Em Fri, Jul 03, 2020 at 09:03:53AM +0800, liwei (GF) escreveu:
> Ping...
Thanks, applied and tested, added the Acked-by Jiri and Namhyung
provided,
- Arnaldo
> On 2020/6/12 23:19, Namhyung Kim wrote:
> > Hello,
> >
> > On Fri, Jun 12, 2020 at 6:58 PM Wei Li wrote:
> >>
> >> The segmentation
Em Thu, Jul 02, 2020 at 02:53:45PM -0400, Steven Rostedt escreveu:
> From: "Steven Rostedt (Red Hat)"
>
> Add the functions kbuffer_subbuf_timestamp() and kbuffer_ptr_delta() to get
> the timing data stored in the ring buffer that is used to produced the time
> stamps of the records.
>
> This
Em Fri, Jul 03, 2020 at 08:25:03AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Jun 30, 2020 at 04:39:33PM +0300, Adrian Hunter escreveu:
> > When recording PEBS-via-PT, the kernel will not accept the intel_pt event
> > with register sampling e.g.
> >
> > # perf
Em Tue, Jun 30, 2020 at 04:39:33PM +0300, Adrian Hunter escreveu:
> When recording PEBS-via-PT, the kernel will not accept the intel_pt event
> with register sampling e.g.
>
> # perf record --kcore -c 1 -e
> '{intel_pt/branch=0/,branch-loads/aux-output/ppp}' -I -- ls -l
> Error:
>
Em Mon, Jun 29, 2020 at 12:19:49PM +0300, Adrian Hunter escreveu:
> Hi
>
> Here are some Intel PT related fixes for v5.8.
Thanks, applied.
- Arnaldo
>
> Adrian Hunter (6):
> perf scripts python: export-to-postgresql.py: Fix struct.pack() int
> argument
> perf record: Fix
Em Fri, Jun 26, 2020 at 02:57:59PM -0700, Andi Kleen escreveu:
> > The name could be a metric or an event, the logic for each is quite
>
> I would say collisions are unlikely. Event names follow quite structured
> patterns.
And when introducing a new metric the build process can detect that
Em Fri, Jun 26, 2020 at 02:44:14PM -0700, Ian Rogers escreveu:
> On Fri, Jun 26, 2020 at 2:25 PM Andi Kleen wrote:
> > On Fri, Jun 26, 2020 at 09:47:10PM +0200, Jiri Olsa wrote:
> > > this patchset is adding the support to reused metric in another
> > > metric. The metric needs to be referenced
Em Tue, Jun 23, 2020 at 04:56:01PM +0200, Jiri Olsa escreveu:
> On Wed, Jun 17, 2020 at 11:36:46AM +0300, Alexey Budankov wrote:
>
> SNIP
>
> > + memset(cmd_data, 0, data_size--);
> > +
> > + do {
> > + err = read(evlist->ctl_fd.fd, , 1);
> > + if (err > 0) {
> > +
Em Fri, Jun 19, 2020 at 05:32:31PM +0200, Andreas Gerstmayr escreveu:
> on some platforms the default encoding is not utf-8,
> which causes an UnicodeDecodeError when reading the flamegraph template
> and writing the flamegraph
Thanks, applied.
- Arnaldo
> Signed-off-by: Andreas Gerstmayr
>
ources affects tooling, and act upon it, simply updating the copy or
doing that + extra tooling adjustments, perhaps a new feature, etc.
Acked-by: Arnaldo Carvalho de Melo
- Arnaldo
> Thx.
>
> ---
> From c1c1a26bc631fafb68ed30c5164d0231acc500ee Mon Sep 17 00:00:00 2001
> From: Boris
Em Fri, Jun 19, 2020 at 04:17:17PM +0200, Heiko Carstens escreveu:
> On Thu, Jun 18, 2020 at 10:14:26PM +0800, Xiaoming Ni wrote:
> > Build error on s390:
> > arch/s390/kernel/entry.o: in function `sys_call_table_emu':
> > >> (.rodata+0x1288): undefined reference to `__s390_'
> >
> > In
Em Fri, Jun 19, 2020 at 09:15:57AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Jun 18, 2020 at 09:33:46PM -0700, Ian Rogers escreveu:
> > All C compiler warnings are disabled are disabled by -w. This change
> > removes the -w from flex and bison targets. To avoid implicit
&
Em Thu, Jun 18, 2020 at 09:33:46PM -0700, Ian Rogers escreveu:
> All C compiler warnings are disabled are disabled by -w. This change
> removes the -w from flex and bison targets. To avoid implicit
> declarations header files are declared as targets and included.
>
> Tested with GCC 9.3.0 and
Em Thu, Jun 18, 2020 at 09:33:46PM -0700, Ian Rogers escreveu:
> All C compiler warnings are disabled are disabled by -w. This change
> removes the -w from flex and bison targets. To avoid implicit
> declarations header files are declared as targets and included.
>
> Tested with GCC 9.3.0 and
=address without required
libraries.
Signed-off-by: Arnaldo Carvalho de Melo
Arnaldo Carvalho de Melo (11):
tools headers API: Update faccessat2 affected files
tools arch x86 uapi: Synch asm/unistd.h with the kernel
Em Thu, Jun 18, 2020 at 02:57:46PM +0200, Jiri Olsa escreveu:
> On Thu, Jun 18, 2020 at 10:06:01AM +0800, Tiezhu Yang wrote:
> > When build perf with ASan or UBSan, if libasan or libubsan can not find,
> > the feature-glibc is 0 and there exists the following error log which is
> > wrong, because
Em Wed, Jun 17, 2020 at 07:55:29PM -0300, Arnaldo Carvalho de Melo escreveu:
>
>
> On June 17, 2020 6:28:04 PM GMT-03:00, Steven Rostedt
> wrote:
> >Hi Arnaldo,
> >
> >I guess these patches were missed.
>
> I'll pick those tomorrow,
>
> Thanks
On June 17, 2020 6:28:04 PM GMT-03:00, Steven Rostedt
wrote:
>Hi Arnaldo,
>
>I guess these patches were missed.
I'll pick those tomorrow,
Thanks for the reminder,
- Arnaldo
>
>-- Steve
>
>
>On Tue, 24 Mar 2020 16:08:45 -0400
>Steven Rostedt wrote:
>
>> Arnaldo,
>>
>> Here's a few
Em Wed, Jun 17, 2020 at 08:31:02PM +0900, Namhyung Kim escreveu:
> On Wed, Jun 17, 2020 at 6:06 PM John Garry wrote:
> >
> > For perf list, the CPU core PMU HW event ordering is such that not all
> > events may will be listed adjacent - consider this example:
> > cstate_pkg/c6-residency/
Em Tue, Jun 16, 2020 at 02:27:40PM +0800, Jin, Yao escreveu:
> On 6/16/2020 2:16 PM, Ian Rogers wrote:
> > On Mon, Jun 15, 2020 at 6:00 PM Jin, Yao wrote:
> > > Can I get an ACK for this patchset?
> > > On 6/3/2020 10:18 AM, Jin Yao wrote:
> > > > This patchset updates CascadelakeX events to
Em Mon, Jun 15, 2020 at 10:20:10AM +0800, Tiezhu Yang escreveu:
> On 06/03/2020 07:32 PM, Arnaldo Carvalho de Melo wrote:
> > Em Wed, Jun 03, 2020 at 02:10:04PM +0800, Tiezhu Yang escreveu:
> > > When build perf with ASan or UBSan, if libasan or libubsan can not find,
> >
Em Thu, Jun 11, 2020 at 10:40:38AM -0300, Arnaldo Carvalho de Melo escreveu:
>
>
> debian:10 is going well so far, some of the builds passed
25 debian:10 : Ok gcc (Debian 8.3.0-6) 8.3.0, clang
version 7.0.1-8 (tags/RELEASE_701/final)
Em Thu, Jun 11, 2020 at 10:38:54AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Jun 11, 2020 at 10:07:58AM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Thu, Jun 11, 2020 at 11:02:49AM +0200, Jiri Olsa escreveu:
> > > On Wed, Jun 10, 2020 at 02:50:50PM -0700
Em Thu, Jun 11, 2020 at 10:07:58AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Jun 11, 2020 at 11:02:49AM +0200, Jiri Olsa escreveu:
> > On Wed, Jun 10, 2020 at 02:50:50PM -0700, Ian Rogers wrote:
> > > All C compiler warnings are disabled are disabled by -w. This ch
Em Thu, Jun 11, 2020 at 09:42:34AM +0800, Chen Wandun escreveu:
> Fix potential memory leak in function parse_events_term__sym_hw()
> and parse_events_term__clone().
>
> 1. Free memory when errors occur.
> 2. Function new_term may return error, so it is need to free memory
>when the return
Em Thu, Jun 11, 2020 at 11:02:49AM +0200, Jiri Olsa escreveu:
> On Wed, Jun 10, 2020 at 02:50:50PM -0700, Ian Rogers wrote:
> > All C compiler warnings are disabled are disabled by -w. This change
> > removes the -w from flex and bison targets. To avoid implicit
> > declarations header files are
Em Thu, Jun 11, 2020 at 10:38:46AM +0200, Jiri Olsa escreveu:
> On Wed, Jun 10, 2020 at 04:58:22PM -0700, Ian Rogers wrote:
> > d_ratio avoids division by 0 yielding infinity, such as when a counter
> > doesn't get scheduled. An example usage is:
> >
> > {
> > "BriefDescription": "DCache L1
Em Wed, Jun 10, 2020 at 05:41:29PM +0200, Jiri Olsa escreveu:
> On Tue, Jun 09, 2020 at 10:17:15PM -0700, Ian Rogers wrote:
> > This simplifies computing ratios in json expressions.
>
> please put in the comment some usage example and add
> a test for this to tests/expr.c
>
> same for the '<>'
Em Tue, Jun 09, 2020 at 10:17:16PM -0700, Ian Rogers escreveu:
> These are broadly useful and necessary for Intel's top-down analysis.
Ditto.
- Arnaldo
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/expr.l | 2 ++
> tools/perf/util/expr.y | 5 -
> 2 files changed, 6 insertions(+), 1
Em Tue, Jun 09, 2020 at 10:17:15PM -0700, Ian Rogers escreveu:
> This simplifies computing ratios in json expressions.
Appling to my local branch, Jiri, can I have your acked-by?
- Arnaldo
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/expr.l | 1 +
> tools/perf/util/expr.y | 14
Em Wed, Jun 10, 2020 at 11:09:56AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Jun 10, 2020 at 11:05:26AM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Tue, Jun 09, 2020 at 04:43:44PM -0700, Ian Rogers escreveu:
> > > All C compiler warnings are disabled are disabled
Em Wed, Jun 10, 2020 at 11:05:26AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Jun 09, 2020 at 04:43:44PM -0700, Ian Rogers escreveu:
> > All C compiler warnings are disabled are disabled by -w. This change
> > removes the -w from flex and bison targets. To avoid implicit
&
Em Tue, Jun 09, 2020 at 04:43:44PM -0700, Ian Rogers escreveu:
> All C compiler warnings are disabled are disabled by -w. This change
> removes the -w from flex and bison targets. To avoid implicit
> declarations header files are declared as targets and included.
>
> Tested with GCC 9.3.0 and
Em Tue, Jun 09, 2020 at 04:43:43PM -0700, Ian Rogers escreveu:
> This avoids multiple declarations if the flex header is included.
Thanks, applied,
- Arnaldo
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/pmu.h | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git
Em Tue, Jun 09, 2020 at 10:37:48PM +0200, Daniel Borkmann escreveu:
> Hey Arnaldo,
>
> On 6/9/20 5:34 PM, Arnaldo Carvalho de Melo wrote:
> > Some systems, such as Android, don't have a define for __WORDSIZE, do it
> > in terms of __SIZEOF_LONG__, as done in perf since 2
Em Mon, Jun 08, 2020 at 10:36:10PM -0700, Ian Rogers escreveu:
> Fixes: a26e47162d76 (perf tools: Move ALLOC_LIST into a function)
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/parse-events.y | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git
Em Mon, Jun 08, 2020 at 10:36:09PM -0700, Ian Rogers escreveu:
> Arrays are pointer types and don't need their address taking.
> Fixes: 8255718f4bed (perf pmu: Expand PMU events by prefix match)
Thanks, applied.
- Arnaldo
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/parse-events.y | 2
and Andrii did some Travis CI build tests too.
Acked-by: Andrii Nakryiko
Signed-off-by: Arnaldo Carvalho de Melo
Em Tue, Jun 09, 2020 at 10:10:19AM +0200, Sumanth Korikkar escreveu:
> Issue:
> bpf_probe_read is no longer available for architecture which has
> overlapping address space. Hence bpf prologue generation fails
>
> Fix:
> Use bpf_probe_read_kernel for kernel member access. For user
> attribute
Em Tue, Jun 09, 2020 at 12:09:31PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Jun 09, 2020 at 10:10:18AM +0200, Sumanth Korikkar escreveu:
> > Issue:
> > perf probe -a 'do_sched_setscheduler pid policy
> > param->sched_priority@user' did not work before.
>
Em Mon, Jun 08, 2020 at 09:52:43AM -0700, Ian Rogers escreveu:
> On Mon, Jun 8, 2020 at 9:18 AM Stephane Eranian wrote:
> > This patch fixes a bug in process_pmu_mappings() where the code
> > would not produce an env->pmu_mappings string that was easily parsable.
> > The function parses the
Em Mon, Jun 08, 2020 at 09:52:43AM -0700, Ian Rogers escreveu:
> On Mon, Jun 8, 2020 at 9:18 AM Stephane Eranian wrote:
> A lot of the complexity in this code came from strbuf not \0
> terminating strings. Would a strbuf that always \0 terminated be a
> useful change? In general there's a lack of
Mi
On June 8, 2020 2:32:16 PM GMT-03:00, Andrii Nakryiko
wrote:
>On Mon, Jun 8, 2020 at 9:11 AM Arnaldo Carvalho de Melo
> wrote:
>>
>> Hi Andrii,
>>
>> We've got that hashmap.[ch] copy from libbpf so that we can
>> build perf in systems where
Em Fri, Jun 05, 2020 at 05:17:40PM +0800, Hongbo Yao escreveu:
> If config->aggr_map is Null and config->aggr_get_id is not Null,
> the function print_aggr() will still calling arrg_update_shadow(),
> which can result in accessing the invalid pointer.
Looks legit, but you forgot to add this:
Cc:
Em Sat, Jun 06, 2020 at 06:44:45PM -0400, gaurav singh escreveu:
> Hi,
>
> evname is assigned if condition (evsel__is_group_event(evsel)) is true . It
> is checked for nullnuess here:
>
> if (evname != NULL) {
> ret += fprintf(fp, " of event%s '%s'",
>
Hi Andrii,
We've got that hashmap.[ch] copy from libbpf so that we can
build perf in systems where libbpf isn't available, and to make it build
in all the containers I regularly test build perf I had to add the patch
below, I test build with many versions of both gcc and clang and
Em Wed, Jun 03, 2020 at 02:10:04PM +0800, Tiezhu Yang escreveu:
> When build perf with ASan or UBSan, if libasan or libubsan can not find,
> the feature-glibc is 0 and there exists the following error log which is
> wrong, because we can find gnu/libc-version.h in /usr/include, glibc-devel
> is
From: Arnaldo Carvalho de Melo
Hi Linus,
These are additional changes to the perf tools, on top of what
Ingo has already submitted and you merged, please let me know if I made
any mistake,
Available from:
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git
perf
Em Tue, Jun 02, 2020 at 04:05:08PM +0200, Jiri Olsa escreveu:
> On Tue, Jun 02, 2020 at 10:42:56AM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Tue, Jun 02, 2020 at 12:17:36PM +0200, Jiri Olsa escreveu:
> > > Jin Yao reported the issue (and posted first versions of this change)
Em Tue, Jun 02, 2020 at 12:15:03PM +0800, Tiezhu Yang escreveu:
> When build perf with ASan or UBSan, if libasan or libubsan can not find,
> the feature-glibc is 0 and there exists the following error log which is
> wrong, because we can find gnu/libc-version.h in /usr/include, glibc-devel
> is
Em Tue, Jun 02, 2020 at 12:15:04PM +0800, Tiezhu Yang escreveu:
> There exists some duplicated includes in tools/perf, remove them.
Applied, thanks.
- Arnaldo
> Signed-off-by: Tiezhu Yang
> ---
> tools/perf/builtin-report.c | 1 -
> tools/perf/util/annotate.c | 1 -
>
Em Tue, Jun 02, 2020 at 02:25:05PM +0300, Adrian Hunter escreveu:
> Adjust pgoff also when moving a map's start address.
>
> Example with v5.4.34 based kernel:
>
> Before:
>
> $ sudo tools/perf/perf record -a --kcore -e intel_pt//k sleep 1
> [ perf record: Woken up 1 times to write
Em Tue, Jun 02, 2020 at 12:17:36PM +0200, Jiri Olsa escreveu:
> Jin Yao reported the issue (and posted first versions of this change)
> with groups being defined over events with different cpu mask.
> This causes assert aborts in get_group_fd, like:
> # perf stat -M "C2_Pkg_Residency" -a --
Em Tue, Jun 02, 2020 at 02:10:17PM +0200, Jiri Olsa escreveu:
> On Tue, Jun 02, 2020 at 08:50:17PM +0900, Namhyung Kim wrote:
> > Hi Jiri,
> >
> > On Tue, Jun 2, 2020 at 5:16 PM Jiri Olsa wrote:
> > >
> > > On Tue, Jun 02, 2020 at 11:47:19AM +0900, Namhyung Kim wrote:
> > > > On Tue, Jun 2, 2020
Em Mon, Jun 01, 2020 at 12:55:44AM -0700, Ian Rogers escreveu:
> On Sun, May 24, 2020 at 3:43 PM Jiri Olsa wrote:
> >
> > Adding new test that process metrics code and checks
> > the expected results. Starting with easy ipc metric.
> >
> > Signed-off-by: Jiri Olsa
>
> Acked-by: Ian Rogers
>
>
Em Mon, Jun 01, 2020 at 01:06:01AM -0700, Ian Rogers escreveu:
> On Sun, May 24, 2020 at 3:43 PM Jiri Olsa wrote:
> >
> > Adding new metri test for frontend metric. It's stolen
>
> s/metri/metric/
>
> > from x86 pmu events.
> >
> > Signed-off-by: Jiri Olsa
>
> Acked-by: Ian Rogers
Ditto.
-
Em Mon, Jun 01, 2020 at 10:24:00AM +0300, Adrian Hunter escreveu:
> On 30/05/20 3:24 pm, Leo Yan wrote:
> > From: Tan Xiaojun
> >
> > This patch is to add four options to synthesize events which are
> > described as below:
> >
> > 'f': synthesize first level cache events
> > 'm': synthesize
Em Mon, Jun 01, 2020 at 11:08:50AM +0200, Jiri Olsa escreveu:
> On Mon, Jun 01, 2020 at 12:28:31AM -0700, Ian Rogers wrote:
> > On Sun, May 24, 2020 at 3:42 PM Jiri Olsa wrote:
> > >
> > > Adding parse_events_fake interface to parse events
> > > and use fake pmu event in case pmu event is parsed.
Em Mon, Jun 01, 2020 at 01:19:13PM +0200, RĂ©mi Bernon escreveu:
> Hi,
>
> I'm currently trying to improve compatibility between Wine and perf, and
> I would like to have you opinion on this approach.
Interesting!
> The main problem is that Wine uses PE binary format for most of its code
> (and
Em Sat, May 30, 2020 at 01:20:13AM -0700, Ian Rogers escreveu:
> Tail call optimizations can remove stack frames that are used in
> unwinding tests. Add an attribute that can be used to disable the tail
> call optimization. Tested on clang and GCC.
>
> Signed-off-by: Ian Rogers
> ---
>
Em Sun, May 31, 2020 at 05:06:08PM -0700, Ian Rogers escreveu:
> On Sun, May 31, 2020 at 7:29 AM Namhyung Kim wrote:
> >
> > Hi Ian,
> >
> > On Sat, May 30, 2020 at 7:53 AM Ian Rogers wrote:
> > >
> > > This is currently working due to extra include paths in the build.
> > >
> > > Before:
> > >
Em Sat, May 30, 2020 at 08:24:39PM +0800, Leo Yan escreveu:
> This patch set is to support synthetic events with enabling Arm SPE
> decoder. This patch set is based Xiaojun Tan (Hisilicon) and
> James Clark (Arm)'s previous patches who have contributed much for
> the related task.
Applied, will
Em Sat, May 30, 2020 at 01:20:12AM -0700, Ian Rogers escreveu:
> Fix stack frame count and memory sanitizer issues when running the
> dwarf unwinding test with the elfutils/libdw unwinder (libunwind
> disabled).
Thanks, applied.
> Ian Rogers (3):
> tools compiler.h: Add attribute to disable
Em Fri, May 29, 2020 at 12:55:51PM -0300, Arnaldo Carvalho de Melo escreveu:
> From: Arnaldo Carvalho de Melo
>
> To help in allowing to disable it from the make command line.
>
> Cc: Adrian Hunter
> Cc: Jiri Olsa
> Cc: Namhyung Kim
> Signed-off-by: Arnaldo Carvalho
Em Fri, May 29, 2020 at 08:07:17PM +0200, Jiri Olsa escreveu:
> On Fri, May 29, 2020 at 12:55:52PM -0300, Arnaldo Carvalho de Melo wrote:
> > From: Arnaldo Carvalho de Melo
> >
> > This is useful to see if, on x86, the legacy libaudit still works, as it
> > is used
Em Fri, May 29, 2020 at 02:23:10PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, May 29, 2020 at 10:03:51AM -0700, Ian Rogers escreveu:
> > On Tue, May 5, 2020 at 11:29 AM Ian Rogers wrote:
> > >
> > > From: Stephane Eranian
> > >
> > > T
Em Fri, May 29, 2020 at 10:03:51AM -0700, Ian Rogers escreveu:
> On Tue, May 5, 2020 at 11:29 AM Ian Rogers wrote:
> >
> > From: Stephane Eranian
> >
> > This patch links perf with the libpfm4 library if it is available
> > and LIBPFM4 is passed to the build. The libpfm4 library
> > contains
Em Fri, May 29, 2020 at 11:28:01PM +0800, Leo Yan escreveu:
> Hi James,
>
> On Fri, May 29, 2020 at 03:58:23PM +0100, James Clark wrote:
> > Hi Will and Leo,
> >
> > I've tested this on an Arm N1 machine and it looks good to me.
>
> This is great! Will respin the new patch set with adding your
Em Thu, May 28, 2020 at 05:08:59PM +, Ed Maste escreveu:
> From: Ed Maste
>
> This header is part of the jsmn json parser, introduced in 867a979a83.
> Correct the SPDX tag to indicate that it is under the MIT license.
Thanks, applied.
- Arnaldo
> Signed-off-by: Ed Maste
> Acked-by: Andi
Em Thu, May 28, 2020 at 12:44:56AM -0700, Ian Rogers escreveu:
> On Wed, May 27, 2020 at 10:19 PM Nick Gasson wrote:
> >
> > Fix an issue where addresses in the DWARF line table are offset by
> > -0x40 (GEN_ELF_TEXT_OFFSET). This can be seen with `objdump -S` on the
> > ELF files after perf
Em Thu, May 28, 2020 at 12:31:31AM -0700, Ian Rogers escreveu:
> On Wed, May 27, 2020 at 10:41 PM Nick Gasson wrote:
> > + */
>
> Thanks!
>
> Acked-by: Ian Rogers
Thanks, applied.
- Arnaldo
From: Arnaldo Carvalho de Melo
To help in allowing to disable it from the make command line.
Cc: Adrian Hunter
Cc: Jiri Olsa
Cc: Namhyung Kim
Signed-off-by: Arnaldo Carvalho de Melo
---
tools/perf/Makefile.config | 23 +++
1 file changed, 15 insertions(+), 8 deletions
From: Arnaldo Carvalho de Melo
Hi Jiri,
Can you please take a look if these are ok? I've tested it
extensively, but being Makefiles, I may be missing something... There
are more patches on top of these in the tmp.perf/core branch in my tree,
if you could take a quick look on those
From: Arnaldo Carvalho de Melo
This is useful to see if, on x86, the legacy libaudit still works, as it
is used in architectures that don't have the SYSCALL_TABLE logic and we
want to have it tested in 'make -C tools/perf/ build-test'.
E.g.:
Without having audit-libs-devel installed:
$ make
Em Thu, May 28, 2020 at 03:08:59PM +0300, Adrian Hunter escreveu:
> Stop the message displaying when user space is not being traced.
>
> Example:
>
> Prerequisites:
>
> sudo setcap
> "cap_sys_rawio,cap_sys_admin,cap_sys_ptrace,cap_syslog,cap_ipc_lock=ep"
> ~/bin/perf
> sudo chmod +r
Em Thu, May 28, 2020 at 03:08:58PM +0300, Adrian Hunter escreveu:
> Context switch events are added automatically by Intel PT and Coresight.
> Make it possible to suppress them. That is useful for tracing the
> scheduler without the disturbance that the switch event processing
> creates.
>
>
Em Wed, May 27, 2020 at 09:02:50PM +0300, Adrian Hunter escreveu:
> Make process_attr() respect -F-ip, noting also that the condition in
> process_attr() (callchain_param.record_mode != CALLCHAIN_NONE) is always
> true so test the sample type directly.
>
> Example:
>
> Before:
>
> $ perf
Em Wed, May 27, 2020 at 01:23:00PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, May 27, 2020 at 11:20:57AM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Mon, Apr 27, 2020 at 02:15:16PM +0800, Nick Gasson escreveu:
> > > For a Java method signature like:
> >
Em Wed, May 27, 2020 at 11:20:57AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Apr 27, 2020 at 02:15:16PM +0800, Nick Gasson escreveu:
> > For a Java method signature like:
> >
> > Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V
> >
Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:
> On Tue, May 19, 2020 at 10:40:01PM -0300, Arnaldo Carvalho de Melo wrote:
> > PeterZ, from what we discussed for the next merge Window, perhaps we
> > should route the kernel bits via the tip tree wh
Em Tue, May 12, 2020 at 03:19:16PM +0300, Adrian Hunter escreveu:
> In the absence of any modules, no "modules" map is created, but there are
> other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them
> by recognizing that the first "module" symbol is not necessarily from a
>
Em Tue, May 12, 2020 at 03:19:17PM +0300, Adrian Hunter escreveu:
> Events marked as 'immediate' are started before other events to ensure
> that there is context at the start of the main tracing events. The same
> is true at the end of tracing, so disable 'immediate' events after other
> events.
65: Demangle Java : Ok
$
Signed-off-by: Nick Gasson
Reviewed-by: Ian Rogers
Tested-by: Arnaldo Carvalho de Melo
Tested-by: Ian Rogers
Cc: Alexander Shishkin
Cc: Jiri Olsa
Cc: Mark Rutland
Cc: Namhyung Kim
Cc
Em Mon, Apr 27, 2020 at 02:15:16PM +0800, Nick Gasson escreveu:
> For a Java method signature like:
>
> Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V
>
> The demangler produces:
>
> void class java.lang.AbstractStringBuilder.appendChars(class java.lang.,
>
Em Wed, May 27, 2020 at 11:07:53AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Apr 27, 2020 at 02:15:15PM +0800, Nick Gasson escreveu:
> > If the Java sources are compiled with -g:none to disable debug
> > information the perf JVMTI plugin reports a lot of errors like:
Em Mon, Apr 27, 2020 at 02:15:15PM +0800, Nick Gasson escreveu:
> If the Java sources are compiled with -g:none to disable debug
> information the perf JVMTI plugin reports a lot of errors like:
>
> java: GetLineNumberTable failed with JVMTI_ERROR_ABSENT_INFORMATION
> java: GetLineNumberTable
On May 27, 2020 2:29:05 AM GMT-03:00, Nick Gasson wrote:
>On 05/26/20 19:55 PM, Jiri Olsa wrote:
>> On Fri, May 22, 2020 at 02:53:30PM +0800, Nick Gasson wrote:
>>> For each PC/BCI pair in the JVMTI compiler inlining record table,
>the
>>> jitdump plugin emits debug line table entries for
On May 26, 2020 4:54:39 PM GMT-03:00, Will Deacon wrote:
>On Tue, May 26, 2020 at 06:43:37PM +0800, Leo Yan wrote:
>> On Tue, May 26, 2020 at 11:26:03AM +0100, Will Deacon wrote:
>> > On Fri, May 22, 2020 at 11:09:19AM +0800, Leo Yan wrote:
>> > > On Mon, May 04, 2020 at 07:56:22PM +0800, Leo
Em Tue, May 26, 2020 at 06:52:07PM +0300, Adrian Hunter escreveu:
> Reportedly, from 19.10 Ubuntu has begun mixing up the location of some
> debug symbol files, putting files expected to be in
> /usr/lib/debug/usr/lib into /usr/lib/debug/lib instead. Fix by adding
> another dso_binary_type.
>
>
Adding a few more folks that worked on the ordering of events over the
years.
Some minor nits at the end of the message.
Thanks!
- Arnaldo
Em Tue, May 26, 2020 at 02:59:28PM +0100, Matt Fleming escreveu:
> ordered_event objects can be placed on the free event list in any order
> which means
Em Mon, May 25, 2020 at 12:42:05AM +0200, Jiri Olsa escreveu:
> hi,
> changes for using metric result in another metric seem
> to change lot of core metric code, so it's better we
> have some more tests before we do that.
>
> Sending as RFC as it's still alive and you guys might
> have some other
Em Sun, May 24, 2020 at 12:19:36AM +0200, Jiri Olsa escreveu:
> On Fri, May 22, 2020 at 10:56:59AM -0700, Ian Rogers wrote:
>
> SNIP
>
> > >> > #11 0x004b6911 in cmd_test (argc=1, argv=0x7fffd7f0)
> > >> > at tests/builtin-test.c:772
> > >> > #12 0x004e977b in
Em Fri, May 22, 2020 at 12:13:11PM +0200, Jiri Olsa escreveu:
> On Thu, May 21, 2020 at 02:22:35PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Thu, May 21, 2020 at 01:43:25PM +0200, Jiri Olsa escreveu:
> > > On Wed, May 20, 2020 at 11:20:04AM -0700, Ian Rogers wrote:
Em Thu, May 21, 2020 at 11:45:46PM -0700, Ian Rogers escreveu:
> Before:
> Usage: perf list [] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
> After:
> Usage: perf list []
> [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob]
> Signed-off-by: Ian Rogers
> ---
>
Em Fri, May 22, 2020 at 02:55:46PM +0530, kajoljain escreveu:
> On 5/20/20 11:50 PM, Ian Rogers wrote:
> > Metric groups contain metrics. Metrics create groups of events to
> > ideally be scheduled together. Often metrics refer to the same events,
> > for example, a cache hit and cache miss rate.
Em Thu, May 21, 2020 at 10:26:02AM -0700, Ian Rogers escreveu:
> On Thu, May 21, 2020 at 3:54 AM Jiri Olsa wrote:
> > ok, I misunderstood and thought you would colaps also M3 to
> > have A,B computed via M1 group and with separate D ...
> >
> > thanks a lot for the explanation, it might be great
Em Thu, May 21, 2020 at 01:43:25PM +0200, Jiri Olsa escreveu:
> On Wed, May 20, 2020 at 11:20:04AM -0700, Ian Rogers wrote:
>
> SNIP
>
> > There are 5 out of 12 metric groups where no events are shared, such
> > as Power, however, disabling grouping of events always reduces the
> > number of
Em Thu, May 07, 2020 at 10:36:24PM -0700, Ian Rogers escreveu:
> Avoid a simple memory leak.
Thanks, applied.
- Arnaldo
> Signed-off-by: Ian Rogers
> ---
> tools/perf/util/metricgroup.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/tools/perf/util/metricgroup.c
Em Thu, May 21, 2020 at 09:32:15PM +0800, Wei Li escreveu:
> From: Hongbo Yao
>
> Fix memory leak of metric_events in function metricgroup__setup_events()
The leak is there but this code has changed a lot recently, please take
a look at my perf/core branch and keep Ian Rogers in the loop,
-
Em Thu, May 21, 2020 at 09:32:17PM +0800, Wei Li escreveu:
> From: Xie XiuQi
>
> Need to free "str" before return when asprintf() failed
> to avoid memory leak.
Thanks, applied.
- Arnaldo
> Signed-off-by: Xie XiuQi
> ---
> tools/perf/util/sort.c | 2 +-
> 1 file changed, 1 insertion(+), 1
801 - 900 of 34296 matches
Mail list logo