* Re: gprofng patch to review
[not found] <603d55a9-e789-11e7-2cf0-1fde08874cdf@oracle.com>
@ 2022-11-09 18:50 ` Vladimir Mezentsev
2022-11-14 11:22 ` Metzger, Markus T
0 siblings, 1 reply; 6+ messages in thread
From: Vladimir Mezentsev @ 2022-11-09 18:50 UTC (permalink / raw)
To: markus.t.metzger, binutils; +Cc: Kurt Goebel
On 11/9/22 07:00, Kurt Goebel wrote:
>
>
> https://sourceware.org/pipermail/binutils/2022-November/124238.html
Hi Markus,
It looks like you sent patch for review to the gdb alias.
I am only in binutils@sourceware.org.
See my comments below.
[PATCH 1/2] gprofng: make cpu identification available to others
Markus Metzger markus.t.metzger@intel.com
Tue Nov 8 05:45:29 GMT 2022
Previous message (by thread): [PATCH] x86: Correct wrong comments in
vex_w_table
Next message (by thread): [PATCH 2/2] gdb, btrace: use cpuident.h to
implement btrace_this_cpu
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
I ran gprofng.display/display.exp on Fedora 36 x86-64 and I got
UNSUPPORTED: jsynprog
It is expected. You built gprofng without java profiling support.
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
PASS: synprog
PASS: synprog
Usually, when synprog passes and mttest fails, it means that
pthread_create interposition is broken in libgp-collector.so.
In any case, it is not result of your patch.
I never run gprofng on Fedora 36.
Please create a bug against gprofng and describe how you configure your
build.
with and without this patch.
---
gprofng/common/hwcdrv.c | 2 +-
gprofng/common/cpuid.c => include/cpuident.h | 17 +++++++++++++----
2 files changed, 14 insertions(+), 5 deletions(-)
rename gprofng/common/cpuid.c => include/cpuident.h (96%)
diff --git a/gprofng/common/hwcdrv.c b/gprofng/common/hwcdrv.c
index 03c3a71c8e2..115638aa623 100644
--- a/gprofng/common/hwcdrv.c
+++ b/gprofng/common/hwcdrv.c
@@ -32,7 +32,7 @@
/* macros */
#define IS_GLOBAL /* Mark global symbols */
-#include "cpuid.c" /* ftns for identifying a chip */
+#include "cpuident.h" /* ftns for identifying a chip */
static hdrv_pcbe_api_t hdrv_pcbe_core_api;
static hdrv_pcbe_api_t hdrv_pcbe_opteron_api;
diff --git a/gprofng/common/cpuid.c b/include/cpuident.h
similarity index 96%
rename from gprofng/common/cpuid.c
rename to include/cpuident.h
index 211e09aa8ac..7ab6fc1f2b1 100644
--- a/gprofng/common/cpuid.c
+++ b/include/cpuident.h
@@ -18,6 +18,11 @@
Foundation, 51 Franklin Street - Fifth Floor, Boston,
MA 02110-1301, USA. */
+#ifndef _CPUIDENT_H
+#define _CPUIDENT_H
+
+#include <stdint.h>
+
#if defined(__i386__) || defined(__x86_64)
#include <cpuid.h> /* GCC-provided */
#elif defined(__aarch64__)
@@ -85,7 +90,7 @@ typedef struct
#if defined(__i386__) || defined(__x86_64)
-static uint_t
+static unsigned int
cpuid_vendorstr_to_vendorcode (char *vendorstr)
{
if (strcmp (vendorstr, X86_VENDORSTR_Intel) == 0)
@@ -101,8 +106,10 @@ my_cpuid (unsigned int op, cpuid_regs_t *regs)
{
regs->eax = regs->ebx = regs->ecx = regs->edx = 0;
int ret = __get_cpuid (op, ®s->eax, ®s->ebx, ®s->ecx,
®s->edx);
+#ifdef DBG_LT1
TprintfT (DBG_LT1, "my_cpuid: __get_cpuid(0x%x, 0x%x, 0x%x, 0x%x,
0x%x) returns %d\n",
op, regs->eax, regs->ebx, regs->ecx, regs->edx, ret);
+#endif
I suggest to just remove TprintfT. This debug output is currently not
used by anyone.
Thanks for fixing this, and please check it in.
-Vladimir
return ret;
}
#endif
@@ -184,20 +191,22 @@ get_cpuid_info ()
return cpi;
}
-static inline uint_t
+static inline unsigned int
cpuid_getvendor ()
{
return get_cpuid_info ()->cpi_vendor;
}
-static inline uint_t
+static inline unsigned int
cpuid_getfamily ()
{
return get_cpuid_info ()->cpi_family;
}
-static inline uint_t
+static inline unsigned int
cpuid_getmodel ()
{
return get_cpuid_info ()->cpi_model;
}
+
+#endif /* _CPUIDENT_H */
--
2.37.3
^ permalink raw reply [flat|nested] 6+ messages in thread
* RE: gprofng patch to review
2022-11-09 18:50 ` gprofng patch to review Vladimir Mezentsev
@ 2022-11-14 11:22 ` Metzger, Markus T
2022-11-14 18:38 ` Vladimir Mezentsev
0 siblings, 1 reply; 6+ messages in thread
From: Metzger, Markus T @ 2022-11-14 11:22 UTC (permalink / raw)
To: Vladimir Mezentsev; +Cc: Kurt Goebel, gdb-patches, binutils
[-- Attachment #1: Type: text/plain, Size: 2266 bytes --]
Hello Vladimir,
>It looks like you sent patch for review to the gdb alias.
>I am only in binutils@sourceware.org.
I had sent the patches to both gdb-patches@sourceware.org
and binutils@sourceware.org.
>I ran gprofng.display/display.exp on Fedora 36 x86-64 and I got
>
> UNSUPPORTED: jsynprog
>
>It is expected. You built gprofng without java profiling support.
>
>
> ERROR: comparison of results in mttest failed
> UNRESOLVED: mttest
> ERROR: comparison of results in mttest failed
>
> UNRESOLVED: mttest
> PASS: synprog
> PASS: synprog
>
>
>Usually, when synprog passes and mttest fails, it means that
>pthread_create interposition is broken in libgp-collector.so.
>In any case, it is not result of your patch.
>I never run gprofng on Fedora 36.
>Please create a bug against gprofng and describe how you configure your
>build.
All I did was:
$ mkdir /tmp/binutils
$ cd /tmp/binutils
$ /path/to/repo/configure
$ make
$ cd gprofng
$ make check
I tried again and this time I get
ERROR: comparison of results in jsynprog failed
UNRESOLVED: jsynprog
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
PASS: synprog
PASS: synprog
already without this patch. I attach the .log in case it helps to analyze this.
>+#ifdef DBG_LT1
> TprintfT (DBG_LT1, "my_cpuid: __get_cpuid(0x%x, 0x%x, 0x%x, 0x%x,
>0x%x) returns %d\n",
> op, regs->eax, regs->ebx, regs->ecx, regs->edx, ret);
>+#endif
>
>
>
>I suggest to just remove TprintfT. This debug output is currently not
>used by anyone.
There are other Tprintf (no trailing T) in the ARM part. I didn't touch those
as it didn't fail on my box and I wouldn't be able to test the changes.
Do you want me to remove those, too? Untested.
thanks,
markus.
Intel Deutschland GmbH
Registered Address: Am Campeon 10, 85579 Neubiberg, Germany
Tel: +49 89 99 8853-0, www.intel.de <http://www.intel.de>
Managing Directors: Christin Eisenschmid, Sharon Heck, Tiffany Doon Silva
Chairperson of the Supervisory Board: Nicole Lau
Registered Office: Munich
Commercial Register: Amtsgericht Muenchen HRB 186928
[-- Attachment #2: gprofng.log --]
[-- Type: application/octet-stream, Size: 23573 bytes --]
Test run by mmetzger on Mon Nov 14 12:04:23 2022
Native configuration is x86_64-pc-linux-gnu
=== gprofng tests ===
Schedule of variations:
unix
Running target unix
Using /usr/share/dejagnu/baseboards/unix.exp as board description file for target.
Using /usr/share/dejagnu/config/unix.exp as generic interface file for target.
Using /users/mmetzger/gdb/git/gprofng/testsuite/config/default.exp as tool-and-target-specific interface file.
Executing on host: sh -c "rm -rf tmpdir; mkdir -p tmpdir" (timeout = 300)
spawn -ignore SIGHUP sh -c rm -rf tmpdir; mkdir -p tmpdir
Executing on host: sh -c "mkdir -p lib; rm -f lib/gprofng; ln -s ../libcollector/.libs lib/gprofng" (timeout = 300)
spawn -ignore SIGHUP sh -c mkdir -p lib; rm -f lib/gprofng; ln -s ../libcollector/.libs lib/gprofng
Executing on host: sh -c "rm -f bin; ln -s src bin" (timeout = 300)
spawn -ignore SIGHUP sh -c rm -f bin; ln -s src bin
Running /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/display.exp ...
create dir: tmpdir/jsynprog.-g-Wall,-pon-jon
mkdir -p tmpdir/jsynprog.-g-Wall,-pon-jon
cd tmpdir/jsynprog.-g-Wall,-pon-jon && make -f /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Makefile srcdir="/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog" builddir="/tmp/binutils/gprofng" VPATH="jsynprog" CC="gcc" CFLAGS="-g -Wall" LDFLAGS="" DISPLAY_FLAGS="-metrics i.totalcpu -func" COLLECT_FLAGS="-p on -j on" GPROFNG="/tmp/binutils/gprofng/src/gprofng" MAKE="make" all
comparison of results in jsynprog failed:
make[3]: Entering directory '/tmp/binutils/gprofng/tmpdir/jsynprog.-g-Wall,-pon-jon'
---- Build: libcloop.so -----
gcc -I/usr/lib/jvm/java-17-openjdk-17.0.5.0.8-2.fc36.x86_64/include -I/usr/lib/jvm/java-17-openjdk-17.0.5.0.8-2.fc36.x86_64/include/linux -fpic -shared -o libcloop.so /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/../mttest/gethrtime.c /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/cloop.cc
---- Build: jsynprog.class -----
/usr/bin/javac -d . /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Intface.java /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Routine.java /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Sub_Routine.java /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/jsynprog.java /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Launcher.java
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Routine.java:57: warning: [removal] Integer(int) in Integer has been deprecated and marked for removal
g_int[k]=new Integer (x);
^
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Routine.java:167: warning: [removal] Integer(int) in Integer has been deprecated and marked for removal
x[i] = new Integer(i);
^
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/Routine.java:193: warning: [removal] Integer(int) in Integer has been deprecated and marked for removal
v1.add(new Integer(i));
^
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/jsynprog.java:56: warning: [removal] Integer(int) in Integer has been deprecated and marked for removal
ni = new Integer (rtn.add_int(scale));
^
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/jsynprog.java:61: warning: [removal] Double(double) in Double has been deprecated and marked for removal
Double nd = new Double(rtn.add_double(scale));
^
/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/jsynprog.java:66: warning: [removal] Integer(int) in Integer has been deprecated and marked for removal
ni = new Integer (sbrt.add_int(scale));
^
6 warnings
---- Build: test.er -----
rm -rf test.er
/tmp/binutils/gprofng/src/gprofng collect app -p on -j on -o test.er /usr/bin/java jsynprog
Creating experiment directory test.er (Process ID: 88051) ...
Picked up JAVA_TOOL_OPTIONS: -agentlib:gp-collector
Directing output to acct file...
libpath:/tmp/binutils/gprofng/tmpdir/jsynprog.-g-Wall,-pon-jon
jvm OpenJDK 64-Bit Server VM
Loading library.... /tmp/binutils/gprofng/tmpdir/jsynprog.-g-Wall,-pon-jon/libcloop.so
Running Routine.memalloc; T = 1.748 UCPU = 1.720
Running Routine.add_int; T = 3.000 UCPU = 2.996
Running Routine.add_double; T = 3.004 UCPU = 3.001
Running Sub_Routine.add_int; T = 3.000 UCPU = 2.997
Running Routine.has_inner_class; T = 3.001 UCPU = 2.998
Running Routine.recurse; T = 4.455 UCPU = 4.449
Running <Truncated-stack>; T = 4.454 UCPU = 4.449
Running Routine.bounce; T = 4.455 UCPU = 4.450
Running Routine.array_op; T = 3.012 UCPU = 3.007
Running Routine.vector_op; T = 3.046 UCPU = 3.027
Running Routine.sys_op; T = 3.021 UCPU = 3.018
Entering jni_JavaJavaC, scale = 1000
Running jsynprog.jni_JavaJavaC; T = 3.980 UCPU = 3.976
Entering Java_jsynprog_JavaCC, scale = 1000
Running jsynprog.JavaCC; T = 3.021 UCPU = 3.018
Entering Java_jsynprog_JavaCJava, scale = 1000
Calling CallStaticIntMethod, scale = 1000
Running jsynprog.JavaCJava; T = 3.005 UCPU = 3.002
Running Launcher.main; T = 0.003 UCPU = 0.003
/tmp/binutils/gprofng/src/gprofng display text -metrics i.totalcpu -func test.er > display.log
perl -I /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/../../lib /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/check_results.pl jsynprog.acct display.log
DEBUG: retVal=94
make[3]: *** [/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/jsynprog/../../lib/Makefile.skel:59: compare] Error 94
make[3]: Leaving directory '/tmp/binutils/gprofng/tmpdir/jsynprog.-g-Wall,-pon-jon'
child process exited abnormally
ERROR: comparison of results in jsynprog failed
UNRESOLVED: jsynprog
create dir: tmpdir/mttest.-g-O0,-pon
mkdir -p tmpdir/mttest.-g-O0,-pon
cd tmpdir/mttest.-g-O0,-pon && make -f /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/Makefile srcdir="/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest" builddir="/tmp/binutils/gprofng" VPATH="mttest" CC="gcc" CFLAGS="-g -O0" LDFLAGS="" DISPLAY_FLAGS="-metrics i.totalcpu -func" COLLECT_FLAGS="-p on" GPROFNG="/tmp/binutils/gprofng/src/gprofng" MAKE="make" all
comparison of results in mttest failed:
make[3]: Entering directory '/tmp/binutils/gprofng/tmpdir/mttest.-g-O0,-pon'
gcc -g -O0 -DBOUND -pthread -o mttest /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/gethrtime.c /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/mttest.c
rm -rf test.er
/tmp/binutils/gprofng/src/gprofng collect app -p on -o test.er ./mttest
Creating experiment directory test.er (Process ID: 88104) ...
compute_set: loop_count=1497603833
./mttest: number of Bound Posix threads = 4, number of blocks = 4, repeat 1 times
Iteration 1, starting Mon 14 Nov 22 12:05:11
begin thread_work, nothreads
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570684262208, il88104, l88104) 3.001558 0.000001 3.001557 2.998495
# 1 (t140570684262208, il88104, l88104) 3.001376 0.000001 3.001376 2.998329
# 2 (t140570684262208, il88104, l88104) 3.001485 0.000001 3.001485 2.998480
# 3 (t140570684262208, il88104, l88104) 3.001444 0.000001 3.001443 2.998462
nothreads 12.005864 0.000003 compute 11.993768
main 12.009881
begin thread_work, cond_timeout_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570621113920, il88104, l88104) 3.000199 0.000001 3.000197 2.997154
# 1 (t140570612721216, il88104, l88104) 9.000894 6.000506 3.000388 2.997171
# 2 (t140570595935808, il88104, l88104) 12.001786 9.000920 3.000866 2.997833
# 3 (t140570604328512, il88104, l88104) 6.000443 3.000198 3.000246 2.997338
cond_timeout_global 30.003322 18.001624 computeH 11.989558
main 12.005896
begin thread_work, lock_none
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570612721216, il88104, l88104) 3.004560 0.000000 3.004560 3.000773
t4 == 0
# 1 (t140570595935808, il88104, l88104) 3.000599 0.000000 3.000599 2.997622
t4 == 0
# 2 (t140570604328512, il88104, l88104) 3.000841 0.000000 3.000841 2.997820
t4 == 0
# 3 (t140570621113920, il88104, l88104) 3.000335 0.000000 3.000335 2.997390
t4 == 0
lock_none 12.006335 0.000000 computeA 11.993604
main 3.008660
begin thread_work, cache_trash
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570612721216, il88104, l88104) 16.137995 0.000000 16.137995 16.119550
t4 == 0
# 1 (t140570604328512, il88104, l88104) 17.298899 0.000000 17.298899 17.281202
t4 == 0
# 2 (t140570621113920, il88104, l88104) 17.334291 0.000000 17.334291 17.317433
t4 == 0
# 3 (t140570595935808, il88104, l88104) 13.423903 0.000000 13.423903 13.409439
t4 == 0
cache_trash 64.195089 0.000000 computeB 64.127624
main 17.338397
begin thread_work, lock_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570612721216, il88104, l88104) 3.000886 0.000001 3.000885 2.997693
# 1 (t140570595935808, il88104, l88104) 6.001465 3.000910 3.000556 2.997488
# 2 (t140570604328512, il88104, l88104) 9.001820 6.001483 3.000337 2.997351
# 3 (t140570621113920, il88104, l88104) 12.002057 9.001828 3.000229 2.997252
lock_global 30.006227 18.004222 computeC 11.989803
main 12.006202
begin thread_work, trylock_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570604328512, il88104, l88104) 3.001747 0.000001 3.001746 2.998531
# 1 (t140570621113920, il88104, l88104) 9.004480 0.000001 9.004479 8.995424
# 2 (t140570612721216, il88104, l88104) 12.005079 0.000001 12.005078 11.992946
# 3 (t140570595935808, il88104, l88104) 6.003592 0.000001 6.003591 5.996369
trylock_global 30.014898 0.000004 computeD 29.983273
main 12.009202
begin thread_work, lock_local
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570612721216, il88104, l88104) 3.000767 0.000001 3.000766 2.997759
# 1 (t140570595935808, il88104, l88104) 3.000718 0.000001 3.000717 2.997688
# 2 (t140570604328512, il88104, l88104) 3.002735 0.000001 3.002734 2.999290
# 3 (t140570621113920, il88104, l88104) 3.001469 0.000001 3.001468 2.997532
lock_local 12.005690 0.000004 computeE 11.992272
main 3.006850
begin thread_work, calladd
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570604328512, il88104, l88104) 3.545583 0.000000 3.545583 3.542003
t4 == 0
# 1 (t140570595935808, il88104, l88104) 3.402183 0.000000 3.402183 3.398714
t4 == 0
# 2 (t140570612721216, il88104, l88104) 3.386044 0.000000 3.386044 3.382267
t4 == 0
# 3 (t140570621113920, il88104, l88104) 3.381365 0.000000 3.381365 3.378023
t4 == 0
calladd 13.715174 0.000000 computeF 13.701007
main 3.549645
begin thread_work, sema_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570612721216, il88104, l88104) 3.000908 0.000001 3.000907 2.997895
# 1 (t140570621113920, il88104, l88104) 3.000692 0.000001 3.000691 2.997555
# 2 (t140570595935808, il88104, l88104) 3.002905 0.000001 3.002904 2.999462
# 3 (t140570604328512, il88104, l88104) 6.001136 3.000711 3.000425 2.997289
sema_global 15.005641 3.000714 computeI 11.992209
main 6.005254
begin thread_work, cond_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140570604328512, il88104, l88104) 3.000934 0.000001 3.000933 2.997743
# 1 (t140570621113920, il88104, l88104) 6.001197 3.000947 3.000250 2.997295
# 2 (t140570612721216, il88104, l88104) 9.001536 6.001227 3.000308 2.997285
# 3 (t140570595935808, il88104, l88104) 12.002655 9.001550 3.001104 2.997205
cond_global 30.006321 18.003725 computeG 11.989549
main 12.006794
/tmp/binutils/gprofng/src/gprofng display text -metrics i.totalcpu -func test.er > display.log
perl -I /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/../../lib /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/check_results.pl mttest.acct display.log
DEBUG: retVal=94
make[3]: *** [/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/../../lib/Makefile.skel:59: compare] Error 27
make[3]: Leaving directory '/tmp/binutils/gprofng/tmpdir/mttest.-g-O0,-pon'
child process exited abnormally
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
create dir: tmpdir/mttest.-g-O0,-pon-hon
mkdir -p tmpdir/mttest.-g-O0,-pon-hon
cd tmpdir/mttest.-g-O0,-pon-hon && make -f /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/Makefile srcdir="/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest" builddir="/tmp/binutils/gprofng" VPATH="mttest" CC="gcc" CFLAGS="-g -O0" LDFLAGS="" DISPLAY_FLAGS="-metrics i.totalcpu -func" COLLECT_FLAGS="-p on -h on" GPROFNG="/tmp/binutils/gprofng/src/gprofng" MAKE="make" all
comparison of results in mttest failed:
make[3]: Entering directory '/tmp/binutils/gprofng/tmpdir/mttest.-g-O0,-pon-hon'
gcc -g -O0 -DBOUND -pthread -o mttest /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/gethrtime.c /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/mttest.c
rm -rf test.er
/tmp/binutils/gprofng/src/gprofng collect app -p on -h on -o test.er ./mttest
Creating experiment directory test.er (Process ID: 88161) ...
compute_set: loop_count=1397038278
./mttest: number of Bound Posix threads = 4, number of blocks = 4, repeat 1 times
Iteration 1, starting Mon 14 Nov 22 12:06:44
begin thread_work, nothreads
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311412741952, il88161, l88161) 2.805345 0.000001 2.805344 2.801940
# 1 (t140311412741952, il88161, l88161) 2.804052 0.000001 2.804052 2.800670
# 2 (t140311412741952, il88161, l88161) 2.804150 0.000001 2.804149 2.800751
# 3 (t140311412741952, il88161, l88161) 2.804031 0.000001 2.804031 2.800635
nothreads 11.217578 0.000003 compute 11.203999
main 11.221900
begin thread_work, cond_timeout_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311348115008, il88161, l88161) 2.798817 0.000001 2.798816 2.795906
# 1 (t140311322936896, il88161, l88161) 5.597782 2.798825 2.798958 2.796174
# 2 (t140311339722304, il88161, l88161) 11.197416 8.398007 2.799409 2.796120
# 3 (t140311331329600, il88161, l88161) 8.397947 5.597795 2.800153 2.796288
cond_timeout_global 27.991963 16.794628 computeH 11.184550
main 11.201567
begin thread_work, lock_none
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311322936896, il88161, l88161) 2.799107 0.000000 2.799107 2.796405
t4 == 0
# 1 (t140311331329600, il88161, l88161) 2.799294 0.000000 2.799294 2.796163
t4 == 0
# 2 (t140311348115008, il88161, l88161) 2.801435 0.000000 2.801435 2.798225
t4 == 0
# 3 (t140311339722304, il88161, l88161) 2.799315 0.000000 2.799315 2.796561
t4 == 0
lock_none 11.199152 0.000000 computeA 11.187353
main 2.805521
begin thread_work, cache_trash
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 16.454026 0.000000 16.454026 16.436913
t4 == 0
# 1 (t140311322936896, il88161, l88161) 12.172262 0.000000 12.172262 12.159612
t4 == 0
# 2 (t140311348115008, il88161, l88161) 16.471261 0.000000 16.471261 16.454845
t4 == 0
# 3 (t140311339722304, il88161, l88161) 15.894843 0.000000 15.894843 15.876512
t4 == 0
cache_trash 60.992392 0.000000 computeB 60.927882
main 16.475378
begin thread_work, lock_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 2.799334 0.000001 2.799333 2.796403
# 1 (t140311322936896, il88161, l88161) 5.598654 2.799352 2.799302 2.796323
# 2 (t140311339722304, il88161, l88161) 8.397649 5.598688 2.798960 2.796080
# 3 (t140311348115008, il88161, l88161) 11.196376 8.397680 2.798697 2.795959
lock_global 27.992013 16.795721 computeC 11.184782
main 11.200468
begin thread_work, trylock_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 2.799875 0.000001 2.799874 2.796946
# 1 (t140311348115008, il88161, l88161) 5.600266 0.000001 5.600265 5.593582
# 2 (t140311339722304, il88161, l88161) 11.199170 0.000001 11.199169 11.187055
# 3 (t140311322936896, il88161, l88161) 8.399642 0.000001 8.399641 8.391192
trylock_global 27.998954 0.000004 computeD 27.968778
main 11.203295
begin thread_work, lock_local
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311339722304, il88161, l88161) 2.798687 0.000001 2.798686 2.795949
# 1 (t140311322936896, il88161, l88161) 2.799121 0.000001 2.799120 2.796415
# 2 (t140311331329600, il88161, l88161) 2.799371 0.000001 2.799370 2.796235
# 3 (t140311348115008, il88161, l88161) 2.801324 0.000001 2.801323 2.798280
lock_local 11.198504 0.000004 computeE 11.186882
main 2.805468
begin thread_work, calladd
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 3.185556 0.000000 3.185556 3.182390
t4 == 0
# 1 (t140311348115008, il88161, l88161) 3.218622 0.000000 3.218622 3.214536
t4 == 0
# 2 (t140311339722304, il88161, l88161) 3.161692 0.000000 3.161692 3.158511
t4 == 0
# 3 (t140311322936896, il88161, l88161) 3.171750 0.000000 3.171750 3.168173
t4 == 0
calladd 12.737620 0.000000 computeF 12.723609
main 3.222737
begin thread_work, sema_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 2.798711 0.000001 2.798710 2.795981
# 1 (t140311322936896, il88161, l88161) 2.799257 0.000001 2.799256 2.796391
# 2 (t140311339722304, il88161, l88161) 2.801689 0.000001 2.801688 2.798445
# 3 (t140311348115008, il88161, l88161) 5.597871 2.798702 2.799168 2.796207
sema_global 13.997529 2.798705 computeI 11.187033
main 5.602022
begin thread_work, cond_global
real real real CPU
idx (t id) total lock crunch crunch
# 0 (t140311331329600, il88161, l88161) 2.798712 0.000001 2.798711 2.795922
# 1 (t140311339722304, il88161, l88161) 5.597889 2.798729 2.799160 2.796214
# 2 (t140311348115008, il88161, l88161) 8.397068 5.597922 2.799146 2.796273
# 3 (t140311322936896, il88161, l88161) 11.196120 8.397073 2.799047 2.796169
cond_global 27.989789 16.793725 computeG 11.184602
main 11.200271
/tmp/binutils/gprofng/src/gprofng display text -metrics i.totalcpu -func test.er > display.log
perl -I /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/../../lib /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/check_results.pl mttest.acct display.log
DEBUG: retVal=94
make[3]: *** [/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/mttest/../../lib/Makefile.skel:59: compare] Error 27
make[3]: Leaving directory '/tmp/binutils/gprofng/tmpdir/mttest.-g-O0,-pon-hon'
child process exited abnormally
ERROR: comparison of results in mttest failed
UNRESOLVED: mttest
create dir: tmpdir/synprog.-g-O0,-pon
mkdir -p tmpdir/synprog.-g-O0,-pon
cd tmpdir/synprog.-g-O0,-pon && make -f /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/synprog/Makefile srcdir="/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/synprog" builddir="/tmp/binutils/gprofng" VPATH="synprog" CC="gcc" CFLAGS="-g -O0" LDFLAGS="" DISPLAY_FLAGS="-metrics i.totalcpu -func" COLLECT_FLAGS="-p on" GPROFNG="/tmp/binutils/gprofng/src/gprofng" MAKE="make" all
PASS: synprog
create dir: tmpdir/synprog.-g-O0,-pon-hon
mkdir -p tmpdir/synprog.-g-O0,-pon-hon
cd tmpdir/synprog.-g-O0,-pon-hon && make -f /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/synprog/Makefile srcdir="/users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/synprog" builddir="/tmp/binutils/gprofng" VPATH="synprog" CC="gcc" CFLAGS="-g -O0" LDFLAGS="" DISPLAY_FLAGS="-metrics i.totalcpu -func" COLLECT_FLAGS="-p on -h on" GPROFNG="/tmp/binutils/gprofng/src/gprofng" MAKE="make" all
PASS: synprog
testcase /users/mmetzger/gdb/git/gprofng/testsuite/gprofng.display/display.exp completed in 336 seconds
=== gprofng Summary ===
# of expected passes 2
# of unresolved testcases 3
runtest completed at Mon Nov 14 12:09:59 2022
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: gprofng patch to review
2022-11-14 11:22 ` Metzger, Markus T
@ 2022-11-14 18:38 ` Vladimir Mezentsev
2022-11-14 18:50 ` Metzger, Markus T
0 siblings, 1 reply; 6+ messages in thread
From: Vladimir Mezentsev @ 2022-11-14 18:38 UTC (permalink / raw)
To: Metzger, Markus T; +Cc: gdb-patches, binutils
Hello Markus,
On 11/14/22 03:22, Metzger, Markus T wrote:
>> +#ifdef DBG_LT1
>> TprintfT (DBG_LT1, "my_cpuid: __get_cpuid(0x%x, 0x%x, 0x%x, 0x%x,
>> 0x%x) returns %d\n",
>> op, regs->eax, regs->ebx, regs->ecx, regs->edx, ret);
>> +#endif
>>
>>
>>
>> I suggest to just remove TprintfT. This debug output is currently not
>> used by anyone.
> There are other Tprintf (no trailing T) in the ARM part. I didn't touch those
> as it didn't fail on my box and I wouldn't be able to test the changes.
>
> Do you want me to remove those, too? Untested.
yes. Please remove those too.
Your Arm build will fail if you use this file.
Thank you,
-Vladimir
^ permalink raw reply [flat|nested] 6+ messages in thread
* RE: gprofng patch to review
2022-11-14 18:38 ` Vladimir Mezentsev
@ 2022-11-14 18:50 ` Metzger, Markus T
2022-11-14 19:11 ` Vladimir Mezentsev
0 siblings, 1 reply; 6+ messages in thread
From: Metzger, Markus T @ 2022-11-14 18:50 UTC (permalink / raw)
To: Vladimir Mezentsev; +Cc: gdb-patches, binutils
Thanks, Vladimir,
>> There are other Tprintf (no trailing T) in the ARM part. I didn't touch those
>> as it didn't fail on my box and I wouldn't be able to test the changes.
>>
>> Do you want me to remove those, too? Untested.
>
>yes. Please remove those too.
I removed them.
This is adding a new file to include/. Do you know who's approval we'd need
for this?
thanks,
markus.
Intel Deutschland GmbH
Registered Address: Am Campeon 10, 85579 Neubiberg, Germany
Tel: +49 89 99 8853-0, www.intel.de <http://www.intel.de>
Managing Directors: Christin Eisenschmid, Sharon Heck, Tiffany Doon Silva
Chairperson of the Supervisory Board: Nicole Lau
Registered Office: Munich
Commercial Register: Amtsgericht Muenchen HRB 186928
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: gprofng patch to review
2022-11-14 18:50 ` Metzger, Markus T
@ 2022-11-14 19:11 ` Vladimir Mezentsev
2022-11-16 10:07 ` Metzger, Markus T
0 siblings, 1 reply; 6+ messages in thread
From: Vladimir Mezentsev @ 2022-11-14 19:11 UTC (permalink / raw)
To: Metzger, Markus T; +Cc: gdb-patches, binutils
On 11/14/22 10:50, Metzger, Markus T wrote:
> Thanks, Vladimir,
>
>>> There are other Tprintf (no trailing T) in the ARM part. I didn't touch those
>>> as it didn't fail on my box and I wouldn't be able to test the changes.
>>>
>>> Do you want me to remove those, too? Untested.
>> yes. Please remove those too.
> I removed them.
>
> This is adding a new file to include/. Do you know who's approval we'd need
> for this?
Nick Clifton did it for the first version of gprofng.
-Vladimir
>
> thanks,
> markus.
> Intel Deutschland GmbH
> Registered Address: Am Campeon 10, 85579 Neubiberg, Germany
> Tel: +49 89 99 8853-0, www.intel.de <http://www.intel.de>
> Managing Directors: Christin Eisenschmid, Sharon Heck, Tiffany Doon Silva
> Chairperson of the Supervisory Board: Nicole Lau
> Registered Office: Munich
> Commercial Register: Amtsgericht Muenchen HRB 186928
^ permalink raw reply [flat|nested] 6+ messages in thread
* RE: gprofng patch to review
2022-11-14 19:11 ` Vladimir Mezentsev
@ 2022-11-16 10:07 ` Metzger, Markus T
0 siblings, 0 replies; 6+ messages in thread
From: Metzger, Markus T @ 2022-11-16 10:07 UTC (permalink / raw)
To: Tom Tromey; +Cc: gdb-patches, binutils, Vladimir Mezentsev
Hello Tom,
>>>> There are other Tprintf (no trailing T) in the ARM part. I didn't touch those
>>>> as it didn't fail on my box and I wouldn't be able to test the changes.
>>>>
>>>> Do you want me to remove those, too? Untested.
>>> yes. Please remove those too.
>> I removed them.
>>
>> This is adding a new file to include/. Do you know who's approval we'd need
>> for this?
>
>Nick Clifton did it for the first version of gprofng.
Could you approve moving a file to include/?
thanks,
markus.
Intel Deutschland GmbH
Registered Address: Am Campeon 10, 85579 Neubiberg, Germany
Tel: +49 89 99 8853-0, www.intel.de <http://www.intel.de>
Managing Directors: Christin Eisenschmid, Sharon Heck, Tiffany Doon Silva
Chairperson of the Supervisory Board: Nicole Lau
Registered Office: Munich
Commercial Register: Amtsgericht Muenchen HRB 186928
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2022-11-16 10:12 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <603d55a9-e789-11e7-2cf0-1fde08874cdf@oracle.com>
2022-11-09 18:50 ` gprofng patch to review Vladimir Mezentsev
2022-11-14 11:22 ` Metzger, Markus T
2022-11-14 18:38 ` Vladimir Mezentsev
2022-11-14 18:50 ` Metzger, Markus T
2022-11-14 19:11 ` Vladimir Mezentsev
2022-11-16 10:07 ` Metzger, Markus T
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).