool.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_stat/cleanup.sh | 21 +++
tools/perf/testsuite/base_stat/settings.sh | 10
tools/perf/testsuite/base_stat/test_basic.sh
This commit adds tests for perf list tool.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_list/cleanup.sh| 19 ++
tools/perf/testsuite/base_list/settings.sh | 15 +
tools/perf/testsuite/base_list/setup.sh | 20 +++
tools/perf/tes
This commit adds tests for perf report tool.
Signed-off-by: Michael Petlan <mpet...@redhat.com>
---
tools/perf/testsuite/base_report/cleanup.sh| 22 +++
tools/perf/testsuite/base_report/settings.sh | 15 ++
tools/perf/testsuite/base_report/setup.sh
Hi,
so I have splitted the suite into more commits that are related to
the logical parts of it. These patches should apply to the latest
Arnaldo's tree on top of perf/core branch.
I hope it works now.
Thanks for reviewing.
Michael
Michael Petlan (9):
perf test: Adding an entry
On Tue, 2015-12-15 at 13:03 +0100, Jiri Olsa wrote:
> On Mon, Dec 07, 2015 at 07:52:52PM +0100, Michael Petlan wrote:
> > Hi,
> >
> > so I have splitted the suite into more commits that are related to
> > the logical parts of it. These patches should apply to the lates
On Wed, 2015-11-25 at 11:43 -0300, Arnaldo Carvalho de Melo wrote:
> Em Wed, Nov 25, 2015 at 02:33:43PM +0100, Jiri Olsa escreveu:
> Looking at it, but how do you envision the workflow when/if this is
> merged into the kernel?
>
> Nowadays, I have to do:
>
> make -C tools/perf build-test
>
>
972c1edab5bdc06cc224af45d510af662a3c6972
#
Signed-off-by: Michael Petlan <mpet...@redhat.com>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu...@hitachi.com>
---
tools/perf/util/build-id.c |
when the function is called, no one cares about
the return value.
Michael
Michael Petlan (1):
perf buildid-list: Show running kernel build id fix
tools/perf/util/build-id.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--
To unsubscribe from this list: send the line "unsubs
On Tue, 2015-11-24 at 12:08 -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Nov 24, 2015 at 12:18:22PM +0100, Michael Petlan escreveu:
> > I have been playing with perf-probe tool and I found out that some bogus
> > values of a function argument are obtained by perf-recor
On Tue, 2015-11-24 at 16:16 -0300, Arnaldo Carvalho de Melo wrote:
>
> > I have met this when writing new tests for perf-probe into the testsuite
> > I had been speaking about some time ago [1]. But if needed, I may add it
> > as a perf-test entry as you wish.
>
> Please :-)
>
Hi,
after a
Hi *,
I have been playing with perf-probe tool and I found out that some bogus
values of a function argument are obtained by perf-record.
How to reproduce:
gcc -O0 -g -o dummy dummy.c
perf probe -x ./dummy --add 'isprime a'
perf record -e probe_dummy:isprime ./dummy
perf script
The actual
33 matches
Mail list logo
